基于WOA-VMD-ELM的煤矿机械胶带机滚动轴承故障诊断研究  

Research on fault diagnosis of rolling bearings in coal mining machinery tape machine based on WOA-VMD-ELM

作　　者：寇磊 李万仕 Kou Lei;Li Wanshi(Shaanxi Yanchang Petroleum and Mining Co.,Ltd.,Shaanxi Yulin,718000,China;Jiangjiahe Coal Mine,Shaanxi Huabin Coal Industry Co.,Ltd.,Shaanxi Xianyang,713500,China)

机构地区：[1]陕西延长石油矿业有限责任公司,陕西榆林718000 [2]陕西华彬煤业股份有限公司蒋家河煤矿,陕西咸阳713500

出　　处：《机械设计与制造工程》2025年第3期111-115,共5页Machine Design and Manufacturing Engineering

摘　　要：为提高煤矿机械胶带机滚动轴承故障诊断的准确率,提出一种基于WOA-VMD-ELM模型的故障诊断方法。首先采用鲸鱼优化算法(WOA)搜索变分模态分解(VMD)算法的最佳分解层数和惩罚因子,以改进VMD算法。然后利用改进VMD算法分解煤矿机械胶带机滚动轴承信号并构建特征矩阵。最后将特征矩阵输入极限学习机(ELM)网络中进行分类。结果表明,该方法可实现不同类型和不同直径的煤矿机械胶带机滚动轴承故障诊断,平均准确率达到97%以上,提高了煤矿机械胶带机滚动轴承故障诊断的准确率。To improve the accuracy of fault diagnosis of rolling bearings in coal mining machinery belt conveyors,a fault diagnosis method based on WOA-VMD-ELM is proposed.Firstly,the Whale Optimization Algorithm(WOA)is used to search for the optimal decomposition level and penalty factor for Variational Mode Decomposition(VMD)for improving VMD.Then,the improved VMD is used to decompose the rolling bearing signals of the coal mine machinery belt conveyor and construct a feature matrix.Finally,it inputs the feature matrix into the extreme learning machine(ELM)for classification.The results show that this method can achieve fault diagnosis of rolling bearings in coal mine machinery belt conveyors of different types and diameters,with an average accuracy of over 97%,improving the accuracy of fault diagnosis of rolling bearings in coal mine machinery belt conveyors.

关 键 词：煤矿机械 滚动轴承 故障诊断 变分模态分解算法 极限学习机 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]