Abstract
Traditional fault diagnosis methods of DC (direct current) motors require high expertise and human labor. However, the other disadvantages of these methods are low efficiency and poor accuracy. To address these problems, a new adaptive and intelligent mechanical fault diagnosis method for DC motors based on variational mode decomposition (VMD), singular value decomposition (SVD), and residual deep convolutional neural networks with wide first-layer kernels (R-WDCNN) was proposed. First, the vibration signals of a DC motor were collected by a designed acquisition system. Subsequently, VMD was employed to decompose the raw signals adaptively into several intrinsic mode functions (IMFs). Moreover, the transient frequency means method, which can quickly and accurately obtain the optimal value of K, is proposed. SVD was applied to reduce the dimensionality of the IMF matrix for further feature extraction. Finally, the reconstructed matrix containing the main fault feature information was used to train and test the R-WDCNN. Based on residual learning, identification and classification of four types of vibration signals were achieved, while the R-WDCNN was optimized by the adaptive batch normalization algorithm (AdaBN). The recognition rate and the convergence were improved by this classifier. The results show that the method proposed in this paper has better adaptability and intelligence than other methods, and the R-WDCNN can reach a 94% recognition rate on unknown samples. Therefore, the proposed method is more intelligent and accurate than other methods.
Similar content being viewed by others
References
Zhang Q, Feng M (2018) Fast fault diagnosis method for hall sensors in brushless dc motor drives[J]. IEEE Trans Power Electron 34(3):2585–2596
Manana M, Arroyo A, Ortiz A, Renedo CJ, Perez S, Delgado F (2011) Field winding fault diagnosis in DC motors during manufacturing using thermal monitoring[J]. Appl Therm Eng 31(5):978–983
Lei Y, Lin J, He Z, Zuo MJ (2013) A review on empirical mode decomposition in fault diagnosis of rotating machinery[J]. Mech Syst Signal Process 35(1–2):108–126
Hu A, Xiang L (2016) An optimal selection method for morphological filter’s parameters and its application in bearing fault diagnosis[J]. J Mech Sci Technol 30(3):1055–1063
Cheng J, Yu D, Tang J, Yang Y (2009) Application of SVM and SVD technique based on EMD to the fault diagnosis of the rotating machinery[J]. Shock Vib 16(1):89–98
Baydar N, Ball A (2001) A comparative study of acoustic and vibration signals in detection of gear failures using wigner–ville distribution[J]. Mech Syst Signal Process 15(6):1091–1107
Oehlmann H, Brie D, Tomczak M, Richard A (1997) A method for analysing gearbox faults using time–frequency representations[J]. Mech Syst Signal Process 11(4):529–545
Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proc Math Phys Eng Sci 454(1971):903–995
Smith JS (2005) The local mean decomposition and its application to EEG perception data. J R Soc Interface 2:443–454
Wang D, Miao Q, Fan X, Huang HZ (2009) Rolling element bearing fault detection using an improved combination of Hilbert and wavelet transforms[J]. J Mech Sci Technol 23(12):3292–3301
Huang NE, Shen Z, Long SR et al (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proc A 454(1971):903–995
Yu D, Cheng J, Yang Y (2005) Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings[J]. Mech Syst Signal Process 19(2):259–270
Rai A, Upadhyay SH (2017) Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering[J]. Mech Syst Signal Process 93:16–29
Daubechies I (1990) The wavelet transform, time-frequency localization and signal analysis[J]. IEEE Trans Inf Theory 36(5):961–1005
Wu Z, Huang NE (2004) A study of the characteristics of white noise using the empirical mode decomposition method[J]. Proc R Soc A Math Phys Eng Sci 460(2046):1597–1611
Liu H, Zhang J, Cheng Y et al (2016) Fault diagnosis of gearbox using empirical mode decomposition and multi-fractal detrended cross-correlation analysis[J]. J Sound Vib 385:350–371
Jiang H, Li C, Li H (2013) An improved EEMD with multiwavelet packet for rotating machinery multi-fault diagnosis[J]. Mech Syst Signal Process 36(2):225–239
Wu Z, Huang NE (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Adv Adapt Data Anal 01(01):1–41
Smith JS (2005) The local mean decomposition and its application to EEG perception data[J]. J R Soc Interface 2(5):443–454
Xu Y, Zhang K, Ma C et al (2019) Optimized LMD method and its applications in rolling bearing fault diagnosis[J]. Meas Sci Technol:30(12)
Dragomiretskiy K, Zosso D (2014) Variational mode decomposition[J]. IEEE Trans Signal Process 62(3):531–544
