Rail surface defect detection method based on depth learning network

Abstract

The invention belongs to the field of depth learning, and provides a rail surface defect detection method based on the depth learning network, aiming at solving various problems existing in the priorrail detection methods. The depth learning method first automatically resets the input rail image to 416*416, and then extracts and processes the image. Image extraction mainly by Darknet-53 model complete. The processing output is mainly accomplished by the FPN-like network model. Firstly, the rail image is divided into cells. According to the position of the defects in the cells, the width, height and coordinates of the center point of the defects are calculated by dimension clustering method, and the coordinates are normalized. At the same time, we use logistic regression to predict the fraction of boundary box object, use binary cross-entropy loss to predict the category contained in the boundary box, calculate the confidence level, and then process the convolution in the output, up-sampling, network feature fusion to get the prediction results. The invention can accurately identify defects and effectively improve the detection and identification rate of rail surface defects.

Description

technical field [0001] The invention belongs to the field of deep learning, in particular to a method for detecting defects on the surface of rails based on a deep learning network. Background technique [0002] With the prosperity of my country's railway industry, the mileage, speed, and density of operations continue to increase, and the testing requirements for rails are further enhanced. When the train runs on the rail, it will produce friction, rolling contact and elastic-plastic deformation with the inner surface of the rail. Accumulate over a long period of time, just can make rail surface produce defect, and its manifestation is rail surface wearing and tearing, crushing, stripping, phenomenons such as wave wearing and tearing, vertical and horizontal crack type nucleation, have a strong impact on even endangering the safety of passengers. Therefore, in order to make the railway safer and run faster, and to increase the safety and comfort of passengers, the detectio...

AI Technical Summary

Problems solved by technology

[0009] The invention discloses a rail surface defect detection method based on a deep learning network. The invention is a rail surface defect detection method based on a deep learning network that can dete...

Images