Multi-fault diagnosis of rolling bearing using two-dimensional feature vector of WP-VMD and PSO-KELM algorithm

Abstract

In order to achieve accurate fault diagnosis of rolling bearing under random noise, a new fault diagnosis method based on wavelet packet-variational mode decomposition (WP-VMD) and kernel extreme learning machine (KELM) optimized by particle swarm optimization (PSO) is proposed in this paper. Firstly, the time-frequency domain feature vectors of the original rolling bearing fault signals are effectively obtained by preprocessing of WMD and decomposition and reconstruction of VMD.Then, the extracted two-dimensional feature vector is input into the KELM neural network for fault identification, and combined with PSO, KELM parameters were optimized. The experimental results show that the proposed method can effectively diagnose the rolling bearing under random noise, with the features of fast speed, stable performance and high accuracy. By comparison, this paper obtains better accuracy and real-time performance with fewer features, which provides a simple and efficient solution for fault diagnosis of rolling bearings.

Health Management of Bearings Using Adaptive Parametric VMD and Flying Squirrel Search Algorithms to Optimize SVM

“…Wang et al [13] constructed a method to reduce the overlap index of adjacent modes to determine the number of decomposition layers in VMD, but ignored the problem of optimization of penalty factor parameters. In addition, parameter optimization combined with intelligent optimization algorithm is also a popular method in recent years [14][15][16], but the optimization effect can only be obtained through iterative calculation, which will increase the running time of the model. Ni et al [17] proposed a VMD method guided by fault information, which used a nested statistical model of two fault cycle information to approximate the number of modes.…”