基于改进ESMD的齿轮故障声发射信号识别  

Fault Recognition of Gear Acoustic Emission Signals Based on Improved ESMD

作　　者：鲍庆祥 于洋[1] Bao Qing-xiang;Yu Yang(School of Information Science and Engineering,Shenyang University of Technology,Liaoning Shenyang 110870)

机构地区：[1]沈阳工业大学信息科学与工程学院,辽宁沈阳110870

出　　处：《内燃机与配件》2024年第21期84-87,共4页Internal Combustion Engine & Parts

摘　　要：针对齿轮故障声发射信号中噪声对极点对称模态分解(ESMD)结果的影响,以及麻雀搜索算法(SSA)在优化支持向量机(SVM)参数时陷入局部最优解的问题,提出了一种改进ESMD方法结合改进麻雀搜索算法优化支持向量机(ISSA-SVM)的故障模式识别方法。经过实验验证,该方法可以实现充分的特征提取以及高准确率的故障识别,故障识别平均准确率达到97.664%。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%.

关 键 词：齿轮 声发射 经验模态分解 支持向量机 

分 类 号：TH165.3[机械工程—机械制造及自动化] TP181[自动化与计算机技术—控制理论与控制工程]