基于IGWO优化LSSVM的采煤机截割部齿轮箱故障诊断  

Fault Diagnosis of Shearer Cutting Unit Gearbox Based on IGWO Optimized LSSVM

作　　者：程亮[1] 张步勤[2] 张金营 Cheng Liang;Zhang Buqin;Zhang Jinying(Handan College,Handan 056005,China;Jizhong Energy Fengfeng Group Co.,Ltd.,Handan 056107,China;China Energy Investment Co.,Ltd.,Beijing 100011,China)

机构地区：[1]邯郸学院,河北邯郸056005 [2]冀中能源峰峰集团有限公司,河北邯郸056107 [3]国家能源投资集团有限责任公司,北京100011

出　　处：《煤矿机械》2021年第5期168-171,共4页Coal Mine Machinery

基　　金：国家重点研发计划资助项目(2018YFB0604204)。

摘　　要：为准确诊断采煤机截割部齿轮箱故障,提出一种新型故障诊断模型。振动信号经变分模态分解得到本征模态函数(IMF),计算IMF分量的样本熵构造特征向量;采用改进灰狼算法(IGWO)优化最小二乘支持向量机(LSSVM)模型的高斯径向基核函数参数和惩罚因子,建立IGWO-LSSVM故障诊断模型进行采煤机截割部齿轮箱故障识别。实验数据对比表明,IGWOLSSVM的采煤机截割部齿轮箱故障诊断模型故障分类性能更好,准确率更高。I n order to accurately diagnose the gearbox fault of shearer cutting unit, a new fault diagnosis model was proposed.The vibration signal was obtained by variational model decomposition to obtain intrinsic mode function(IMF), and the sample entropy of IMF was calculated to construct the feature vector. Improved grey wolf optimization(IGWO) was used to optimize the Gaussian radial basis kernel function parameters and penalty factors in the model of least squares support vector machine(LSSVM), and the fault diagnosis model of IGWO-LSSVM was established for fault identification of shearer cutting unit gearbox. The comparison of experimental data shows that the fault diagnosis model of IGWO-LSSVM shearer cutting unit gearbox has better fault classification performance and higher accuracy.

关 键 词：采煤机截割部 齿轮箱 故障诊断 IGWO LSSVM 

分 类 号：TD421.6[矿业工程—矿山机电]