Sage Journals: Discover world-class research

Abstract

Nowadays, condition-based maintenance (CBM) and fault diagnosis (FD) of rotating machinery (RM) has a vital role in the modern industrial world. However, the remaining useful life (RUL) of machinery is crucial for continuous monitoring and timely maintenance. Moreover, reduced maintenance costs, enhanced safety, efficiency, reliability, and availability are the main important industrial issues to maintain valuable and high-cost machinery. Undoubtedly, induction motor (IM) is considered to be a pivotal component in industrial machines. Recently, acoustic emission (AE) becomes a very accurate and efficient method for fault, leaks and fatigue detection and monitoring techniques. Moreover, CM and FD based on the AE of IM have been growing over recent years. The proposed research study aims to review condition monitoring (CM) and fault diagnosis (FD) studies based on sound and AE for four types of faults: bearings, rotor, stator, and compound. The study also points out the advantages and limitations of using sound and AE analysis in CM and FD. Existing public datasets for AE based analysis for CM and FD of IM are also mentioned. Finally, challenges facing AE based CM and FD for RM, especially for IM, and possible future works are addressed in this study.

Keywords

Acoustic emission condition monitoring fault diagnosis fault detection induction motor rotating machinery sound analysis

Introduction

Nowadays, condition monitoring (CM) along with early and continuous fault diagnosis (FD)^1–11 is vital in the modern life of industries.^12–17 The importance of CM and FD engineering processes comes from the serious need for continuous monitoring of the health of the industrial components and systems through their life.^18–23 Moreover, the main goals are to improve the reliability,^24–26 safety,^27–29 availability,^30,31 efficiency,^32,33 and to reduce the maintenance costs^34,35 as well as to avoid a breakdown or sudden failures.^36,37 In modern industrial applications,^38,39 rotating machinery (RM)^40–42 becomes the most important equipment. RM has been widely used in many vital industrial areas,^43,44 which include blowers, expanders, engines, pumps, turbines, motors, and generators.^45–47

Induction motor (IM) is considered to be one of the main components in industries. However, the importance of extensively using IM comes from some features of it. IM is basic, cheap with high availability and reliability.⁴⁸ IM consists of three main parts: bearing, stator, and rotor. Figure 1 shows the main parts of IM and the percentage of their faults.^49,50

Figure 1.

IM main parts and the percentage of their faults.

On the other hand, CM and FD of IM is widely used to maintain the normal operating condition of the equipment.^51–54 However, the main purpose of CM and FD is to diagnose and detect faults and failures.^55–59 Hazardously, the impact of any failure may arrive to a serious breakdown of the over whole system and heavy losses, which leads to expensive maintenance cost.^60–62 However, to avoid that loss, variety of methodologies for CM and FD have been analyzed and developed. Moreover, several data driven based methods have been proposed such as, data fusion techniques,^63–67 signal and image processing based techniques,^68–72 artificial intelligent (AI) based techniques,^73,74 data acquisition and mining techniques,^75–80 and expert system techniques.^81–83 All previous techniques have used specific analyses to develop the FD methodology to arrive to the best efficient and accurate results.^84–87 Three main types of analysis are used in that studies including, electrical based analysis, oil and chemical based analysis, and finally, mechanical analysis.⁸⁸ In more details, twelve analysis based on electrical, mechanical, and chemical are found in the literature, including, vibration,^89–92 noise,^93,94 radio-frequency (RF),^95–98 infrared,^99–104 current and voltage,^105,106 electromagnetic field,^107–109 oil,^110–113 pressure,^114–118 ultrasound,^119–121 temperature,^122–126 and sound and acoustic emission (AE) analysis. Table 1 highlight main analysis used in CM and FD for IM.¹²⁷

Table 1.

Comparison between main types of CM and FD analysis for IM.

The technique	Fault’s type	Advantages	Drawbacks
Vibration analysis	Mechanical	Reliable for early FD	Expensive
Temperature analysis	Mechanical andelectrical	Simple to implement	Expensive
Chemical analysis	Mechanical	Reliable for remote andcontinuous monitoring	Used for large machines
Electrical analysis(current and voltage)	Electrical	Cheap	Sensitive to the background noise
AE analysis	Mechanical	Fault localization and severity capabilities	Sensitive to the background noise
		Reliable for early FD
		High signal to noise ratio

The proposed study aims to review the CM and FD based on sound and AE for IM. The study also points out the advantages and limitations of using sound and AE analysis in CM and FD. Finally, challenges and possible future works are also addressed in this study.

The rest of the paper has been organized as follows. Firstly, a general background and introduction of AE analysis is discussed in section 2. Secondly, CM and FD of IM based on AE is discussed in section 3. Thirdly, CM and FD for IM based on AE for four types of faults: bearings, rotor, stator, and compound is presented in section 4. Fourthly, existing public datasets are mentioned in section 5. Finally, challenges facing AE based CM and FD for IM, and possible future works are addressed in section 5.

General background of AE analysis

The acoustic emission (AE)^128–130 is a passive powerful non-destructive evaluation (NDE) technique that monitors the transient stress waves for the materials.¹³¹ Moreover, as a result of microstructural changes for the materials or structures, acoustic emission shows the acoustic stress waves that appear from the release of the energy. Conventionally, sensors (typically piezoelectric types) applied directly on the surface to capture these waves.¹³² However, analysis of the picked stress waves can be used as a CM and FD.^133–135

Nowadays, AE¹³⁶ becomes a very accurate and efficient method for fault, leaks and fatigue detection and monitoring techniques in materials^137,138 and structural analysis.¹³⁹ That include, concrete,^140,141 plastics,^142–144 polymers,^145–147 ceramics,^148–150 pipelines,^151–153 pressure vessels,^154,155 storage tanks,^156–159 bridges,^160–162 aircraft,^163,164 bucket trucks,¹⁶⁵ wood,^166–168 fiberglass,^169–172 composites,^173–175 welding,^176–178, tubes,¹⁷⁹ aerospace structures^180–182 and finally for military applications.^183–185 Figure 2 illustrates AE instrumentation chain.

Figure 2.

AE instrumentation chain.

Introduction of CM and FD of IM based on AE

Importantly, CM and FD based on the AE of RM have been growing over recent years. AE is widely used in rotating electric motors CM and FD^186–188 for both electrical and mechanical faults including, the shaft misalignment,¹⁸⁹ the bearing,^190–192 the rotor^193,194 and the stator.¹⁹⁵ In addition, AE is extensively used in CM and FD for the gearbox.^196–199 The wind turbine CM and FD using AE are also proposed and discussed.^200–203 Figure 3 shows the CM and FD process based on AE.

Figure 3.

CM and FD process based on AE.

Once the AE signals are caught, several signal processing techniques are applied in the pre-processing stage and the feature extraction stage.^204,205 Importantly, since AE signals are sensitive to the environmental noise, filtering, signal discrimination and noise reduction are crucial in the pre-processing stage.^206–208 Feature extraction and classification stages are the most important stages in the CM.^209–211 Characteristic patterns (time and frequency as well as time/frequency domains features) could be extracted from AE signals for fault recognition and classification.^212–216

However, choosing acoustic feature extraction algorithms is a challenge. Thus, noise could prevent acoustic feature extraction algorithms from achieving accurate results as well as because the AE is non-stationary. In this regard, how to choose the most functional AE feature extraction and classification algorithms to achieve the most effective features is the target of all new CM and FD based on AE studies.^217–220 Figure 4 shows a test rig schematic diagram for CM and FD of IM based on AE.

Figure 4.

Test rig schematic diagram for CM and FD of IM based on AE.

Advantage and limitations of AE analysis in CM and FD

The advantages of AE based analysis in CM and FD for IM compared with the rest of CM and FD methods (i.e. vibration) could be summarizes as:

AE based analysis provides earlier and rapid detection for mechanical and electrical faults.²²¹

AE based analysis provides high sensitivity to friction and energy level.²²²

AE based analysis provides accurate information about several aspects of the fault.²²³

Fault localization capability.²²⁴

AE based analysis provides dynamic processes capability.²²⁵

Non-invasive and cheap.

The Limitations of AE based analysis in CM and FD for IM are:

Lack of size and shape fault detection.²²⁶

The effects of frequency-dependent energy attenuation.²²⁷

AE based analysis is more susceptible to the background noise.^228,229

AE based analysis showes better performance for electrical faults than mechanical faults.

CM and FD for IM based on AE

Importantly, in order to enhance the reliability and availability of the IM, there is a vital need for fault detection and diagnosis. However, Four main types are available in the litretue including, bearing, stator, rotor and compund, as shown in Figure 5.

Figure 5.

Faults types of of IM.

Bearings

Rolling bearings are one of the most important components of IM.^230–232 In Glowacz et al.,²³³ an early FD technique based on AE for single-phase IM is introduced. The proposed technique used a method called the selection of amplitudes of frequency – multi expanded in the feature extraction stage to create a feature vector. Gaussian mixture models (GMM), nearest neighbor (NN), and nearest mean (NM) classifiers are used in the classification stage. Non-invasive and inexpensive techniques are the main advantages of using this technique. Sensitivity to environmental noises is the main drawback of the proposed method.

In Van Hecke et al.,²³⁴ a low-speed rolling element bearing FD using an AE signal is proposed. Firstly, to sample AE signals, a heterodyne frequency reduction approach is applied. After that, the sampled AE resampled again according to shaft crossing times to account for fluctuations. Secondly, to extract features, an even number of data points (obtained from the resampled process) are used to find the single spectral average for all bearings fault types. Effective diagnosis method for extracting condition indicators is the main advantage of using this method. However, one single-fault detection that is, low shaft speeds bearing fault is the main limitation for this method.

Stief et al.²³⁵ proposed a data fusion system to combine multiple features. An AE, vibration and electric signals are all used and measured. Moreover, a two-stage Bayesian inference approach is applied to combine information from multiple sources. The main advantages of applying this method are, the proposed approach can be operating under normal and noisy working conditions, and it is reliable and efficient for use on health assessment. The drawbacks of applying this approach are, the approach is valid only for steady-state signals and it is not able to identify the severity of faults as well as (similar to all data-driven approaches), large quantities of comparable measurement data must be available.

