Enhancing crack detection in railway tracks through AI-optimized ultrasonic guided wave modes

Biomimetic Intelligence and Robotics Pub Date : 2024-08-03 DOI:10.1016/j.birob.2024.100175

Jianjun Liu , Huan Luo , Han Hu , Jian Li

{"title":"Enhancing crack detection in railway tracks through AI-optimized ultrasonic guided wave modes","authors":"Jianjun Liu , Huan Luo , Han Hu , Jian Li","doi":"10.1016/j.birob.2024.100175","DOIUrl":null,"url":null,"abstract":"<div><p>The utilization of ultrasonic guided wave technology for detecting cracks in railway tracks involves analyzing echo signals produced by the interaction of cracks with guided wave modes to achieve precise crack localization, which is extremely important in a real-time railway crack robotic detection system. Addressing the challenge of selecting the optimal detection mode for cracks in various regions of railway tracks, this paper presents a method for optimal crack detection mode selection. This method is based on the sensitivity of guided wave modes to cracks. By examining the frequency dispersion characteristics and mode shapes of guided wave modes, we establish indicators for crack zone energy and crack reflection intensity. Our focus is on the railhead of the railway track, selecting guided wave modes characterized by specific cracks for detection purposes. Experimental findings validate the accuracy of our proposed mode selection method in detecting cracks in railway tracks. This research not only enhances crack detection but also lays the groundwork for exploring advanced detection and localization techniques for cracks in railway tracks.</p></div>","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"4 3","pages":"Article 100175"},"PeriodicalIF":0.0000,"publicationDate":"2024-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667379724000330/pdfft?md5=f1d6b4975e49e463a5e7c59e37f53ce9&pid=1-s2.0-S2667379724000330-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomimetic Intelligence and Robotics","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667379724000330","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

The utilization of ultrasonic guided wave technology for detecting cracks in railway tracks involves analyzing echo signals produced by the interaction of cracks with guided wave modes to achieve precise crack localization, which is extremely important in a real-time railway crack robotic detection system. Addressing the challenge of selecting the optimal detection mode for cracks in various regions of railway tracks, this paper presents a method for optimal crack detection mode selection. This method is based on the sensitivity of guided wave modes to cracks. By examining the frequency dispersion characteristics and mode shapes of guided wave modes, we establish indicators for crack zone energy and crack reflection intensity. Our focus is on the railhead of the railway track, selecting guided wave modes characterized by specific cracks for detection purposes. Experimental findings validate the accuracy of our proposed mode selection method in detecting cracks in railway tracks. This research not only enhances crack detection but also lays the groundwork for exploring advanced detection and localization techniques for cracks in railway tracks.

查看原文本刊更多论文

通过人工智能优化超声波导波模式加强铁轨裂缝检测

利用超声导波技术检测铁轨裂缝，需要分析裂缝与导波模式相互作用产生的回波信号，以实现精确的裂缝定位，这对于实时铁路裂缝机器人检测系统极为重要。针对如何为铁轨不同区域的裂缝选择最佳检测模式这一难题，本文提出了一种最佳裂缝检测模式选择方法。该方法基于导波模式对裂缝的敏感性。通过研究导波模式的频散特性和模形，我们建立了裂纹区能量和裂纹反射强度指标。我们的重点是铁轨的轨头，选择以特定裂缝为特征的导波模式进行检测。实验结果验证了我们提出的模式选择方法在检测铁轨裂缝方面的准确性。这项研究不仅增强了裂缝检测能力，还为探索先进的铁轨裂缝检测和定位技术奠定了基础。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Biomimetic Intelligence and Robotics

CiteScore

1.80

自引率

0.00%

发文量