Object-Size-Driven Design of Convolutional Neural Networks: Virtual Axle Detection based on Raw Data

TL;DR

This paper introduces a real-time, sensor-agnostic train axle detection method using CNNs that outperforms spectrogram-based approaches in speed and memory, and proposes a new hyperparameter optimization rule based on object size.

Contribution

It presents VADER, a novel CNN-based axle detection system using raw acceleration data, and introduces the MRF rule for hyperparameter tuning based on object size, applicable to various deep learning tasks.

Findings

Achieved 99.9% axle detection accuracy with 3.69cm error.

Outperformed spectrogram-based methods in speed and memory by 99%.

Proposed MRF rule reduces hyperparameter tuning effort.

Abstract

As infrastructure ages, the need for efficient monitoring methods becomes increasingly critical. Bridge Weigh-In-Motion (BWIM) systems are crucial for cost-effective determination of loads and, consequently, the residual service life of road and railway infrastructure. However, conventional BWIM systems require additional sensors for axle detection, which must be installed in potentially inaccessible locations or places that interfere with bridge operation. This study presents a novel approach for real-time detection of train axles using sensors arbitrarily placed on bridges, providing an alternative to dedicated axle detectors. The developed Virtual Axle Detector with Enhanced Receptive Field (VADER) has been validated on a single-track railway bridge using only acceleration measurements, detecting 99.9% of axles with a spatial error of 3.69cm. Using raw data as input outperformed the state-of-the-art spectrogram-based method in both speed and memory usage by 99%, thereby making real-time application feasible for the first time. Additionally, we introduce the Maximum Receptive Field (MRF) rule, a novel approach to optimise hyperparameters of Convolutional Neural Networks (CNNs) based on the size of objects. In this context, the object size relates to the fundamental frequency of a bridge. The MRF rule effectively narrows the hyperparameter search space, overcoming the need for extensive hyperparameter tuning. Since the MRF rule can theoretically be applied to all unstructured data, it could have implications for a wide range of deep learning problems, from earthquake prediction to object recognition.