摘要
为了提高电能质量扰动的识别分类准确率,提出了一种基于变分模态分解(Variational Mode Decomposition,VMD)和LIBSVM的电能质量扰动(Power Quality Disturbance,PQD)识别分类方法。首先,运用VMD对电能质量扰动信号进行分解;接着,对VMD分解所得的本征模态函数(Intrinsic Mode Function,IMF)进行特征量计算并得到特征向量;最后,将提取后的特征量输入分类器中,并通过十折交叉验证对LIBSVM分类器的核函数进行优选,以提升模型的分类性能,进而实现最终的扰动识别分类。仿真结果表明,所提方法的识别准确率较高,抗噪性能优良。
In order to improve the classification accuracy of power quality disturbance,a power quality disturbance(PQD)recognition and classification method based on variational mode decomposition(VMD)and LIBSVM is proposed in this paper.Firstly,VMD is used to decompose the power quality disturbance signal.Then,the intrinsic mode function(IMF)obtained by VMD decomposition is calculated and the feature vector is obtained.Finally,the extracted feature quantity is input into the classifier,and the kernel function of the LIBSVM classifier is optimized by ten-fold cross validation to improve the classification performance of the model,and then the final disturbance recognition classification is realized.The simulation results show that the proposed method has high recognition accuracy and excellent anti-noise performance.
作者
许广林
邓圣徵
张世碧
陈文涛
李钊
岳莉
钟建伟
XU Guanglin;DENG Shengzheng;ZHANG Shibi;CHEN Wentao;LI Zhao;YUE Li;ZHONG Jianwei(State Grid Hubei Electric Power Co.,Ltd.Enshi Power Supply Company,Enshi 445000,China;Hubei Minzu University,College of Intelligent Systems Science and Engineering,Enshi 445000,China)
出处
《电工技术》
2025年第11期52-55,59,共5页
Electric Engineering