A bearing FD with several operating conditions using AE was proposed in Kumar et al.²³⁶ A decision tree is used to extract statistical features. Following that, in order to classify faults, the Bayes classifier is applied. Simple, low-cost, non-invasive and the ability to word with different operating conditions are the main strength points of this approach. However, Sensitivity to the noise and one single-fault detection are the main limitations of using this method. Similarly, in He and He,²³⁷ an approach for bearing FD using AE and deep learning (DL) is introduced. In this approach, the Fourier transform (FT) is used to preprocess the data. Then, in order to obtain a DL network (neural network NN), a simple spectrum matrix is applied. The main advantages of using this approach are, working with different operating conditions, dealing with big data, and extract features rapidly. However, single-fault detection is the main disadvantage of applying this approach.

In Martin-del-Campo and Sandin,²³⁸ an online CM and FD approach based on unsupervised learning are introduced. The signal fidelity approach along with dictionary learning-based heuristics for faults detection is also described. Moreover, sparse approximation and time-domain are both employed for vibration and AE signals. Importantly, the results in terms of the adaptation rate, accuracy, and cost of computation are presented. However, once a fault occurs, the features change very slowly in low operation conditions in comparison with a high-speed variation. Online feature condition monitoring and working under different operational conditions are the main strength points for this approach. However, high computation cost and single-fault detection are the main disadvantages of this approach.

Kedadouche et al.²³⁹ proposed a comparative study between empirical wavelet transforms (EWT) and ensemble empirical mode decomposition (EEMD) methods based on AE signal. Moreover, an index selection approach that is, Kurtosis is applied to automatic selection of the Intrinsic Mode Functions (IMF). The results showed that the computational time is better for EWT compared with The EEMD. Furthermore, EWT has the ability to seek the frequency and associated harmonics of the faulty bearing. However, a numerically simulated signal is used in this study.

An early FD of online monitoring for rolling element bearings is developed in Hemmati et al.²⁴⁰ To extract the features, kurtosis and Shannon entropy methods are used in order to find the optimal bandpass filter and wavelet packet transform (WPT) as well as envelope detection. Furthermore, the spectrum of squared Hilbert transform is also applied to add a new layer of improvement. The main strength points of the proposed technique that it has the ability to detect the size and location of faults, operating speed capability, and loading conditions capability. However, the very high computation cost is the main disadvantage of this approach. A range of data processing and analysis methods are applied for AE data to extract faults in the bearing according to Elforjani and Mba.²⁴¹ Moreover, these methods are; eigen-analysis, evelop analysis, entropy, signal shape factor (SHF), Prony’s energy method, regression and wavelet transform WT. Furthermore, statistical analysis and tools are employed. That includes kurtosis (KU), the root mean square (RMS), shape factor (SHF), impulse factor (IF), and crest factor (CF). Detecting the size of a natural defect on bearings whilst in operation is the main strong point for applying the proposed approach. However, single-fault detection and very high computation cost are the main disadvantages of this approach.

In Ferrando et al.,²⁴² an envelope analysis based method for bearing FD is proposed. The method consists of the wavelet packet method and the Hilbert transform (HT). Moreover, in the feature extraction stage, the wavelet packet method is used as AE signal denoising and HT is used as envelope extraction and autocorrelation function. The main advantages of applying this approach are that the ability to identify localized defects in an incipient stage and dealing with the background noise capability whereas the signal-to-noise ratio (SNR) is very low with reduced computation cost. However, single-fault detection is the main disadvantage of applying this method.

Liu et al.²⁴³ proposed a framework based on compressive sensing (CS) signal processing for the running state of the rolling bearing. Moreover, compressive sensing is applied to extract compressive features from the AE signal directly. As a result, simple, high efficiency, small input data and reduced computation cost are the main strength points of applying this approach. However, single-fault detection and sensitivity to the interferences are the main disadvantages of applying this method. In Sharma and Parey,²⁴⁴ a mathematical model is developed as a fault mechanism of rolling element bearing. Furthermore, Hertzian contact, statistical concepts and contact load distribution approaches are all used in order to build the model. The ability to deal with contact load distribution during the load zone is the main advantage of this model. It has been noted that there is no noise consideration with this model.

In Holguín-Londoño et al.²⁴⁵ vibration and AE analysis methodology based on filter bank similarity features is proposed. Moreover, as a feature extraction stage, empirical mode decomposition (EMD), wavelet packet transform (WPT) and Fourier-based filtering methods are applied to decompose the signals into several narrowband spectral components. After that, a similarity measure, that is, cumulative spectral density index, is used to obtain a feature vector. Finally, different types of faults are classified using K-nearest neighbors algorithm. Working in noisy environments with low SNR and the ability to diagnose multiple rotating machine faults are the main advantages of this methodology. The main disadvantage of applying this methodology is the very high computation cost.

Zhong et al.²⁴⁶ introduced an intelligent FD of the IM framework. In the feature extraction stage, EEMD is used to decompose the signal into proper intrinsic mode functions (IMF). The correlation coefficient (CC) and singular value decomposition (SVD) are applied to eliminate the redundant IMF and obtain fault features. To add a new layer of improvement, five single classifiers based on probabilistic committee machine (PCM) and pairwise-coupled sparse Bayesian extreme learning machines (PCSBELM) are trained and used in the classification stage. The ability to diagnose both single and simultaneous faults and solving the multi-signal problem are the main advantages of using the proposed framework. Complex data calculations and sensitivity to the environmental noises are the main disadvantages of applying the proposed approach.

An automatic bearing FD and localization approach using vibration and AE is introduced in Jena and Panigrahi,²⁴⁷ where many signal processing methods are applied. Moreover, WPT is applied first in order to identify the denoised signal. Then, smooth envelope signal (SES) and enhanced spectrogram coefficients techniques are employed. Furthermore, in order to localize faults in time domain, the corresponding enhanced time–frequency spectrogram is obtained using complex Morlet wavelet transform (CMWT) and a thresholding routine. Finally, a robust peak detection technique is applied. Real-time monitoring, 100% accuracy, multiple-fault detection and dealing with noise by using multiple layers of filtering are the main strength points for this approach. In the other side, very high computation cost is the main drawback. In Amarnath and Praveen Krishna,²⁴⁸ an empirical mode decomposition (EMD) based approach of AE for diagnosis of faults in helical gears and rolling element bearings is proposed. By using the EMD approach, the AE is decomposed into several intrinsic mode functions (IMFs) based on the time domain analysis in order to seek the embedded intrinsic oscillation modes of the acoustic signal. As a feature extraction process, kurtosis and crest factor values are obtained and extracted from IMFs. Early and multiple-fault detection capabilities as well as the ability to decompose the signals into higher and lower frequency modes are the main advantages of this approach. However, poor classification capabilities and poor noise consideration are the main drawbacks of this approach. Table 2 summarizes AE based studies for CM and FD for bearings of IM.

Table 2.

AE based studies for CM and FD for bearings of IM.

Reference	Feature extraction method	Classification technique	Highlight
Glowacz et al.²³³	Selection of amplitudes offrequency – multiexpanded	GMM, NN, and NM	Non-invasive and inexpensive technique
Glowacz et al.²³³	Selection of amplitudes offrequency – multiexpanded	GMM, NN, and NM	The proposed technique is sensitive to the enviromental interferences
Van Hecke et al.²³⁴	Spectral analysis andShannon’s entropy	Condition indicators	Effective diagnose method for extracting condition indicators
Van Hecke et al.²³⁴	Spectral analysis andShannon’s entropy	Condition indicators	Single-fault detection
Stief et al.²³⁵	Two-stage Bayesian inference	Unsupervised clustering	Operating under normal and noisy working conditions
			Valid only for steady state signals
			It is not able to identify the severity of faults
Kumar et al.²³⁶	Decision tree	Bayes classifier	Simple, low-cost, non-invasive and different operating conditions capabilities
Kumar et al.²³⁶	Decision tree	Bayes classifier	The proposed technique is sensitive to the enviromental noise
He and He²³⁷	FT	DL	Dealing with several operating conditions and big data
			Rapid feature extraction
			Single-fault detection
Martin-del-Campo and Sandin²³⁸	Feature learning	Dictionary propagation	Online feature condition monitoring and working under different operational conditions
Martin-del-Campo and Sandin²³⁸	Feature learning	Dictionary propagation	High computation cost and single-fault detection
Kedadouche et al.²³⁹	EWT and EEMD	Index selection approach	Computational time is better
Kedadouche et al.²³⁹	EWT and EEMD	Index selection approach	It isable to identify the location and severity of faults
Hemmati et al.²⁴⁰	WPT and envelope detection	Hilbert transform	The proposed method has an ability to detect the size and location of faults, operating speed capability, and loading conditions capability
Hemmati et al.²⁴⁰	WPT and envelope detection	Hilbert transform	High computation cost
Elforjani and Mba²⁴¹	Entropy, SHF, envelopanalysis, and WT	Statistical analysis	Operating under normal and noisy working conditions
Elforjani and Mba²⁴¹	Entropy, SHF, envelopanalysis, and WT	Statistical analysis	It is able to identify the location and severity of faults
Ferrando et al.²⁴²	Envelope analysis	HT	The ability to identify localized defects in an incipient stage
Ferrando et al.²⁴²	Envelope analysis	HT	Dealing with the background noise
Liu et al.²⁴³	CS	Advances signal processingtechniques	Simple, high efficiency, effective for small input data and very low computation cost
			Single-fault detection
			The proposed technique is sensitive to the enviromental noise
Sharma and Parey²⁴⁴	Hertzian contact and statistical analysis	Statistical analysis	Dealing with contact load distribution with different loads
Sharma and Parey²⁴⁴	Hertzian contact and statistical analysis	Statistical analysis	No noise consideration with this model
Holguín-Londoño et al.²⁴⁵	Filter bank similarity,EMD, and WPT	NN	Working in noisy environments with low SNR
			Ability to diagnose multiple faults
			Very high computation cost
Zhong et al.²⁴⁶	EEMD	PCSBELM	Ability to diagnose both single and simultaneous faults and solving multi- signal problem
Zhong et al.²⁴⁶	EEMD	PCSBELM	Complex data calculations and sensitivity to the environmental noises
Jena and Panigrahi²⁴⁷	WPT and SES	CMWT	Real time monitoring, 100% accuracy, multiple-faul detection and dealing with noise by using multiple layers of filtering
Jena and Panigrahi²⁴⁷	WPT and SES	CMWT	Very high computation cost
Amarnath and Praveen Krishna²⁴⁸	EMD	Kurtosis and crest factor	Early and multiple-fault detection capabilities
Amarnath and Praveen Krishna²⁴⁸	EMD	Kurtosis and crest factor	Poor classification capabilities and poor noise consideration
Hasan et al.²⁴⁹	Acoustic spectral imaging (ASI)	Convolutional neuralnetworks (CNN)	Variable operating conditions are diagnosed
Hasan et al.²⁴⁹	Acoustic spectral imaging (ASI)	Convolutional neuralnetworks (CNN)	Different operational speeds are analyzed
Kim and Kim²⁵⁰	CNN	CNN	High classification accuracy is achieved (99.00%)
Kim and Kim²⁵¹	WPT	Adaptive deep CNN	Multi-fault classification with high precision approach is proposed
Omoregbee and Heyns²⁵²	Genetic algorithms (GA)	SVM	Faults in low-speed bearings are analyzed
			Variable operating conditions are diagnosed
			Different operational speeds are analyzed
Piltan and Kim²⁵³	Fuzzy logic	SVM	Single and multi fault classification are applied
			Simulation data is used
			Reliability and performance are improved
Tian et al.²⁵⁴	Entropy	Random forest	The proposed method shows high diagnostic and classification accuracy
Tian et al.²⁵⁴	Entropy	Random forest	Overfitting is decreased

