Intelligent fault diagnosis method for common rail injectors based on hierarchical weighted permutation entropy and pair-wise feature proximity feature selection
Restricted accessResearch articleFirst published online September, 2022
Intelligent fault diagnosis method for common rail injectors based on hierarchical weighted permutation entropy and pair-wise feature proximity feature selection
It is of great significance for intelligent manufacturing to study diagnosis methods to realize the diagnosis of mechanical equipment faults. Multiscale weighted permutation entropy is an effective method recently proposed to measure the complexity and dynamic changes of dynamic systems. To solve the shortcoming of multiscale weighted permutation entropy that does not consider high-frequency components, this article proposes hierarchical weighted permutation entropy, which can comprehensively and accurately reflect the low-frequency and high-frequency information of the time series. The simulation signal verifies the effectiveness and superiority of hierarchical weighted permutation entropy. Then, a novel intelligent fault diagnosis method for common rail injectors based on hierarchical weighted permutation entropy and pair-wise feature proximity is proposed. Finally, the proposed method is applied to the common rail injector fault data, and the results verify the effectiveness of the proposed method. Compared with other methods, this method has a higher fault recognition rate and stronger robustness.
AggarwalCCHinneburgAKeimDA (2001) On the surprising behavior of distance metrics in high dimensional space. In: Lecture notes in computer science 1973, London, England, 4–6 January, pp. 420–434.
2.
BandtCPompeB (2002) Permutation entropy: a natural complexity measure for time series. Physical Review Letters88(17): 174102.
3.
BolourchiPMoradiMDemirelH, et al. (2020) Improved SAR target recognition by selecting moment methods based on fisher score. Signal, Image and Video Processing14(1): 39–47.
4.
BradleyPSMangasarianOL (1998) Mangasarian feature selection via concaveminimization and support vector machines. International Conferenceon Machine Learning (ICML)98: 82–90.
5.
ChenSShangP (2020) Financial time series analysis using the relation between MPE and MWPE. Physica A: Statistical Mechanics and its Applications537: 122716.
6.
ChenWZhuangJYuW, et al. (2009) Measuring complexity using fuzzyen, apen, and sampen[J]. Medical Engineering & Physics31(1): 61–68.
7.
FadlallahBChenBDKeilA (2013) Weighted-permutation entropy: A complexity measure for time series incorporating amplitude information. Physical Reviewe87(2): 022911.
8.
HappySLMohantyRAurobindaRoutray (2017) An effective feature selection method based on pair-wise feature proximity for high dimensional low sample size data. In: 25th European signal processing conference (EUSIPCO), Greece, 28 August–2 September, pp. 1574–1578.
9.
Hernandez-MurielJABermeo-UlloaJBHolguin-LondoñoM, et al. (2020) Bearing health monitoring using relief-f-based feature relevance analysis and HMM. Applied Sciences10(15): 5170.
10.
HuYGLuWBZhangL, et al. (2019) Dynamic response and control of middle rock sidewall under impact of blast loading. Journal Of Vibration And Control25(9):1572–1584.
11.
HuYHuXXuZ, et al. (2000) Fault simulation and characteristic analysis of circulating fuel system[J]. Surgical Endoscopy2: 40–67.
12.
IrcioJLojoAMoriU, et al. (2020) Mutual information based feature subset selection in multivariate time series classification. Pattern Recognition108: 107525.
13.
KowalskiJKrawczykBWoźniakM (2017) Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble. Engineering Applications of Artificial Intelligence57: 134–141.
14.
LeeYHoon LeeC (2018) An uncertainty analysis of the time-resolved fuel injection pressure wave based on BOSCH method for a common rail diesel injector with a varying current wave pattern. Journal of Mechanical Science and Technology32: 5937–5945.
15.
LiuHXieHHeW, et al. (2010) Characterization and classification of EEG sleep stage based on fuzzy entropy[J]. Journal of Data Acquisition & Processing25(4): 484–489.
16.
MaoXWeiXWangJ, et al. (2016) Start-of-injection-based software optimization for consistency between the cylinders in common-rail diesel engines. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering230(5): 709–720.
17.
PincusS (1995) Approximate entropy (ApEn) as a complexity measure. Chaos: An Interdisciplinary Journal of Nonlinear Science5(1): 110–117.
18.
RichmanJSMoormanJR (2000) Physiological time series analysis using approximate entropy and sample entropy[J]. American Journal of Physiology Heart and Circulatory Physiology278(6): 2039–2049.
19.
SinghNKSinghYSharmaA, et al. (2020) Prediction of performance and emission parameters of Kusum biodiesel based diesel engine using neuro-fuzzy techniques combined with genetic algorithm. FUEL280: 118629.
20.
SongEZKeYYaoC, et al. (2019) Fault diagnosis method for high-pressure common rail injector based on IFOA-VMD and hierarchical dispersion entropy. ENTROPY21(10): 923.
21.
TogacarMErgenBComertZ (2020) Classification of flower species by using features extracted from the intersection of feature selection methods in convolutional neural network models. Measurement158: 07703.
22.
WangX.LuZ.WeiJ., et al. (2019) Fault diagnosis for rail vehicle axle-box bearings based on energy feature reconstruction and composite multiscale permutation entropy. Entropy21(9): 865.
23.
WangXSiSLiY, et al. (2020a) An integrated method based on refined composite multivariate hierarchical permutation entropy and random forest and its application in rotating machinery.Journal of Vibration and Control, 26(3–4): 146–160.
24.
WangZYYaoLGCaiYW (2020b) Rolling bearing fault diagnosis using generalized refined composite multiscale sample entropy and optimized support vector machine. Measurement156: 107574.
25.
YanRGaoRX (2007) Approximate entropy as a diagnostic tool for machine health monitoring[J]. Mechanical Systems and Signal Processing21(2): 824–839.
26.
YangXJLiuGYuQ, et al. (2018) Stable and orthogonal local discriminant embedding using trace ratio criterion for dimensionality reduction. Multimedia Tools And Applications77(3): 3071–3081.
27.
Yong-shengYAn-boMYou-yunZ, et al. (2017) Discriminative non-negative matrix factorization (DNMF) and its application to the fault diagnosis of diesel engine. Mechanical Systems and Signal Processing95: 158–171.
28.
ZhangWZhouJ (2019) Fault diagnosis for rolling element bearings based on feature space reconstruction and multiscale permutation entropy. Entropy21(5): 519.
29.
ZhengJPanHYangS, et al. (2018) Generalized composite multiscale permutation entropy and Laplacian score based rolling bearing fault diagnosis. Mechanical Systems and Signal Processing99: 229–243.
30.
ZhengJDongZPanH, et al. (2019) multi-scale weighted permutation entropy and extreme learning machine based intelligent fault diagnosis for rolling bearing. Measurement143: 69–80.
31.
ZhongZ (2020) Adaptive graph learning and low-rank constraint for supervised spectral feature selection. Neural Computing and Applications32(11): 6503–6512.
