In the field of rotating machinery fault diagnosis, convolutional neural networks (CNNs) have received lots of attention due to their wide application, and improving the performance of CNNs has extremely profound significance in engineering practice. Reasonable noise injection can effectively enhance the capability of CNN in extracting mechanical fault features. As a result, developing effective noise injection strategies has become an important issue worthy of in-depth investigation and research. Therefore, this article proposes a hierarchical-injected noise-enhanced CNN (HINECNN) model aimed at improving the fault diagnosis capability of CNN, particularly when processing the limited training samples. Specifically, different noise injection modes are designed in the convolutional and activation layers of the model, thereby enhancing the capacity for extracting complex data features and generalization performance. Furthermore, a noise intensity adaptive determination method combining network parameters and training epochs is designed. It can not only accelerate the early training process of the network but also effectively reduce the potential interference of noise on model convergence in the later stage of training. Finally, to evaluate the ability of the HINECNN model to generalize, two fault datasets of rolling bearing are used to construct testing tasks with different sample sizes. The results illustrate that when compared with traditional methods, the suggested model achieves significant improvements in diagnostic accuracy and generalization capability, particularly when processing the limited training samples. This research can offer a reference for exploring the utilization of noise benefits in mechanical fault intelligent diagnosis.
ChenJLiuH.A multi-gradient hierarchical domain adaptation network for transfer diagnosis of bearing faults. Expert Syst Appl2023; 225: 120139.
2.
ZhangYHanDYShiPM.Semi-supervised prototype network based on compact-uniform-sparse representation for rotating machinery few-shot class incremental fault diagnosis. Expert Systems Appl2024; 255: 124660.
3.
CuiJGaoJXingR, et al. Fault diagnosis method for rolling bearing based on attention mechanism and BiTCN model. Digital Signal Process2025; 167: 105454.
4.
LiJZhangXYueK, et al. An auto-regulated universal domain adaptation network for uncertain diagnostic scenarios of rotating machinery. Expert Syst Appl2024; 249: 123836.
5.
QinZZhangZWuZ, et al. Fault diagnosis method for rolling bearings under a small sample dataset based on improved WGAN-GP. Measurement2025; 256: 118456.
6.
ZhouHYanPHuangQ, et al. Weighted average selective ensemble strategy of deep convolutional models based on grey wolf optimizer and its application in rotating machinery fault diagnosis. Expert Syst Appl2023; 234: 117716.
7.
ChenHChenZChaiZ, et al. A single-side neural network-aided canonical correlation analysis with applications to fault diagnosis. IEEE Trans Cybernetics2022; 52: 9454–9466.
8.
BhaktaKSikderNNahidAA, et al. Fault diagnosis of induction motor bearing using cepstrum-based preprocessing and ensemble learning algorithm. In: 2019 International conference on electrical, computer and communication engineering, Cox’sBazar, Bangladesh, 2019, pp. 1–6.
9.
GuoJLiuYYangR, et al. Differgram: a convex optimization-based method for extracting optimal frequency band for fault diagnosis of rotating machinery. Expert Syst Appl2024; 245: 123051.
10.
DongHRYuGJiangQT.Time–frequency-multisqueezing transform. IEEE Trans Ind Electron2024; 71: 4151–4161.
11.
RajabiSSaman AzariMSantiniS, et al. Fault diagnosis in industrial rotating equipment based on permutation entropy, signal processing and multi-output neuro-fuzzy classifier. Expert Syst Appl2022; 206: 117754.
12.
WuT. Fault diagnosis method of rolling bearing based on EMD-Hilbert envelope spectrum and BPNN. In: IOP Conference Series: Earth and environmental science, 2021, Kamakura, Japan, vol. 632, p. 052084.
13.
KulevomeDKBWangHCobbinahBM, et al. Effective time-series data augmentation with analytic wavelets for bearing fault diagnosis. Expert Syst Appl2024; 249: 123536.
14.
LiWChenJLiJ, et al. Derivative and enhanced discrete analytic wavelet algorithm for rolling bearing fault diagnosis. Microprocessors Microsyst2021; 82: 103872.
15.
FuQJingBHePJ, et al. Fault feature selection and diagnosis of rolling bearings based on EEMD and optimized Elman_AdaBoost algorithm. IEEE Sens J2018; 18: 5024–5034.
16.
PatelSPUpadhyaySH.Euclidean distance based feature ranking and subset selection for bearing fault diagnosis. Expert Syst Appl2020; 154: 113400.
17.
LiWPCaoYLiLJ, et al. An orthogonal wavelet transform-based K-nearest neighbor algorithm to detect faults in bearings. Shock Vibration2022; 2022: 5242106.
18.
ChenFFChengMTTangBP, et al. Pattern recognition of a sensitive feature set based on the orthogonal neighborhood preserving embedding and adaboost_SVM algorithm for rolling bearing early fault diagnosis. Meas Sci Technol2020; 31: 105007.
19.
GunerkarRSJalanAKBelgamwarSU.Fault diagnosis of rolling element bearing based on artificial neural network. J Mech Sci Technol2019; 33: 505–511.
20.