Rotor faults

Detection of rotor faults is vital.²⁵⁵ In Delgado-Arredondo et al.,²⁵⁶ AE and vibration signals are used together as a combined FD methodology. This proposed methodology uses the complete ensemble empirical mode decomposition (CEEMD) to seek the intrinsic mode functions (IMF). Gabor representation and the frequency marginal methods are applied to obtain the spectral content. The main advantages of this method are, a non-invasive method with good accuracy, and it can be extended to diagnose and detect more types of faults. Miss knowledge about the number of modes for signal decomposition and motor speed dependencies are the main disadvantages of applying this method. Glowacz²⁵⁷ applied two feature extraction methods based on the frequency selection of AE. In the classification stage, the NN classifier, backpropagation NN (BNN), and word coding are applied as AE recognition. Very good results for real data, high accuracy, non-invasive and low cost are the main advantages for applying this method. The disadvantage of applying this method is the sensitivity to the environmental noises. In Głowacz and Głowacz,²⁵⁸ a technique of early FD of rotor damages using AE is introduced. For a feature extraction from AE, a method called shortened method of frequencies selection (SMoFS-15) and linear discriminant analysis (LDA), are applied for real-world data of the motor. The nearest neighbor (NN) and nearest mean (NM) algorithms are employed in the classification stage. Importantly, the proposed technique is very cheap. Hazardously, the proposed technique can detect the faults, which have the same size and type. Moreover, sensitivity to the noise and a high computation cost are the main disadvantages of this technique. Table 3 summarizes AE based studies for CM and FD for rotor of IM.

Table 3.

AE based studies for CM and FD for rotor of IM.

Reference	Feature extractionmethod	Classification technique	Highlight
Delgado-Arredondoet al.²⁵⁶	Complete EEMD	Spectral analysis	Non-invasive method, good accuracy, and it can be extended to diagnose and detect more types of faults
Miss knowledge about number of modes for signal decomposition and motor speed dependencies
Glowacz²⁵⁷	Shortened Method of Frequencies Selection Multiexpanded	NN and BNN	High accuracy, non-invasive and low cost are the main advantages for applying this method
The proposed technique is sensitive to the enviromental noise
Głowacz andGłowacz²⁵⁸	SMoFS and LDA	NN and NM	The proposed technique is very cheap\|
Single-fault classification is applied
Sensitivity to the noise and a high computation cost are the main disadvantages of this technique
Barusu et al.²⁵⁹	FFT and WPT		The poposed method is simple, cheap, and non-invasive
No classification consideration is discussed
Li et al.²⁶⁰	Teager–Kaiser energy operator (TKEO) and spectral analysis	Frequency-domain energy operator (FDEO)	Various operating load conditions are checked

Stator faults

Stator faults represent 38% of total IM faults. In Glowacz and Glowacz,²⁶¹ an early FD method of stator faults of the IM is introduced. In the feature extraction stage and to obtain the feature vector, a method called the selection of amplitudes of frequency is applied. Then, the linear perceptron, KNN, and K-Means clustering are all applied in the classification stage. The proposed approach is inexpensive and non-invasive. However, single-fault detection is the main disadvantage of applying this approach. In Glowacz,²⁶² an AE recognition system for detecting shorted stator coils faults in motors is proposed. In the feature extraction stage, the normalization method, Fast Fourier Transform (FFT), frequency selection technique, and neural network (i.e. BNN) are all applied. Moreover, word coding and NN classifiers are applied in the classification stage. On one hand, the proposed approach is simple, on the other hand, it has some limitations such as the ability to detect a single failure only and noise interference. Table 4 summarizes AE based studies for CM and FD for the stator of IM.

Table 4.

AE based studies for CM and FD for stator of IM.

Reference	Feature extraction method	Classification technique	Highlight
Glowacz and Glowacz²⁶¹	Selection of amplitudes of frequency	Linear perceptron, KNN, and K-Means clustering	The proposed approach is inexpensive and non-invasive
Single-fault detection is the main disadvantage for applying this approach
Glowacz²⁶²	FFT and frequency selection	BNN, words coding, and NN	The poposed method is simple, cheap, and non-invasive
Sensitivity to the noise is main drawback of this technique

Compound faults

Compund faluts CM and FD of IM using AE is recently discussed. In Glowacz,²⁶³ bearing, stator and rotor FD methods of a single-phase IM using AE are proposed. In the feature extraction stage, a method called SMOFS-22-MULTIEXPANDED (Shortened Method of Frequencies Selection Multiexpanded) is implemented. NN classifier is applied in the classification stage. Early FD and compound fault detection capabilities are the main advantages of applying this approach. The main drawback of applying this approach is that the AE may interfere and mix (e.g. reflections, overlapping). Similarly, in Germen et al.,²⁶⁴ bearing (misalignment), bearing (ball defect), broken rotor bars and short circuit in stator winding IM faults are diagnosed and classified using AE data recorded by using several microphones. In the feature extraction stage depending on the recorded data, correlation and wavelet-based analyses are applied. Moreover, the self-organizing maps (SOM) method is used as a classifier. The proposed approach has given much attention to the classification stage. Furthermore, it has an ability not only to identify the possible differences between faulty and healthy motors but also to provide the definition of the fault type for all three groups (bearing, rotor and stator). However, the main drawback of applying this approach is the sensitivity to the environmental noises. Table 5 summarizes AE based studies for CM and FD for compound IM faults.

Table 5.

AE based studies for CM and FD for compound IM faults.

Reference	Fault	Featureextraction method	Classificationtechnique	Highlight
Glowacz²⁶³	Bearing, statorand rotor	SMOFS	NN	Early FD capability is the main advantage
Glowacz²⁶³	Bearing, statorand rotor	SMOFS	NN	Sensitivity to the noise is the mein dwawback
Germen et al.²⁶⁴	Bearing, statorand rotor	WT	SOM	Fault identification and fault severity are provided
Germen et al.²⁶⁴	Bearing, statorand rotor	WT	SOM	Sensitivity to the noise is main drawback of thistechnique
Pan et al.²⁶⁵	Stator and rotor	Higher-orderstatistics (HOS)	Accuracy of timedifference ofarrival (TDOA)	Fault identification with rapid manner is provided
Stief et al.²⁶⁶	Bearing, stator and rotor	Data fusion andBayesian inferencemethod	-	Data fusion FD system based on AE,vibration, current data is proposed

Table 6 summarizes advantages and drawbacks for AE based alogorithms for CM and FD of IM.

Table 6.

Advantages and drawbacks for AE based CM FD of IM.

The technique	Advantages	Drawbacks
AE without AI	Simple	Less diagnostic and classification accuracy
	Less computational time
	Dealing with small data sets
AE with deep learning	Effective with big data	Computationally expensive
AE with deep learning	Automatic feature extraction	High time for training data
AE with ANN	Giving high diagnostic andclassification accuracy	Black box hidden problem
AE with ANN	Effective with big data	Computationally expensive
AE with SVM	Giving high classification accuracy	Dealing with small data sets
AE with SVM	Giving high classification accuracy	Sensitive to the noise
AE with K-NN	Simple	Slow for classification
		Giving less diagnostic and classification accuracy
		Dealing with small data sets
		Sensitive to the noise
AE with RF	Computationally inexpensive	Overfitting
AE with RF	Simple	Overfitting
AE with DT	Simple	Sensitive to the noise
AE with DT	Effective with small data sets	Sensitive to the noise
AE with GMM	Efficient with data clustering	Giving good diagnostic and classificationperformance
AE with GMM	less sensitivity to the noise	Giving good diagnostic and classificationperformance
AE with NM	Giving good classification accuracy	Computationally expensive
AE with Fuzzy logic	Robust	Black box hidden problem
	Giving high diagnostic andclassification accuracy
	Effective with big data
AE with K-Means clustering	Computationally inexpensive	Dealing with small data sets
AE with K-Means clustering	Simple	Dealing with small data sets
AE with logistic regression	Simple	Giving poor diagnostic and classificationperformance
	Effective with small data sets
	Computationally inexpensive

Public datasets

Based on our review for the existing public datasets for AE-based CM and FD of IM including bearings, rotor, and stator, we were able to find only one dataset for bearing, which is Smart Health, Safety, Environment (SHSE) Lab Acoustic Emission (AE) Bearing (multi-crack bearing faults, including, inner, outer, and ball faults).^253,267 We were able to spot only one dataset of bearing without any dataset for rotor and stator. However, as a future direction, we aim to generate data to provide such datasets.

Challenges and future trends

Intelligent CM and FD is considered as a key factor of fault diagnosis development. This section summarizes the challenges and the future trends of CM and FD based on sounds and AE for IM^268–271:

AE data for CM and FD of machines still in infant stage. However, more contribution must be done to evaluate the performance of it.

Recent advances such as internet of things (IoT) and big data analytics must be used with AE to build a remote, continuous, online, accurate, and robust CM and FD techniques.²⁷²

Rotor and stator FD based on AE needs more contributions and should be investigated more.²⁷³

Fault localization and identification based on AE should be more investigated.

Compound CM and FD based on several types of data (vibration, current, image, etc.) along with AE may lead to better diagnostic capability.

AE considers to be efficient FD technique for low speed condition. However, more efforts should be given to evaluate AE based FD technique for moderate and high speed cases.

FD based on AE for multi- motor system, complicated faults, and for several types of RM have to be evaluated.

Building an FD system based on AE with taking into consideration all advantages of each algorithm may lead to immune system.

Compound FD approaches for all faults of IM still needs more contributions.

Very recently, DL becomes the hero and it overcomes the drawbacks of traditional ML. However, more efforts should be done to befit from it in the field of CM and FD.

