摘要
提高智能电表故障不平衡多分类准确率对用电采集系统的可靠运行具有重要意义。传统机器学习中以合成少数类过采样(synthetic minority oversampling technique,SMOTE)算法及其变体为代表的过采样方法,较少考虑数据全局分布,而后续采用的分类算法难以从数据中获取更深层特征信息。基于深度学习思想,提出一种基于条件变分自编码器-卷积神经网络(conditional variational auto encoder-convolutional neural network,CVAE-CNN)模型的不平衡多分类方法,将类别标签作为约束条件,搭建由全连接层构成的CVAE网络生成少数类样本,根据变分下界对服从多维且各维度为独立高斯分布的隐变量建模,学习各类分布特点和数据集全局特征,提高生成数据质量。平衡后的数据采用卷积神经网络进行分类,设计一维卷积层提取数据中潜藏的复杂特征,构造最大池化方法提高模型容错率,依据各类分布特点进行分类处理,提高对少数类别的识别率。以15个KEEL公开数据集和近年采集的智能电表故障数据作为实际算例,所提模型与典型的过采样方法和分类方法进行对比,实验结果表明具有更高的分类精度。
The improvement of the accuracy of multiple classification of faults in smart meters is of great significance in the operation of power systems.In the traditional machine learning,the oversampling methods,such as the smote algorithm and its variants,seldom consider the global distribution of the data.And the subsequent classification algorithms are unable to obtain the deeper feature information from the data.We propose an imbalanced multi-classification model of CVAE-CNN.It takes labels as constraints and builds a CVAE network composed of fully connected layers to generate minority class samples.The network models the hidden variables that obey the multi-dimensional and independent Gaussian distribution in each dimension according to the lower bound of variation,and learns various distribution characteristics and the global characteristics of the data set to improve the quality of the generated data.The balanced data is classified using a CNN,in which the hidden complex features are extracted through the one-dimensional convolution operation.The maximum pooling method is constructed to improve the fault tolerance rate of the model,the recognition rate of a few categories increased.Taking 15 KEEL public data sets and the smart meter fault data collected in recent years as actual calculation examples,the proposed model is verified to have higher classification accuracy compared with the typical oversampling methods and classification methods.
作者
高欣
纪维佳
赵兵
贾欣
黄子健
任昺
GAO Xin;JI Weijia;ZHAO Bing;JIA Xin;HUANG Zijian;REN Bing(School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Haidian District,Beijing 100876,China;School of Electrical and Electronic Engineering,North China Electric Power University,Changping District,Beijing 102206,China;China Electric Power Research Institute,Haidian District,Beijing 100192,China)
出处
《电网技术》
EI
CSCD
北大核心
2021年第8期3052-3060,共9页
Power System Technology
基金
国家重点研发计划项目(2016YFF0201201)。
关键词
智能电表
故障多分类
不平衡数据
条件变分自编码器
卷积神经网络
smart meter
multi-classification of fault types
imbalanced data
conditional variational autoencoder
convolutional neural network
