Gear Fault Diagnosis Based on Genetic Mutation Particle Swarm Optimization VMD and Probabilistic Neural Network Algorithm

Xuejun Li,Dongming Xiao,Jiakai Ding

doi:10.1109/access.2020.2968382

Abstract

The decomposition number $K$ and penalty factor $\alpha $ in the variational mode decomposition (VMD) algorithm have a great influence on the decomposition effect and the accuracy of subsequent fault diagnosis. Therefore, a gear fault diagnosis method based on genetic mutation particle swarm optimization VMD and probabilistic neural network (GMPSO-VMD-PNN) algorithm is proposed in this paper. Firstly, the GMPSO algorithm is used to optimize the $[K,\alpha]$ parameter combination in the VMD algorithm, and the optimal $[K,\alpha]$ parameter combination of each gear fault vibration signal to be decomposed is selected. Then, the gear fault vibration signal is decomposed into several intrinsic mode functions (IMFs) by VMD, and the sample entropy value of each IMFs is extracted to form the feature vector of subsequent fault diagnosis. Finally, the characteristic vector of gear fault vibration signal is input into PNN model, and gear fault is accurately classified. By comparing with fixed parameter VMD algorithm, empirical mode decomposition (EMD) and complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) algorithm, the superiority of this method in gear fault diagnosis is verified. Therefore, the GMPSO-VMD-PNN algorithm proposed in this paper has certain application value for gear fault diagnosis.

Highlights

Gearbox play a very important role in the mechanical transmission system [1] and are widely used in wind turbines, power transmission machinery and other equipment [2]–[5]
Li et al [38] used the variational mode decomposition (VMD) algorithm to carry out adaptive decomposition of signals, and used the improved kernel extreme learning machine (KELM) to diagnose rolling bearing faults. They compared with BP neural network (BPNN), support vector machine (SVM) and traditional ELM, and the results showed that this method was better than other methods in fault diagnosis accuracy
In this paper, a gear fault diagnosis based on genetic mutation particle swarm optimization (GMPSO)-VMDPNN algorithm is proposed, and the following conclusions are obtained: (1) GMPSO-VMD algorithm can effectively avoid the adverse effects of mode confusion in empirical mode decomposition (EMD) algorithm, and overcome the difficulty of parameter selection in VMD algorithm

Summary

INTRODUCTION

Gearbox play a very important role in the mechanical transmission system [1] and are widely used in wind turbines, power transmission machinery and other equipment [2]–[5]. The optimal value of [K , α] combined parameters can be effectively obtained to perform VMD decomposition of gear fault vibration signal, which can effectively avoid the occurrence of mode mixing. Gear fault diagnosis flow chart based on genetic mutation particle swarm optimization variational mode decomposition and probabilistic neural network (GMPSO-VMD-PNN). According to the GMPSO algorithm proposed in this paper, the parameter combination [K , α] in the VMD decomposition algorithm is optimized, and the parameter combination [K , α] obtained by optimizing the vibration signals of normal gear, gear with tooth wear, gear with tooth crack and gear with tooth break are [7, 2570], [7, 4140], [7, 4929] and [7, 4322] respectively. This paper adopts the parameter combination of [K , α] for overall optimization

PARAMETER ADAPTIVE OPTIMIZATION OF VMD METHOD BASED ON GMPSO

ENVELOPE ENTROPY

SAMPLE ENTROPY

Findings

CONCLUSION