Generating public datasets for stator and rotor CM and FD of IM are crucial.²⁷⁴

Conclusion

Importantly, enhance the reliability, availability, safety and reducing maintenance cost of modern industrial systems and applications is crucial. Thus, follow up the health and the remaining useful life (RUL) in modern industrial machinery (i.e. IM) is vital. However, finding the best diagnostic method is challenging. Recently, acoustic emission (AE) becomes a very accurate and efficient FD and monitoring techniques for IM. Thus, in this paper, a general descriptive review for diagnostics methods of IM based on AE is presented. Moreover, FD methods for bearing faults, stator faults, and rotor faults of IM are discussed. The advantages and limitations of each method are also highlighted. As a main conclusion for the proposed study, AE data for CM and FD of machines still in the infant stage. However, more contribution must be done for intelligent FD based on AE to evaluate its performance.

Footnotes

Handling Editor: James Baldwin

Declaration of conflicting interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) received no financial support for the research, authorship, and/or publication of this article.

ORCID iDs

Omar AlShorman

Adam Glowacz

References

Xia

, et al. Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks. IEEE/ASME Trans Mechatron 2018; 23: 101–110.

Gómez

Castejón

García-Prada

. Automatic condition monitoring system for crack detection in rotating machinery. Reliab Eng Syst Safety 2016; 152: 239–247.

Song

Wang

Chen

. Vibration-based intelligent fault diagnosis for roller bearings in low-speed rotating machinery. IEEE Trans Instrument Measure 2018; 67: 1887–1899.

Choudhary

Goyal

Shimi

, et al. Condition monitoring and fault diagnosis of induction motors: a review. Arch Comput Methods E 2018; 1–18.

Qiao

. A survey on wind turbine condition monitoring and fault diagnosis—Part I: Components and subsystems. IEEE Trans Ind Electr 2015; 62: 6536–6545.

Goyal

Pabla

Dhami

. Condition monitoring parameters for fault diagnosis of fixed axis gearbox: a review. Arch Comput Methods E 2017; 24: 543–556.

Riera-Guasp

Antonino-Daviu

Capolino

G-A

. Advances in electrical machine, power electronic, and drive condition monitoring and fault detection: state of the art. IEEE Trans Ind Electr 2015; 62: 1746–1759.

de Azevedo

HDM

Araújo

Bouchonneau

. A review of wind turbine bearing condition monitoring: State of the art and challenges. Renew Sustain Energ Rev 2016; 56: 368–379.

Lei

Jia

Lin

, et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data. IEEE Trans Ind Electr 2016; 63: 3137–3147.

10.

Jia

Lei

Guo

, et al. A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines. Neurocomputing 2018; 272: 619–628.

11.

AlShorman

Alkahtani

. A review of wearable sensors based monitoring with daily physical activity to manage type 2 diabetes. Int J Electr Comput Eng 2021; 11: 646–653.

12.

Peeters

Antoni

Helsen

. Blind filters based on envelope spectrum sparsity indicators for bearing and gear vibration-based condition monitoring. Mech Syst Signal Pr 2020; 138: 106556.

13.

Lin

Wang , et al. Time-reassigned multisynchrosqueezing transform for bearing fault diagnosis of rotating machinery. IEEE Trans Ind Electr 2020; 68: 1486–1496.

14.

Rani

Dhok

Deshmukh

. A machine condition monitoring framework using compressed signal processing. Sensors 2020; 20: 319.

15.

Papaelias

Márquez

FPG

. Wind turbine inspection and condition monitoring. In: Papaelias

García Márquez

Karyotakis

(eds) Non-destructive testing and condition monitoring techniques for renewable energy industrial assets. Oxford, United Kingdom: Elsevier, 2020, pp. 19–29.

16.

Samson

Rajan

. Condition monitoring of cavitation-induced centrifugal pump. In: Suryan

MinoruYaga Zhang

(eds) Recent Asian research on thermal and fluid sciences. Singapore: Springer, 2020, pp. 393–408.

17.

Feng

Zhang

, et al. Generalized adaptive mode decomposition for nonstationary signal analysis of rotating machinery: Principle and applications. Mech Syst Signal Process 2020; 136: 106530.

18.

Zhao

Jia

Lin

. Deep Laplacian Auto-encoder and its application into imbalanced fault diagnosis of rotating machinery. Measurement 2020; 152: 107320.

19.

Bai

Lin

, et al. Intelligent condition assessment of industry machinery using multiple type of signal from monitoring system. Measurement 2020; 149: 107018.

20.

Wang

Liu

, et al. A new method to realize cyclic time averaging for change detection in dynamical machine status. Measurement 2020; 154: 107443.

21.

Wang

Shao

. Fault feature extraction of rotating machinery using a reweighted complete ensemble empirical mode decomposition with adaptive noise and demodulation analysis. Mech Syst Signal Process 2020; 138: 106545.

22.

Ramesh

Dutta

Neog

, et al. Implementation of Predictive Maintenance Systems in Remotely Located Process Plants under Industry 4.0 Scenario. In: Karanki

Vinod

Ajit

(eds) Advances in RAMS engineering. NJ, USA: Springer, 2020, pp. 293–326.

23.

Jalali

Ghandi

Motamedi

. Intelligent condition monitoring of ball bearings faults by combination of genetic algorithm and support vector machines. J Nondestruct Eval 2020; 39: 1–12.

24.

Goyal

Pabla

Dhami

. Non-contact sensor placement strategy for condition monitoring of rotating machine-elements. Eng Sci Technol Int J 2019; 22: 489–501.

25.

Saucedo-Dorantes

Delgado-Prieto

Osornio-Rios

, et al. Spectral analysis of nonlinear vibration effects produced by worn gears and damaged bearing in electromechanical systems: a condition monitoring approach. In: Jauregui

(eds) Nonlinear structural dynamics and damping. New York: Springer, 2019, pp. 293–320.

26.

Pan

Zheng

Liu

. A novel roller bearing condition monitoring method based on RHLCD and FVPMCD. IEEE Access 2019; 7: 96753–96763.

27.

Liu

Zhi

Zhang

, et al. Related entropy theories application in condition monitoring of rotating machineries. Entropy 2019; 21: 1061.

28.

Xiong

, et al. A novel fault diagnosis algorithm for rotating machinery based on a sparsity and neighborhood preserving deep extreme learning machine. Neurocomputing 2019; 350: 261–270.

29.

Ding

E-J

, et al. Safety detection approach in industrial equipment based on RSSD with adaptive parameter optimization algorithm. Safety Sci 2020; 125: 104605.

30.

Cattaneo

Macchi

. A digital twin proof of concept to support machine prognostics with low availability of run-to-failure data. IFAC-PapersOnLine 2019; 52: 37–42.

31.

Jagtap

Bewoor

Kumar

. Thermal power plant condenser fault diagnosis using coordinated condition monitoring approach. J Homepage 2019; 18: 223–235.

32.

Ong

Tieh

THC

Lai

, et al. Efficient gear fault feature selection based on moth-flame optimisation in discrete wavelet packet analysis domain. J Braz Soc Mech Sci Eng 2019; 41: 266.

33.

Altaf

Uzair

Naeem

, et al. Automatic and efficient fault detection in rotating machinery using sound signals. Acoust Aust 2019; 47: 125–139.

34.

Choudhary

Jamwal

Goyal

, et al. Condition monitoring of induction motor using internet of things (IoT). In: Kumar

Jain

(eds) Recent advances in mechanical engineering. Singapore: Springer, 2020, pp. 353–365.

35.

Lee

Huang

, et al. Learning via acceleration spectrograms of a DC motor system with application to condition monitoring. Int J Adv Manuf Technol 2020; 106: 803–816.

36.

Choudhary

Goyal

Shimi

, et al. Condition monitoring and fault diagnosis of induction motors: a review. Arch Comput Methods Eng 2018; 26: 1221–1238.

37.

Choudhary

Khan

. Introduction to conditioning monitoring of mechanical systems. In: Malik

Iqbal

Yadav

(eds) Soft computing in condition monitoring and diagnostics of electrical and mechanical systems. Singapore: Springer, 2020, pp. 205–230.

38.

Mazzei

Baldi

Fantoni

, et al. A Blockchain Tokenizer for Industrial IOT trustless applications. Future Gener Comput Syst 2020; 105: 432–445.

39.

Joshi

Agrawal

Yadav

, et al. Soft computing methods and its applications in condition monitoring of dgs—a review. In: Malik

Hasmat

Iqbal

Yadav

(eds) Soft computing in condition monitoring and diagnostics of electrical and mechanical systems. Singapore: Springer, 2020, pp. 189–204.

40.

Ragab

Yacout

Ouali

M-S

, et al. Prognostics of multiple failure modes in rotating machinery using a pattern-based classifier and cumulative incidence functions. J Intell Manuf 2019; 30: 255–274.

41.

Bai

Ganeriwala

Sawalhi

. A rational basis for determining vibration signature of shaft/coupling misalignment in rotating machinery. In Maio

(ed) Rotating machinery, vibro-acoustics & laser vibrometry, volume 7. New York: Springer, 2019, pp. 207–217.

42.

Jiang

Ding

, et al. Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network. Comput Ind 2019; 108: 53–61.

43.

Zhao

Wang

Zhang

. Fault diagnosis of broken rotor bars in squirrel-cage induction motor of hoister based on duffing oscillator and multifractal dimension. Adv Mech Eng 2014; 6: 849670.

44.

Irfan

. A novel non-intrusive method to diagnose bearings surface roughness faults in induction motors. J Failure Anal Prev 2018; 18: 145–152.

45.

Muthanandan

Nor

KAB

. Condition monitoring and assessment for rotating machinery. In: Sulaiman

(ed) Rotating machineries. Berlin, Germany: Springer, 2019, pp. 1–22.

46.

Zheng

Wang

Yin

, et al. A new intelligent fault identification method based on transfer locality preserving projection for actual diagnosis scenario of rotating machinery. Mech Syst Signal Pr 2020; 135: 106344.

47.

Wang

, et al. An integrated method based on refined composite multivariate hierarchical permutation entropy and random forest and its application in rotating machinery. J Vib Control 2020; 1077546319877711.

48.

Lee

J-H

Pack

J-H

Lee

I-S

. Fault diagnosis of induction motor using convolutional neural network. Appl Sci 2019; 9: 2950.

49.

Irfan

Saad

Ibrahim

, et al. Analysis of bearing outer race defects in induction motors. In: 2014 5th international conference on intelligent and advanced systems (ICIAS), Kuala Lumpur, Malaysia, 2014, pp. 1–6.

