Abstract
In this paper, a quantification method for sub-surface crack evaluation based on extreme learning machine (ELM) neural network is proposed to the application of alternating current field measurement (ACFM). According to simulation results of finite element model, the dimensions of cracks can be described by four features of the Bz and Bx curves. An optimized ELM feasible for ACFM detection is trained and validated based on the selected features. Taking the advantage of our proposed sub-surface crack sizing method, the experimental results indicate that the detection and quantification for sub-surface crack is conducted readily. The maximum errors of length and depth predicted by ELM can be limited to 5.65 % and 6.27 %, respectively.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