Jianchang L, He Q, Xia Y, Wei H, Zhenhua L. Fault diagnosis of rolling bearings based on parameter optimization of VMD and sample entropy [J/OL]. Acta Autom Sin 1–12[2019-10-31]. https://doi.org/10.16383/j.aas.190345
Cheng H, Zhang Y, Lu W et al (2019) A bearing fault diagnosis method based on VMD-SVD and fuzzy clustering[J]. Int J Pattern Recognit Artif Intell:33(12)
Lin J, Liangsheng QU (2000) Feature extraction based on morlet wavelet and its application for mechanical fault diagnosis[J]. J Sound Vib 234(1):135–148
Peng ZK, Chu FL (2004) Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography[J]. Mech Syst Signal Process 18(2):199–221
Jiao J, Zhao M, Lin J, et al. (2018) Hierarchical discriminating sparse coding for weak fault feature extraction of rolling bearings[J]. Reliab Eng Syst Saf 184(APR.):41-54
Van Der Veen A-J, Deprettere EF, Swindlehurst AL (1993) Subspace-based signal analysis using singular value decomposition[J]. Proc IEEE 81(9):1277–1308
Golafshan R, Sanliturk KY (2015) SVD and Hankel matrix based de-noising approach for ball bearing fault detection and its assessment using artificial faults[J]. Mech Syst Signal Process 70–71:36–50
Guozheng H (2017) Distribution network fault detection based on wavelet transform and singular value decomposition [D]. decomposition.(Master Thesis, Shandong University of Science and Technology) https://kns.cnki.net/KCMS/detail/detail.aspx?dbname;CMFD201801amp;filename;1017296897.nh
Velazquez A, Swartz RA (2015) Output-only cyclo-stationary linear-parameter time-varying stochastic subspace identification method for rotating machinery and spinning structures[J]. J Sound Vib 337:45–70
Cong F, Zhong W, Tong S, Tang N, Chen J (2015) Research of singular value decomposition based on slip matrix for rolling bearing fault diagnosis[J]. J Sound Vib 344:447–463
Chang L, Gang C, Xihui C et al (2018) Planetary gears feature extraction and fault diagnosis method based on VMD and CNN[J]. Sensors 18(5):1523
Xuezhi Z, Bangyan Y, Tongjian C (2010) Singular value difference Spectrum theory and its application in fault diagnosis of lathe headstock[J]. J Mech Eng 01:104–112
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition[J]. Proc IEEE 86(11):2278–2324
Chen Y, Jiang H, Li C, Jia X, Ghamisi P (2016) Deep feature extraction and classification of HyperspectralImages based on convolutional neural networks. IEEE Trans Geosci Remote Sens 54:6232–6251
Huang Y, Wu R, Sun Y, Wang W, Ding X (2015) Vehicle logo recognition system based on convolutional neural networks with a Pretraining strategy[J]. IEEE Trans Intell Transp Syst 16(4):1951–1960
Aytar Y, Vondrick C, Torralba A (2016) SoundNet: learning sound Representations from unlabeled video[C]//Advances in neural information processing systems. 892-900
Li Y, Wang N, Shi J, et al. (2016) Revisiting batch normalization for practical domain adaptation[J]. Pattern Recogn 80
Ma S, Chu F (2019) Ensemble deep learning-based fault diagnosis of rotor bearing systems[J]. Comput Ind 105:143–152
Wei Z, Gaoliang P, Chuanhao L et al (2017) A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals[J]. Sensors 17(2):425
Jixiang YE, Haixiang HU (2014) Application of Hilbert marginal energy spectrum in speech emotion recognition[J]. Comput Eng Appl 50(7):203–207
Jiang P, Hu Z, Liu J, Yu S, Wu F (2016) Fault diagnosis based on chemical sensor data with an active deep neural network[J]. Sensors 16(10):1695
Wang Z, Jia L, Qin Y (2018) Adaptive diagnosis for rotating machineries using information geometrical kernel-ELM based on VMD-SVD[J]. Entropy 20(1):73
Levent E, Turker I, Serkan K (2018) A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier. Signal Process Syst 179–189
Xingxing J, Shunming L, Chun C (2016) A novel method for adaptive multiresonance bands detection based on VMD and using MTEO to enhance rolling element bearing fault diagnosis[J]. Shock Vib 1–20
Bing L, Mingliang L, Zijian G, et al. (2018) Mechanical fault diagnosis of high voltage circuit breakers utilizing EWT-improved time frequency entropy and optimal GRNN Classifier[J]. Entropy 20(6):448
Acknowledgments
This work is supported by natural science foundation of Heilongjiang province of China (No.LH2020F046), Graduate Innovation Research Project of Heilongjiang University (No.YJSCX2020-169HLJU).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Qin, H., Liu, M., Wang, J. et al. Adaptive diagnosis of DC motors using R-WDCNN classifiers based on VMD-SVD. Appl Intell 51, 4888–4907 (2021). https://doi.org/10.1007/s10489-020-02087-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-02087-3