Research on degradation prediction of rolling bearing based on adaptive multi-GA-BP

Abstract

Rolling bearings are widely used in industrial equipment. It is of great significance to study the degradation trend of rolling bearings. In this paper, an Adaptive Multi-population Genetic Algorithm (AMGA) is proposed. Firstly, Kernel Principal Component Analysis (KPCA) method is used to fuse the vibration signal in both time domain and frequency domain, which uses kernel to map the sample space to higher dimensional space and uses the higher dimensional space for linear dimensionality reduction. It can effectively reduce the dimension of nonlinear correlation variables and obtain the trend signal representing the Remaining Useful Life (RUL) characteristics of rolling bearing. Moreover, AMGA is proposed to optimize the number of neurons, initial weight, and initial threshold of the Back Propagation (BP) neural network prediction model. AMGA applies chaos algorithm to Genetic Algorithm (GA) to improve the diversity of the initial population. Meanwhile, the communication frequency between different populations is controlled by judging the similarity of the optimal solution among different populations, so as to effectively jump out of the local optimum and obtain the global optimal solution. Finally, the whole life data of the spin-up process of the rolling bearing from University of Cincinnati is taken as an example to analyze the performance of the algorithm. Compared with the traditional BP, the R2-score performance and the MAPE performance of KPCA-AMGA-BP are improved by 0.297 and 2.46% respectively. Furthermore, compared with the optimized BP, this method obtains the improved R2-score performance and the MAPE performance by 0.218 and 0.46%.