基于改进人工蜂群算法优化支持向量机的设备故障诊断方法
Equipment Fault Diagnosis Method Based on Improved Artificial Bee Colony Algorithm Optimized Support Vector Machine
巩世勇1
作者信息
- 1. 山西离柳焦煤集团有限公司 朱家店煤矿,山西 吕梁 033400
- 折叠
摘要
为了对煤矿井下带式输送机的核心部件滚动轴承的运行状态进行精确诊断,针对故障分类方法中支持向量机存在的惩罚因子确定困难的问题,引入交叉操作和全局最优解结合的改进人工蜂群算法,构建了故障诊断模型,通过仿真分析对比了改进模型与传统模型之间的差异性,仿真结果表明,改进的诊断模型能够快速精准地识别设备故障的类型,缩短了设备故障的诊断时间,提高了井下设备故障诊断的工作效率.
Abstract
In order to accurately diagnose the operation status of rolling bearings,which is the core component of underground belt conveyors in coal mines,the improved artificial bee colony algorithm combining crossover operation and global optimal solution was introduced for the problem of difficulty in determining the penalty factor of the support vector machine in the fault classification method,and the fault diagnostic model was constructed,and the differences between the improved model and the traditional model were compared through simulation analysis.The simulation results showed that the improved diagnostic model can quickly and accurately identify the types of equipment faults,shorten the diagnostic time of equipment faults,and improve the efficiency of underground equipment fault diagnosis.
关键词
皮带输送机/轴承故障诊断/支持向量机/人工蜂群算法/交叉操作/全局最优理念Key words
Belt conveyor/Bearing fault diagnosis/Support vector machine/Artificial bee colony algorithm/Crossover operation/Global optimum concept引用本文复制引用
出版年
2024
NETL
NSTL
万方数据