摘要
针对支持向量机(support vector machine, SVM)的分类性能受自身参数选择影响较大的问题,提出了基于麻雀搜索算法(sparrow search algorithm, SSA)优化SVM的故障诊断方法。利用麻雀搜索算法(SSA)对支持向量机的惩罚参数(C)与核参数(g)进行优化,并构建SSA-SVM滚动轴承故障诊断模型。结果表明:对于滚动轴承的常见故障,SSA-SVM诊断模型的测试正确率为96.67%,比传统的遗传算法(genetic algorithm, GA)-SVM和粒子群算法(particle swarm optimization, PSO)-SVM诊断模型分别提高3.34%和1.67%,且收敛速度更快,可有效应用于故障诊断。
Aiming at solving the problem that the classification performance of support vector machine(SVM) is greatly affected by its own parameter selection, a fault diagnosis method based on sparrow search algorithm(SSA) to optimize SVM was proposed. The sparrow search algorithm(SSA) was used to optimize the penalty factor(C) and the kernel function(g) of the support vector machine, and the SSA-SVM rolling bearing fault diagnosis model was constructed. Results show that for several common faults of rolling bearings, the test accuracy of the SSA-SVM diagnostic model is 96.67%, which is improved by 3.34% and 1.67% compared with the traditional genetic algorithm-support vector machine(GA-SVM) and particle swarm optimization-support vector machine(PSO-SVM) diagnostic models, respectively. Additionally, the convergence speed of the SSA-SVM diagnostic model is faster. This study indicates that the SSA-SVM diagnostic model can be effectively applied to fault diagnosis.
作者
马晨佩
李明辉
巩强令
杨白月
MA Chen-pei;LI Ming-hui;GONG Qiang-ling;YANG Bai-yue(Mechanical and Electrical Engineering Institute,Shaanxi University of Science and Technology,Xi’an 710021,China)
出处
《科学技术与工程》
北大核心
2021年第10期4025-4029,共5页
Science Technology and Engineering
基金
咸阳市科技计划(2019k02-04)。
关键词
支持向量机
麻雀搜索算法
参数优化
故障诊断
support vector machines
sparrow search algorithm
parameter optimization
fault diagnosis
