ABB IRB 1100 Robot Synthetic Data for Predictive Maintenance

Mohamed Lamine Soudani published a synthetic dataset for predictive maintenance of industrial robots on figshare in May 2026. The dataset comprises 2,000 instances and 215 explanatory characteristics generated from a simulation model of an ABB IRB 1100 robot's six axes. It includes simulated multisensory signals monitoring electrical, mechanical, thermal, and vibration parameters.

Use Cases

• Training machine learning models for fault detection based on simulated electrical, mechanical, thermal, and vibration parameters.
• Evaluating feature selection methods for predictive maintenance systems based on the 215 explanatory characteristics.
• Benchmarking ensemble tree methods against SVM-based approaches for industrial robot failure classification.
• Developing severity-level classification models for maintenance prioritization based on three levels per defect type.

Strengths

• Dataset contains 2,000 instances, providing a substantial synthetic sample for model development.
• Includes 215 explanatory characteristics derived from a detailed simulation model of a robot's six axes.
• Results from the associated study demonstrate specific model performance metrics, such as LightGBM achieving an F1-macro score of 0.7625.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is synthetic, generated from a simulation model, and may not fully capture real-world operational complexities.

Provenance

Source

Mohamed Lamine Soudani

Collection Method

Generated via a sophisticated simulation model incorporating the robot's six axes and multisensory parameters.

Freshness

Last updated 2026-05-22 12:48:59; freshness should be verified.