Axle Sensor Fusion for Online Continual Wheel Fault Detection in Wayside Railway Monitoring

TL;DR

This paper introduces a semantic-aware continual learning framework for railway wheel fault detection that fuses sensor data and metadata, enabling online adaptation and improved anomaly detection in wayside monitoring systems.

Contribution

It presents a novel fusion of VAE-encoded sensor signals with semantic metadata and a replay-based continual learning approach for robust, online railway fault diagnostics.

Findings

Detects minor wheel imperfections like flats and polygonization

Adapts to changing operational conditions such as train type and speed

Uses minimal labels and simple sensors for effective fault detection

Abstract

Reliable and cost-effective maintenance is essential for railway safety, particularly at the wheel-rail interface, which is prone to wear and failure. Predictive maintenance frameworks increasingly leverage sensor-generated time-series data, yet traditional methods require manual feature engineering, and deep learning models often degrade in online settings with evolving operational patterns. This work presents a semantic-aware, label-efficient continual learning framework for railway fault diagnostics. Accelerometer signals are encoded via a Variational AutoEncoder into latent representations capturing the normal operational structure in a fully unsupervised manner. Importantly, semantic metadata, including axle counts, wheel indexes, and strain-based deformations, is extracted via AI-driven peak detection on fiber Bragg grating sensors (resistant to electromagnetic interference) and fused with the VAE embeddings, enhancing anomaly detection under unknown operational conditions. A lightweight gradient boosting supervised classifier stabilizes anomaly scoring with minimal labels, while a replay-based continual learning strategy enables adaptation to evolving domains without catastrophic forgetting. Experiments show the model detects minor imperfections due to flats and polygonization, while adapting to evolving operational conditions, such as changes in train type, speed, load, and track profiles, captured using a single accelerometer and strain gauge in wayside monitoring.