Gear Fault Intelligent Diagnosis Based on Frequency-Domain Feature Extraction

PurposeFor purpose of automatically diagnosing gear faults, intelligent fault diagnosis methods have been paid increasing attentions by researchers.MethodologyThis paper presents an intelligent fault diagnosis method based on an unsupervised learning algorithm called sparse filtering. First, sparse filtering is employed to extract fault features from gear frequency-domain samples. Then, softmax regression is adopted as a classifier to classify different fault types by the learned features. Finally, two different gear datasets are adopted to testify the validity and feasibility of our method.ConclusionThe test results appear that our method can not only adaptively extract discriminative characteristics from the spectra of measured signals, but also achieve a superior performance than some other methods.

[1]  Shunming Li,et al.  Construction of a batch-normalized autoencoder network and its application in mechanical intelligent fault diagnosis , 2018, Measurement Science and Technology.

[2]  Jay Lee,et al.  Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications , 2014 .

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

[4]  Jay Lee,et al.  Investigation on the kurtosis filter and the derivation of convolutional sparse filter for impulsive signature enhancement , 2017 .

[5]  Jiquan Ngiam,et al.  Sparse Filtering , 2011, NIPS.

[6]  Steven Verstockt,et al.  Convolutional Neural Network Based Fault Detection for Rotating Machinery , 2016 .

[7]  Shunming Li,et al.  An Intelligent Fault Diagnosis Approach Considering the Elimination of the Weight Matrix Multi-Correlation , 2018, Applied Sciences.

[8]  Yu Xue,et al.  Text classification based on deep belief network and softmax regression , 2016, Neural Computing and Applications.

[9]  Ibrahim Esat,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROTATING MACHINERY USING WAVELET TRANSFORMS AS A PREPROCESSOR , 1997 .

[10]  Shunming Li,et al.  A novel method for self-adaptive feature extraction using scaling crossover characteristics of signals and combining with LS-SVM for multi-fault diagnosis of gearbox , 2015 .

[11]  Krzysztof Patan,et al.  Artificial Neural Networks in Fault Diagnosis , 2004 .

[12]  Yeping Xiong,et al.  Vibration source model estimation and state specificity perception of a rotor structure , 2015 .

[13]  Changqing Shen,et al.  A coarse-to-fine decomposing strategy of VMD for extraction of weak repetitive transients in fault diagnosis of rotating machines , 2019, Mechanical Systems and Signal Processing.

[14]  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 .

[15]  Liang Chen,et al.  Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis , 2016 .

[16]  Fengshou Gu,et al.  Thermal image enhancement using bi-dimensional empirical mode decomposition in combination with relevance vector machine for rotating machinery fault diagnosis , 2013 .

[17]  J. Rafiee,et al.  INTELLIGENT CONDITION MONITORING OF A GEARBOX USING ARTIFICIAL NEURAL NETWORK , 2007 .

[18]  Pingfeng Wang,et al.  Failure diagnosis using deep belief learning based health state classification , 2013, Reliab. Eng. Syst. Saf..

[19]  Xuelong Li,et al.  Two-Stage Learning to Predict Human Eye Fixations via SDAEs , 2016, IEEE Transactions on Cybernetics.

[20]  Chen Lu,et al.  Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification , 2017, Signal Process..

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

[22]  Feng Jia,et al.  An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data , 2016, IEEE Transactions on Industrial Electronics.

[23]  Weiguo Huang,et al.  Adaptive spectral kurtosis filtering based on Morlet wavelet and its application for signal transients detection , 2014, Signal Process..