A Compact Convolutional Neural Network Augmented with Multiscale Feature Extraction of Acquired Monitoring Data for Mechanical Intelligent Fault Diagnosis

Abstract Considering all the monitoring data of bearings until failure, very few data are acquired when the bearings are faulty. Such circumstance leads to small faulty sample problem when an intelligent fault diagnosis method is applied. A deep neural network trained with small samples cannot be trained completely, and tends to overfit, which results in poor performance in practical application. To solve this problem, a compact convolutional neural network augmented with multiscale feature extraction is proposed in this paper. Multiscale feature extraction unit is introduced to extract features at different time scales without adding convolution layers, which can reduce the depth of the network while ensuring classification ability and alleviating the overfitting problem caused by the network being too complicated. Besides, a specially designed compact convolutional neural network synthetically analyzes the multiscale features. By combing these two tricks, the proposed neural network can extract more sensitive features with a relatively shallow structure, which increases classification accuracy under small samples. Dropout technique is also used to prevent the network from overfitting. Effectiveness of the proposed method is verified by three bearing datasets. Experiments show that this network can achieve competitive results with limited training samples even with different load and mixed rotating speed.

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

[2]  Wei Zhang,et al.  Understanding and improving deep learning-based rolling bearing fault diagnosis with attention mechanism , 2019, Signal Process..

[3]  Jeffrey L. Andrews,et al.  Addressing overfitting and underfitting in Gaussian model-based clustering , 2018, Comput. Stat. Data Anal..

[4]  Wentao Mao,et al.  Online detection of bearing incipient fault with semi-supervised architecture and deep feature representation , 2020 .

[5]  Jin Cui,et al.  Multi-bearing remaining useful life collaborative prediction: A deep learning approach , 2017 .

[6]  Ngo Van Linh,et al.  Eliminating overfitting of probabilistic topic models on short and noisy text: The role of dropout , 2019, Int. J. Approx. Reason..

[7]  Guanghua Xu,et al.  Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks , 2020 .

[8]  Diego Cabrera,et al.  A review on data-driven fault severity assessment in rolling bearings , 2018 .

[9]  Daniel Morinigo-Sotelo,et al.  Early Fault Detection in Induction Motors Using AdaBoost With Imbalanced Small Data and Optimized Sampling , 2017, IEEE Transactions on Industry Applications.

[10]  Wentao Mao,et al.  Online sequential prediction of bearings imbalanced fault diagnosis by extreme learning machine , 2017 .

[11]  Shuilong He,et al.  A Novel Deep Learning Network via Multiscale Inner Product With Locally Connected Feature Extraction for Intelligent Fault Detection , 2019, IEEE Transactions on Industrial Informatics.

[12]  Jun Sun,et al.  Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition , 2017, Pattern Recognit..

[13]  Xueqing Zhou,et al.  Forming a new small sample deep learning model to predict total organic carbon content by combining unsupervised learning with semisupervised learning , 2019, Appl. Soft Comput..

[14]  Lei Ren,et al.  Bearing remaining useful life prediction based on deep autoencoder and deep neural networks , 2018, Journal of Manufacturing Systems.

[15]  Xining Zhang,et al.  Fault diagnosis of rolling bearing under fluctuating speed and variable load based on TCO Spectrum and Stacking Auto-encoder , 2019, Measurement.

[16]  Mohamed Saber Naceur,et al.  Reinforcement learning for neural architecture search: A review , 2019, Image Vis. Comput..

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

[18]  Gianpaolo Francesco Trotta,et al.  A performance comparison between shallow and deeper neural networks supervised classification of tomosynthesis breast lesions images , 2019, Cognitive Systems Research.

[19]  Wenquan Feng,et al.  Interpretable Relative Squeezing bottleneck design for compact convolutional neural networks model , 2019, Image Vis. Comput..

[20]  Michel F. Valstar,et al.  Postnatal gestational age estimation of newborns using Small Sample Deep Learning☆ , 2019, Image Vis. Comput..

[21]  Gurpreet Singh,et al.  A novel method to classify bearing faults by integrating standard deviation to refined composite multi-scale fuzzy entropy , 2020, Measurement.

[22]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[23]  Wei Guo,et al.  Identification of key features using topological data analysis for accurate prediction of manufacturing system outputs , 2017 .

[24]  Weidong Cheng,et al.  Generalized demodulation with tunable E-Factor for rolling bearing diagnosis under time-varying rotational speed , 2018, Journal of Sound and Vibration.

[25]  Jinjiang Wang,et al.  Machine vision intelligence for product defect inspection based on deep learning and Hough transform , 2019, Journal of Manufacturing Systems.

[26]  Dean Zhao,et al.  An optimized RBF neural network algorithm based on partial least squares and genetic algorithm for classification of small sample , 2016, Appl. Soft Comput..

[27]  Biao Wang,et al.  LiftingNet: A Novel Deep Learning Network With Layerwise Feature Learning From Noisy Mechanical Data for Fault Classification , 2018, IEEE Transactions on Industrial Electronics.

[28]  Minping Jia,et al.  A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing , 2018, Neurocomputing.

[29]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[30]  Lihui Wang,et al.  Imbalanced data fault diagnosis of rotating machinery using synthetic oversampling and feature learning , 2018, Journal of Manufacturing Systems.

[31]  Hasan Asy'ari Arief,et al.  Addressing Overfitting on Pointcloud Classification using Atrous XCRF , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[32]  Junsheng Cheng,et al.  An improved deep convolutional neural network with multi-scale information for bearing fault diagnosis , 2019, Neurocomputing.

[33]  Jong-Myon Kim,et al.  Automated bearing fault diagnosis scheme using 2D representation of wavelet packet transform and deep convolutional neural network , 2019, Comput. Ind..

[34]  Hee-Jun Kang,et al.  Rolling element bearing fault diagnosis using convolutional neural network and vibration image , 2019, Cognitive Systems Research.

[35]  Xiangdong Wang,et al.  Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis , 2020, Measurement.

[36]  Maolin Cai,et al.  Manufacturing cost estimation based on a deep-learning method , 2020, Journal of Manufacturing Systems.

[37]  Robert X. Gao,et al.  Dual-scale cascaded adaptive stochastic resonance for rotary machine health monitoring , 2013 .

[38]  Giuseppe De Pietro,et al.  Deep neural network for hierarchical extreme multi-label text classification , 2019, Appl. Soft Comput..

[39]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Xiang Li,et al.  Cross-Domain Fault Diagnosis of Rolling Element Bearings Using Deep Generative Neural Networks , 2019, IEEE Transactions on Industrial Electronics.

[41]  Pingyu Jiang,et al.  Combining granular computing technique with deep learning for service planning under social manufacturing contexts , 2017, Knowl. Based Syst..

[42]  Adam P. Piotrowski,et al.  Impact of deep learning-based dropout on shallow neural networks applied to stream temperature modelling , 2020 .

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

[44]  Fang Tang,et al.  Deep Learning With Grouped Features for Spatial Spectral Classification of Hyperspectral Images , 2017, IEEE Geoscience and Remote Sensing Letters.