An adaptive fault diagnosis approach using pipeline implementation for railway inspection

Abstract

Railway tracks must be periodically inspected. This study proposes a new approach for eliminating two major disadvantages experienced during rail inspection applications performed via computer vision. The first is the blurring effect on images, resulting from physical vibration during movement on the rail lines. This effect significantly reduces the high accuracy rate expected from anomaly inspection algorithms. The second disadvantage is the need to operate in real time. This study presents a new three-stage computer vision method approach that eliminates both disadvantages. First, a three-stage pipeline architecture is implemented and IMU-assisted blur detection is performed on images taken from the left and right rail lines. Next, a convolutional neural network is used for learning. In the third test stage, anomaly detection and classification training are conducted. By performing the implementation with parallel programming on graphic processing units, a highly accurate, cost-effective computer vision rail inspection, based on image processing and capable of operating in real time, is successfully carried out.

SCueU-Net: Efficient Damage Detection Method for Railway Rail

“…The paper [38] proposed an optimization method based on Chouqet fuzzy integral to improve the overall accuracy of the method described in the paper [37]. The paper [39] proposed a method of using the IMU original to deblur the acquired image and then applying the CNN method to classify the railway track image and then complete the track status monitoring method, and achieved good results. The paper [40] proposed a method for railway line condition monitoring and surface defect detection.…”

The Recent Applications of Machine Learning in Rail Track Maintenance: A Survey

“…the number of convolutional layers) was not mentioned in their research. However, in their next experiment, Santur et al [49] used normal video cameras and proposed a three-stage pipeline with a blur elimination step and trained a three-layers CNN model. As a part of a more comprehensive big data-oriented methodology, Jamshidi et al [27] in their recent analysis, trained a CNN network on both Axle Box Acceleration (ABA) inspection data and a manually labeled image dataset collected from a specific section of the Dutch rail network.…”

Parallel computing in railway research

“…For example, most modern CPUs accommodate a maximum eight cores each while a GPU nowadays can easily accommodate hundreds of computing cores. The Compute Unified Device Architecture (CUDA) parallel computing platform can enable GPUs to be used as GPGPUs; a few such railway applications [17,57,58] have been reported. Deriving from the original purpose of GPUs, the GPGPU technique is very suitable for graphic processing such as image processing in machine vision condition monitoring [17,57] and results analysis for FEA [58].…”

“…For signal and image processing, parallel GPUs and FPGA are often used. Parallel GPUs were used by Santur et al [57] and Wang et al [17] to process machine vision rail and catenary inspections respectively. In the former application, two GPUs were used to process the image captured by two cameras in parallel.…”