摘要
为了提高燃气轮机气路故障诊断的准确率,提出了一种基于交叉全局人工蜂群算法(CGABC)和支持向量机(SVM)的故障诊断方法。针对支持向量机的参数难以选取的问题,采用交叉全局人工蜂群算法对支持向量机的惩罚因子C和核函数参数σ进行优化。实验结果表明,与基于人工蜂群算法的ABC-SVM模型和基于粒子群算法的PSO-SVM模型相比,CGABC-SVM模型能更加准确、快速地识别故障。
In order to improve the accuracy of fault diagnosis,a fault diagnosis method based oncross-global artificial bee colony algorithm(CGABC)and support vector machines(SVM)is proposed.The problem that the parameters of the support vector machine are not easy to select,cross-global artificial bee colony algorithm is used to optimize the penalty factor C and the parameterσof kernel function in the support vector machine.The experimental results show that compared with ABC-SVM model based on artificial bee colony algorithm and PSO-SVM model based on particle swarm algorithm,CGABC-SVM model can identify faults more accurately and quickly.
作者
涂雷
茅大钧
李伯勋
汤诚
钟帆
TU Lei;MAO Da-jun;LI Bo-xun;TANG Cheng;ZHONG Fan(School of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China;Hangzhou HuadianJiangdong Thermal Power Company Limited,Hangzhou 310000,China)
出处
《汽轮机技术》
北大核心
2020年第5期377-380,共4页
Turbine Technology
基金
中国华电集团有限公司2019年度重点科技项目(CHDKJ19-01-80)
上海市“科技创新行动计划”地方院校能力建设专项项目(19020500700)。
关键词
燃气轮机
故障诊断
交叉全局人工蜂群算法
支持向量机
gas turbine
fault diagnosis
cross-global artificial bee colony algorithm
support vector machine
