|
|
|
| Physics-guided Prediction of Corrosion Rate Inside Gathering and Transportation Pipelines and Explanatory Analysis |
CHEN Qian1, HUANG Wei1( ), ZHANG Changhui2, GUAN Aocheng1, ZHANG Chen3, YE Xiaopeng4 |
1.School of Petroleum Engineering, Yangtze University, Wuhan 430100, China
2.Central Sichuan Oil and Gas Mine, PetroChina Southwest Oil and Gas Field Company, Suining 629000, China
3.Chongqing Division, PetroChina Southwest Oil & Gasfield Company, Chongqing 400707, China
4.Central and Northern Sichuan Gas Production Management Office of Southwest Oil and Gas, Field Company, Suining 629000, China |
|
Cite this article:
CHEN Qian, HUANG Wei, ZHANG Changhui, GUAN Aocheng, ZHANG Chen, YE Xiaopeng. Physics-guided Prediction of Corrosion Rate Inside Gathering and Transportation Pipelines and Explanatory Analysis. Journal of Chinese Society for Corrosion and protection, 2025, 45(3): 720-730.
|
|
|
Abstract Due to the harsh operating environment, the corrosion problem of gathering and transportation pipelines has become increasingly severe, necessitating the development of an accurate model to predict the internal corrosion rate of such pipelines. Herein, a pipeline corrosion prediction method that combines physics-guided neural networks (PGNN) with an improved particle swarm optimization (IPSO) algorithm is proposed. By analyzing the electrochemical corrosion mechanism, the universal impact of variations in different corrosion factors on the corrosion rate is summarized. Subsequently, based on these universal laws, a loss function characterization method is proposed to construct a physics-guided internal corrosion rate prediction model. The model's hyperparameters are optimized using a particle swarm algorithm improved through reverse learning, nonlinear weight adjustment mechanisms, and cosine algorithm enhancements. Finally, the predictive model is subjected to interpretability analysis using electrochemical corrosion mechanisms, partial dependence plots, and the SHAP algorithm. The accuracy of the model is evaluated using four metrics: mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and R-squared (R2), while its reliability is assessed based on its consistency with corrosion mechanisms. Results demonstrate that the PGNN-IPSO method can avoid learning erroneous patterns contradicting physical principles, thereby enhancing prediction accuracy. This research holds significant implications for corrosion protection, reliability assessment, and maintenance decision-making regarding gathering and transportation pipelines.
|
|
Received: 12 April 2024
32134.14.1005.4537.2024.121
|
|
|
| Fund: China Petroleum Southwest Gas & Oilfield Company Postdoctoral Fund(20220305-18) |
Corresponding Authors:
HUANG Wei, E-mail: cjhuangwei@foxmail.com
|
| [1] |
Wang Q Y, Song Y H, Zhang X S, et al. Evolution of corrosion prediction models for oil and gas pipelines: from empirical-driven to data-driven [J]. Eng. Fail. Anal., 2023, 146: 107097
|
| [2] |
Wang B Q, Mu Y Q, Shen F M, et al. Identification of corrosion factors in blast furnace gas pipe network with corrosion big data online monitoring technology [J]. Corros. Sci., 2024, 230: 111906
|
| [3] |
Farhadian A, Zhao Y, Naeiji P, et al. Simultaneous inhibition of natural gas hydrate formation and CO2/H2S corrosion for flow assurance inside the oil and gas pipelines [J]. Energy, 2023, 269: 126797
|
| [4] |
Ma H N, Zhang W D, Wang Y, et al. Advances in corrosion growth modeling for oil and gas pipelines: a review [J]. Process Saf. Environ. Prot., 2023, 171: 71
|
| [5] |
Dao U, Sajid Z, Khan F, et al. Modeling and analysis of internal corrosion induced failure of oil and gas pipelines [J]. Reliab. Eng. Syst. Saf., 2023, 234: 109170
|
| [6] |
Qin G J, Cheng Y F, Zhang P. Finite element modeling of corrosion defect growth and failure pressure prediction of pipelines [J]. Int. J. Pressure Vessels Piping, 2021, 194: 104509
