Transformer Vibration Forecasting for Advancing Rail Safety and Maintenance 4.0

2025-01-20

AI Summary

Addressing the challenges of early fault detection in railway wheelsets and excessive reliance on scarce real-world measurement data, this paper proposes a vibration trend prediction method tailored for predictive maintenance. We introduce ShaftFormer—the first Transformer-based architecture specifically designed for modeling non-stationary axle vibration signals—and propose a dual-path modeling paradigm integrating time-frequency spectral analysis with physics-guided enhanced observation. Leveraging joint training on both synthetic and real-world datasets, the method achieves high-accuracy prediction of pre-failure vibration evolution across diverse operating conditions (e.g., varying speeds and loads). Experimental results demonstrate an average prediction accuracy of 92.7%, substantially outperforming state-of-the-art approaches; moreover, it reduces dependency on real measurement data by 68%. This work establishes a deployable, intelligent maintenance paradigm for proactive safety assurance of railway axle systems.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Railway Maintenance Optimization
• Train Axle Vibration Prediction
• Complex Vibration Analysis

Innovation

• Deep Learning
• ShaftFormer
• Predictive Maintenance