Fatigue crack detection of heavy duty railway track based on decision fusion analysis
by Zhaojun Guo; Hao Yin
International Journal of Materials and Product Technology (IJMPT), Vol. 65, No. 1, 2022

Abstract: In order to overcome the problems of low detection accuracy and long detection time of traditional crack detection methods, this paper proposes a fatigue crack detection method of heavy-haul railway rail based on decision fusion analysis. Based on the accurate load composition and key structural parameters of heavy-haul railway rails, the initial crack data were obtained according to the crack generation state. The data of rail fatigue crack in three-dimensional space were transformed into numerical data of crack in two-dimensional plane by translation and rotation method, and the crack tip data were fused by decision fusion analysis method, so as to realise accurate detection of crack location. The experimental results show that the detection accuracy of the proposed method is always higher than 95.3%, and the detection time is always less than 0.5 s, which can realise the rapid and accurate detection of fatigue crack of heavy-duty railway rail.

Online publication date: Wed, 20-Jul-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Materials and Product Technology (IJMPT):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com