Pressure Signal Dataset for Leak Detection in Electro-Pneumatic Systems 核心 · 已核验

mxds0zwqd4ahyr58

This dataset contains pressure time-series signals acquired from an electro-pneumatic system operating under normal conditions and different leak scenarios. The signals were obtained from controlled experiments and simulations, representing distinct operating states such as normal operation, advance and retraction movements, and internal and external leakage conditions.

All signals were sampled at a fixed sampling frequency and stored in CSV format. The dataset was designed to support research on condition monitoring, fault diagnosis, and automatic leak detection using machine learning and signal processing techniques.

The dataset was used in the development and evaluation of multiple classification models, including linear models, decision trees, ensemble methods, neural networks, and reservoir computing approaches. Feature extraction was performed using the TSFEL library, resulting in a total of 156 features per signal window.

This dataset is publicly available to promote reproducibility and further research in intelligent monitoring of electro-pneumatic systems.

本卡描述如含来自官方页的原文片段,其版权归原作者,不在本站 CC-BY 4.0 许可范围(见关于与许可)。

落地页

https://zenodo.org/doi/10.5281/zenodo.18446324

许可证

CC-BY-4.0 (置信:verified_official)

国内可访问性

国内直连:可达 (2026-07-11 检测) 非直连:可达 (2026-07-11 检测)
「直连超时」表示检测窗口内未完成,系慢或不稳定证据,不构成封锁证据。

发布年份

2026

发布方

Zenodo

PHM 任务

condition_monitoring fault_diagnosis fault_detection

故障工况