首页|A Fault Diagnosis Method for Smart Meters via Two-layer Stacking Ensemble Optimization and Data Augmentation
A Fault Diagnosis Method for Smart Meters via Two-layer Stacking Ensemble Optimization and Data Augmentation
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
万方数据
维普
The accurate identification of smart meter(SM)fault types is crucial for enhancing the efficiency of operation and maintenance(O&M)and the reliability of power collection systems.However,the intelligent classification of SM fault types faces significant challenges owing to the complexity of features and the imbalance between fault categories.To address these is-sues,this study presents a fault diagnosis method for SM incor-porating three distinct modules.The first module employs a combination of standardization,data imputation,and feature extraction to enhance the data quality,thereby facilitating im-proved training and learning by the classifiers.To enhance the classification performance,the data imputation method consid-ers feature correlation measurement and sequential imputation,and the feature extractor utilizes the discriminative enhanced sparse autoencoder.To tackle the interclass imbalance of data with discrete and continuous features,the second module intro-duces an assisted classifier generative adversarial network,which includes a discrete feature generation module.Finally,a novel Stacking ensemble classifier for SM fault diagnosis is de-veloped.In contrast to previous studies,we construct a two-lay-er heuristic optimization framework to address the synchronous dynamic optimization problem of the combinations and hyper-parameters of the Stacking ensemble classifier,enabling better handling of complex classification tasks using SM data.The pro-posed fault diagnosis method for SM via two-layer stacking en-semble optimization and data augmentation is trained and vali-dated using SM fault data collected from 2010 to 2018 in Zheji-ang Province,China.Experimental results demonstrate the ef-fectiveness of the proposed method in improving the accuracy of SM fault diagnosis,particularly for minority classes.
Data augmentationfault diagnosisfeature ex-traction, smart meter, Stacking ensemble optimization
Leijiao Ge、Tianshuo Du、Zhengyang Xu、Luyang Hou、Jun Yan、Yuanliang Li
展开 >
School of Elec-trical and Information Engineering,Tianjin University,Tianjin 300072,China
School of Computer Science(National Pilot Software En-gineering School),Beijing University of Posts and Telecommunications,Beijing 100876,China
Concordia Institute for Information Systems Engi-neering,Concordia University,Montreal,QC H3G 1M8,Canada
万方数据
维普
