摘要
为了提升配电网故障辨识准确率,提出了一种基于自适应概率学习的早期故障诊断方法。该方法通过波形分解和最大化特征相似性找到最佳线性映射,将仿真数据和真实数据映射至同一特征空间,且在此空间中两者分布差异最小,之后即可使用仿真数据训练模型并对真实数据进行分类,从而解决配电网故障辨识中样本量不足这一重要问题。基于系统仿真数据和现场实际数据表明:所提方法对于自适应学习条件下早期故障诊断的可靠性和准确率,远优于同等条件下的卷积神经网络、支持向量机和K邻近算法等常用分类模型;为自适应学习条件下的配电网故障辨识技术提供了一种新的思路。
To improve the fault identification accuracy in power distribution systems,a diagnosis method for incipient faults is proposed based on Domain Adaption Probabilistic Learning in this paper.The proposed method finds out the best linear mapping by waveform decomposition and feature similarity,which maps simulation data and field data into the same feature space.In this space,the distribution difference between two kinds of features reaches its minimum,allowing the model to use simulation data for training and field data for test.The whole process helps to solve the essential problem of few samples in the fault identification.The experiments show that the proposed method is much better than other commonly-used classification models,such as Convolutional Neural Network,Support Vector Machine and K-nearest Neighbors,in the aspects of reliability and accuracy.This research can provide a new idea for the fault identification in power distribution systems under the condition of domain adaptation.
作者
杨帆
方健
张敏
田妍
陈创升
刘振东
杨炎龙
YANG Fan;FANG Jian;ZHANG Min;TIAN Yan;CHEN Chuangsheng;LIU Zhendong;YANG Yanlong(China Southern Power Grid Middle-Low Voltage Electric Equipment Inspection and Testing Key Laboratory,Power Test Research Institute of Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd.,Guangzhou 510410,Guangdong,China;Guangzhou Conghua Power Supply Bureau of Guangdong Power Grid Co.,Ltd.,Guangzhou 510900,Guangdong,China;Guangzhou Zengcheng Power Supply Bureau of Guangdong Power Grid Co.,Ltd.,Guangzhou 511300,Guangdong,China)
出处
《电网与清洁能源》
北大核心
2021年第12期47-55,共9页
Power System and Clean Energy
基金
国家自然科学基金项目(51307109)
中国南方电网有限责任公司科技项目(GZHKJXM20180060)。
关键词
配电网
早期故障
故障辨识
特征提取
自适应概率学习
power distribution systems
incipient faults
fault identification
feature extraction
domain adaption probabilistic learning
