一种PSO-SVM的光伏阵列故障检测与分类

Fault detection and classification for photovoltaic arrays based on PSO-SVM

提出一种粒子群优化支持向量机的光伏阵列故障检测与分类的方法.分析了光伏阵列输出特性和故障类型,选择合适的特征向量及归一化方式.选用径向基核函数优化模型结构,并利用PSO算法对参数进行寻优,提高模型精确度.结合实验平台获取光伏阵列正常工作和8种故障状态的实测数据,随机划分为训练集和测试集,并建立PSO-SVM故障检测与分类模型.实验表明,应用本模型进行故障检测准确率达99.89%,分类准确率达98.68%,优于BP神经网络以及决策树的检测和分类结果.

A fault detection and classification model for photovoltaic arrays is presented by using particle swarm optimization-support vector machine（PSO-SVM）.The characteristic and faults of PV arrays are analyzed.Moreover,the appropriate feature vectors are selected and the normalized method is designed,respectively.In order to strengthen the accuracy of the proposed model,the RBF kernel function is applied to improve the model structure,whose parameters are optimized by the PSO algorithm.Based on the measured platform,the experiment data set of the PV array under normal working condition and eight types of faults are recorded.The data set are randomly divided into testing set and training set to train the PSO-SVM model.The accuracy of fault detection and fault classification are 99.89% and 98.68%,respectively,which are superior to those of BP neural network and decision tree.