Detecting train driveshaft damages using accelerometer signals and Differential Convolutional Neural Networks

TL;DR

This paper introduces a novel railway axle damage detection system using 2D CNNs on spectrograms of vibration signals, significantly improving classification accuracy for different defect levels.

Contribution

It develops an advanced deep learning approach combining time-frequency analysis and CNNs for accurate railway axle damage detection, outperforming existing methods.

Findings

Achieved high AUC scores of 0.93, 0.86, and 0.75 across different wheelset assemblies.

Successfully classified four defect levels with high reliability.

Outperformed several alternative classification methods.

Abstract

Railway axle maintenance is critical to avoid catastrophic failures. Nowadays, condition monitoring techniques are becoming more prominent in the industry to prevent enormous costs and damage to human lives. This paper proposes the development of a railway axle condition monitoring system based on advanced 2D-Convolutional Neural Network (CNN) architectures applied to time-frequency representations of vibration signals. For this purpose, several preprocessing steps and different types of Deep Learning (DL) and Machine Learning (ML) architectures are discussed to design an accurate classification system. The resultant system converts the railway axle vibration signals into time-frequency domain representations, i.e., spectrograms, and, thus, trains a two-dimensional CNN to classify them depending on their cracks. The results showed that the proposed approach outperforms several alternative methods tested. The CNN architecture has been tested in 3 different wheelset assemblies, achieving AUC scores of 0.93, 0.86, and 0.75 outperforming any other architecture and showing a high level of reliability when classifying 4 different levels of defects.