摘要
针对基本和声搜索算法在优化支持向量机参数时,其局部搜索能力不足且后期收敛速度比较慢的缺点,提出利用改进和声搜索算法对支持向量机相关参数进行选择优化(IHS-SVM)的方法。在这一方法中,将原算法中控制参数—记忆库取值概率(HMCR)、微调概率(PAR)和调节宽度(bw)由静态值改进为随迭代次数的不同而进行动态变化。通过对UCI中的2个数据集进行分类正确率测试,并与未优化的支持向量机(SVM)和基本和声算法优化的支持向量机(HS-SVM)测试结果对比,证明了该改进方法的优越性。最后,将其用于柴油机故障诊断,并将分类正确率与未优化SVM和HSSVM分类结果进行比较,进一步说明改进和声搜索算法优化的支持向量机(IHS-SVM)能获得更高的分类结果正确率,即证明了该改进方法的实用性。
In viewof the question which insufficient local search ability and slowconvergence speed at the late period of basic harmony search algorithm in the optimization of support vector machine parameters,the paper uses improved harmony search algorithm to optimize the related parameters of support vector machine.In the method,it changes the static values of control parameters- memory value probability（ HMCR）,trimming probability（ PAR） and width（ bw） in the original algorithm to dynamic values depending on the number of iterations. Through classification accuracy test of two UCI data sets and comparison with test results from unoptimized SVMand HS-SVM,it demonstrates the superiority of the method. Finally,the method is for diesel engine fault diagnosis,and through comparison with unoptimized SVMand HS-SVM,it further proves that IHS-SVMcan obtain higher classification accuracy. Namely,it illustrates practicability of the proposed method.
出处
《组合机床与自动化加工技术》
北大核心
2016年第4期83-88,共6页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家自然科学基金资助项目(51175480)
关键词
改进和声搜索算法
支持向量机
参数优化
柴油机故障诊断
improved harmony search algorithm
support vector machine
parameter optimization
diesel engine fault diagnosis
