Machine condition monitoring, vibration and bearing analysis, remaining-useful-life benchmarks, SCADA/OT telemetry and factory-floor sensor logs.
Large bearing condition-monitoring dataset for independent cart systems with vibration and system-variable signals. Zenodo archives total about 1.5 TB for fault diagnosis and PdM.
Labeled CSV dataset of ball-bearing vibration metrics captured every two minutes with an IFM VVB001 sensor. 752.6 kB for multi-class predictive-maintenance modeling.
SCADA sensor dataset from automotive welding sub-assembly lines with 147 sensors. 3.9 GB 7z archive for anomaly thresholds and predictive maintenance analysis.
Lab-scale vibration dataset with 4,000 CSV files for normal, bearing fault, misalignment, and unbalance states. 3.8 GB ZIP for predictive-maintenance classification.
Electric-motor vibration sensor dataset from the CHIST-ERA SOON project. ZIP format, 35.1 MB, with labeled functioning states for ML predictive-maintenance experiments.
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.
Real train-compressor sensor dataset from Porto metro with 7,116,940 time-series instances and 21 attributes. CSV files support anomaly detection, failure prediction, and RUL research.
Anonymized elevator-door IoT sensor time series from Huawei Munich Research Center. ZIP format, 453.9 kB, sampled at 4 Hz for predictive maintenance of elevator doors.
Industrial IoT IDS dataset with labelled TCP/IP and DNP3 flow statistics plus PCAP files for 9 SCADA cyberattacks. CSV and PCAP formats for ML/DL IDS research.
Smart-grid IDS dataset with labelled IEC 60870-5-104 and TCP/IP flow statistics plus PCAP files across 12 cyberattack scenarios. CSV and PCAP formats.
Real-world IIoT multivariate time series dataset tracking physicochemical degradation of metalworking fluid over several months. Includes imputed benchmark variants for 5 methods. CSV format. Designed for predictive maintenance and anomaly detection research in manufacturing.
One of Kaggle's largest IIoT manufacturing datasets with 1.18 million parts measured across Bosch's assembly lines. Thousands of anonymized sensor features split across numeric, categorical, and date files. CSV format. Used for quality control and failure prediction.
Synthetic IIoT dataset reflecting real milling machine predictive maintenance scenarios. 10,000 records with 14 features including air temperature, process temperature, rotational speed, torque, and 5 labeled failure types. CSV format. Ideal for multi-label fault classification.
Benchmark bearing vibration dataset from Case Western Reserve University with drive-end and fan-end faults at 4 severity levels. Sampled at 12 kHz and 48 kHz. MATLAB MAT and CSV formats. Used for fault diagnosis and vibration-based condition monitoring.
NASA Prognostics Center run-to-failure simulation dataset for turbofan engines. Four operational sub-datasets with 21 sensor channels and 3 operational settings. TXT/CSV format. Primary benchmark for Remaining Useful Life (RUL) estimation.
Time-series sensor readings from industrial machines for predictive maintenance and anomaly detection applications.
ToN_IoT is a large-scale dataset featuring heterogeneous data from IoT sensors, operating systems, and network traffic for advanced intrusion detection research in Industry 4.0.
Sensor data from factory environments used for identifying power fluctuations and unauthorized access.
A large-scale dataset (245GB) collected from real-world industrial control systems for advanced threat detection.
Industrial IoT dataset for efficient monitoring and control of power generation and distribution processes in smart grid applications with real-time fault detection capabilities.
Public (anonymized) predictive maintenance datasets from Huawei Munich Research Center for elevator industry; operation time series sampled at 4Hz (16:30–23:30) using electromechanical sensors, humidity, and vibration.
Published in October 2025, this dataset includes command logs and sensor feedback for an SLM-based assistant designed for IoT maintenance tasks. It bridges voice commands with shell-level operations in industrial environments, facilitating the training of AI assistants for hardware management.
Released in October 2025, this dataset captures performance metrics and network traffic associated with implementing Post-Quantum Cryptography (PQC) in Industrial IoT (IIoT) scenarios. It supports research into the feasibility and overhead of quantum-resistant security protocols on resource-constrained industrial hardware.
The Industrial IoT Dataset (Synthetic) provides a large-scale simulation of sensor readings and operational metrics from machines deployed in a smart factory environment. It focuses on predictive maintenance and anomaly detection.