A semi-supervised transferable LSTM with feature evaluation for fault diagnosis of rotating machinery

Aiming at the issue of impracticality or costliness of collecting enough labeled signals under all working conditions, the performance of a method usually suffers a significant loss when the model trained on one working condition is directly applied to another working condition. Thus, the entropy gain ratio combined with a semi-supervised transferable LSTM (EGR-STLSTM) network is established for fault diagnosis of rotating machinery under variable working conditions. First, the ERG is devoted to evaluating the multi-domain features extracted based on the characteristics of rotating machinery. Then, the optimal feature subset is fed into the STLSTM to obtain a pre-trained network. Finally, a semi-supervised transfer learning strategy, that is, with the aid of a small number of target labeled samples, is applied to the pre-trained model to achieve competitive performance in target tasks. The proposed EGR-STLSTM network fully uses the vibration characteristics of rotating machinery and retains the specialized knowledge derived from the source domain. The fault diagnosis method is verified with raw vibration signals from a bearing test rig and a gearbox test rig. The experimental results indicate that compared with the well-known methods, the proposed method significantly improves the diagnostic performance by reusing the pre-trained model and reduces the demand for massive labeled samples under variable working conditions.

[1]  Liang Guo,et al.  A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines , 2018, Neurocomputing.

[2]  Daniel S. Kermany,et al.  Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning , 2018, Cell.

[3]  Tang Tang,et al.  A simple data augmentation algorithm and a self-adaptive convolutional architecture for few-shot fault diagnosis under different working conditions , 2020 .

[4]  Fei Liu,et al.  Feature selection for machine fault diagnosis using clustering of non-negation matrix factorization , 2016 .

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

[6]  Huijun Gao,et al.  A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis , 2019, Neurocomputing.

[7]  Junwei Gao,et al.  The Feature Extraction and Diagnosis of Rolling Bearing Based on CEEMD and LDWPSO-PNN , 2020, IEEE Access.

[8]  Yimin Shao,et al.  Crack Fault Classification for Planetary Gearbox Based on Feature Selection Technique and K-means Clustering Method , 2018, Chinese Journal of Mechanical Engineering.

[9]  Wentao Mao,et al.  Predicting Remaining Useful Life of Rolling Bearings Based on Deep Feature Representation and Transfer Learning , 2020, IEEE Transactions on Instrumentation and Measurement.

[10]  Peng Fan,et al.  A sparse stacked denoising autoencoder with optimized transfer learning applied to the fault diagnosis of rolling bearings , 2019, Measurement.

[11]  Noureddine Guersi,et al.  Bearing fault diagnostics using EEMD processing and convolutional neural network methods , 2020, The International Journal of Advanced Manufacturing Technology.

[12]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[13]  Wuyin Jin,et al.  Intelligent fault diagnosis of rolling bearings using a semi-supervised convolutional neural network , 2020, Applied Intelligence.

[14]  Meng Ma,et al.  Deep-Convolution-Based LSTM Network for Remaining Useful Life Prediction , 2021, IEEE Transactions on Industrial Informatics.

[15]  Xianzhi Wang,et al.  Entropy Based Fault Classification Using the Case Western Reserve University Data: A Benchmark Study , 2020, IEEE Transactions on Reliability.

[16]  P. K. Kankar,et al.  A comparison of feature ranking techniques for fault diagnosis of ball bearing , 2016, Soft Comput..

[17]  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.

[18]  Hongmei Li,et al.  Bearing Fault Diagnosis with a Feature Fusion Method Based on an Ensemble Convolutional Neural Network and Deep Neural Network , 2019, Sensors.

[19]  Rajesh P. N. Rao,et al.  Generalized neural decoders for transfer learning across participants and recording modalities , 2020, bioRxiv.

[20]  Shunming Li,et al.  Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method , 2019, Neurocomputing.

[21]  Kate Saenko,et al.  Correlation Alignment for Unsupervised Domain Adaptation , 2016, Domain Adaptation in Computer Vision Applications.

[22]  Sakshi Gupta,et al.  Deep Learning Bidirectional LSTM based Detection of Prolongation and Repetition in Stuttered Speech using Weighted MFCC , 2020 .

[23]  Tao Zhang,et al.  Deep Model Based Domain Adaptation for Fault Diagnosis , 2017, IEEE Transactions on Industrial Electronics.

[24]  Lin Bo,et al.  Fault Diagnosis for High-Speed Train Axle-Box Bearing Using Simplified Shallow Information Fusion Convolutional Neural Network , 2020, Sensors.

[25]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[26]  Ming Hong,et al.  Distance Variance Score: An Efficient Feature Selection Method in Text Classification , 2015 .

[27]  Xiao-Sheng Si,et al.  A rotating machinery fault diagnosis method based on multi-scale dimensionless indicators and random forests , 2020 .

[28]  DeLiang Wang,et al.  Long short-term memory for speaker generalization in supervised speech separation. , 2017, The Journal of the Acoustical Society of America.

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

[30]  Yun Gao,et al.  A hybrid of FEM simulations and generative adversarial networks to classify faults in rotor-bearing systems. , 2020, ISA transactions.

[31]  Xin Zhou,et al.  Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data , 2016 .

[32]  Philip S. Yu,et al.  Transfer Feature Learning with Joint Distribution Adaptation , 2013, 2013 IEEE International Conference on Computer Vision.

[33]  Aske Plaat,et al.  On the Impact of Data Set Size in Transfer Learning Using Deep Neural Networks , 2016, IDA.

[34]  Mohammad Modarres,et al.  Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings , 2017 .

[35]  Shunming Li,et al.  A novel transfer learning method for robust fault diagnosis of rotating machines under variable working conditions , 2019, Measurement.

[36]  Yunpu Wu,et al.  A multi-perspective architecture for high-speed train fault diagnosis based on variational mode decomposition and enhanced multi-scale structure , 2019, Applied Intelligence.

[37]  Pavan Kumar Kankar,et al.  Efficient fault diagnosis of ball bearing using ReliefF and Random Forest classifier , 2017 .

[38]  Jiang Li,et al.  Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model , 2016 .

[39]  Deqing Wang,et al.  t-Test feature selection approach based on term frequency for text categorization , 2014, Pattern Recognit. Lett..

[40]  Gaoliang Peng,et al.  A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load , 2018, Mechanical Systems and Signal Processing.

[41]  Tania Stathaki,et al.  Automatic crack detection for tunnel inspection using deep learning and heuristic image post-processing , 2018, Applied Intelligence.

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

[43]  Generalized neural decoders for transfer learning across participants and recording modalities , 2021, Journal of neural engineering.

[44]  Haizhou Huang,et al.  A personalized diagnosis method to detect faults in gears using numerical simulation and extreme learning machine , 2020, Knowl. Based Syst..

[45]  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.