Research on gear fault diagnosis based on feature fusion optimization and improved two hidden layer extreme learning machine

Abstract Aiming at gear fault diagnosis in rotating machinery, a novel state assessment method based on feature fusion optimization and improved two-hidden-layer extreme learning machine (ITELM) was proposed in order to improve the fault diagnosis accuracy. Firstly, variational mode decomposition (VMD) and wavelet packet (WP) are employed to decompose the vibration signal, and statistical parameter features are extracted. Then, ReliefF algorithm is adopted to manage the extracted features and obtain the optimal feature subset. Finally, in order to avoid the network structure limitation of the existing two-hidden layer extreme learning machine with same hidden-layer node number, ITELM with different hidden-layer node number is proposed to evaluate the gear running states. Meanwhile, the empirical formula and fuzzy logic reasoning methods are developed in order to effectively determine the number of nodes for first and second hidden layers, respectively. The experimental results from different perspectives verified the effectiveness of the proposed method.

[1]  Peter W. Tse,et al.  Use of autocorrelation of wavelet coefficients for fault diagnosis , 2009 .

[2]  Zhiwei Ye,et al.  Fast bearing fault diagnosis of rolling element using Lévy Moth-Flame optimization algorithm and Naive Bayes , 2020 .

[3]  Dewa Made Sri Arsa,et al.  Optimization of Stacked Unsupervised Extreme Learning Machine to improve classifier performance , 2017, 2017 International Workshop on Big Data and Information Security (IWBIS).

[4]  Bing Wu,et al.  Fault diagnosis on slipper abrasion of axial piston pump based on Extreme Learning Machine , 2018, Measurement.

[5]  Jing J. Liang,et al.  Two-hidden-layer extreme learning machine for regression and classification , 2016, Neurocomputing.

[6]  Peng Chen,et al.  A Precise Diagnosis Method of Structural Faults of Rotating Machinery based on Combination of Empirical Mode Decomposition, Sample Entropy, and Deep Belief Network , 2019, Sensors.

[7]  Qingsong Xu,et al.  Improved shuffled frog leaping algorithm-based BP neural network and its application in bearing early fault diagnosis , 2015, Neural Computing and Applications.

[8]  Yanxue Wang,et al.  Research on variational mode decomposition and its application in detecting rub-impact fault of the rotor system , 2015 .

[9]  Lizheng Pan,et al.  Emotional State Recognition from Peripheral Physiological Signals Using Fused Nonlinear Features and Team-Collaboration Identification Strategy , 2020, Entropy.

[10]  Cancan Yi,et al.  Tensor Singular Spectrum Decomposition Algorithm Based on Permutation Entropy for Rolling Bearing Fault Diagnosis , 2017, Entropy.

[11]  Xiaoli Wang,et al.  Fault Diagnosis for Wind Turbines Based on ReliefF and eXtreme Gradient Boosting , 2020, Applied Sciences.

[12]  Xian-Bo Wang,et al.  Novel Particle Swarm Optimization-Based Variational Mode Decomposition Method for the Fault Diagnosis of Complex Rotating Machinery , 2017, IEEE/ASME Transactions on Mechatronics.

[13]  Shunming Li,et al.  Gear Fault Intelligent Diagnosis Based on Frequency-Domain Feature Extraction , 2019, Journal of Vibration Engineering & Technologies.

[14]  Yanxue Wang,et al.  Filter bank property of variational mode decomposition and its applications , 2016, Signal Process..

[15]  Jie Tang,et al.  Leakage fault diagnosis method of aircraft landing gear hydraulic cylinder based on wavelet packet , 2019 .

[16]  Jie Chen,et al.  Incipient fault diagnosis of rolling bearings based on adaptive variational mode decomposition and Teager energy operator , 2020 .

[17]  Aiguo Song,et al.  Gear fault diagnosis method based on wavelet-packet independent component analysis and support vector machine with kernel function fusion , 2018 .

[18]  Qinghua Hu,et al.  Mechanical fault diagnosis based on redundant second generation wavelet packet transform, neighborhood rough set and support vector machine , 2012 .

