Interpretable Rules for Online Failure Prediction: A Case Study on the Metro do Porto dataset

2025-02-11

AI Summary

This work addresses the lack of interpretability in online fault prediction for Porto Metro trains. We propose a lightweight, real-time executable, rule-based explainable method grounded in interpretable feature engineering and rule mining algorithms. Our approach establishes the first online explainable rule generation framework tailored to rail transit maintenance operations. Relying solely on three critical sensor signals, it achieves high prediction accuracy on the MetroPT2 real-world dataset via a streaming inference mechanism. The generated rules are concise and intuitive—e.g., “If sensor A remains above threshold X and sensor B’s decline rate exceeds Y, then fault probability is high within 48 hours.” This significantly enhances model transparency, deployment efficiency, and frontline maintenance responsiveness, while preserving both predictive accuracy and human interpretability.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Data Mining & Knowledge Management: Rule Mining & Pattern Mining
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Due to their high predictive performance, predictive maintenance applications have increasingly been approached with Deep Learning techniques in recent years. However, as in other real-world application scenarios, the need for explainability is often stated but not sufficiently addressed. This study will focus on predicting failures on Metro trains in Porto, Portugal. While recent works have found high-performing deep neural network architectures that feature a parallel explainability pipeline, the generated explanations are fairly complicated and need help explaining why the failures are happening. This work proposes a simple online rule-based explainability approach with interpretable features that leads to straightforward, interpretable rules. We showcase our approach on MetroPT2 and find that three specific sensors on the Metro do Porto trains suffice to predict the failures present in the dataset with simple rules.

Problem

• Predicting Metro train failures in Porto.
• Addressing explainability in predictive maintenance.
• Simplifying interpretable rules for failure prediction.

Innovation

• rule-based explainability approach
• interpretable features for failures
• specific sensors predict failures