WangLRaoHDongZ, et al. Automatic fault diagnosis of rolling bearings under multiple working conditions based on unsupervised stack denoising autoencoder. Struct Health Monit2024; 23: 3084–3104.
21.
HeDZhaoJJinZ, et al. DCAGGCN: a novel method for remaining useful life prediction of bearings. Reliab Eng Syst Safety2025; 260: 110978.
22.
JiangHKLiXQShaoHD, et al. Intelligent fault diagnosis of rolling bearings using an improved deep recurrent neural network. Meas Sci Technol2018; 29: 065107.
23.
LiJLiuYLiQ.Intelligent fault diagnosis of rolling bearings under imbalanced data conditions using attention-based deep learning method. Measurement2022; 189: 110500.
24.
ZhangBZhangSLiW.Bearing performance degradation assessment using long short-term memory recurrent network. Comput Industry2019; 106: 14–29.
25.
GaoDWZhuYSRenZJ, et al. A novel weak fault diagnosis method for rolling bearings based on LSTM considering quasi-periodicity. Knowledge-Based Syst2021; 231: 107413.
26.
HanTMaRZhengJ.Combination bidirectional long short-term memory and capsule network for rotating machinery fault diagnosis. Measurement2021; 176: 109208.
27.
BhadaneMRamachandranKI.Bearing fault identification and classification with convolutional neural network. In: 2017 International conference on circuit, power and computing technologies, 2017, Kollam, India, pp. 1–5.
28.
WenLLiXYGaoL, et al. A new convolutional neural network-based data-driven fault diagnosis method, IEEE Trans Industrial Electronics2018; 65: 5990–5998.
29.
GuoSZhangBYangT, et al. Multitask convolutional neural network with information fusion for bearing fault diagnosis and localization. IEEE Trans Ind Electronics2020; 67: 8005–8015.
30.
GuJPengYLuH, et al. A novel fault diagnosis method of rotating machinery via VMD, CWT and improved CNN. Measurement2022; 200: 111635.
31.
LiuBYanCHeC, et al. An interpretable physics-informed subdomain moment-enhanced adaptation network for unsupervised transfer fault diagnosis of rolling bearing. Adv Eng Inform2025; 67: 103491.
32.
ZhangWPengGLiC, et al. A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors2017; 17: 425.
33.
LiXWanSLiuS, et al. Bearing fault diagnosis method based on attention mechanism and multilayer fusion network. ISA Trans2022; 128: 550–564.
34.
LiXMaZQYuanZH, et al. A review on convolutional neural network in rolling bearing fault diagnosis. Meas Sci Technol2024; 35: 072002.
35.
LiuBYanCLiuY, et al. ISEANet: an interpretable subdomain enhanced adaptive network for unsupervised cross-domain fault diagnosis of rolling bearing. Adv Eng Inform2024; 62: 102610.
36.
WangZPanS. An improved convolutional neural network based on noise layer. In: 14th International conference on knowledge science, engineering, and management, 2021, Tokyo, Japan, pp. 64–74.
37.
BenziRSuteraAVulpianiA.The mechanism of stochastic resonance. J Phys A Mathematical General1981; 14: L453–L457.
38.
SampannaRMitaimS.Noise benefits in motor imagery classification using ensemble support vector machine. In: 2014 IEEE Biomedical Circuits and Systems Conference, 2014, Lausanne, Switzerland, pp. 53–56.
39.
KoskoBAudhkhasiKOsobaO.Noise can speed backpropagation learning and deep bidirectional pretraining. Neural Netw2020; 129: 359–384.
XiaoLTangJXZhangXH, et al. Remaining useful life prediction based on intentional noise injection and feature reconstruction. Reliab Eng Syst Safety2021; 215: 107871.
42.
ChenLAnKHuangDL, et al. Noise-boosted convolutional neural network for edge-based motor fault diagnosis with limited samples. IEEE Trans Industrial Inform2023; 19: 9491–9502.
43.
BohorquezJLambert MartinFAlexanderB, et al. Stochastic resonance enhancement for leak detection in pipelines using fluid transients and convolutional neural networks. J Water Resources Planning Management2022; 148: 04022001.
44.
YangCPQiaoZJZhuRH, et al. An intelligent fault diagnosis method enhanced by noise injection for machinery. IEEE Trans Instrumen Meas2023; 72: 3534011.
45.
GulcehreCMoczulskiMDenilM, et al. Noisy activation functions. In: International conference on machine learning, 2016, [New York, America, p. 48.
46.
XiaoLPengYJHongLJ, et al. Training artificial neural networks by generalized likelihood ratio method: an effective way to improve robustness. In: 2020 IEEE 16th International conference on automation science and engineering, 2020, Hong Kong, China, pp. 1343–1348.
47.
BaiSDuanFChapeau-BlondeauF, et al. Generalization of stochastic-resonance-based threshold networks with Tikhonov regularization. Phys Rev E2022; 106: L012101.
48.
DuanFBChapeau-BlondeauFAbbottD.Optimized injection of noise in activation functions to improve generalization of neural networks. Chaos Solitons Fract2024; 178: 114363.
49.
KumarAZhouYGandhiCP, et al. Bearing defect size assessment using wavelet transform based deep convolutional neural network (DCNN). Alexandria Eng J2020; 59: 999–1012.