|
| [7] |
Kairy S K, Zhou S, Turnbull A, et al. Corrosion of pipeline steel in dense phase CO2 containing impurities: a critical review of test methodologies [J]. Corros. Sci., 2023, 214: 110986
|
| [8] |
Nadj M, Jegadeesan H, Maedche A, et al. A situation awareness driven design for predictive maintenance systems: the case of oil and gas pipeline operations [A]. Proceedings of the Twenty-Fourth European Conference on Information Systems (ECIS) [C]. İstanbul, 2016
|
| [9] |
Zakikhani K, Nasiri F, Zayed T. A review of failure prediction models for oil and gas pipelines [J]. J. Pipeline Syst. Eng. Pract., 2020, 11: 03119001
|
| [10] |
Xie M J, Tian Z G. A review on pipeline integrity management utilizing in-line inspection data [J]. Eng. Failure Anal., 2018, 92: 222
|
| [11] |
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 [J]. Eng. Fail. Anal., 2021, 122: 105285
|
| [12] |
Thorat U, Jones M, Woollam R, et al. Computational fluid dynamics driven mass transfer model for the prediction of CO2 corrosion in pipelines [J]. J. Pipeline Sci. Eng., 2024, 4(1): 100148
|
| [13] |
Adams C, Garber J, Walters F, et al. Verification of computer modeled tubing life predictions by field data [A]. Proceedings of the Corrosion-National Association of Corrosion Engineers Annual Conference [C]. Houston, 1993
|
| [14] |
Nešić S, Lunde L. Carbon dioxide corrosion of carbon steel in two-phase flow [J]. Corrosion, 1994, 50: 717
|
| [15] |
Li D R, Fang Z, Ma T, et al. A mechanistic model for flow accelerated corrosion prediction of a 90° carbon steel elbow in CO2 environments [J]. J. Pipeline Sci. Eng., 2025.
|
| [16] |
Wu L S, Liao K S, He G X, et al. Wet gas pipeline internal general corrosion prediction based on improved De Waard 95 model [J]. J. Pipeline Syst. Eng. Pract., 2023, 14: 04023041
|
| [17] |
Nesic S, Postlethwaite J, Olsen S. An electrochemical model for prediction of corrosion of mild steel in aqueous carbon dioxide solutions [J]. Corrosion, 1996, 52: 280
|
| [18] |
Nesic S, Nyborg R, Stangeland A, et al. Mechanistic modeling for CO2 corrosion with protective iron carbonate films [A]. Paper Presented at the CORROSION 2001 [C]. Houston, 2001
|
| [19] |
Nesic S. Effects of multiphase flow on internal CO2 corrosion of mild steel pipelines [J]. Energy Fuels, 2012, 26: 4098
|
| [20] |
Nešić S, Kahyarian A, Choi Y S. Implementation of a comprehensive mechanistic prediction model of mild steel corrosion in multiphase oil and gas pipelines [J]. Corrosion, 2019, 75: 274
|
| [21] |
Zhang X R, Hou L, Liu J Q, et al. Energy consumption prediction for crude oil pipelines based on integrating mechanism analysis and data mining [J]. Energy, 2022, 254: 124382
|
| [22] |
Xu L, Hou L, Zhu Z Y, et al. Mid-term prediction of electrical energy consumption for crude oil pipelines using a hybrid algorithm of support vector machine and genetic algorithm [J]. Energy, 2021, 222: 119955
|
| [23] |
Xu L, Wang Y F, Mo L, et al. The research progress and prospect of data mining methods on corrosion prediction of oil and gas pipelines [J]. Eng. Fail. Anal., 2023, 144: 106951
|
| [24] |
Xu L, Yu J, Zhu Z Y, et al. Research and application for corrosion rate prediction of natural gas pipelines based on a novel hybrid machine learning approach [J]. Coatings, 2023, 13: 856
|
| [25] |
Li X H, Jia R C, Zhang R R, et al. A KPCA-BRANN based data-driven approach to model corrosion degradation of subsea oil pipelines [J]. Reliab. Eng. Syst. Saf., 2022, 219: 108231
|
| [26] |
Li X H, Zhang L Y, Khan F, et al. A data-driven corrosion prediction model to support digitization of subsea operations [J]. Process Saf. Environ. Prot., 2021, 153: 413
|
| [27] |
Fang J, Cheng X, Gai H L, et al. Development of machine learning algorithms for predicting internal corrosion of crude oil and natural gas pipelines [J]. Comput. Chem. Eng., 2023, 177: 108358