50.

Irfan

Saad

Ibrahim

, et al. An online fault diagnosis system for induction motors via instantaneous power analysis. Tribol Trans 2017; 60: 592–604.

51.

Dinardo

Fabbiano

Vacca

. A smart and intuitive machine condition monitoring in the Industry 4.0 scenario. Measurement 2018; 126: 1–12.

52.

Shao

Jiang

Zhao

, et al. A novel deep autoencoder feature learning method for rotating machinery fault diagnosis. Mech Sys Signal Pr 2017; 95: 187–204.

53.

Jia

Lei

Lin

, et al. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech Sys Signal Pr 2016; 72: 303–315.

54.

Zhao

Lin

. Health assessment of rotating machinery using a rotary encoder. IEEE Trans Ind Electr 2017; 65: 2548–2556.

55.

Wang

Lei

Yan

, et al. Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery. Neurocomput 2020; 379: 117–129.

56.

Zhang

Jia

X-D

, et al. Machinery fault diagnosis with imbalanced data using deep generative adversarial networks. Measurement 2020; 152: 107377.

57.

Isavand

Kasaei

Peplow

, et al. Comparison of vibration and acoustic responses in a rotary machine balancing process. Appl Acoust 2020; 164: 107258.

58.

Alshorman

Irfan

, et al. Fuzzy-based fault-Tolerant control for omnidirectional mobile robot. Machines 2020; 8: 55.

59.

Saad

Irfan

Ibrahim

. Condition monitoring and faults diagnosis of induction motors: electrical signature analysis. New York: CRC Press, 2018.

60.

Tang

Liu

, et al. Multi-fault diagnosis for rotating machinery based on orthogonal supervised linear local tangent space alignment and least square support vector machine. Neurocomput 2015; 157: 208–222.

61.

Chen

Zhang

, et al. Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks. J Manuf Syst 2020; 54: 1–11.

62.

Peng

Xia

, et al. A mixed intelligent condition monitoring method for nuclear power plant. Ann Nucl Energ 2020; 140: 107307.

63.

Jiang

L-I

Yin

H-K

X-J

, et al. Fault diagnosis of rotating machinery based on multisensor information fusion using SVM and time-domain features. Shock and Vibration 2014; 2014: 1–8.

64.

Ayaz

Öztürk

Şeker

, et al. Fault detection based on continuous wavelet transform and sensor fusion in electric motors. Int J Comput Mathematics Electr Electron Eng 2009; 28: 454–470.

65.

Liu

Mathew

. Machinery fault diagnosis based on fuzzy measure and fuzzy integral data fusion techniques. Mech Syst Signal Pr 2009; 23: 690–700.

66.

Niu

Han

Yang

B-S

, et al. Multi-agent decision fusion for motor fault diagnosis. Mech Syst Signal Pr 2007; 21: 1285–1299.

67.

Sanchez

R-V

Zurita

, et al. Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals. Mech Syst Signal Pr 2016; 76–77: 283–293.

68.

McInerny

Dai

. Basic vibration signal processing for bearing fault detection. IEEE Trans Educ 2003; 46: 149–156.

69.

Benbouzid

Nejjari

Beguenane

, et al. Induction motor asymmetrical faults detection using advanced signal processing techniques. IEEE Trans Energ Conversion 1999; 14: 147–152.

70.

Dutta

Pal

Mukhopadhyay

, et al. Application of digital image processing in tool condition monitoring: A review. CIRP J Manuf Sci Technol 2013; 6: 212–232.

71.

Wong

Nee

, et al. Tool condition monitoring using laser scatter pattern. J Mater Process Technol 1997; 63: 205–210.

72.

Castejon

Alegre

Barreiro

, et al. On-line tool wear monitoring using geometric descriptors from digital images. Int J Machine Tools Manuf 2007; 47: 1847–1853.

73.

Yang

B-S

Han

Hwang

W-W

. Fault diagnosis of rotating machinery based on multi-class support vector machines. J Mech Sci Technol 2005; 19: 846–859.

74.

Nyanteh

Srivastava

Edrington

, et al. Application of artificial intelligence to stator winding fault diagnosis in Permanent Magnet Synchronous Machines. Electr Power Syst Res 2013; 103: 201–213.

75.

Bagheri

Ahmadi

Labbafi

. Application of data mining and feature extraction on intelligent fault diagnosis by artificial neural network and k-nearest neighbor. In: Electrical machines (ICEM), 2010 XIX international conference on, Rome, Italy, 2010, pp. 1–7.

76.

Purarjomandlangrudi

Ghapanchi

Esmalifalak

. A data mining approach for fault diagnosis: An application of anomaly detection algorithm. Measurement 2014; 55: 343–352.

77.

Blair

Shirkhodaie

. Diagnosis and prognosis of bearings using data mining and numerical visualization techniques. In: System theory, 2001. Proceedings of the 33rd southeastern symposium on, Athens, OH, USA, USA, 2001, pp. 395–399.

78.

Zhu

, et al. Data mining based full ceramic bearing fault diagnostic system using AE sensors. IEEE Trans Neural Networks 2011; 22: 2022–2031.

79.

Zhu

. Plastic bearing fault diagnosis based on a two-step data mining approach. IEEE Trans Ind Electr 2013; 60: 3429–3440.

80.

Verma

Zhang

Kusiak

. Modeling and prediction of gearbox faults with data-mining algorithms. J Solar Energ Eng 2013; 135: 031007.

81.

Yang

B-S

Lim

D-S

Tan

ACC

. VIBEX: an expert system for vibration fault diagnosis of rotating machinery using decision tree and decision table. Exp Syst Appl 2005; 28: 735–742.

82.

J-D

Bai

F-C

, et al. An expert system for the diagnosis of faults in rotating machinery using adaptive order-tracking algorithm. Exp Syst Appl 2009; 36: 5424–5431.

83.

Berredjem

Benidir

. Bearing faults diagnosis using fuzzy expert system relying on an Improved Range Overlaps and Similarity method. Exp Syst Appl 2018; 108: 134–142.

84.

Brkovic

Gajic

Gligorijevic

, et al. Early fault detection and diagnosis in bearings for more efficient operation of rotating machinery. Energy 2017; 136: 63–71.

85.

Zhang

Wang

, et al. General normalized sparse filtering: A novel unsupervised learning method for rotating machinery fault diagnosis. Mech Syst Signal Pr 2019; 124: 596–612.

86.

Zhang

Ding

, et al. Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation. J Intell Manuf 2020; 31: 433–452.

87.

Xue

Zhou

. A hybrid fault diagnosis approach based on mixed-domain state features for rotating machinery. ISA Trans 2017; 66: 284–295.

88.

Irfan

Saad

Ibrahim

, et al. Condition monitoring of induction motors via instantaneous power analysis. J Intell Manuf 2017; 28: 1259–1267.

89.

Chung

. Misalignment diagnosis of rotating machinery through vibration analysis via the hybrid EEMD and EMD approach. Smart Mater and Struct 2009; 18: e095004.

90.

Jiang

Chen

. Analysis and sensitivity evaluation of ae signals and vibration signals for fault diagnosis of low-speed rotating machinery. Appl Mech Mater 2011 128–129: 79–84.

91.

Medoued

Mordjaoui

Soufi

, et al. Induction machine bearing fault diagnosis based on the axial vibration analytic signal. Int J Hydrogen Energ 2016; 41: 12688–12695.

92.

Sinha

Elbhbah

. A future possibility of vibration based condition monitoring of rotating machines. Mech Syst Signal Pr 2013; 34: 231–240.

93.

Chaturved

Thomas

. Adaptive noise cancelling and condition monitoring. J Sound Vibration 1981; 76: 391–405.

94.

Wang

Liang

, et al. Bearing fault diagnosis under unknown variable speed via gear noise cancellation and rotational order sideband identification. Mech Syst Signal Pr 2015; 62: 30–53.

95.

Gungor

. Online and remote motor energy monitoring and fault diagnostics using wireless sensor networks. IEEE Trans Ind Electr 2009; 56: 4651–4659.

96.

Cheng

Tom

Thomas

, et al. A wireless sensor system for prognostics and health management. IEEE Sensors J 2010; 10: 856–862.

97.

Timperley

. Incipient fault identification through neutral RF monitoring of large rotating machines. IEEE Trans Power Apparatus and Syst 1983; 693–698.

98.

Henson

Restrepo

. Devices, systems, and methods for adaptive RF sensing in arc fault detection. ed: Google Patents, 2008.

99.

Agoston

Schneidhofer

Dörr

, et al. A concept of an infrared sensor system for oil condition monitoring. e & i Elektrotechnik und Informationstechnik 2008; 125: 71–75.

100.

Caneca

Pimentel

Galvão

RKH

, et al. Assessment of infrared spectroscopy and multivariate techniques for monitoring the service condition of diesel-engine lubricating oils. Talanta 2006; 70: 344–352.

101.

Jadin

Taib

. Recent progress in diagnosing the reliability of electrical equipment by using infrared thermography. Infrared Phys Technol 2012; 55: 236–245.

102.

Bagavathiappan

Saravanan

George

, et al. Condition monitoring of exhaust system blowers using infrared thermography. Insight-Non-Destructive Testing and Condition Monitoring 2008; 50: 512–515.

103.

Utami

Tamsir

Pharmatrisanti

, et al. Evaluation condition of transformer based on infrared thermography results. In: Properties and applications of dielectric materials, 2009. ICPADM 2009. IEEE 9th international conference on the, Harbin, China, 2009, pp. 1055–1058.

104.

Huda

Taib

. Suitable features selection for monitoring thermal condition of electrical equipment using infrared thermography. Infrared Phys Technol 2013; 61: 184–191.

105.

Lopes

Goedtel

Palácios

RHC

, et al. Bearing fault identification of three-phase induction motors bases on two current sensor strategy. Soft Comput 2016; 21: 6673–6685.

106.

Diallo

Benbouzid

MEH

Hamad

, et al. Fault detection and diagnosis in an induction machine drive: a pattern recognition approach based on concordia stator mean current vector. IEEE Trans Energ Conversion 2005; 20: 512–519.

107.

Roscoe

Judd

. Harvesting energy from magnetic fields to power condition monitoring sensors. IEEE Sensor J 2013; 13: 2263–2270.

108.

Pöyhönen

Negrea

Jover

, et al. Numerical magnetic field analysis and signal processing for fault diagnostics of electrical machines. Int J Comput Mathematics Elec Electr Eng 2003; 22: 969–981.

109.

