Case Western Reserve University Bearing Data Center 核心 · 已核验
atlas:cwru-bearing
电机驱动试验台上人工植入缺陷的滚动轴承振动数据集;缺陷由电火花加工(EDM)植入, 含驱动端/风扇端/基座多测点,是复用最广的公开轴承故障数据集。
- 落地页
- https://engineering.case.edu/bearingdatacenter
- 国内可访问性
-
国内直连:可达 (2026-07-11 检测)
代理通道:可达 (2026-07-11 检测)
检测口径:lychee 双通道单轮探测;「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。 - 发布方
- Case Western Reserve University
- 别名
- CWRU
- 设备类型
rolling_bearinginduction_motor- PHM 任务
fault_diagnosisfault_severity_estimationdomain_adaptation
分发点
| university_site | https://engineering.case.edu/bearingdatacenter | |
| university_site | https://engineering.case.edu/bearingdatacenter/download-data-file | 官方下载页;并卡自候选副本卡(atlas:quarry-url-https-engineering-case-edu-...,2026-07-10 用户裁决) |
数据概要
Matlab .mat 文件,按故障类型 × 缺陷尺寸 × 负载组织
故障工况
| fault_type: healthy_baseline |
| description: EDM 缺陷直径 0.007/0.014/0.021 in(个别子集含 0.028 in)fault_type: bearing_inner_race_faultseverity_levels: 3induction: artificially_seeded |
| description: 外圈缺陷含 3/6/12 点钟方位变体fault_type: bearing_outer_race_faultseverity_levels: 3induction: artificially_seeded |
| fault_type: bearing_rolling_element_faultseverity_levels: 3induction: artificially_seeded |
传感器
| sensor_type: accelerometerobserved_property: vibration_accelerationsampling_rate_hz: 12000.0mounting_note: 驱动端/风扇端/基座测点,12 kHz 子集 |
| sensor_type: accelerometerobserved_property: vibration_accelerationsampling_rate_hz: 48000.0mounting_note: 驱动端 48 kHz 子集 |
运行工况
| description: 电机负载 0/1/2/3 hp 四档condition_type: loadmin_value: 0.0max_value: 3.0unit: hpis_varying: False |
| condition_type: rotating_speedmin_value: 1730.0max_value: 1797.0unit: rpmis_varying: False |
关联论文(616 篇,候选区未经人工核验;candidate_citation = 共引启发式候选关联,非使用断言)
- Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study 2015 · reviews
- Nonlinear dynamic analysis of supporting bearing in rotor-bearing system considering vibration interaction 2025 · 候选关联(启发式)
- A novel bearing fault diagnosis method using a hybrid TCN-transformer architecture: A deep learning approach 2025 · 候选关联(启发式)
- An adaptive fault diagnosis method for rotating machinery based on GCN deep feature extraction and OptGBM 2025 · 候选关联(启发式)
- Multi-scale bidirectional transformer network for rolling bearing fault diagnosis 2025 · 候选关联(启发式)
- A supervised contrastive learning method based on online complement strategy for long-tailed fine-grained fault diagnosis 2025 · 候选关联(启发式)
- FD-LLM: Large language model for fault diagnosis of complex equipment 2025 · 候选关联(启发式)
- A dual-perspective joint domain generalization network for bearing fault diagnosis under unseen working conditions 2025 · 候选关联(启发式)
- Dynamic adaptive fault diagnosis using multi-channel image fusion and deep learning in channel failure occasions on rolling bearings 2025 · 候选关联(启发式)
- A fully interpretable convolutional neural network for intelligent fault diagnosis of rotating machinery 2025 · 候选关联(启发式)
- FPGA implementation of edge-side motor fault diagnosis using a Kalman filter-based empirical mode decomposition algorithm 2025 · 候选关联(启发式)
- Fault diagnosis of motor bearing in complex scenarios based on Mamba and Indicative Contrastive Learning 2025 · 候选关联(启发式)
- A novel adaptive gating neurons model with physical features weighted for bearing fault diagnosis under strong noise 2025 · 候选关联(启发式)
- Sample less meta-learning fault diagnosis based on ordered time–frequency features 2025 · 候选关联(启发式)
- Unsupervised multiple-target domain adaptation for bearing fault diagnosis 2025 · 候选关联(启发式)
- Unsupervised fault diagnosis and novel fault recognition for rotating machinery based on enhanced clustered autoencoder 2025 · 候选关联(启发式)
- A novel interpretability paradigm based on semantic features of time–frequency images for trustworthy cross-machine fault diagnosis 2025 · 候选关联(启发式)
- An improved lightweight residual network model deployed on the edge device for the unsupervised cross-domain fault diagnosis 2025 · 候选关联(启发式)
- HSE: A plug-and-play module for unified fault diagnosis foundation models 2025 · 候选关联(启发式)
- Deep meta-domain-adversarial neural network for machinery fault diagnosis under multiple operating conditions 2025 · 候选关联(启发式)
仅列前 20 篇(首发/综述优先,按年份倒序);全量见 API。
溯源(PROV,6 条)
| source_url: https://engineering.case.edu/bearingdatacenterretrieved_on: 2026-07-07asserted_by: human_curatornote: 试验台/传感器/缺陷参数见官方站说明页 |
| about_field: fault_conditionssource_citation: Smith & Randall (2015) MSSP, doi:10.1016/j.ymssp.2015.04.021retrieved_on: 2026-07-07asserted_by: human_curator |
| about_field: source_citation: 人工核验:zfbin(委托批准 2026-07-09)retrieved_on: 2026-07-09asserted_by: human_curatorconfidence_level: human_verifiednote: 晋升核心区。首晋升批次 01:KLS-005 手工填卡,实质核验于 KLS-005 完成(评审见 evidence/KLS-005/);委托代理执行 |
| about_field: distributionssource_citation: 人工核验:zfbin(四问拍板 2026-07-10)retrieved_on: 2026-07-10asserted_by: human_curatorconfidence_level: human_verifiednote: 人工改写。并卡增量:副本/镜像卡的 alt 分发点并入(2026-07-10 用户裁决,详见各条目 access_note) |
| about_field: china_accessibilitysource_citation: KLS-009 链接健康扫描(lychee 双通道)retrieved_on: 2026-07-11asserted_by: automated_harvestnote: 定期刷新标注,仅覆盖本字段;历史结果以最新扫描为准 |
| about_field: notessource_citation: 人工核验:zfbin(委托批次 KLS-032,2026-07-15)retrieved_on: 2026-07-14asserted_by: human_curatorconfidence_level: human_verifiednote: 人工改写。KLS-032 license 补判:官方页 engineering.case.edu/bearingdatacenter 无任何许可/条款声明(2026-07-15 核) |