Bearing fault diagnosis method based on fractional divergence entropy and improved pelican algorithm to optimize ELM
MI Zhentao
YANG Yanshuai
ZHU Guoqing
SONG Yuxi
ZHANG Ruifeng
LIU Bing
Abstract：[Objective]Aiming at the problems of insufficient classification performance and strong parameter selection sensitivity of extreme learning machine(ELM)in rolling bearing fault diagnosis,an optimized ELM fault diagnosis method based on fractional divergence entropy and improved pelican optimization algorithm(IPOA)was proposed to improve the accuracy and efficiency of bearing fault diagnosis.[Methods]Firstly,fractional divergence entropy was used to process bearing vibration signals to extract entropy features characterizing fault states,realizing in-depth mining of fault information.Secondly,Tent chaotic mapping,adaptive weight and golden sine strategy were introduced to improve the pelican optimization algorithm,enhancing the global search ability and convergence speed of the algorithm.Thirdly,the improved algorithm was adopted to optimize the key parameters of ELM,reducing the influence of parameter sensitivity on classification performance.Finally,multiple groups of controlled tests were carried out based on two public bearing datasets to verify the performance of the proposed method.[Results]The results show that the improved pelican optimization algorithm has better optimization performance in both unimodal and multimodal test functions.The proposed IPOA-ELM model achieves a maximum overall accuracy of 92.2%in bearing fault diagnosis,which is 7.75 percentage points higher than that of the basic ELM model,with the classification accuracy stable above 90%.It provides a reference for the engineering application of rotating machinery fault diagnosis.
Keywords：Divergence entropyFractional divergence entropyPelican optimization algorithmExtreme learning machineFault diagnosis
Publication Date：2026-07-15
Online Publishing Date：2026-09-12(First online date of this platform, not the publication date of the document)
Pages：10( 175-184 )