用于卫星电源系统故障检测的物理信息 Real NVP
Physics-Informed Real NVP for Satellite Power System Fault Detection
AI总结：
本文提出物理信息 Real NVP 故障检测方法，在 NASA ADAPT 电力系统数据集上优于 GRU 和 Autoencoder 等方法，可提升卫星 EPS 故障检测的稳健性与可靠性。
摘要：
空间环境以极端条件和可达性有限为特征，其带来的独特挑战使人们需要稳健可靠的技术来识别和预防卫星故障。航天领域的故障检测方法必须确保任务成功并保护宝贵资产。在此背景下，本文提出一种基于人工智能（AI）的故障检测方法，并在 ADAPT（Advanced Diagnostics and Prognostics Testbed，先进诊断与预测测试平台）上评估其性能；该数据集是由 NASA 在实验室中构建的电力系统（Electrical Power System，EPS）数据集。本研究聚焦于将物理信息（physics-informed，PI）实值非体积保持（real-valued non-volume preserving，Real NVP）模型应用于空间系统故障检测。研究将该方法的有效性与门控循环单元（Gated Recurrent Unit，GRU）和基于 Autoencoder 的技术等其他 AI 方法进行了系统比较。结果表明，我们的物理信息方法优于现有故障检测方法，证明其适合应对卫星 EPS 子系统故障的独特挑战。此外，我们揭示了 AI 模型中物理信息损失在满足特定航天需求方面的竞争优势，即稳健性、可靠性和功率约束，这些对于空间探索和卫星任务至关重要。
英文摘要：
The unique challenges posed by the space environment, characterized by extreme conditions and limited accessibility, raise the need for robust and reliable techniques to identify and prevent satellite faults. Fault detection methods in the space sector are required to ensure mission success and to protect valuable assets. In this context, this paper proposes an Artificial Intelligence (AI) based fault detection methodology and evaluates its performance on ADAPT (Advanced Diagnostics and Prognostics Testbed), an Electrical Power System (EPS) dataset, crafted in laboratory by NASA. Our study focuses on the application of a physics-informed (PI) real-valued non-volume preserving (Real NVP) model for fault detection in space systems. The efficacy of this method is systematically compared against other AI approaches such as Gated Recurrent Unit (GRU) and Autoencoder-based techniques. Results show that our physics-informed approach outperforms existing methods of fault detection, demonstrating its suitability for addressing the unique challenges of satellite EPS sub-system faults. Furthermore, we unveil the competitive advantage of physics-informed loss in AI models to address specific space needs, namely robustness, reliability, and power constraints, crucial for space exploration and satellite missions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
