本文已被:浏览 1575次 下载 504次
投稿时间:2019-02-21
投稿时间:2019-02-21
中文摘要: 将灰狼优化算法和支持向量机算法作为理论指导,并采用灰狼优化算法对支持向量机算法进行优化,以实现燃气轮机故障类型的分类。将灰狼优化算法与遗传算法优化支持向量机方法和粒子群算法优化支持向量机方法进行对比,结果表明,通过灰狼算法优化支持向量机的方法对燃气轮机故障分类的准确率要高于遗传算法优化支持向量机算法和粒子群算法优化支持向量机的故障分类方法。
Abstract:With Gray Wolf algorithm and support vector machine theory as the theoretical guidance, a method of optimizing support vector machines based on Gray Wolf algorithm is proposed to classify the extracted gas turbine feature vectors. The method is compared with genetic algorithm optimization support vector machine and particle swarm optimization support vector machine respectively. The results show that the accuracy of fault classification based on the grey wolf algorithm optimization support vector machine is higher than that of genetic algorithm optimization support vector machine algorithm and particle swarm optimization support vector machine.
文章编号:20192017 中图分类号:TK221 文献标志码:
基金项目:上海市"扬帆计划"高新技术领域项目(16YF1404700)。
作者 | 单位 | |
张云 | 上海电力学院 自动化工程学院, 上海 200090 | zhangyun0911@126.com |
钱玉良 | 上海电力学院 自动化工程学院, 上海 200090 | |
邱正 | 上海电力学院 自动化工程学院, 上海 200090 | |
张霄 | 上海电力学院 自动化工程学院, 上海 200090 |
引用文本:
张云,钱玉良,邱正,等.采用GWO优化SVM的燃气轮机气路故障诊断[J].上海电力大学学报,2019,35(2):187-192,196.
ZHANG Yun,QIAN Yuliang,QIU Zheng,et al.Gas Turbine Fault Diagnosis Using GWO Optimized SVM[J].Journal of Shanghai University of Electric Power,2019,35(2):187-192,196.
张云,钱玉良,邱正,等.采用GWO优化SVM的燃气轮机气路故障诊断[J].上海电力大学学报,2019,35(2):187-192,196.
ZHANG Yun,QIAN Yuliang,QIU Zheng,et al.Gas Turbine Fault Diagnosis Using GWO Optimized SVM[J].Journal of Shanghai University of Electric Power,2019,35(2):187-192,196.