本文提出基于传感器数据排列的自监督任务并结合 Physics-Informed Real NVP,用于提升卫星多元时间序列故障检测性能,实验表明纯自监督训练效果最佳。
摘要:
在航天领域,由于环境条件和受限的可达性,鲁棒的故障检测方法对于确保任务成功和保护宝贵资产至关重要。本工作提出了一种利用 Physics-Informed Real NVP 神经网络的新颖方法,该网络以建模复杂高维分布的能力而闻名,并通过基于传感器数据排列的自监督任务进行增强。该方法专注于增强卫星多元时间序列中的故障检测。实验涉及多种配置,包括自监督预训练、多任务学习和独立自监督训练。结果表明,所有设置下均取得显著性能提升。特别是,仅采用自监督损失产生了最佳总体结果,表明其能有效引导网络提取与故障检测相关的特征。本研究为改进空间系统中的故障检测提供了有前景的方向,并值得在其他数据集和应用中进一步探索。
英文摘要:
In the space sector, due to environmental conditions and restricted accessibility, robust fault detection methods are imperative for ensuring mission success and safeguarding valuable assets. This work proposes a novel approach leveraging Physics-Informed Real NVP neural networks, renowned for their ability to model complex and high-dimensional distributions, augmented with a self-supervised task based on sensors' data permutation. It focuses on enhancing fault detection within the satellite multivariate time series. The experiments involve various configurations, including pre-training with self-supervision, multi-task learning, and standalone self-supervised training. Results indicate significant performance improvements across all settings. In particular, employing only the self-supervised loss yields the best overall results, suggesting its efficacy in guiding the network to extract relevant features for fault detection. This study presents a promising direction for improving fault detection in space systems and warrants further exploration in other datasets and applications.
Satellite-based feature extraction and multivariate time-series prediction of biotoxin contamination in shellfish
NOVA School of Science and Technology (NOVA FCT)(新里斯本大学科学与技术学院(NOVA FCT));IPMA - Instituto Português do Mar e da Atmosfera(葡萄牙海洋与大气研究所(IPMA));NOVA Laboratory for Computer Science and Informatics (NOVA LINCS)(新里斯本大学计算机科学与信息学实验室(NOVA LINCS));Center for Mathematics and Applications (NOVA Math)(新里斯本大学数学与应用中心(NOVA Math));NOVA Research & Development Unit for Mechanical and Industrial Engineering (UNIDEMI)(新里斯本大学机械与工业工程研发单元(UNIDEMI))
Deep Multi-Manifold Transformation Based Multivariate Time Series Fault Detection
School of Information and Electrical Engineering, Hangzhou City University(杭州城市大学信息与电子工程学院);Academy of Edge Intelligence, Hangzhou City University(杭州城市大学边缘智能研究院);College of Information Engineering, Zhejiang University of Technology(浙江工业大学信息工程学院);Institute of Cyber-Systems and Control, Zhejiang University(浙江大学网络系统与控制研究所);Centre for Artificial Intelligence and Robotics (CAIR), HKISI-CAS(人工智能与机器人中心(CAIR));State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA)(多模态人工智能系统国家重点实验室(MAIS));School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)(中国科学院大学人工智能学院)
Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics with Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis
Physics-Guided Counterfactual Explanations for Large-Scale Multivariate Time Series: Application in Scalable and Interpretable SEP Event Prediction
Dept. of Computer Science Georgia State University Atlanta, GA, USA(计算机科学系 佐治亚州立大学);Dept. of Computer Science California State University Fullerton, CA, USA(计算机科学系 加州州立大学Fullerton分校)
Simultaneous Multivariate Forecast of Space Weather Indices using Deep Neural Network Ensembles
The University of Alabama in Huntsville(阿拉巴马大学亨茨维尔分校);University of Cambridge(剑桥大学);University of Colorado, Boulder(科罗拉多大学博尔德分校);University of Strathclyde(斯特拉斯克莱德大学);Mexico National Autonomous University(墨西哥国立自治大学);University of Texas, Austin(德克萨斯大学奥斯汀分校);University of Surrey(萨里大学);University of Oxford(牛津大学)
European Space Agency Benchmark for Anomaly Detection in Satellite Telemetry
KP Labs;Airbus Defence and Space GmbH(空客防务与航天有限公司);Opole University of Technology(奥波莱理工大学);Silesian University of Technology(西里西亚理工大学);CGI Deutschland B.V. & Co. KG(CGI 德国有限两合公司);European Space Operations Centre, European Space Agency(欧洲空间局欧洲空间操作中心);Telespazio Germany GmbH(意大利空间公司德国有限公司);LSE Space GmbH(LSE Space 有限公司);Solenix GmbH(Solenix 有限公司)
Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detection
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);Kuaishou Technology(快手科技);Purple Mountain Laboratories(紫金山实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
Trojan Horse Hunt in Time Series Forecasting for Space Operations
KP Labs(KP实验室);Silesian University of Technology(桑特大学);Warsaw University of Technology(华沙技术大学);European Space Agency(欧洲航天局);European Space Operations Center(欧洲空间运营中心)