Farooq

Djerdir

Miraoui

. Analytical modeling approach to detect magnet defects in permanent-magnet brushless motors. IEEE Trans Magnet 2008; 44: 4599–4604.

110.

Feng

Fan

Mao

, et al. Prediction on wear of a spur gearbox by on-line wear debris concentration monitoring. Wear 2015; 336–337: 1–8.

111.

Agoston

Ötsch

Jakoby

. Viscosity sensors for engine oil condition monitoring—Application and interpretation of results. Sensors Actuators A: Phys 2005; 121: 327–332.

112.

Kumar

Mukherjee

Mishra

. Online condition monitoring of engine oil. Ind Lubric Tribol 2005; 57: 260–267.

113.

Loutas

Roulias

Pauly

, et al. The combined use of vibration, acoustic emission and oil debris on-line monitoring towards a more effective condition monitoring of rotating machinery. Mech Syst Signal Pr 2011; 25: 1339–1352.

114.

Schultheis

Lickteig

Parchewsky

. Reciprocating compressor condition monitoring. In: Proceedings of the 36th turbomachinery symposium, Houston, Texas, USA, Houston, Texas, USA, 2007.

115.

Elhaj

Almrabet

Rgeai

, et al. A combined practical approach to condition monitoring of reciprocating compressors using IAS and dynamic pressure. World Acad Sci Eng and Technol 2010; 63: 186–192.

116.

Gao

Zhang

Kong

. Wavelet–based pressure analysis for hydraulic pump health diagnosis. Trans ASAE 2003; 46: 969.

117.

Sun

Xiao

Liu

, et al. Analysis of S characteristics and pressure pulsations in a pump-turbine with misaligned guide vanes. J Fluid Eng 2013; 135: 051101.

118.

Mucchi

Dalpiaz

Del Rincon

. Elastodynamic analysis of a gear pump. Part I: Pressure distribution and gear eccentricity. Mech Syst Signal Pr 2010; 24: 2160–2179.

119.

Kim

Tan

Mathew

, et al. Condition monitoring of low speed bearings: A comparative study of the ultrasound technique versus vibration measurements. Aust J Mech Eng 2008; 5: 177–189.

120.

Zhang

Drinkwater

Dwyer-Joyce

. Monitoring of lubricant film failure in a ball bearing using ultrasound. J Tribol 2006; 128: 612–618.

121.

Abu-Zahra

. Gradual wear monitoring of turning inserts using wavelet analysis of ultrasound waves. Int J Machine Tools Manuf 2003; 43: 337–343.

122.

Reigosa

Guerrero

Diez

, et al. Rotor temperature estimation in doubly-fed induction machines using rotating high-frequency signal injection. IEEE Trans Industry Appl 2017; 53: 3652–3662.

123.

Mohammed

Djurovic

. Stator winding internal thermal monitoring and analysis using In Situ FBG sensing technology. IEEE Trans Energ Conversion 2018; 33: 1508–1518.

124.

Zhao

Guan

, et al. Method and experiment of temperature collaborative monitoring based on characteristic points for tilting pad bearings. Tribol Int 2017; 114: 77–83.

125.

Visnadi

de Castro

. Influence of bearing clearance and oil temperature uncertainties on the stability threshold of cylindrical journal bearings. Mech Machine Theory 2019; 134: 57–73.

126.

Bagavathiappan

Lahiri

Saravanan

, et al. Infrared thermography for condition monitoring – A review. Infrared Phys Technol 2013; 60: 35–55.

127.

AlShorman

Irfan

Saad

, et al. A review of artificial intelligence methods for condition monitoring and fault diagnosis of rolling element bearings for induction motor. Shock and Vibration 2020; 2020: 1–20.

128.

Zhou

Duan

Mba

. Wireless acoustic emission transmission system designed for fault detection of rotating machine. In: Bahei-El-Din

Hassan

(eds) Advanced technologies for sustainable systems. Switzerland: Springer, 2017, pp. 201–207.

129.

Crivelli

Hutt

Clarke

, et al. Condition monitoring of rotating machinery with acoustic emission: a british–australian collaboration. In: Mathew

Lim

Sands

Cholette

Borghesani

(eds) Asset Intelligence through Integration and interoperability and contemporary vibration engineering technologies. Switzerland: Springer, 2019, pp. 119-128.

130.

Janeliukstis

Clark

Papaelias

, et al. Flexural cracking-induced acoustic emission peak frequency shift in railway prestressed concrete sleepers. Eng Struct 2019; 178: 493–505.

131.

Vahaviolos

. Acoustic emission: standards and technology update. 1999.

132.

Yin

Liu

Huang

, et al. Gas face seal status estimation based on acoustic emission monitoring and support vector machine regression. Adv Mech Eng 2020; 12: 1687814020921323.

133.

Desa

Ibrahim

Shahidan

, et al. Fundamental and assessment of concrete structure monitoring by using acoustic emission technique testing: A review. In: IOP Conference series: earth and environmental science, Langkawi, Malaysia, 2018, p. 012142.

134.

Ono

. Review on structural health evaluation with acoustic emission. Appl Sci 2018; 8: 958.

135.

Kishawy

Hegab

Umer

, et al. Application of acoustic emissions in machining processes: analysis and critical review. Int J Adv Manuf Technol 2018; 98: 1391–1407.

136.

Deng

Pei

Wang

, et al. Research on fault diagnosis of mud pump fluid end based on acoustic emission. Adv Mech Eng 2017; 9: 1687814017711393.

137.

G-Y

K-J

W-K

. Standard deviation based acoustic emission signal analysis for detecting valve internal leakage. Sensors Actuators A: Phys 2018; 283: 340–347.

138.

Ahn

Kim

Choi

. Artificial intelligence-based machine learning considering flow and temperature of the pipeline for leak early detection using acoustic emission. Engineering Fracture Mechanics 2018; 210: 381–392.

139.

Bhuiyan

Bao

Poddar

, et al. Toward identifying crack-length-related resonances in acoustic emission waveforms for structural health monitoring applications. Struct Health Monitoring 2018; 17: 577–585.

140.

Xargay

Folino

Nuñez

, et al. Acoustic emission behavior of thermally damaged self-compacting high strength fiber reinforced concrete. Constr Build Mater 2018; 187: 519–530.

141.

Han

, et al. Micro-cracking monitoring and fracture evaluation for crumb rubber concrete based on acoustic emission techniques. Struct Health Monit 2018; 17: 946–958.

142.

Bhuiyan

Choudhury

Dahari

, et al. Application of acoustic emission sensor to investigate the frequency of tool wear and plastic deformation in tool condition monitoring. Measurement 2016; 92: 208–217.

143.

Okabe

, et al. The identification of damage types in carbon fiber–reinforced plastic cross-ply laminates using a novel fiber-optic acoustic emission sensor. Struct Health Monit 2016; 15: 93–103.

144.

Schnabel

Marklund

Larsson

, et al. The detection of plastic deformation in rolling element bearings by acoustic emission. Tribol Int 2017; 110: 209–215.

145.

Bauchet

J-PT

. Process to mitigate unwanted formation of popcorn polymers using acoustic emission signals. ed: Google Patents, 2019.

146.

Baran

Nowak

Chłopek

, et al. Acoustic emission from microcrack initiation in polymer matrix composites in short beam shear test. J Nondestructive Eval 2018; 37: 7.

147.

Brunner

. Identification of damage mechanisms in fiber-reinforced polymer-matrix composites with Acoustic Emission and the challenge of assessing structural integrity and service-life. Construct Build Mater 2018; 173: 629–637.

148.

Whitlow

Jones

Przybyla

. In-situ damage monitoring of a SiC/SiC ceramic matrix composite using acoustic emission and digital image correlation. Composite Struct 2016; 158: 245–251.

149.

Godin

Reynaud

Mili

, et al. Identification of a critical time with acoustic emission monitoring during static fatigue tests on ceramic matrix composites: Towards lifetime prediction. Appl Sci 2016; 6: 43.

150.

Racle

Godin

Reynaud

, et al. Fatigue lifetime of ceramic matrix composites at intermediate temperature by acoustic emission. Materials 2017; 10: 658.

151.

Droubi

Reuben

Steel

. Flow noise identification using acoustic emission (AE) energy decomposition for sand monitoring in flow pipeline. Appl Acoust 2018; 131: 5–15.

152.

Pan

, et al. Research on detection and location of fluid-filled pipeline leakage based on acoustic emission technology. Sensors 2018; 18: 3628.

153.

Song

Zhou

. Leak detection of water distribution pipeline subject to failure of socket joint based on acoustic emission and pattern recognition. Measurement 2018; 115: 39–44.

154.

Sause

Schmitt

Hoeck

, et al. Acoustic emission based prediction of local stress exposure. Composites Science and Technology 2019.

155.

Ramirez

JPB

Halm

Grandidier

. Assessment of a damage model for wound composite structures by acoustic emission. Compos Struct 2019.

156.

Gong

. Online Detection and Evaluation of Tank Bottom Corrosion Based on Acoustic Emission. In: Proceedings of the international field exploration and development conference 2017, 2019, Beijing, China, pp. 1284–1291.

157.

Han

Yoon

Park

, et al. Impact source location on composite CNG storage tank using acoustic emission energy based signal mapping method. J Korean Soc Nondestruct Testing 2016; 36: 391–398.

158.

Sohaib

Islam

Kim

, et al. Leakage detection of a spherical water storage tank in a chemical industry using acoustic emissions. Appl Sci 2019; 9: 196.

159.

Liu

, et al. Study on pitting corrosion of storage tank bottom steel in acidic condition using acoustic emission. Int J Electrochem Sci 2015; 10:4416–4427.

160.

Zeng

Hartell

Emerson

, et al. I-235 bridge load test combine with acoustic emission monitoring. NDE Aerospace Mater Struct 2018; 2018: 263–274.

161.

Han

Carpinteri

, et al. Localization of acoustic emission sources in structural health monitoring of masonry bridge. Struct Control Health Monit 2015; 22:314–329.

162.

Parks

Papulak

Pantelides

. Acoustic emission monitoring of grouted splice sleeve connectors and reinforced precast concrete bridge assemblies. Construct Build Mater 2016; 122: 537–547.

163.

Esola

Wisner

Vanniamparambil

, et al. Part qualification methodology for composite aircraft components using acoustic emission monitoring. Appl Sci 2018; 8: 1490.

164.

James

Salton

Downing

, et al. Acoustic emissions from F-35 aircraft during ground run-up. In: 21st AIAA/CEAS aeroacoustics conference, Dallas, TX, USA, 2015, p. 2375.

