LD-RPMNet: Near-Sensor Diagnosis for Railway Point Machines
This work addresses fault diagnosis for railway infrastructure, offering a practical near-sensor solution with improved efficiency and accuracy, though it is incremental in its method integration.
The study tackled near-sensor fault diagnosis for railway point machines by proposing LD-RPMNet, a lightweight model that integrates Transformers and CNNs, reducing parameters and computational complexity by 50% and improving diagnostic accuracy to 98.86%.
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.