摘要
提出了一种基于PCA-PNN-LVQ的电压跌落扰动源分类辨识模型。该模型基于模拟电压跌落数据,利用主成分分析(principal component analysis,PCA)对数据进行降维,基于深度学习方法概率神经网络(probabilistic neural network,PNN)提取数据特征,利用学习向量量化(learning vector quantization,LVQ)对电压跌落类型进行分类。仿真实验表明,该模型能有效识别电压跌落类型。与其他仅使用PNN、PCAPNN和PNN-LVQ的模型相比,该模型对其中电压跌落源的识别精度最好。PCA-PNN-LVQ方法在中小型样本数据集上具有较好的性能。
This paper presents a classification and identification model of voltage sags based on PCA-PNN-LVQ.The model is based on the simulated voltage sag data.Principal component analysis(PCA)is used to reduce the dimensions of the data.Probabilistic neural network(PNN)based on depth learning method is used to extract data features,and learning vector quantization(LVQ)is used to classify the types of voltage sags.The simulation results show that the model can effectively identify the types of voltage sags.Compared with other models that only use PNN,PCA-PNN and PNN-LVQ,it has the best identification accuracy for voltage sag sources.PCA-PNNN-LVQ has very good performance on small and medium-sized sample datasets.
作者
杨振南
陈锦昌
李新超
刘昊一
古一灿
YANG Zhennan;CHEN Jinchang;LI Xinchao;LIU Haoyi;GU Yican(Guangdong Power Grid Power Dispatching Control Center,Guangzhou 510600,China;China Energy Engineering Group Guangdong Electric Power Design Institute Co.,Ltd.,Guangzhou 510663,China)
出处
《供用电》
2023年第7期48-56,共9页
Distribution & Utilization
基金
广东省重点领域研发计划(2019B111109001)。
关键词
电压跌落
主成成分分析
数据特征
数据降维
深度学习
voltage drop
principal component analysis
data characteristics
data dimension reduction
deep learning
