A novel method of combining nonlinear frequency spectrum and deep learning for complex system fault diagnosis

Abstract A novel fault diagnosis method is proposed for complex systems by combining nonlinear frequency spectrum and stacked denoising auto-encoders (SDAE). In order to solve the problem of large calculation amount of generalized frequency response functions (GFRF), one-dimensional nonlinear output frequency response functions (NOFRF) are used to obtain nonlinear frequency spectrum. In order to overcome the problem of weak ability of fault features extraction, stacked denoising auto-encoders (SDAE) neural network is adopted to extract the fault features from nonlinear frequency spectrum. In this novel method, four orders nonlinear frequency spectrum of each state of Permanent Magnet Synchronous Motor (PMSM) are obtained by identification algorithm; Then, choosing suitable sampling points from four orders frequency spectrum to construct high-dimensional data; Finally, stacked denoising auto-encoders (SDAE) neural network is designed to realize the output of fault classification. Simulations indicate that the proposed method has good real-time performance and high diagnosis accuracy.

[1]  Guangquan Zhao,et al.  A novel approach for analog circuit fault diagnosis based on Deep Belief Network , 2018, Measurement.

[2]  Xiaopeng Li,et al.  Nonlinear response analysis of gear-shaft-bearing system considering tooth contact temperature and random excitations , 2019, Applied Mathematical Modelling.

[3]  F. Chu,et al.  Numerical analysis of cracked beams using nonlinear output frequency response functions , 2008 .

[4]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[5]  Nikos A. Aspragathos,et al.  Introduction to the special issue on Theories and Methodologies for mechatronics design , 2010 .

[6]  Fei Xue,et al.  Modelling of Automotive Engine Dynamics using Diagonal Recurrent Neural Network , 2018, J. Univers. Comput. Sci..

[7]  Marios M. Polycarpou,et al.  Fault detection for service mobile robots using model-based method , 2015, Autonomous Robots.

[8]  Sergey Akhmetov,et al.  Fault Detection and Diagnosis In Hall–Héroult Cells Based on Individual Anode Current Measurements Using Dynamic Kernel PCA , 2018, Metallurgical and Materials Transactions B.

[9]  Teng Ren,et al.  Track circuit fault prediction method based on grey theory and expert system , 2019, J. Vis. Commun. Image Represent..

[10]  S. A. Billings,et al.  Crack detection using nonlinear output frequency response functions - an experimental study , 2006 .

[11]  Junsheng Cheng,et al.  Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosis , 2019 .

[12]  Zi-Qiang Lang,et al.  Fault diagnosis methodology based on nonlinear system modelling and frequency analysis , 2014 .

[13]  Robert X. Gao,et al.  Deep learning and its applications to machine health monitoring , 2019, Mechanical Systems and Signal Processing.

[14]  Chao Liu,et al.  A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults , 2019, Knowl. Based Syst..

[15]  Zi-Qiang Lang,et al.  The analysis of nonlinear systems in the frequency domain using Nonlinear Output Frequency Response Functions , 2018, Autom..

[16]  Weihua Li,et al.  Deep Learning With Emerging New Labels for Fault Diagnosis , 2019, IEEE Access.

[17]  Yong-Hwa Kim,et al.  Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear , 2018 .

[18]  Shunming Li,et al.  Batch-normalized deep neural networks for achieving fast intelligent fault diagnosis of machines , 2019, Neurocomputing.

[19]  Yunpeng Zhu,et al.  Design of Nonlinear Systems in the Frequency Domain: An Output Frequency Response Function-Based Approach , 2018, IEEE Transactions on Control Systems Technology.

[20]  Xin Ye,et al.  A novel adaptive fault detection methodology for complex system using deep belief networks and multiple models: A case study on cryogenic propellant loading system , 2018, Neurocomputing.

[21]  Zhike Peng,et al.  The Nonlinear Output Frequency Response Functions of One-Dimensional Chain Type Structures , 2010 .

[22]  Subhojit Ghosh,et al.  Enhancing the reliability of protection scheme for PV integrated microgrid by discriminating between array faults and symmetrical line faults using sparse auto encoder , 2018, IET Renewable Power Generation.

[23]  Liang Gao,et al.  A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[24]  Sungyoung Lee,et al.  RDR-based knowledge based system to the failure detection in industrial cyber physical systems , 2018, Knowl. Based Syst..

[25]  Martin Riera-Guasp,et al.  Automatic Fault Diagnostic System for Induction Motors under Transient Regime Optimized with Expert Systems , 2018, Electronics.

[26]  Jun Gao,et al.  A cable fault recognition method based on a deep belief network , 2018, Comput. Electr. Eng..

[27]  Zehui Mao,et al.  Deep PCA Based Real-Time Incipient Fault Detection and Diagnosis Methodology for Electrical Drive in High-Speed Trains , 2018, IEEE Transactions on Vehicular Technology.

[28]  Jianfu Cao,et al.  Fault diagnosis of complex system based on nonlinear frequency spectrum fusion , 2013 .

[29]  Jun Yan,et al.  Multiscale Convolutional Neural Networks for Fault Diagnosis of Wind Turbine Gearbox , 2019, IEEE Transactions on Industrial Electronics.

[30]  Wei Jiang,et al.  Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders. , 2018, ISA transactions.

[31]  Junling Zhang,et al.  Application of stack marginalised sparse denoising auto-encoder in fault diagnosis of rolling bearing , 2018 .

[32]  Feng Gao,et al.  Fault diagnosis for multivariable non-linear systems based on non-linear spectrum feature , 2017 .