Computational Technology Resources - CCC

T. Fujimasu¹, A. Hibino¹, M. Sakuma¹, Y. Himeki², G. Katayose² and T. Kokubo²

¹, Central Japan Railway Company, Japan
², ITOCHU Techno-Solutions Corporation, Japan

doi:10.4203/ccc.15.11.7

T. Fujimasu, A. Hibino, M. Sakuma, Y. Himeki, G. Katayose, T. Kokubo, "Development of SCMaglev Tire Anomaly Detection Model", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 11.7, 2026, doi:10.4203/ccc.15.11.7

Keywords: SCMaglev, rolling stock maintenance, visual inspection, object detection, image recognition, multi-scale.

Abstract

In recent years, image analysis AI, including deep learning–based methods, has rapidly advanced. As a result, numerous cases have been reported in which operational labor savings and efficiency improvements have been achieved across various industries through the application of image analysis AI. At Central Japan Railway Company (JR Central), an in-house AI development environment has been established to detect tire surface flaws on SCMaglev vehicle tires, and efforts have been made to internalize AI-based image analysis technologies. In this study, we investigate the impact of upgrading camera resolution on the detection performance of an existing trained model and examine detection methods for identifying smaller-scale flaws. The results provide insights into how high-resolution imaging can be effectively utilized without retraining the detection model.

download the full-text of this paper (PDF, 9 pages, 517 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: 15 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 11.7 Development of SCMaglev Tire Anomaly Detection Model T. Fujimasu¹, A. Hibino¹, M. Sakuma¹, Y. Himeki², G. Katayose² and T. Kokubo² ¹, Central Japan Railway Company, Japan ², ITOCHU Techno-Solutions Corporation, Japan doi:10.4203/ccc.15.11.7 Full Bibliographic Reference for this paper T. Fujimasu, A. Hibino, M. Sakuma, Y. Himeki, G. Katayose, T. Kokubo, "Development of SCMaglev Tire Anomaly Detection Model", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 11.7, 2026, doi:10.4203/ccc.15.11.7 Keywords: SCMaglev, rolling stock maintenance, visual inspection, object detection, image recognition, multi-scale. Abstract In recent years, image analysis AI, including deep learning–based methods, has rapidly advanced. As a result, numerous cases have been reported in which operational labor savings and efficiency improvements have been achieved across various industries through the application of image analysis AI. At Central Japan Railway Company (JR Central), an in-house AI development environment has been established to detect tire surface flaws on SCMaglev vehicle tires, and efforts have been made to internalize AI-based image analysis technologies. In this study, we investigate the impact of upgrading camera resolution on the detection performance of an existing trained model and examine detection methods for identifying smaller-scale flaws. The results provide insights into how high-resolution imaging can be effectively utilized without retraining the detection model. download the full-text of this paper (PDF, 9 pages, 517 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