|
| [28] |
Zhang Y F, Ren W, Wang W L, et al. Interpretable hardness prediction of high-entropy alloys through ensemble learning [J]. J. Alloy. Compd., 2023, 945: 169329
|
| [29] |
Song Y H, Wang Q Y, Xi Y C, et al. Interpretability study on prediction models for alloy pitting based on ensemble learning [J]. Corros. Sci., 2024, 228: 111790
|
| [30] |
Li M, Yang Y, He Z S, et al. A wind speed forecasting model based on multi-objective algorithm and interpretability learning [J]. Energy, 2023, 269: 126778
|
| [31] |
Lazer D, Kennedy R, King G, et al. The parable of Google Flu: traps in big data analysis [J]. Science, 2014, 343: 1203
|
| [32] |
Karpatne A, Atluri G, Faghmous J H, et al. Theory-guided data science: a new paradigm for scientific discovery from data [J]. IEEE Trans. Knowl. Data Eng., 2017, 29: 2318
|
| [33] |
Daw A, Karpatne A, Watkins W D, et al. Physics-guided neural networks (PGNN): an application in lake temperature modeling [A]. KarpatneA, KannanR, KumarV, et al. Knowledge Guided Machine Learning [M]. New York: Chapman and Hall/CRC, 2022: 353
|
| [34] |
Jeong H, Batuwatta-Gamage C, Bai J, et al. An advanced physics-informed neural network-based framework for nonlinear and complex topology optimization [J]. Eng. Struct., 2025, 322: 119194
|
| [35] |
Zou Z R, Meng X H, Karniadakis G E. Uncertainty quantification for noisy inputs–outputs in physics-informed neural networks and neural operators [J]. Comput. Meth. Appl. Mech. Eng., 2025, 433: 117479
|
| [36] |
Sun L N, Gao H, Pan S W, et al. Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data [J]. Comput. Methods Appl. Mech. Eng., 2020, 361: 112732
|
| [37] |
Nesic S, Thevenot N, Crolet J L, et al. Electrochemical properties of iron dissolution in the presence of CO2-basics revisited [A]. Paper Presented at the Corrosion 96 [C]. Colorado, 1996
|
| [38] |
De Waard C, Milliams D E. Carbonic acid corrosion of steel [J]. Corrosion, 1975, 31: 177
|
| [39] |
Huang X G, Zhou L C, Li Y K, et al. The synergistic effect of temperature, H2S/CO2 partial pressure and stress toward corrosion of X80 pipeline steel [J]. Eng. Failure Anal., 2023, 146: 107079
|
| [40] |
Asadian M, Sabzi M, Anijdan S H M. The effect of temperature, CO2, H2S gases and the resultant iron carbonate and iron sulfide compounds on the sour corrosion behaviour of ASTM A-106 steel for pipeline transportation [J]. Int. J. Pressure Vessels Piping, 2019, 171: 184
|
| [41] |
Xiang Y, Wang Z, Li Z, et al. Effect of temperature on corrosion behaviour of X70 steel in high pressure CO2/SO2/O2/H2O environments [J]. Corros. Eng. Sci. Technol., 2013, 48: 121
|
| [42] |
Liu M, Wang J, Ke W. Corrosion behaviour of X52 pipeline steel in high H2S concentration solutions at temperatures ranging from 25 ℃ to 140 ℃ [J]. Corros. Eng. Sci. Technol., 2013, 48: 380
|
| [43] |
Abdar P S, Hariri M B, Kahyarian A, et al. A revision of mechanistic modeling of mild steel corrosion in H2S environments [J]. Electrochim. Acta, 2021, 382: 138231
|
| [44] |
Xiao S, Sun Y B, Wang S H, et al. H2S corrosion mechanism of thermal recovery well and performance of H2S corrosion inhibitor [J]. Corros. Prot., 2023, 44(1): 30
|
|
肖 洒, 孙玉豹, 王少华 等. L80钢的H2S腐蚀机理及H2S缓蚀剂的性能 [J]. 腐蚀与防护, 2023, 44(1): 30
|
| [45] |
Wang F, Li J, Li J L, et al. Corrosion behavior of metallic pipes in CO2/H2S environment [J]. Hot Working Technol., 2021, 50(4): 1
|
|
王 帆, 李 娟, 李金灵 等. 金属管道在CO2/H2S环境中的腐蚀行为 [J]. 热加工工艺, 2021, 50(4): 1
|
| [46] |
Ye N, Liao K X, He G X, et al. Summary on influencing factors and evaluation methods of the efficiency of corrosion inhibitor for oil and gas gathering and transportation [J]. Mater. Prot., 2022, 55(9): 167
|
|
叶 男, 廖柯熹, 何国玺 等. 油气集输缓蚀剂缓蚀效率的影响因素及评价方法综述 [J]. 材料保护, 2022, 55(9): 167
|
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
