| 基于S变换和IWOA-SVM的复合电能质量扰动识别 |
| |
| 引用本文： | 李琦,许素安,施阁,袁科,王家祥.基于S变换和IWOA-SVM的复合电能质量扰动识别[J].陕西电力,2023,0(5):30-35,50. |
| |
| 作者姓名： | 李琦 许素安 施阁 袁科 王家祥 |
| |
| 作者单位： | （中国计量大学 机电工程学院，浙江 杭州 310018） |
| |
| 摘 要： | 针对目前复合电能质量扰动（PQD）信号特征冗余，分类识别准确率低的问题，提出了一种基于S变换和改进鲸鱼算法支持向量机（IWOA-SVM）的复合电能质量扰动识别方法。首先，利用S变换对7种单一电能质量扰动和生成的13种复合扰动信号进行时频分析，使复杂扰动信号的特征得以凸显。设计特征提取方法，从实频矩阵中尽可能地获取便于分类的信号特征信息；其次，引入自适应权重因子和随机差分变异策略对WOA进行优化，提升其搜索能力；最后建立IWOA-SVM分类预测模型，优化SVM高斯核函数参数，以获得更好的鲁棒性和泛化能力，对提取的特征样本进行自动分类和识别。实验结果表明，所提方法分类识别准确率高，能有效识别多种复合PQD信号，有助于评估与治理电能质量问题。
|
| 关 键 词： | 电能质量 复合信号扰动识别 S变换 改进鲸鱼算法 支持向量机 |
Identification of Composite Power Quality Disturbance Based on S-transform and IWOA-SVM |
| |
| LI Qi,XU Su′an,SHI Ge,YUAN Ke,WANG Jiaxiang.Identification of Composite Power Quality Disturbance Based on S-transform and IWOA-SVM[J].Shanxi Electric Power,2023,0(5):30-35,50. |
| |
| Authors: | LI Qi XU Su′an SHI Ge YUAN Ke WANG Jiaxiang |
| |
| Affiliation: | （College of Mechanical and Electrical Engineering， China Jiliang University， Hangzhou 310018，China） |
| |
| Abstract: | In order to solve the problems of redundant features and low classification and recognition accuracy of composite PQD signals， a method of complex power quality disturbance recognition based on S-transform and IWOA-SVM is proposed. First of all，the S-transform is used to analyze the time and frequency of 7 single power quality disturbances and 13 compound disturbance signals， so that the characteristics of complex disturbance signals can be highlighted. Then，a feature extraction method is designed to obtain the signal feature information from the real frequency matrix as much as possible. Secondly，adaptive weight factor and random difference variation strategy are introduced to optimize WOA to improve its searching ability. The IWOA-SVM classification prediction model is established，and the Gaussian kernel function parameters of SVM are optimized to obtain better robustness and generalization ability， and the extracted feature samples are automatically classified and recognized. The experimental results show that the proposed method has high classification and recognition accuracy，and can effectively identify a variety of complex PQD signals，which is helpful to evaluate and control power quality. |
| |
| Keywords: | power quality disturbance identification of composite signals S-transform improved whale algorithm support vector machine |
|
| 点击此处可从《陕西电力》浏览原始摘要信息 |
|
点击此处可从《陕西电力》下载全文 |
