MetroPT-3 Dataset (Metro Train Air Production Unit) 核心 · 已核验
mxdsa9tqvkvjn354
MetroPT-3(波尔图地铁):列车空气生产单元(APU)压缩机真实运营监测数据,15 路模拟+数字信号 1 Hz 连续采集,含真实失效与维修记录;面向异常检测/失效预测/RUL 的真实运维基准(UCI #791)
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://archive.ics.uci.edu/dataset/791/metropt+3+dataset
- 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
- 2021
- 发布方
- UCI Machine Learning Repository
- 别名
- MetroPT-3
- 设备类型
compressor- PHM 任务
anomaly_detectionrul_prediction
故障工况
| description: 真实运营失效:APU 空气/油泄漏等,维修报告标注失效区间fault_type: seal_leakageinduction: natural_operation |
传感器
| sensor_type: pressure_transducerobserved_property: pressuresampling_rate_hz: 1.0mounting_note: 气路多点压力(TP2/TP3/H1 等) |
| sensor_type: thermocoupleobserved_property: temperaturemounting_note: 油温 |
| sensor_type: current_sensorobserved_property: electric_currentmounting_note: 电机电流 |
| sensor_type: otherobserved_property: othermounting_note: 电磁阀/压力开关/塔控等数字信号 |
运行工况
| description: 城轨列车真实运营连续采集(1 Hz,约 1500+ 小时),含正常/失效/维修全周期condition_type: duty_cycleis_varying: True |
关联论文(104 篇)
仅表示这篇论文与本数据集在文献网络中相邻, 不代表该论文确实使用了本数据集。
- The MetroPT dataset for predictive maintenance 2022 · 首发该数据集
- MetroPT: A Benchmark dataset for predictive maintenance 2022 · 首发该数据集
- IntelliMetro‐Hybrid: A Machine Learning and Deep Learning Fusion Model for Economic Optimization in Smart Metro Systems 2026 · 用于方法验证
- FusionNet: intelligent sequence fusion for predictive maintenance in edge-enabled industrial IoT systems 2026 · 使用该数据集
- Interpretable rules for online failure prediction: a case study on metro do porto datasets 2026 · 用于方法验证
- Survival-analysis-guided machine learning for failure and remaining-useful-life prediction in railway compressor 2026 · 用于方法验证
- ASPIRE: An Agentic Decision System for Early Equipment Failure Prediction and Intervention in Industrial IIoT 2026 · 用于方法验证
- "Profile-Parametric Evidence Governance for Auditable Prognostics and Health Management Claims (PEAR) - IEEE Transactions on Instrumentation and Measurement Submission Data" 2026 · 使用该数据集
- A Unified Engineering-Informatics Framework for Noise-Robust and Explainable Edge Predictive Maintenance 2026 · 用于方法验证
- Dynamically Gated TinyMLPs for Extreme Edge Predictive Maintenance: A Noise-Robust Feasibility Study 2026 · 使用该数据集
- Kharisara/mer-jit-llm-fgcs: ReplayBench-PG v2.6.0 2026 · 用于方法验证
- When Does Cost-Sensitive Learning Help in Predictive Maintenance? A Cross-Dataset Benchmark Study — Code and Data 2026 · 用于方法验证
- When Does Cost-Sensitive Learning Help in Predictive Maintenance? A Cross-Dataset Benchmark Study — Code and Data 2026 · 用于方法验证
- Kharisara/mer-jit-llm-fgcs: ReplayBench-PG: Reproducibility Package for Fault-Aware Deterministic Replay Benchmarking of Policy-Gated AI Pipelines 2026 · 用于方法验证
- Kharisara/mer-jit-llm-fgcs: ReplayBench-PG: Reproducibility Package for Fault-Aware Deterministic Replay Benchmarking of Policy-Gated AI Pipelines 2026 · 使用该数据集
- Kharisara/mer-jit-llm-fgcs: ReplayBench-PG Reproducibility Artifact v2.3.0 2026 · 用于方法验证
- Kharisara/mer-jit-llm-fgcs: Submission-Aligned Reproducibility and Validation Release 2026 · 用于方法验证
- Kharisara/mer-jit-llm-fgcs: ReplayBench-PG v2.4.1 2026 · 使用该数据集
- Kharisara/mer-jit-llm-fgcs: Complete Reproducibility Artifact 2026 · 用于方法验证
- Kharisara/mer-jit-llm-fgcs: Complete Reproducibility Artifact 2026 · 用于方法验证
仅列前 20 篇(首发/综述优先,按年份倒序);全量见 API。
溯源(10 条)
| 日期: 2026-07-08 |
| 来源链接: https://api.datacite.org/dois/10.24432/C5VW3R 日期: 2026-07-08 |
| 日期: 2026-07-08 |
| 日期: 2026-07-09 |
| 日期: 2026-07-11 |
| 日期: 2026-07-11 |
| 日期: 2026-07-21 |
| 日期: 2026-07-25 |
| 日期: 2026-07-26 |
| 日期: 2026-07-31 |