河南理工大学学报（自然科学版）2025，Vol.44Issue(4)：59-65,7.DOI:10.16186/j.cnki.1673-9787.2024070038
基于深度学习的电网指标数据异常检测方法研究
Anomaly detection method for power grid indicator data based on deep learning
摘要
Abstract
Objectives Time series anomaly detection based on deep learning has plays a key role in intelli-gent operation and maintenance scenarios such as power system operations,equipment fault detection,and power grid fault monitoring.While existing methods have achieved notable success,they often focus on fixed time windows and overlook correlations between different feature dimensions of the time series,which can lead to false positives and reduced detection accuracy.Methods This paper proposes a Temporal-Feature Fusion Anomaly Transformer(TFFAT)model for unsupervised anomaly detection in multivariate power grid indicator data.TFFAT leverages a graph attention mechanism to capture complex dependencies from both the temporal and feature dimensions in parallel.It employs an anomaly transformer to process the fused hidden features and compute anomaly scores.Results Experimental results on three publicly available time series anomaly detection datasets show that TFFAT achieves detection accuracies of 89.73%,92.12%,and 97.14%,respectively,significantly outperforming existing benchmark methods.Conclusions TFFAT effectively captures interdependencies across temporal and feature dimensions,enabling more accu-rate detection of anomalies in time series data.It demonstrates strong potential for application in power grid operation and maintenance,significantly improving fault detection accuracy,reducing false positives,and enhancing the stability and reliability of the power grid.关键词
深度学习/电网数据/异常检测/电网运维/电网监控/时间序列Key words
deep learning/power grid data/anomaly detection/power grid operation and maintenance/power grid monitoring/time series分类
动力与电气工程引用本文复制引用
盛振明,郭耀松,刘超,成阳,韩肖,方巍..基于深度学习的电网指标数据异常检测方法研究[J].河南理工大学学报（自然科学版）,2025,44(4):59-65,7.基金项目
国家自然科学基金资助项目(42475149) （42475149）
2023年国电南瑞南京控制系统有限公司科技信息项目(524609230052) （524609230052）