165.

Ling

Zheng

Bin

, et al. Research on the acoustic emission testing of the tank truck and on the defect acoustic emission source location method. In: Kao

JCM

Sung

(eds) Civil, architecture and environmental engineering. London: CRC Press, 2017, pp. 1038–1041.

166.

Diakhaté

Bastidas-Arteaga

Pitti

, et al. Cluster analysis of acoustic emission activity within wood material: Towards a real-time monitoring of crack tip propagation. Eng Fracture Mech 2017; 180:254–267.

167.

Diakhate

Angellier

Pitti

, et al. On the crack tip propagation monitoring within wood material: Cluster analysis of acoustic emission data compared with numerical modelling. Construct Build Mater 2017; 156: 911–920.

168.

Lamy

Takarli

Angellier

, et al. Acoustic emission technique for fracture analysis in wood materials. Int J Fracture 2015; 192: 57–70.

169.

Chen

Siegmund

. Acoustic emission from a porous non-woven fiberglass material. Exp Mech 2019; 59: 179–186.

170.

de Souza Rios

de Amorim Junior

de Moura

, et al. Effects of accelerated aging on mechanical, thermal and morphological behavior of polyurethane/epoxy/fiberglass composites. Polymer Testing 2016; 50: 152–163.

171.

Kholodov

Grigor’ev

Shchipakov

, et al. Acoustic emission monitoring of damaging of fiberglass. Polym Sci Ser D 2016; 9: 411–414.

172.

Nunemaker

Voth

Miller

, et al. Effects of moisture absorption on damage progression and strength of unidirectional and cross-ply fiberglass–epoxy composites. Wind Energ Sci 2018; 3: 427–438.

173.

McCrory

Al-Jumaili

Crivelli

, et al. Damage classification in carbon fibre composites using acoustic emission: A comparison of three techniques. Composit Part B: Eng 2015; 68: 424–430.

174.

Mohammadi

Najafabadi

Saeedifar

, et al. Correlation of acoustic emission with finite element predicted damages in open-hole tensile laminated composites. Composit Part B: Eng 2017; 108: 427–435.

175.

Karimi

Minak

Kianfar

. Analysis of damage mechanisms in drilling of composite materials by acoustic emission. Compos Struct 2015; 131: 107–114.

176.

Chai

Qin

Zheng

, et al. Acoustic emission detection during welding residual stresses release in 2.25 Cr1Mo0. 25V steel welds. Materials Today: Proc 2018; 5: 13759–13766.

177.

Luo

Zhu

Han

, et al. Study on the acoustic emission effect of plasma plume in pulsed laser welding. Mech Syst Signal Pr 2019; 124: 715–723.

178.

Xiao

. Time-frequency characteristics of acoustic emission signal for monitoring of welding structural state using Stockwell transform. J Acoust Soc Am 2019; 145: 469–479.

179.

Narayan

Ramirez

Russell

Brock

David

. Acoustic Emission Technology for High Power Microwave Radar Tubes. BoD -Books on Demand, 2019.

180.

Courtier

Croxford

Atherton

. Guided wave propagation modelling to aid understanding of acoustic emission system performance on complex aerospace structures. In: 8th European workshop on structural health monitoring (EWSHM 2016), Bilbao, Spain, 2016.

181.

Holford

Eaton

Hensman

, et al. A new methodology for automating acoustic emission detection of metallic fatigue fractures in highly demanding aerospace environments: An overview. Prog Aerosp Sci 2017; 90: 1–11.

182.

De Simone

Ciampa

Boccardi

, et al. Impact source localisation in aerospace composite structures. Smart Mater Struct 2017; 26: 125026.

183.

Jowkar

Bahmani

Jowkar

, et al. Design of automatic gain control (AGC) circuit for using in a laboratory military submarine sonar systems based on native knowledge. In: Kouhsari

(ed) Fundamental research in electrical engineering. Singapore: Springer, 2019, pp. 227–237.

184.

Reichman

Gee

Neilsen

, et al. Acoustic shock formation in noise propagation during ground run-up operations of military aircraft. In: 23rd AIAA/CEAS aeroacoustics conference, Denver, Colorado, 2017, p. 4043.

185.

Powers

McLaughlin

. Acoustics measurements of military-style supersonic beveled nozzle jets with interior corrugations. Int J Aeroacoust 2017; 16: 21–43.

186.

Glowacz

. Fault diagnostics of DC motor using acoustic signals and MSAF-RATIO30-EXPANDED. Arch Electr Eng 2016; 65: 733–744.

187.

Othman

Nuawi

Mohamed

. Experimental comparison of vibration and acoustic emission signal analysis using kurtosis-based methods for induction motor bearing condition monitoring. Przegląd Elektrotechniczny 2016; 92: 208–212.

188.

Kumar

Narayanan

. Variable-switching frequency PWM technique for induction motor drive to spread acoustic noise spectrum with reduced current ripple. IEEE Trans Ind Appl 2016; 52: 3927–3938.

189.

Gama

de Lima

de Veneza

. Detection of shaft misalignment using piezoelectric strain sensors. Exp Techniques 2017; 41: 87–93.

190.

Elforjani

Shanbr

. Prognosis of bearing acoustic emission signals using supervised machine learning. IEEE Trans Ind Electr 2018; 65: 5864–5871.

191.

Hase

Mishina

Wada

. Fundamental study on early detection of seizure in journal bearing by using acoustic emission technique. Wear 2016; 346: 132–139.

192.

Aye

Heyns

. An integrated Gaussian process regression for prediction of remaining useful life of slow speed bearings based on acoustic emission. Mech Syst Signal Pr 2017; 84: 485–498.

193.

Glowacz

. Diagnostics of rotor damages of three-phase induction motors using acoustic signals and SMOFS-20-EXPANDED. Arch Acoust 2016; 41: 507–515.

194.

Peng

Liu

Cheng

, et al. Feedforward chaotic neural network model for rotor rub-impact fault recognition using acoustic emission method. J Electr Comput Eng 2018; 2018. doi: 10.1155/2018/9718951

195.

Sarma

Djurovic

, et al. Analysis of a wound rotor induction machine low frequency vibroacoustic emissions under stator winding fault conditions. 2016.

196.

Heydarzadeh

Nourani

Hansen

, et al. Non-invasive gearbox fault diagnosis using scattering transform of acoustic emission. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), New Orleans, LA, USA, 2017, pp. 371–375.

197.

Leaman

Niedringhaus

Hinderer

, et al. Evaluation of acoustic emission burst detection methods in a gearbox under different operating conditions. J Vib Control 2019; 25: 895–906.

198.

Leaman

Hinderer

Baltes

, et al. Acoustic Emission Source Localization in Ring Gears from Wind Turbine Planetary Gearboxes. Forschung im Ingenieurwesen 2019; 1–10.

199.

, et al. Gear pitting fault diagnosis using integrated CNN and GRU network with both vibration and acoustic emission signals. Appl Sci 2019; 9: 768.

200.

Gómez Muñoz

García Marquez

Hernandez Crespo

, et al. Structural health monitoring for delamination detection and location in wind turbine blades employing guided waves. Wind Energ 2019; 22: 698–711.

201.

Bastián-Monarca

Álvarez

Darr

, et al. Acoustic characterization of wind farms in chile: wind turbine noise measurements throughout the country. In: INTER-NOISE and NOISE-CON congress and conference proceedings, Chicago, 2018, pp. 5763–5774.

202.

Gómez Muñoz

García Márquez

. A new fault location approach for acoustic emission techniques in wind turbines. Energies 2016; 9: 40.

203.

Tang

Soua

Mares

, et al. An experimental study of acoustic emission methodology for in service condition monitoring of wind turbine blades. Renew Energ 2016; 99: 170–179.

204.

Caesarendra

Kosasih

Tieu

, et al. Acoustic emission-based condition monitoring methods: Review and application for low speed slew bearing. Mech Syst Signal Pr 2016; 72: 134–159.

205.

Rai

Upadhyay

. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribol Int 2016; 96: 289–306.

206.

Tsilfidis

Mporas

Mourjopoulos

, et al. Automatic speech recognition performance in different room acoustic environments with and without dereverberation preprocessing. Comput Speech Language 2013; 27: 380–395.

207.

Brown

Garg

Montgomery

. Scalable preprocessing of high volume environmental acoustic data for bioacoustic monitoring. PloS One 2018; 13: e0201542.

208.

AlShorman

Alkhassaweneh

, et al. A review of internet of medical things (IoMT)–based remote health monitoring through wearable sensors: A case study for diabetic patients. Indonesian J Electr Eng Comput Sci 2020; 20: 414–422.

209.

Jing

Zhao

, et al. A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox. Measurement 2017; 111: 1–10.

210.

Caesarendra

Tjahjowidodo

. A review of feature extraction methods in vibration-based condition monitoring and its application for degradation trend estimation of low-speed slew bearing. Machines 2017; 5: 21.

211.

Vishwakarma

Purohit

Harshlata

, et al. Vibration analysis & condition monitoring for rotating machines: a review. Materials Today: Proc 2017; 4: 2659–2664.

212.

Kiktova-Vozarikova

Juhar

Cizmar

. Feature selection for acoustic events detection. Multimed Tools Appl 2015; 74: 4213–4233.

213.

Sumesh

Rameshkumar

Mohandas

, et al. Use of machine learning algorithms for weld quality monitoring using acoustic signature. Proc Comput Sci 2015; 50: 316–322.

214.

Sharma

Imtiaz

Rodriguez-Villegas

. An algorithm for heart rate extraction from acoustic recordings at the neck. IEEE Trans Biomed Eng 2019; 66: 246–256.

215.

Chen

, et al. A fusion frequency feature extraction method for underwater acoustic signal based on variational mode decomposition, duffing chaotic oscillator and a kind of permutation entropy. Electr 2019; 8: 61.

216.

Xie

Zhu

. Investigation of acoustic and visual features for acoustic scene classification. Exp Syst Appl 2019; 126: 20–29.

217.

Bahr

Schultz

. Automated classification of transient contamination in stationary acoustic data. Exp Fluids 2019; 60: 31.

218.

Shetty

Livitsanos

Van Roy

, et al. Quantification of progressive structural integrity loss in masonry with Acoustic Emission-based damage classification. Construct Build Mater 2019; 194: 192–204.

219.

Nasir

Nourian

Avramidis

, et al. Stress wave evaluation by accelerometer and acoustic emission sensor for thermally modified wood classification using three types of neural networks. Eur J Wood Wood Product 2019; 77: 45–55.

