LD-RPMNet: Near-Sensor Diagnosis for Railway Point Machines

TL;DR

This paper introduces LD-RPMNet, a lightweight model combining Transformers and CNNs for efficient near-sensor fault diagnosis in railway point machines, achieving high accuracy with reduced computational resources.

Contribution

The study presents a novel lightweight model with a Multi-scale Depthwise Separable Convolution and Broadcast Self-Attention for improved efficiency and accuracy in railway fault diagnosis.

Findings

Parameter count and complexity reduced by 50%.

Diagnostic accuracy improved by nearly 3%.

Achieved 98.86% overall accuracy.

Abstract

Near-sensor diagnosis has become increasingly prevalent in industry. This study proposes a lightweight model named LD-RPMNet that integrates Transformers and Convolutional Neural Networks, leveraging both local and global feature extraction to optimize computational efficiency for a practical railway application. The LD-RPMNet introduces a Multi-scale Depthwise Separable Convolution (MDSC) module, which decomposes cross-channel convolutions into pointwise and depthwise convolutions while employing multi-scale kernels to enhance feature extraction. Meanwhile, a Broadcast Self-Attention (BSA) mechanism is incorporated to simplify complex matrix multiplications and improve computational efficiency. Experimental results based on collected sound signals during the operation of railway point machines demonstrate that the optimized model reduces parameter count and computational complexity by 50% while improving diagnostic accuracy by nearly 3%, ultimately achieving an accuracy of 98.86%. This demonstrates the possibility of near-sensor fault diagnosis applications in railway point machines.