Aiming at the problem that it is complex to determine the profile for the wheelset online inspect system, a novel wheelset profile extraction algorithm is proposed. Firstly, six types of typical wheelset profiles are analyzed, then the DBSCAN method is used to cluster the profile data, and an improved Huff transform is employed to determine the effective area of the profile. Secondly, a curve fit is performed based on the curvature entropy and the least square methods thus the reference point of the wheelset rim is obtained. Thirdly, the complete wheel profile is acquired after the operation of coordinate rotation and translation. Finally, the feasibility of the proposed method is verified through field experiments. The result indicates that the online inspect system has better performance than manual detection, which shows the proposed method can satisfy the profile calculation requirement of the wheelset online inspect system.
Research on Algorithm of Wheelset Profile Extraction Based on Clustering and Huff Transform
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Chapter : 3 ; 17-25
2022-02-23
9 pages
Article/Chapter (Book)
Electronic Resource
English
Research on Algorithm of Wheelset Profile Extraction Based on Clustering and Huff Transform
British Library Conference Proceedings | 2022
|