220.

Thirumalaiselvi

Sasmal

. Acoustic emission monitoring and classification of signals in cement composites during early-age hydration. Construct Build Mater 2019; 196: 411–427.

221.

Smith

Dixon

Fowmes

. Early detection of first-time slope failures using acoustic emission measurements: large-scale physical modelling. 2017.

222.

Geng

Puhan

Reddyhoff

. Using acoustic emission to characterize friction and wear in dry sliding steel contacts. Tribol Int 2019; 134: 394–407.

223.

Fotouhi

Suwarta

Jalalvand

, et al. Detection of fibre fracture and ply fragmentation in thin-ply UD carbon/glass hybrid laminates using acoustic emission. Composit Part A: Appl Sci Manuf 2016; 86: 66–76.

224.

Al-Jumaili

Pearson

Holford

, et al. Acoustic emission source location in complex structures using full automatic delta T mapping technique. Mech Syst Signal Pr 2016; 72: 513–524.

225.

Xiao

Liu

Zhang

, et al. Acoustic emission characteristics and stress release rate of coal samples in different dynamic destruction time. Int J Mining Sci Technol 2016; 26: 981–988.

226.

Godin

Reynaud

Fantozzi

. Challenges and limitations in the identification of acoustic emission signature of damage mechanisms in composites materials. Appl Sci 2018; 8: 1267.

227.

Maillet

Baker

Morscher

, et al. Feasibility and limitations of damage identification in composite materials using acoustic emission. Composit Part A: Appl Sci Manuf 2015; 75: 77–83.

228.

Soobbarayen

Besset

. A simplified approach for the calculation of acoustic emission in the case of friction-induced noise and vibration. Mech Syst Signal Pr 2015; 50: 732–756.

229.

Moses

Anderson

Phophongviwat

. Localized surface vibration and acoustic noise emitted from laboratory-scale transformer cores assembled from grain-oriented electrical steel. IEEE Trans Magnetics 2016; 52: 1–15.

230.

Kaplan

Kaya

Kuncan

, et al. An improved feature extraction method using texture analysis with LBP for bearing fault diagnosis. Appl Soft Comput 2020; 87: 106019.

231.

Jiang

Niu

, et al. An enhanced selective ensemble deep learning method for rolling bearing fault diagnosis with beetle antennae search algorithm. Mech Syst Signal Pr 2020; 142:106752.

232.

Irfan

Saad

Ibrahim

, et al. Analysis of distributed faults in inner and outer race of bearing via Park vector analysis method. Neural Comput and Appl 2019; 31: 683–691.

233.

Glowacz

, et al. Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals. Measurement 2018; 113: 19–24.

234.

Van Hecke

Yoon

. Low speed bearing fault diagnosis using acoustic emission sensors. Appl Acoust 2016; 105: 35–44.

235.

Stief

Ottewill

Orkisz

, et al. Two Stage data fusion of acoustic, electric and vibration signals for diagnosing faults in induction motors. Elektronika ir Elektrotechnika 2017; 23.

236.

Kumar

Sugumaran

Amarnath

. Fault diagnosis of bearings through sound signal using statistical features and bayes classifier. J Vibration Eng Technol 2016; 4: 87–96.

237.

. Deep learning based approach for bearing fault diagnosis. IEEE Trans Ind Appl 2017; 53: 3057–3065.

238.

Martin-del-Campo

Sandin

. Online feature learning for condition monitoring of rotating machinery. Eng Appl Artif Intell 2017; 64: 187–196.

239.

Kedadouche

Thomas

Tahan

. A comparative study between empirical wavelet transforms and empirical mode decomposition methods: application to bearing defect diagnosis. Mech Syst Signal Pr 2016; 81: 88–107.

240.

Hemmati

Orfali

Gadala

. Roller bearing acoustic signature extraction by wavelet packet transform, applications in fault detection and size estimation. Appl Acoust 2016; 104: 101–118.

241.

Elforjani

Mba

. Accelerated natural fault diagnosis in slow speed bearings with acoustic emission. Eng Fract Mech 2010; 77: 112–127.

242.

Ferrando

Chacon

Kappatos

, et al. A novel approach for incipient defect detection in rolling bearings using acoustic emission technique. Appl Acoust 2015; 89: 88–100.

243.

Liu

Mao

, et al. Acoustic emission signal processing for rolling bearing running state assessment using compressive sensing. Mech Syst Signal Pr 2017; 91: 395–406.

244.

Sharma

Parey

. Modelling of acoustic emission generated in rolling element bearing. Appl Acoust 2019; 144: 96–112.

245.

Holguín-Londoño

Cardona-Morales

Sierra-Alonso

, et al. Machine fault detection based on filter bank similarity features using acoustic and vibration analysis. Math Prob Eng 2016; 2016: 1–14.

246.

Zhong

J-H

Wong

Yang

Z-X

. Fault diagnosis of rotating machinery based on multiple probabilistic classifiers. Mech Syst Signal Pr 2018; 108: 99–114.

247.

Jena

Panigrahi

. Automatic gear and bearing fault localization using vibration and acoustic signals. Appl Acoust 2015; 98: 20–33.

248.

Amarnath

Praveen Krishna

. Empirical mode decomposition of acoustic signals for diagnosis of faults in gears and rolling element bearings. IET Sci,Measure Technol 2012; 6: 279–287

249.

Hasan

Islam

Kim

J-M

. Acoustic spectral imaging and transfer learning for reliable bearing fault diagnosis under variable speed conditions. Measurement 2019 138: 620–631.

250.

Kim

J-M

. Bearing fault diagnosis using grad-CAM and acoustic emission signals. Appl Sci 2020; 10: 2050.

251.

Islam

Kim

J-M

. Automated bearing fault diagnosis scheme using 2D representation of wavelet packet transform and deep convolutional neural network. Comput Ind 2019; 106: 142–153.

252.

Omoregbee

Heyns

. Fault classification of low-speed bearings based on support vector machine for regression and genetic algorithms using acoustic emission. J Vib Eng Technol 2019; 7: 455–464.

253.

Piltan

Kim

J-M

. Hybrid fault diagnosis of bearings: adaptive fuzzy orthonormal-ARX robust feedback observer. Appl Sci 2020; 10: 3587.

254.

Tian

Liu

Zhang

, et al. Multi-domain entropy-random forest method for the fusion diagnosis of inter-shaft bearing faults with acoustic emission signals. Entropy 2020; 22:57.

255.

Bossio

Ruschetti

Bossio

, et al. Rotor fault diagnosis in permanent magnet synchronous machine using the midpoint voltage of windings. IET Electr Power Appl 2020; 14: 256–261.

256.

Delgado-Arredondo

Morinigo-Sotelo

Osornio-Rios

, et al. Methodology for fault detection in induction motors via sound and vibration signals. Mech Syst Signal Pr 2017; 83: 568–589.

257.

Glowacz

. Acoustic based fault diagnosis of three-phase induction motor. Appl Acoust 2018; 137: 82–89.

258.

Głowacz

. Recognition of rotor damages in a DC motor using acoustic signals. Bull Polish Acad Sci Tech Sci 2017; 65: 187–194.

259.

Barusu

Sethurajan

Deivasigamani

. Non-invasive method for rotor bar fault diagnosis in three-phase squirrel cage induction motor with advanced signal processing technique. J Eng 2019; 2019: 4415–4419.

260.

Feng

Zhen

, et al. A normalized frequency domain energy operator for broken rotor bar fault diagnosis. IEEE Trans Instrument Measure 2020.

261.

Glowacz

. Diagnosis of stator faults of the single-phase induction motor using acoustic signals. Appl Acoust 2017; 117: 20–27.

262.

Glowacz

. Recognition of acoustic signals of synchronous motors with the use of MoFS and selected classifiers. Measurement Sci Rev 2015; 15: 167–175.

263.

Glowacz

. Fault diagnosis of single-phase induction motor based on acoustic signals. Mech Syst Signal Pr 2019; 117: 65–80.

264.

Germen

Başaran

Fidan

. Sound based induction motor fault diagnosis using Kohonen self-organizing map. Mech Syst Signal Pr 2014; 46: 45–58.

265.

Pan

Zhou

, et al. Automatic localization of the rotor-stator rubbing fault based on acoustic emission method and higher-order statistics. J Mech Sci Technol 2019; 33:513–524.

266.

Stief

Ottewill

Orkisz

, et al. Two stage data fusion of acoustic, electric and vibration signals for diagnosing faults in induction motors. Elektronika ir Elektrotechnika 2017; 23: 19–24.

267.

Piltan

Kim

J-M

. Nonlinear extended-state ARX-Laguerre PI observer fault diagnosis of bearings. Appl Sci 2019; 9: 888.

268.

Raghav

Sharma

. A review on fault diagnosis and condition monitoring of gearboxes by using AE technique. Arch Comput Methods Eng 2020; 1–15. doi: 10.1007/s11831-020-09480-8

269.

Glowacz

. Acoustic-based fault diagnosis of commutator motor. Electron 2018; 7: 299.

270.

AlShorman

Alshorman

Masadeh

. A review of physical human activity recognition chain using sensors. Indonesian J Electr Eng Inform (IJEEI) 2020; 8: 560–573.

271.

Qiao

Zhang

, et al. Review of intelligent fault diagnosis for permanent magnet synchronous motors in electric vehicles. Adv Mech Eng 2020; 12: 1687814020944323.

272.

AlShorman

Masadeh

Alkahtani

, et al. A review of condition monitoring and fault diagnosis and detection of rotating machinery based on image aspects. In: 2020 international conference on data analytics for business and industry: way towards a sustainable economy (ICDABI), Sakheer, Bahrain, 2020, pp. 1–5.

273.

AlShorman

. A review of intelligent methods for condition monitoring and fault diagnosis of stator and rotor faults of induction machines. Int J Electr Comput Eng (IJECE) 2021; 11: 4.

274.

Guragai

AlShorman

Masadeh

, et al. A survey on deep learning classification algorithms for motor imagery. In: 2020 32nd international conference on microelectronics (ICM), Aqaba, Jordan, 2020, pp. 1–4.

Sounds and acoustic emission-based early fault diagnosis of induction motor: A review study

Abstract

Keywords

Introduction

General background of AE analysis

Introduction of CM and FD of IM based on AE

Advantage and limitations of AE analysis in CM and FD

CM and FD for IM based on AE

Bearings

Rotor faults

Stator faults

Compound faults

Public datasets

Challenges and future trends

Conclusion

Footnotes

Declaration of conflicting interests

Funding

ORCID iDs

References