[19]  Zhi Chen,et al.  V-ELMpiRNAPred: Identification of human piRNAs by the voting-based extreme learning machine (V-ELM) with a new hybrid feature , 2017, J. Bioinform. Comput. Biol..

[20]  H. Zheng,et al.  GEAR FAULT DIAGNOSIS BASED ON CONTINUOUS WAVELET TRANSFORM , 2002 .

[21]  Ajalmar R. da Rocha Neto,et al.  A new pruning method for extreme learning machines via genetic algorithms , 2016, Appl. Soft Comput..

[22]  Liu Jian,et al.  Fault Diagnosis of Piezoelectric Sensor Patches for Vibration Control Based on Multifeature Fusion and Improved SVM , 2019 .

[23]  Min Xie,et al.  A Dynamic-Bayesian-Network-Based Fault Diagnosis Methodology Considering Transient and Intermittent Faults , 2017, IEEE Transactions on Automation Science and Engineering.

[24]  Panos J. Antsaklis,et al.  A simple method to derive bounds on the size and to train multilayer neural networks , 1991, IEEE Trans. Neural Networks.

[25]  Na Zhao,et al.  Gear fault feature extraction and diagnosis method under different load excitation based on EMD, PSO-SVM and fractal box dimension , 2019, Journal of Mechanical Science and Technology.

[26]  Qiang Feng,et al.  Availability-based engineering resilience metric and its corresponding evaluation methodology , 2018, Reliab. Eng. Syst. Saf..

[27]  K. I. Ramachandran,et al.  Pattern recognition based on-line vibration monitoring system for fault diagnosis of automobile gearbox , 2018 .

[28]  Shuanfeng Zhao,et al.  Study on the Fault Diagnosis Method of Scraper Conveyor Gear under Time-Varying Load Condition , 2020 .

[29]  J. Rafiee,et al.  Application of mother wavelet functions for automatic gear and bearing fault diagnosis , 2010, Expert Syst. Appl..

[30]  Shifei Ding,et al.  Extreme learning machine and its applications , 2013, Neural Computing and Applications.

[31]  Yong Zhu,et al.  Effective component extraction for hydraulic pump pressure signal based on fast empirical mode decomposition and relative entropy , 2020 .

[32]  Adam Glowacz,et al.  Novel Convolutional Neural Network (NCNN) for the Diagnosis of Bearing Defects in Rotary Machinery , 2021, IEEE Transactions on Instrumentation and Measurement.

[33]  Weijia Li,et al.  A Comparative Study of Multiscale Sample Entropy and Hierarchical Entropy and Its Application in Feature Extraction for Ship-Radiated Noise , 2019, Entropy.

[34]  Deepak Raj Munirathinam,et al.  A new improved filter-based feature selection model for high-dimensional data , 2019, The Journal of Supercomputing.

[35]  A. Prasanth,et al.  Certain Investigations on Energy-Efficient Fault Detection and Recovery Management in Underwater Wireless Sensor Networks , 2020, J. Circuits Syst. Comput..

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

[37]  Yiqiang Chen,et al.  Weighted extreme learning machine for imbalance learning , 2013, Neurocomputing.

[38]  Djamel Benazzouz,et al.  Multi-fault diagnosis of rolling bearing using fuzzy entropy of empirical mode decomposition, principal component analysis, and SOM neural network , 2018, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science.

[39]  Shin'ichi Tamura,et al.  Capabilities of a four-layered feedforward neural network: four layers versus three , 1997, IEEE Trans. Neural Networks.

[40]  Igor Kononenko,et al.  Estimating Attributes: Analysis and Extensions of RELIEF , 1994, ECML.

[41]  Hongkun Li,et al.  Early Fault Diagnosis for Planetary Gearbox Based on Adaptive Parameter Optimized VMD and Singular Kurtosis Difference Spectrum , 2019, IEEE Access.

[42]  Taher Niknam,et al.  Probabilistic Load Forecasting Using an Improved Wavelet Neural Network Trained by Generalized Extreme Learning Machine , 2018, IEEE Transactions on Smart Grid.