Unveiling the predictive power: intelligent peel strength prediction using structured data model

Ziyi Zhang; Qiyuan Wang; Wang Zhang; Kun Meng; Jiaxin Xu

doi:10.1117/12.3032796

5 July 2024 Unveiling the predictive power: intelligent peel strength prediction using structured data model

Ziyi Zhang, Qiyuan Wang, Wang Zhang, Kun Meng, Jiaxin Xu

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 1318443 (2024) https://doi.org/10.1117/12.3032796
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

Given that the widely employed manual spot check method for oil and gas pipeline joint coatings is significantly influenced by operator skills and conditions, posing a potential for destructive outcomes, there is a subsequent need for costly repairs upon completion of the test. The analysis of extensive ultrasonic testing data offers the ability to predict peel strength. Consequently, we propose the principles and characteristics for peel strength prediction. Key factors crucial to peel strength prediction are extracted from the extensive ultrasonic testing data, encompassing reference sensitivity, coupling sensitivity, amplitude, and dB value, all of which serve as input parameters for the peel strength prediction model leveraging the Baidu EasyDL artificial intelligence platform. The ability to predict peel strength using structured data without causing damage to the joint coating is paramount in ensuring the quality of pipeline joint coatings, mitigating the risk of incidents, and upholding the overall safety of oil and gas pipelines.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ziyi Zhang, Qiyuan Wang, Wang Zhang, Kun Meng, and Jiaxin Xu "Unveiling the predictive power: intelligent peel strength prediction using structured data model", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 1318443 (5 July 2024); https://doi.org/10.1117/12.3032796

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available