Pipeline wall thinning rate prediction model based on machine learning

• Published in: Nuclear engineering and technology Vol. 53; no. 12; pp. 4060 - 4066
• Main Authors: Moon, Seongin, Kim, Kyungmo, Lee, Gyeong-Geun, Yu, Yongkyun, Kim, Dong-Jin
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2021; Elsevier; 한국원자력학회
• Subjects: Artificial neural network; Convolutional neural network; Flow-accelerated corrosion; Machine learning; Wall thinning; 원자력공학; Wall thinning; Artificial neural network; Convolutional neural network; Machine learning; Flow-accelerated corrosion
• ISSN: 1738-5733; 2234-358X
• DOI: 10.1016/j.net.2021.06.040

Flow-accelerated corrosion (FAC) of carbon steel piping is a significant problem in nuclear power plants. The basic process of FAC is currently understood relatively well; however, the accuracy of prediction models of the wall-thinning rate under an FAC environment is not reliable. Herein, we propose a methodology to construct pipe wall-thinning rate prediction models using artificial neural networks and a convolutional neural network, which is confined to a straight pipe without geometric changes. Furthermore, a methodology to generate training data is proposed to efficiently train the neural network for the development of a machine learning-based FAC prediction model. Consequently, it is concluded that machine learning can be used to construct pipe wall thinning rate prediction models and optimize the number of training datasets for training the machine learning algorithm. The proposed methodology can be applied to efficiently generate a large dataset from an FAC test to develop a wall thinning rate prediction model for a real situation.