Development of a Predictive Model for Carbon Dioxide Corrosion Rate and Severity Based on Machine Learning Algorithms
Abstract
:1. Introduction
2. Overview of Algorithms and Evaluation Metrics for Models
2.1. Introduction to Machine Learning Algorithms
2.1.1. Overview of the Random Forest Algorithm
2.1.2. Introduction to XGBoost Algorithm Principle
2.2. Evaluation of Multiple Model
2.2.1. Performance Evaluation Metrics for Regression Models
2.2.2. Evaluation Metrics for Classification Performance
3. Data Mining
3.1. Data Preprocessing
3.2. Correlation Analysis
4. Discussion
4.1. ML Models for Carbon Dioxide Corrosion Rate
4.2. ML Models for Carbon Dioxide Corrosion Severity
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
RF | Random Forest |
XGBoost | Extreme Gradient Boosting |
GBDT | Gradient Boosting Decision Tree |
KNN | K-Nearest Neighbors |
SVM | Support Vector Machine |
MSE | Mean Squared Error |
Coefficient of Determination |
Appendix A
References
- Xhanari, K.; Wang, Y.; Yang, Z.; Finšgar, M. A Review of Recent Advances in the Inhibition of Sweet Corrosion. Chem. Rec. 2021, 21, 1845–1875. [Google Scholar] [CrossRef] [PubMed]
- Yevtushenko, O.; Bettge, D.; Bohraus, S.; Bäßler, R.; Pfennig, A.; Kranzmann, A. Corrosion Behavior of Steels for CO2 Injection. Process Saf. Environ. Prot. 2014, 92, 108–118. [Google Scholar] [CrossRef]
- Nesic, S.; Postlethwaite, J.; Olsen, S. An Electrochemical Model for Prediction of Corrosion of Mild Steel in Aqueous Carbon Dioxide Solutions. Corrosion 1996, 52, 280–294. [Google Scholar] [CrossRef]
- Bin, H.J.; Yang, Y.; Brown, B.; Nesic, S. Electrochemical Investigation of Localized CO2 Corrosion on Mild Steel; OnePetro: Richardson, TX, USA, 2007. [Google Scholar]
- Pessu, F.; Barker, R.; Neville, A. Pitting and Uniform Corrosion of X65 Carbon Steel in Sour Corrosion Environments: The Influence of CO2, H2S, and Temperature. Corrosion 2017, 73, 1168–1183. [Google Scholar] [CrossRef] [PubMed]
- Zhu, G.Y.; Li, Y.Y.; Hou, B.S.; Zhang, Q.H.; Zhang, G.A. Corrosion Behavior of 13Cr Stainless Steel under Stress and Crevice in High Pressure CO2/O2 Environment. J. Mater. Sci. Technol. 2021, 88, 79–89. [Google Scholar] [CrossRef]
- Senatore, E.V.; Taleb, W.; Owen, J.; Hua, Y.; Gomes, J.A.C.P.; Barker, R.; Neville, A. Evaluation of High Shear Inhibitor Performance in CO2-Containing Flow-Induced Corrosion and Erosion-Corrosion Environments in the Presence and Absence of Iron Carbonate Films. Wear 2018, 404–405, 143–152. [Google Scholar] [CrossRef]
- Kahyarian, A.; Achour, M.; Nesic, S. Mathematical Modeling of Uniform CO2 Corrosion. In Trends in Oil and Gas Corrosion Research and Technologies; El-Sherik, A.M., Ed.; Woodhead Publishing Series in Energy; Woodhead Publishing: Boston, MA, USA, 2017; pp. 805–849. ISBN 978-0-08-101105-8. [Google Scholar]
- Nesic, S.; Nordsveen, M.; Maxwell, N.; Vrhovac, M. Probabilistic Modelling of CO2 Corrosion Laboratory Data Using Neural Networks. Corros. Sci. 2001, 43, 1373–1392. [Google Scholar] [CrossRef]
- Jones, M.; Owen, J.; de Boer, G.; Woollam, R.C.; Folena, M.C.; Farhat, H.; Barker, R. Numerical Exploration of a Fully Mechanistic Mathematical Model of Aqueous CO2 Corrosion in Steel Pipelines. Corros. Sci. 2024, 236, 112235. [Google Scholar] [CrossRef]
- Dana, M.M.; Javidi, M. Corrosion Simulation via Coupling Computational Fluid Dynamics and NORSOK CO2 Corrosion Rate Prediction Model for an Outlet Header Piping of an Air-Cooled Heat Exchanger. Eng. Fail. Anal. 2021, 122, 105285. [Google Scholar] [CrossRef]
- De Waard, C.; Milliams, D.E. Carbonic Acid Corrosion of Steel. Corrosion 2013, 31, 177–181. [Google Scholar] [CrossRef]
- De Waard, C.; Lotz, U.; Milliams, D.E. Predictive Model for CO2 Corrosion Engineering in Wet Natural Gas Pipelines. Corrosion 1991, 47, 976–985. [Google Scholar] [CrossRef]
- Waard, C.D.; Lotz, U. Prediction of CO2 Corrosion of Carbon Steel; Institute of Materials: London, UK, 1994. [Google Scholar]
- Eliyan, F.F.; Alfantazi, A. On the Theory of CO2 Corrosion Reactions—Investigating Their Interrelation with the Corrosion Products and API-X100 Steel Microstructure. Corros. Sci. 2014, 85, 380–393. [Google Scholar] [CrossRef]
