Hybrid Intelligent Model for Predicting Corrosion Rate of Carbon Steel in CO2 Environments
- 23 March 2025
- journal article
- Published by Wiley in Materials and Corrosion
- Vol. 76 (9) , 1319-1326
Abstract
This study aims to construct a prediction model for the internal corrosion rate of offshore pipelines in CO2 environments, with the intention of providing effective corrosion prediction and protection strategies for the oil and gas industry. By conducting investigative analysis and integrating CO2 corrosion experimental data, principal component analysis (PCA) was employed to extract the primary influencing factors, which were used as input variables for the support vector regression (SVR) model with corrosion rate as the output variable. The particle swarm optimization (PSO) algorithm was utilized to optimize the hyperparameters of the model, enhancing prediction accuracy. The results indicate that the first eight principal components account for 95.9% of the cumulative contribution, and the optimized SVR model achieved a correlation coefficient (R2) exceeding 0.90. Compared to other models and optimization methods, the SVR model optimized with PCA and PSO effectively predicts the corrosion rate of offshore pipelines, offering theoretical support for corrosion protection.Keywords
This publication has 26 references indexed in Scilit:
- Evolution of corrosion prediction models for oil and gas pipelines: From empirical-driven to data-drivenEngineering Failure Analysis, 2023
- Machine learning-driven seismic failure mode identification of reinforced concrete shear walls based on PCA feature extractionStructures, 2022
- Applications of machine learning in pipeline integrity management: A state-of-the-art reviewInternational Journal of Pressure Vessels and Piping, 2021
- Effect of height on the corrosion of steel and galvanized steel in nontropical coastal marine environmentsMaterials and Corrosion, 2020
- Protectiveness, morphology and composition of corrosion products formed on carbon steel in the presence of Cl−, Ca2+ and Mg2+ in high pressure CO2 environmentsApplied Surface Science, 2018
- Modified response surface method basis harmony search to predict the burst pressure of corroded pipelinesEngineering Failure Analysis, 2018
- Failure analysis of an oil pipe wall perforated by pitting corrosionMaterials and Corrosion, 2017
- Effects of chloride content on CO2 corrosion of carbon steel in simulated oil and gas well environmentsCorrosion Science, 2014
- Reliability assessment of buried pipelines based on different corrosion rate modelsCorrosion Science, 2013
- Corrosion of N80 carbon steel in oil field formation water containing CO2 in the absence and presence of acetic acidCorrosion Science, 2011