HVAC Fault Detection: Synthetic Anomaly Detection Results

Anomaly detection results from HVAC equipment monitoring using the Isolation Forest algorithm. The dataset includes detected faults, anomaly scores, and equipment status. It was created by shahabsalehi and last updated on March 15, 2026.

Use Cases

• Benchmarking anomaly detection algorithms based on synthetic HVAC fault data.
• Testing fault classification models using detected fault labels.
• Evaluating anomaly scoring methods based on provided anomaly scores.
• Simulating building management system alerts based on equipment status data.

Strengths

• Dataset includes anomaly scores from the Isolation Forest algorithm, providing a quantitative measure for fault severity.
• Explicitly labels detected faults and equipment status, offering clear targets for supervised or semi-supervised learning tasks.

Limitations

• Dataset contains synthetically generated data and does not represent real equipment faults or actual building systems.
• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

huggingface

Collection Method

Results generated by an anomaly detection pipeline named 'hvac_fault_detection_anomaly', likely using the Isolation Forest algorithm.

Freshness

Last updated 2026-03-15 00:20:21; freshness should be verified.