摘要
针对支持向量机(SVM)用于变压器故障诊断中模型参数具有不确定性的问题,采用粒子群优化(PSO)算法对支持向量机参数进行优化,减少了模型参数的不确定性。故障数据测试表明,PSO能快速、准确地优化SVM参数,二者的结合可有效完成变压器故障分类,并取得较为满意的效果。
To solve the parameters uncertainty of support vector machine (SVM) model when used in fault diagnosis of power transformers, particle swarm optimization (PSO) algorithm is adopted to optimize the parameters of SVM, which can decrease the uncertainty of model parameters. The results of fault example show that PSO can optimize the pa- rameters of SVM rapidly and exactly; combination of PSO and SVM can be used in classification diagnosing faults of pow- er transformers~ it can obtain good effect.
出处
《水电能源科学》
北大核心
2012年第4期179-182,共4页
Water Resources and Power
基金
浙江省自然科学基金资助项目(Y1100243)