Anomaly-TCM — Steel Tandem Cold Mill Predictive Maintenance [61.9 MB]
Abstract
"Synthetic steel cold-rolling predictive-maintenance benchmark with six chronological CSV streams, 51 features, and anomaly labels for work roll, bearing, motor, and reduction faults."
Description
Overview
Anomaly-TCM is a benchmark dataset for predictive maintenance in steel manufacturing, focused on tandem cold mills.
The six CSV datasets were generated using a mathematical model of a 5-stand tandem cold mill.
Four anomaly families are included: reduction scheme anomaly, increased work-roll friction, increased bearing motor torque, and decreased electric-motor efficiency.
Column Schema
| Column | Description |
|---|---|
| thickness_entry | Steel entry thickness in millimetres. |
| thickness_exit | Steel exit thickness in millimetres. |
| work_roll_mileage_1_to_5 | Chronological mileage of work rolls for stands 1 through 5. |
| reduction_1_to_5 | Thickness reduction at each rolling stand. |
| tension_0_to_5 | Inter-stand tension values. |
| roll_speed_1_to_5 | Linear work-roll speed for each stand. |
| force_1_to_5 | Rolling force for each stand. |
| torque_1_to_5 | Rolling torque for each stand. |
| motor_power_1_to_5 | Electric motor power in kW. |
| Anomaly_Bearing_1_to_5 | Labels for bearing anomalies by stand. |
| Anomaly_Electric_1_to_5 | Labels for electric-motor anomalies by stand. |
Key Statistics
- Total Records: Six datasets with about 20,000 observations each
- Features: 51 features plus anomaly labels
- File Format: CSV
- File Size: 61.9 MB total files
- Time Period: Published 2024
Use Cases
- Predictive maintenance in steel manufacturing
- Data-stream anomaly detection
- Explainable AI benchmarking for industrial processes
- Failure-mode classification for rolling mills
Source & Attribution
Created by Jakub Jakubowski, Szymon Bobek, and Grzegorz J. Nalepa. Published on Zenodo with DOI 10.5281/zenodo.11469702.
View Data Structure
To explore column names, data types, and sample rows, visit the official dataset page on Zenodo.
Preview on ZenodoCite This Dataset
Jakubowski, Jakub, Bobek, Szymon, & Nalepa, Grzegorz J. (2024). Anomaly-TCM — Steel Tandem Cold Mill Predictive Maintenance [61.9 MB]. [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.11469702
Source: Zenodo (2024) · DOI: 10.5281/zenodo.11469702
Indexed by IoTDataset.com on Jun 06, 2026
Ready to Start Your Research?
Download this dataset directly from the official repository and start building your next breakthrough project.