Data-driven Methods to Predict the Burst Strength of Corroded Line Pipelines Subjected to Internal Pressure

• Published in: Journal of marine science and application Vol. 21; no. 2; pp. 115 - 132
• Main Authors: Cai, Jie, Jiang, Xiaoli, Yang, Yazhou, Lodewijks, Gabriel, Wang, Minchang
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2022; Springer Nature B.V; Department of Technology and Innovation,University of Southern Denmark,Campusvej 55-5230 Odense,Denmark%Department of Maritime and Transport Technology,Delft University of Technology,2628 CD Delft,the Netherlands%College of Advanced Interdisciplinary Studies,National University of Defence Technology,Changsha,410073,P.R.China%School of Engineering,University of Newcastle,NSW 2308,Australia%Hangzhou Silan Microelectronics Co.Ltd.,Hangzhou,Zhejiang,310008,P.R.China
• Subjects: Accuracy; Algorithms; Artificial neural networks; Bursting strength; Corrosion; Data analysis; Decision making; Electrical Machines and Networks; Empirical analysis; Engineering; Finite element analysis; Finite element method; Geotechnical Engineering & Applied Earth Sciences; Internal pressure; Machine learning; Machinery and Machine Elements; Methods; Model accuracy; Offshore Engineering; Pipelines; Power Electronics; Pressure; Research Article; Strength; Support vector machines; Training; Burst strength; Corrosion; Pipelines; Machine learning; Internal pressure; Data-driven method
• ISSN: 1671-9433; 1993-5048
• DOI: 10.1007/s11804-022-00263-0

A corrosion defect is recognized as one of the most severe phenomena for high-pressure pipelines, especially those served for a long time. Finite-element method and empirical formulas are thereby used for the strength prediction of such pipes with corrosion. However, it is time-consuming for finite-element method and there is a limited application range by using empirical formulas. In order to improve the prediction of strength, this paper investigates the burst pressure of line pipelines with a single corrosion defect subjected to internal pressure based on data-driven methods. Three supervised ML (machine learning) algorithms, including the ANN (artificial neural network), the SVM (support vector machine) and the LR (linear regression), are deployed to train models based on experimental data. Data analysis is first conducted to determine proper pipe features for training. Hyperparameter tuning to control the learning process is then performed to fit the best strength models for corroded pipelines. Among all the proposed data-driven models, the ANN model with three neural layers has the highest training accuracy, but also presents the largest variance. The SVM model provides both high training accuracy and high validation accuracy. The LR model has the best performance in terms of generalization ability. These models can be served as surrogate models by transfer learning with new coming data in future research, facilitating a sustainable and intelligent decision-making of corroded pipelines.