Corrosion prediction of iron-based metals by the prophet model

Quan Shi; Xuan WU; Lin Shen; Xueqin Li

doi:10.1117/12.2684779

19 October 2023 Corrosion prediction of iron-based metals by the prophet model

Quan Shi, Xuan WU, Lin Shen, Xueqin Li

Proceedings Volume 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023); 127094U (2023) https://doi.org/10.1117/12.2684779
Event: Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 2023, Nanjing, China

Abstract

This paper proposes the prophet model for corrosion prediction of iron-based materials. The corrosive degree of iron-based materials under different conditions is assessed though the weight loss method and the experimental results are fed to the proposed model as the training data. It indicated that HT200, Q345B, and 45 steel are easily and rapidly corroded in the periodic immersion condition. The predicted results from the Prophet model are compared with the experimental results to evaluate the performance of the prediction model. The highest RMSE is 2.35×10^-4 and the largest MAPE is 2.90×10^{- 4}%. That means the proposed model is a reliable machine learning model for corrosion prediction of iron-based materials.

Citation Download Citation

Quan Shi, Xuan WU, Lin Shen, and Xueqin Li "Corrosion prediction of iron-based metals by the prophet model", Proc. SPIE 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 127094U (19 October 2023); https://doi.org/10.1117/12.2684779

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