Transformer Vibration Forecasting for Advancing Rail Safety and Maintenance 4.0

TL;DR

This paper presents ShaftFormer, a transformer-based deep learning model for predicting railway axle vibrations, enhancing maintenance and safety by enabling early fault detection through simulated and real data analysis.

Contribution

Introduction of ShaftFormer, a transformer model tailored for time series vibration data, and an alternative spectral method to improve predictive maintenance in railways.

Findings

Effective vibration signal simulation under various conditions.

Improved fault detection accuracy with the proposed models.

Addressed non-stationary signal challenges in railway maintenance.

Abstract

Maintaining railway axles is critical to preventing severe accidents and financial losses. The railway industry is increasingly interested in advanced condition monitoring techniques to enhance safety and efficiency, moving beyond traditional periodic inspections toward Maintenance 4.0. This study introduces a robust Deep Autoregressive solution that integrates seamlessly with existing systems to avert mechanical failures. Our approach simulates and predicts vibration signals under various conditions and fault scenarios, improving dataset robustness for more effective detection systems. These systems can alert maintenance needs, preventing accidents preemptively. We use experimental vibration signals from accelerometers on train axles. Our primary contributions include a transformer model, ShaftFormer, designed for processing time series data, and an alternative model incorporating spectral methods and enhanced observation models. Simulating vibration signals under diverse conditions mitigates the high cost of obtaining experimental signals for all scenarios. Given the non-stationary nature of railway vibration signals, influenced by speed and load changes, our models address these complexities, offering a powerful tool for predictive maintenance in the rail industry.