A Novel Hybrid Signal Decomposition Technique for Transfer Learning Based Industrial Fault Diagnosis

In the fourth industrial revolution, data-driven intelligent fault diagnosis for industrial purposes serves a crucial role. In contemporary times, although deep learning is a popular approach for fault diagnosis, it requires massive amounts of labelled samples for training, which is arduous to come by in the real world. Our contribution to introduce a novel comprehensive intelligent fault detection model using the Case Western Reserve University dataset is divided into two steps. Firstly, a new hybrid signal decomposition methodology is developed comprising Empirical Mode Decomposition and Variational Mode Decomposition to leverage signal information from both processes for effective feature extraction. Secondly, transfer learning with DenseNet121 is employed to alleviate the constraints of deep learning models. Finally, our proposed novel technique surpassed not only previous outcomes but also generated state-of-the-art outcomes represented via the F1 score.

[1]  Junsheng Cheng,et al.  Rolling bearing fault diagnosis and performance degradation assessment under variable operation conditions based on nuisance attribute projection , 2019, Mechanical Systems and Signal Processing.

[2]  Dominique Zosso,et al.  Variational Mode Decomposition , 2014, IEEE Transactions on Signal Processing.

[3]  Abdel-Ouahab Boudraa,et al.  EMD-Based Signal Filtering , 2007, IEEE Transactions on Instrumentation and Measurement.

[4]  Hui Liu,et al.  Data processing strategies in wind energy forecasting models and applications: A comprehensive review , 2019, Applied Energy.

[5]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[7]  Hongli Gao,et al.  A new bearing fault diagnosis method based on modified convolutional neural networks , 2020, Chinese Journal of Aeronautics.

[8]  Shu-Kai S. Fan,et al.  A Review on Fault Detection and Process Diagnostics in Industrial Processes , 2020, Processes.

[9]  Muhammad Abid,et al.  Robust fault detection for wind turbines using reference model-based approach , 2017 .

[10]  Yasushi Makihara,et al.  Adaptive Pooling Is All You Need: An Empirical Study on Hyperparameter-insensitive Human Action Recognition Using Wearable Sensors , 2020, 2020 International Joint Conference on Neural Networks (IJCNN).

[11]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[12]  Uday Maji,et al.  Empirical mode decomposition vs. variational mode decomposition on ECG signal processing: A comparative study , 2016, 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[13]  Liang Gao,et al.  A transfer convolutional neural network for fault diagnosis based on ResNet-50 , 2019, Neural Computing and Applications.

[14]  Yong Zhu,et al.  Deep Learning-Based Intelligent Fault Diagnosis Methods Toward Rotating Machinery , 2020, IEEE Access.

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

[16]  Martin Howarth,et al.  A Novel Deep Learning Model for the Detection and Identification of Rolling Element-Bearing Faults , 2020, Sensors.

[17]  Qiang Miao,et al.  A Deep Learning Method for Bearing Fault Diagnosis Based on Time-Frequency Image , 2019, IEEE Access.

[18]  Xinyu Shao,et al.  Sensor Data-Driven Bearing Fault Diagnosis Based on Deep Convolutional Neural Networks and S-Transform , 2019, Sensors.

[19]  Jong-Myon Kim,et al.  A Hybrid Feature Model and Deep-Learning-Based Bearing Fault Diagnosis , 2017, Sensors.

[20]  Laohu Yuan,et al.  Rolling Bearing Fault Diagnosis Based on Convolutional Neural Network and Support Vector Machine , 2020, IEEE Access.

[21]  Hui Liu,et al.  Intelligent modeling strategies for forecasting air quality time series: A review , 2021, Appl. Soft Comput..

[22]  Dongrui Wu,et al.  Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis , 2019, Neurocomputing.

[23]  Wentao Mao,et al.  Imbalanced Fault Diagnosis of Rolling Bearing Based on Generative Adversarial Network: A Comparative Study , 2019, IEEE Access.

[24]  Robert B. Randall,et al.  Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study , 2015 .

[25]  Chenglin Wen,et al.  Deep learning fault diagnosis method based on global optimization GAN for unbalanced data , 2020, Knowl. Based Syst..

[26]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  M. Salman Leong,et al.  Variational mode decomposition: mode determination method for rotating machinery diagnosis , 2018, Journal of Vibroengineering.

[28]  Gavriel Salomon,et al.  T RANSFER OF LEARNING , 1992 .

[29]  Abdel-Ouahab Boudraa,et al.  On signal denoising by EMD in the frequency domain , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[30]  Feng Liu,et al.  Bearing Fault Diagnosis Based on the Switchable Normalization SSGAN with 1-D Representation of Vibration Signals as Input , 2019, Sensors.

[31]  Haidong Shao,et al.  Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet. , 2017, ISA transactions.

[32]  Cong Wang,et al.  Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings , 2016 .

[33]  Hongyi Li,et al.  An Improved EMD and Its Applications to Find the Basis Functions of EMI Signals , 2015 .

[34]  Niall O' Mahony,et al.  Deep Learning vs. Traditional Computer Vision , 2019, CVC.

[35]  Dazhong Wu,et al.  Deep learning for smart manufacturing: Methods and applications , 2018, Journal of Manufacturing Systems.

[36]  Jong-Myon Kim,et al.  A two-dimensional fault diagnosis model of induction motors using a gabor filter on segmented images , 2016 .

[37]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[38]  Mohan Kumar Pradhan,et al.  Fault detection analysis in rolling element bearing: A review , 2017 .

[39]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).