Railway track fault detection using optimised convolution neural network

被引：0

作者：

Chitra R. ^{[1
]}

Bamini A.M.A. ^{[1
]}

Brindha D. ^{[1
]}

Jegan T.M.C. ^{[2
]}

Kirubakaran S.S. ^{[2
]}

机构：

[1] Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Tamil Nadu, Coimbatore

[2] Department of Mechanical Engineering, Sri Ranganathar Institute of Engineering and Technology, Tamil Nadu, Coimbatore

来源：

International Journal of Reliability and Safety | 2024年 / 18卷 / 02期

关键词：

activation function; neural network; optimisation; track; VGG;

D O I：

10.1504/IJRS.2024.139215

中图分类号：

学科分类号：

摘要：

Railway accidents are an under-scrutinised cause of death in India. Train accidents are caused by various consequences of collisions, derailments, signal errors and so on. Furthermore, when train derailments become disastrous, they can have tremendous repercussions. It is practically difficult to identify the cause of the derailment efficiently within a limited period. In recent years, we have been making progress in reducing derailments, but even if not deadly, identifying faulty tracks can waste a lot of time and money. And doing this error-free is a pressing matter, as tracks always experience wear and tear with more usage. Here is where neural networks can pitch in their solution. We can train a model to look at train tracks and identify any issues. This paper goes into the methodology of achieving this and optimising a neural network to predict problems in the track with the best possible accuracy that images can provide. The objective of this paper is to identify, develop and optimise neural networks to detect faulty tracks. In this work, a good Convolution Neural Network model is developed to identify the crack in the railway track. The developed model produced 95.54% accuracy in fault classification. Copyright © 2024 Inderscience Enterprises Ltd.

引用

页码：163 / 186

页数：23

共 17 条

[1]

Acikgoz H., Korkmaz D., MSRConvNet: classification of railway track defects using multi-scale residual convolutional neural network, Engineering Applications of Artificial Intelligence, 121, (2023)

[2]

Vidhya Analytics, Analytics Vidhya

[3]

Aydin A., Salur M.U., Aydin I., Fine-tuning convolutional neural network based railway damage detection, Proceedings of the 19th IEEE International Conference on Smart Technologies, pp. 216-221, (2021)

[4]

Brito M.P., Stevenson M., Bravo C., Subjective machines: probabilistic risk assessment based on deep learning of soft information, Risk Analysis, 43, 3, pp. 516-529, (2022)

[5]

Britain's digital railways

[6]

Over 13,000 Train Accidents in 2020, 32 Lives Lost Daily on Average, NCRB Reports, (2020)

[7]

Huang F., Xie G., Xiao R., Research on Ensemble Learning, International Conference on Artificial Intelligence and Computational Intelligence, (2009)

[8]

James A., Jie W., Xulei Y., Chenghao Y., Ngan N.B., Yuxin L., Yi S., Chandrasekhar V., Zeng Z., Tracknet-a deep learning based fault detection for railway track inspection, Proceedings of the IEEE International Conference on Intelligent Rail Transportation (ICIRT), pp. 1-5, (2018)

[9]

Jin X., Wang Y., Zhang H., Zhong H., Liu L., Wu Q.M.J., Yang Y., DM-RIS: deep multimodal rail inspection system with improved MRF-GMM and CNN, IEEE Transactions on Instrumentation and Measurement, 69, pp. 1051-1065, (2020)

[10]

Krishna B., Seshendra D., Raja G., Sudharshan T., Srikanth K., Railway track fault detection system by using sensors and Bluetooth technology, Asian Journal of Applied Science and Technology (AJAST), 1, pp. 82-84, (2017)

← 1 2 →