- Nesic, S.; Lee, J.; Ruzic, V. A Mechanistic Model of Iron Carbonate Film Growth and the Effect on CO2 Corrosion of Mild Steel. In Proceedings of the CORROSION 2002, Denver, CO, USA, 7–11 April 2002. [Google Scholar]
- Abbas, M.H.; Norman, R.; Charles, A. Neural Network Modelling of High Pressure CO2 Corrosion in Pipeline Steels. Process Saf. Environ. Prot. 2018, 119, 36–45. [Google Scholar] [CrossRef]
- Ossai, C.I. A Data-Driven Machine Learning Approach for Corrosion Risk Assessment—A Comparative Study. Big Data Cogn. Comput. 2019, 3, 28. [Google Scholar] [CrossRef]
- Yan, L.; Diao, Y.; Lang, Z.; Gao, K. Corrosion Rate Prediction and Influencing Factors Evaluation of Low-Alloy Steels in Marine Atmosphere Using Machine Learning Approach. Sci. Technol. Adv. Mater. 2020, 21, 359–370. [Google Scholar] [CrossRef] [PubMed]
- Aghaaminiha, M.; Mehrani, R.; Colahan, M.; Brown, B.; Singer, M.; Nesic, S.; Vargas, S.M.; Sharma, S. Machine Learning Modeling of Time-Dependent Corrosion Rates of Carbon Steel in Presence of Corrosion Inhibitors. Corros. Sci. 2021, 193, 109904. [Google Scholar] [CrossRef]
- Paul, A.; Mukherjee, D.P.; Das, P.; Gangopadhyay, A.; Chintha, A.R.; Kundu, S. Improved Random Forest for Classification. IEEE Trans. Image Process. 2018, 27, 4012–4024. [Google Scholar] [CrossRef] [PubMed]
- Dasarathy, B.V.; Sheela, B.V. A Composite Classifier System Design: Concepts and Methodology. Proc. IEEE 1979, 67, 708–713. [Google Scholar] [CrossRef]
- Chen, T.; Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Fracisco, CA, USA, 13–17 August 2016; Association for Computing Machinery: New York, NY, USA, 2016; pp. 785–794. [Google Scholar]
- Farelas, F.; Choi, Y.S.; Nešić, S. Corrosion Behavior of API 5L X65 Carbon Steel Under Supercritical and Liquid Carbon Dioxide Phases in the Presence of Water and Sulfur Dioxide. Corrosion 2013, 69, 243–250. [Google Scholar] [CrossRef] [PubMed]
- Xiang, Y.; Wang, Z.; Li, Z.; Ni, W.D. Effect of Exposure Time on the Corrosion Rates of X70 Steel in Supercritical CO2/SO2/O2/H2O Environments. Corrosion 2013, 69, 251–258. [Google Scholar] [CrossRef]
- Wang, T.; Li, J.; Liu, Y. Based on Pearson Correlation Coefficient and Monte Carlo Simulation Method, the Calculation Formula of Frictional Resistance Is Optimized for Soft Shaft Bending and Pulling of Steel Wire. J. Phys. Conf. Ser. 2021, 1939, 012088. [Google Scholar] [CrossRef]
Factor | Chrome | Temperature | H2O | O2 | SO2 | NO2 | Time | CR | Severity | |
---|---|---|---|---|---|---|---|---|---|---|
Statistics | ||||||||||
Mean | 0.09 | 48.27 | 29.50 | 5208.75 | 2034.76 | 34.30 | 191.01 | 0.50 | 1.14 | |
Std | 0.13 | 20.37 | 62.88 | 11,634.29 | 5961.86 | 127.01 | 254.14 | 1.81 | 1.17 | |
Min | 0.00 | 25.00 | 0.08 | 0.00 | 0.00 | 0.00 | 1.50 | 0.00 | 0.00 | |
25% | 0.01 | 40.00 | 0.96 | 0.00 | 0.02 | 0.00 | 48.00 | 0.03 | 0.00 | |
50% | 0.04 | 50.00 | 2.73 | 20.00 | 0.08 | 0.00 | 120.00 | 0.08 | 1.00 | |
75% | 0.11 | 50.00 | 34.00 | 1000.00 | 0.33 | 0.00 | 168.00 | 0.30 | 2.00 | |
Max | 0.54 | 200.00 | 400.00 | 47,000.00 | 26.00 | 1000.00 | 1512.00 | 26.00 | 3.00 |
Algorithm | Accuracy (%) | F1-Score |
---|---|---|
RF | 99 | 0.99 |
KNN | 82 | 0.81 |
SVM | 92 | 0.92 |
LightGBM | 96 | 0.96 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Dong, Z.; Zhang, M.; Li, W.; Wen, F.; Dong, G.; Zou, L.; Zhang, Y. Development of a Predictive Model for Carbon Dioxide Corrosion Rate and Severity Based on Machine Learning Algorithms. Materials 2024, 17, 4046. https://doi.org/10.3390/ma17164046
Dong Z, Zhang M, Li W, Wen F, Dong G, Zou L, Zhang Y. Development of a Predictive Model for Carbon Dioxide Corrosion Rate and Severity Based on Machine Learning Algorithms. Materials. 2024; 17(16):4046. https://doi.org/10.3390/ma17164046
Chicago/Turabian StyleDong, Zhenzhen, Min Zhang, Weirong Li, Fenggang Wen, Guoqing Dong, Lu Zou, and Yongqiang Zhang. 2024. "Development of a Predictive Model for Carbon Dioxide Corrosion Rate and Severity Based on Machine Learning Algorithms" Materials 17, no. 16: 4046. https://doi.org/10.3390/ma17164046