Published December 18, 2024 | Version v1

Gaussian Mixture Model for Battery Operation Anomaly Detection

  • 1. ROR icon INESC TEC

Description

This research presents an anomaly detection algorithm for a Vanadium Redox Flow Battery (VRFB) using battery dataset as an example. The algorithm determines the anomaly detection threshold by fitting a Gaussian mixed model (GMM) to an anomaly-free dataset and testing it against a dataset containing only anomalies. By forcing the test dataset to classify all observations as anomalies, the threshold can be found. Applying again the model to the training dataset, classifies 11% of normal observations as failures, indicating that, not all observations were captured by the GMM, resulting in false positives. A percentage based on the likelihood values is suggested for replication to other systems, and a ratio of anomaly detection over time is proposed for preventive maintenance alerts.

Files

Conference Article - Gaussian Mixture Model for Battery Operation.pdf

Files (2.4 MB)

Additional details

Funding

European Commission
INTERSTORE - Interoperable opeN-source Tools to Enable hybRidisation, utiliSation, and moneTisation of stORage flExibility 101096511

Dates

Available
2024-09-30