Wavelet-Prototypical Network Based on Fusion of Time and Frequency Domain for Fault Diagnosis

Neural networks for fault diagnosis need enough samples for training, but in practical applications, there are often insufficient samples. In order to solve this problem, we propose a wavelet-prototypical network based on fusion of time and frequency domain (WPNF). The time domain and frequency domain information of the vibration signal can be sent to the model simultaneously to expand the characteristics of the data, a parallel two-channel convolutional structure is proposed to process the information of the signal. After that, a wavelet layer is designed to further extract features. Finally, a prototypical layer is applied to train this network. Experimental results show that the proposed method can accurately identify new classes that have never been used during the training phase when the number of samples in each class is very small, and it is far better than other traditional machine learning models in few-shot scenarios.

[1]  Jie Tan,et al.  Deep prototypical networks based domain adaptation for fault diagnosis , 2019, Journal of Intelligent Manufacturing.

[2]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[3]  Di Miao,et al.  Research on Fault Diagnosis of High-Voltage Circuit Breaker Based on Support Vector Machine , 2019, Int. J. Pattern Recognit. Artif. Intell..

[4]  Chao Liu,et al.  Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application , 2018, ISA transactions.

[5]  Yu Zheng,et al.  An ensemble framework based on convolutional bi-directional LSTM with multiple time windows for remaining useful life estimation , 2020, Comput. Ind..

[6]  Shou-Ching Hsiao,et al.  Malware Image Classification Using One-Shot Learning with Siamese Networks , 2019, KES.

[7]  Hui Xiong,et al.  A Comprehensive Survey on Transfer Learning , 2019, Proceedings of the IEEE.

[8]  Yinghuan Shi,et al.  Differentiable Meta-learning Model for Few-shot Semantic Segmentation , 2019, AAAI.

[9]  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.

[10]  Feng Wu,et al.  Automatic fault feature extraction of mechanical anomaly on induction motor bearing using ensemble super-wavelet transform , 2015 .

[11]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[12]  Zhihao Liu,et al.  Application of Multi-Dimension Input Convolutional Neural Network in Fault Diagnosis of Rolling Bearings , 2019, Applied Sciences.

[13]  M. Moraud.  Wavelet Networks , 2018, Foundations of Wavelet Networks and Applications.

[14]  Lei Deng,et al.  Multiscale dynamic fusion prototypical cluster network for fault diagnosis of planetary gearbox under few labeled samples , 2020, Comput. Ind..

[15]  Haiyang Pan,et al.  Symplectic geometry mode decomposition and its application to rotating machinery compound fault diagnosis , 2019, Mechanical Systems and Signal Processing.

[16]  Xiao-Ming Wu,et al.  Variational Metric Scaling for Metric-Based Meta-Learning , 2019, AAAI.

[17]  Peng Chen,et al.  Automated function generation of symptom parameters and application to fault diagnosis of machinery under variable operating conditions , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[18]  Suixian Yang,et al.  Learning Attention Representation with a Multi-Scale CNN for Gear Fault Diagnosis under Different Working Conditions , 2020, Sensors.

[19]  Dongyang Dou,et al.  Multi-fault diagnosis of rotating machinery based on deep convolution neural network and support vector machine , 2020 .

[20]  Amos J. Storkey,et al.  How to train your MAML , 2018, ICLR.

[21]  Yu-Chiang Frank Wang,et al.  A Closer Look at Few-shot Classification , 2019, ICLR.

[22]  lt,et al.  Fault diagnosis method based on sensitive feature selection and manifold learning dimension reduction , 2014 .

[23]  Adam Glowacz,et al.  Fault diagnosis of electric impact drills using thermal imaging , 2021 .

[24]  Yong-June Shin,et al.  Fault Diagnosis for Electrical Systems and Power Networks: A Review , 2021, IEEE Sensors Journal.

[25]  Paolo Pennacchi,et al.  Crack effects in rotordynamics , 2008 .

[26]  Yaguo Lei,et al.  Applications of machine learning to machine fault diagnosis: A review and roadmap , 2020 .

[27]  J. Vanschoren.  Meta-Learning , 2018, Automated Machine Learning.

[28]  Wei Zhang,et al.  A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals , 2017, Sensors.

[29]  Md. Palash Uddin,et al.  PCA-based Feature Reduction for Hyperspectral Remote Sensing Image Classification , 2020 .

[30]  Qing Zhao,et al.  Multipoint Optimal Minimum Entropy Deconvolution and Convolution Fix: Application to vibration fault detection , 2017 .

[31]  Yi Wang,et al.  Deep balanced domain adaptation neural networks for fault diagnosis of planetary gearboxes with limited labeled data , 2020 .

[32]  Yuxin Cui,et al.  Limited Data Rolling Bearing Fault Diagnosis With Few-Shot Learning , 2019, IEEE Access.

[33]  Zhenbao Liu,et al.  A Rotating Machinery Fault Diagnosis Method Based on Feature Learning of Thermal Images , 2019, IEEE Access.

[34]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[35]  Shuilong He,et al.  Intelligent fault diagnosis of mechanical equipment under varying working condition via iterative matching network augmented with selective Signal reuse strategy , 2020 .

[36]  Jiwen Dong,et al.  Time-series prediction using a local linear wavelet neural network , 2006, Neurocomputing.

[37]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[38]  Davide Chicco,et al.  Siamese Neural Networks: An Overview , 2021, Artificial Neural Networks, 3rd Edition.

[39]  Yao Lei,et al.  A novel intelligent method for fault diagnosis of electric vehicle battery system based on wavelet neural network , 2020 .

[40]  James T. Kwok,et al.  Generalizing from a Few Examples , 2019, ACM Comput. Surv..

[41]  Yu Zhou,et al.  Application of neural network algorithm in fault diagnosis of mechanical intelligence , 2020, Mechanical Systems and Signal Processing.

[42]  Yiqiang Chen,et al.  Transfer Learning with Dynamic Distribution Adaptation , 2019, ACM Trans. Intell. Syst. Technol..

[43]  Shruti Jadon,et al.  Improving Siamese Networks for One Shot Learning using Kernel Based Activation functions , 2019, ArXiv.

[44]  Konstantinos Gryllias,et al.  A deep learning method for bearing fault diagnosis based on Cyclic Spectral Coherence and Convolutional Neural Networks , 2020 .

[45]  Qing Li,et al.  Bearings fault detection using wavelet transform and generalized Gaussian density modeling , 2020 .