Enhancing AI Model for Fault Detection in Rail Through the Evaluation of AE Parameters with Proper Weighting Approach: A Comprehensive Study

DOI

10.2991/978-94-6463-314-6_10How to use a DOI?

Keywords

Structural Health Monitoring (SHM); Artificial Neural Network (ANN); Non-destructive Testing (NDT); Artificial Intelligence (AI); Rail Section

Abstract

The reliable detection of faults in rail systems plays a crucial role in ensuring safe and efficient transportation. In recent years, artificial intelligence (AI) techniques, particularly neural networks, have shown promising results in fault detection applications. However, the selection of input parameters with proper weight function is not considered scientifically in the prevailing studies. The study focuses on the evaluation of Acoustic Emission (AE) parameters using an appropriate weight function to enhance the accuracy and effectiveness of fault detection. The research explores the significance of various AE parameters, including amplitude, count, energy, frequency, RMS, etc., containing the fault information through the signal. Additionally, a new methodology is introduced to assign different weights to individual AE parameters based on their importance, ensuring the AI model concentrates on the most relevant features. Extensive experiments are conducted in the laboratory to generate the AE data using pencil lead break (PLB) on the top flange of the rail, as it is considered more prone to damage. The performance of the AI model is compared in terms of accurate fault localization using the developed artificial neural network (ANN) model, demonstrating its superiority in terms of accuracy, robustness, and efficiency. The results highlight the considerable enhancement achieved through the evaluation of AE parameters with a proper weight function, contributing to safer and more reliable transportation infrastructure.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Rajdeep Majumder
AU  - Apurba Pal
AU  - Tamal Kundu
AU  - Aloke Kumar Datta
PY  - 2023
DA  - 2023/12/21
TI  - Enhancing AI Model for Fault Detection in Rail Through the Evaluation of AE Parameters with Proper Weighting Approach: A Comprehensive Study
BT  - Proceedings of the International e-Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2023)
PB  - Atlantis Press
SP  - 97
EP  - 105
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-314-6_10
DO  - 10.2991/978-94-6463-314-6_10
ID  - Majumder2023
ER  -