Fault Recognition of Gear Acoustic Emission Signals Based on Improved ESMD
Aiming at addressing the influence of noise on the Empirical Mode Decomposition(ESMD)decomposition results of gear fault acoustic emission signals,as well as the issue of sparrow search algorithm(SSA)optimized Support Vector Machine(SVM)parameters getting stuck in local optimal solutions,this study proposes an improved ESMD method combined with an improved sparrow search algorithm optimized Support Vector Machine(ISSA-SVM)for fault pattern recognition.Experimental results demonstrate that this method achieves comprehensive feature extraction and high accuracy in fault recognition,with an average fault recognition accuracy of up to 97.664%.
万方数据
维普
