Scalable, Technology-Agnostic Diagnosis and Predictive Maintenance for Point Machine using Deep Learning

2025-08-12

AI Summary

To address the challenges of multi-signal dependency, labor-intensive manual feature engineering, and poor cross-device generalizability in point machine (PM) fault diagnosis, this paper proposes an end-to-end deep learning–based predictive maintenance method leveraging solely single-channel power supply current signals. The approach eliminates handcrafted feature extraction and multi-source signal fusion, directly modeling temporal patterns in actuation current waveforms. Conformal prediction is integrated to rigorously quantify classification confidence, ensuring compliance with ISO 17359. Evaluated across diverse electromechanical point machines, the method achieves >99.99% precision, <0.01% false alarm rate, and negligible missed detection rate. It demonstrates strong robustness, broad cross-device applicability, and high interpretability—significantly enhancing operational reliability and practical deployability in railway signaling systems.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The Point Machine (PM) is a critical piece of railway equipment that switches train routes by diverting tracks through a switchblade. As with any critical safety equipment, a failure will halt operations leading to service disruptions; therefore, pre-emptive maintenance may avoid unnecessary interruptions by detecting anomalies before they become failures. Previous work relies on several inputs and crafting custom features by segmenting the signal. This not only adds additional requirements for data collection and processing, but it is also specific to the PM technology, the installed locations and operational conditions limiting scalability. Based on the available maintenance records, the main failure causes for PM are obstacles, friction, power source issues and misalignment. Those failures affect the energy consumption pattern of PMs, altering the usual (or healthy) shape of the power signal during the PM movement. In contrast to the current state-of-the-art, our method requires only one input. We apply a deep learning model to the power signal pattern to classify if the PM is nominal or associated with any failure type, achieving >99.99% precision, <0.01% false positives and negligible false negatives. Our methodology is generic and technology-agnostic, proven to be scalable on several electromechanical PM types deployed in both real-world and test bench environments. Finally, by using conformal prediction the maintainer gets a clear indication of the certainty of the system outputs, adding a confidence layer to operations and making the method compliant with the ISO-17359 standard.

Problem

• Detecting railway point machine failures using power signals
• Overcoming technology-specific limitations in predictive maintenance
• Providing confidence-aware anomaly classification for maintenance compliance

Innovation

• Deep learning model analyzes power signal patterns
• Technology-agnostic method requires only one input
• Conformal prediction provides confidence layer for outputs