TY - JOUR
T1 - Use of deep convolutional neural networks and change detection technology for railway track inspections
AU - Harrington, Ryan M.
AU - Lima, Arthur de O.
AU - Fox-Ivey, Richard
AU - Nguyen, Thanh
AU - Laurent, John
AU - Dersch, Marcus S.
AU - Edwards, J. Riley
N1 - The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This study was funded by the Federal Railroad Administration (FRA), part of the United States Department of Transportation (US DOT). This work was also supported by the National University Rail Center, a U.S. Department of Transportation Office of the Assistant Secretary for Research and Technology Tier 1 University Transportation Center.
The material in this paper represents the position of the authors and not necessarily that of its sponsors. Finally, the authors acknowledge the involvement and support from, Amtrak, BNSF, and CN in their role as Industry Partners. J. Riley Edwards has been funded in part through grants to the Rail Transportation and Engineering Center (RailTEC) from CN and Hanson Professional Services, Inc.
PY - 2023/2
Y1 - 2023/2
N2 - Railroad track inspections conducted in accordance with federal regulations and internal railway operating practices result in significant labor costs and occupy valuable network capacity. These factors, combined with advancements in the field of machine vision, have encouraged a transition from human visual inspections to machine-based alternatives. Commercial machine vision technologies for railway inspection currently exist, and automated analysis approaches—which deliver objective results—are available in some systems. However, they are limited to a “pass/fail” approach through the detection of components which fail to meet maintenance or geometry thresholds, as opposed to being able to detect subtle changes in track conditions to identify evolving problems. To overcome these limitations, this paper presents results from the field deployment and validation of a system that pairs three-dimensional (3D) machine vision with automated change detection technology. The change detection approach uses a deep convolution neural network (DCNN) to accurately characterize track conditions between repeat runs. Current automated track inspection technologies were studied, and the applicability of change detection is discussed. The paper presents the process for 3D image capture, DCNN training, and evaluation by comparing DCNN results to an expert human evaluator. Finally, it presents change detection results for fastener presence and spike height. Results indicate that this technology can successfully identify fasteners and spikes with percent accuracies greater than 98% and that it can successfully generate change detection results for comparison of track condition among runs.
AB - Railroad track inspections conducted in accordance with federal regulations and internal railway operating practices result in significant labor costs and occupy valuable network capacity. These factors, combined with advancements in the field of machine vision, have encouraged a transition from human visual inspections to machine-based alternatives. Commercial machine vision technologies for railway inspection currently exist, and automated analysis approaches—which deliver objective results—are available in some systems. However, they are limited to a “pass/fail” approach through the detection of components which fail to meet maintenance or geometry thresholds, as opposed to being able to detect subtle changes in track conditions to identify evolving problems. To overcome these limitations, this paper presents results from the field deployment and validation of a system that pairs three-dimensional (3D) machine vision with automated change detection technology. The change detection approach uses a deep convolution neural network (DCNN) to accurately characterize track conditions between repeat runs. Current automated track inspection technologies were studied, and the applicability of change detection is discussed. The paper presents the process for 3D image capture, DCNN training, and evaluation by comparing DCNN results to an expert human evaluator. Finally, it presents change detection results for fastener presence and spike height. Results indicate that this technology can successfully identify fasteners and spikes with percent accuracies greater than 98% and that it can successfully generate change detection results for comparison of track condition among runs.
KW - 3D laser triangulation
KW - algorithms
KW - artificial intelligence
KW - change detection
KW - deep convolutional neural networks
KW - inspection
KW - operational efficiency
KW - safety
UR - http://www.scopus.com/inward/record.url?scp=85130464403&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85130464403&partnerID=8YFLogxK
U2 - 10.1177/09544097221093486
DO - 10.1177/09544097221093486
M3 - Article
AN - SCOPUS:85130464403
SN - 0954-4097
VL - 237
SP - 137
EP - 145
JO - Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit
JF - Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit
IS - 2
ER -