Unified Spacecraft Anomaly Detection Benchmark Dataset

Anomaly detection plays a crucial role in various domains, including but not limited to cybersecurity, space science, finance, and healthcare. However, the lack of standardized benchmark datasets hinders the comparative evaluation of anomaly detection algorithms. In this work, we address this gap by presenting a curated collection of preprocessed datasets for spacecraft anomalies sourced from multiple sources. These datasets cover a diverse range of anomalies and real-world scenarios for the spacecrafts. Furthermore, we have added two general datsets ensuring comprehensive evaluation and generalizability of anomaly detection algorithms. Our compilation process involves rigorous preprocessing steps to ensure data integrity and privacy protection. Each dataset is thoroughly documented, including descriptions of anomalies, preprocessing methodologies, and evaluation metrics. By providing this unified benchmark dataset, we aim to facilitate fair and transparent evaluation of anomaly detection algorithms, ultimately advancing the state-of-the-art in anomaly detection research.异常检测在诸多领域均发挥着关键作用，涵盖网络安全、空间科学、金融与医疗健康等方向。然而，当前缺乏标准化的基准数据集，这一短板阻碍了异常检测算法的对比评估工作。为此，本研究构建了一套源自多渠道、经过预处理的航天器异常数据集合集，该合集涵盖了多样化的航天器异常类型与真实应用场景。此外，我们额外加入了两个通用数据集，以保障异常检测算法评估的全面性与泛化能力。本数据集的构建流程采用了严格的预处理步骤，以确保数据完整性与隐私保护。每份数据集均附带详尽的文档说明，内容包括异常类型描述、预处理方法与评估指标。本统一基准数据集的发布，旨在为异常检测算法提供公平透明的评估基础，最终推动异常检测领域研究的前沿进展。

搜集汇总

背景与挑战

背景概述

该数据集是一个专门用于航天器异常检测的标准化基准数据集，旨在解决该领域缺乏统一评估标准的问题。它包含来自多源的预处理航天器异常数据，覆盖多种异常类型和真实场景，并额外添加了两个通用数据集以增强评估的全面性。数据集以numpy数组格式提供，已进行训练-测试分割，可直接用于算法开发和测试，促进异常检测研究的公平比较和进展。