Computational Technology Resources - CCC

A. Gharaei, F. Mauz, A. Andres, "Pre-Grinding Surface Defect Identification using Supervised Machine-Learning and Laser Triangulation Data", in J. Pombo, (Editor), "Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 1, Paper 10.19, 2022, doi:10.4203/ccc.1.10.19

Keywords: This paper proposes a novel technique to identify rail surface defects using laser triangulation optoNCDT 2300-10LL. Two defect types, squat and flaking, are artificially applied on the surface of a rotary steel ring setup. Various supervised binary classification algorithms are implemented, and their performance in defect identification are compared against each other. Linear classifiers, Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA), are observed to be the most performant. The results also show that in spite of 2-dimensional longitudinal measurement, the collected sensory data can be used effectively to detect defects and potentially be extended to other types along with consideration of multiclassification..

Abstract

rail surface defects, laser triangulation sensor, automated defect detection, supervised classification, feature analysis, machine learning

download the full-text of this paper (PDF, 6 pages, 892 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 1 PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 10.19 Pre-Grinding Surface Defect Identification using Supervised Machine-Learning and Laser Triangulation Data A. Gharaei, F. Mauz and A. Andres Institute for Machine Tools and Manufacturing, ETH Zürich, Switzerland doi:10.4203/ccc.1.10.19 Full Bibliographic Reference for this paper A. Gharaei, F. Mauz, A. Andres, "Pre-Grinding Surface Defect Identification using Supervised Machine-Learning and Laser Triangulation Data", in J. Pombo, (Editor), "Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 1, Paper 10.19, 2022, doi:10.4203/ccc.1.10.19 Keywords: This paper proposes a novel technique to identify rail surface defects using laser triangulation optoNCDT 2300-10LL. Two defect types, squat and flaking, are artificially applied on the surface of a rotary steel ring setup. Various supervised binary classification algorithms are implemented, and their performance in defect identification are compared against each other. Linear classifiers, Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA), are observed to be the most performant. The results also show that in spite of 2-dimensional longitudinal measurement, the collected sensory data can be used effectively to detect defects and potentially be extended to other types along with consideration of multiclassification.. Abstract rail surface defects, laser triangulation sensor, automated defect detection, supervised classification, feature analysis, machine learning download the full-text of this paper (PDF, 6 pages, 892 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions