Research on application of deep convolutional network in high-speed railway track inspection based on distributed fiber acoustic sensing

摘要

The shortcomings of the commonly used track inspection methods in high-speed railway are the high cost and the safety risks. Distributed optical fiber acoustic sensors (DAS) technology owns lots of performance benefits (e.g. anti-interference and real-time performance) and its potential to be a great help in the field of track inspection has been proved by various empirical certifications under its accuracy and practicability. In this paper, we first take a part of tracks in some high-speed rail track as the experimental object, and describe the deployment of DAS and the process of data collection. Then we propose a new scheme for the rail track state inspection with a deep convolutional network as the core. The selection and processing of data and the innovation of network structure have been experimentally verified.