Explainable Condition Monitoring via Probabilistic Anomaly Detection Applied to Helicopter Transmissions

2026-03-09

AI Summary

This work addresses the challenge of scarce fault data in safety-critical applications such as helicopter transmission systems by proposing an interpretable anomaly detection method that relies solely on healthy operational data. The approach employs Bayesian probabilistic modeling to learn the distribution of normal system states and introduces a tailored anomaly metric for real-time fault warning. By integrating uncertainty quantification with a visualization-based explanation mechanism, the method enhances the trustworthiness of diagnostic decisions. Experimental evaluation on both public predictive maintenance benchmarks and multi-year real-world helicopter transmission datasets demonstrates that the proposed technique achieves state-of-the-art detection performance while offering clear interpretability, making it well-suited for industrial settings demanding high reliability.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Security and Privacy: Data transparency and provenance
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We present a novel Explainable methodology for Condition Monitoring, relying on healthy data only. Since faults are rare events, we propose to focus on learning the probability distribution of healthy observations only, and detect Anomalies at runtime. This objective is achieved via the definition of probabilistic measures of deviation from nominality, which allow to detect and anticipate faults. The Bayesian perspective underpinning our approach allows us to perform Uncertainty Quantification to inform decisions. At the same time, we provide descriptive tools to enhance the interpretability of the results, supporting the deployment of the proposed strategy also in safety-critical applications. The methodology is validated experimentally on two use cases: a publicly available benchmark for Predictive Maintenance, and a real-world Helicopter Transmission dataset collected over multiple years. In both applications, the method achieves competitive detection performance with respect to state-of-the-art anomaly detection methods.

Problem

• Explainable Condition Monitoring
• Probabilistic Anomaly Detection
• Helicopter Transmissions
• Predictive Maintenance
• Uncertainty Quantification

Innovation

• Explainable AI
• Probabilistic Anomaly Detection
• Uncertainty Quantification
• Condition Monitoring
• Bayesian Methods