空间控制技术与应用2023，Vol.49Issue(6)：86-93,8.DOI:10.3969/j.issn.1674-1579.2023.06.009
基于自监督学习的动力设备异常检测方法
Anomaly Detection Method for Power Equipment Based on Self-Supervised Learning
摘要
Abstract
Efficient and accurate anomaly detection of power equipment is essential for aerospace safety.Scientific detection and maintenance can promptly identify potential faults and ensure the safety and reliability of the system.The data collected by sensors from power equipment contains valuable information.Feature extraction is usually re-quired for processing these data.Although deep learning methods historically obtain excellent results,there is al-ways a trade-off between fine-tuning existing networks or designing models from scratch for sensor data processing.To address this issue,we propose a temporal feature extraction network for time series data based on self-supervised learning.First,we use self-supervised learning methods to pre-train the network.Then we devise a novel network model structure that can effectively extract the representation of time series data.Finally,we evaluate the proposed method on relevant datasets,and the experimental results demonstrate the effectiveness of the proposed method.关键词
动力设备/时序数据/自监督学习/异常检测Key words
power equipment/anomaly detection/self-supervised learning/series data分类
航空航天引用本文复制引用
乔怡群,王田,刘克新,王丽,吕坤,郭云翔..基于自监督学习的动力设备异常检测方法[J].空间控制技术与应用,2023,49(6):86-93,8.基金项目
国家自然科学基金资助项目(61972016、62032016和92067204)和北京市科技新星资助项目(20220484106和20230484451)Supported by National Natural Science Foundation of China(61972016,62032016 and 92067204)and Beijing Nova Program(20220484106,20230484451) （61972016、62032016和92067204）
