Pipeline Corrosion Risk Prediction Based on Particle Swarm Optimized Random Forest Model

XIAO Wenwen; GE Pengli; HU Guangqiang; LYU Yao; LONG Wu; LIU Qingshan; GAO Shuangwu; QU Zhihao; ZHANG Lei

doi:10.11973/fsyfh220684

Corrosion & Protection > 2025 > 46(2): 59-65. > DOI: 10.11973/fsyfh220684

XIAO Wenwen, GE Pengli, HU Guangqiang, LYU Yao, LONG Wu, LIU Qingshan, GAO Shuangwu, QU Zhihao, ZHANG Lei. Pipeline Corrosion Risk Prediction Based on Particle Swarm Optimized Random Forest Model[J]. Corrosion & Protection, 2025, 46(2): 59-65. DOI: 10.11973/fsyfh220684

Citation:

PDF (2025 KB)

Pipeline Corrosion Risk Prediction Based on Particle Swarm Optimized Random Forest Model

1.
Petroleum Engineering Technology Research Institute, Northwest Oil Field Branch Company, Urumqi 830441, China
2.
Institute for Advanced Materials and Technology, University of Science and Technology Beijing, Beijing 100083, China

More Information

Received Date: November 17, 2022

Graphical Abstract

Abstract

Abstract

Based on the historical failure data of Tahe oilfield, Pearson correlation analysis and Grey correlation degree analysis were used to determine the main controlling factors of pipeline corrosion, and the random forest (RF) corrosion prediction model was established by taking them as input variables and corrosion rate as output variables. The particle swarm optimization (PSO) algorithm was used to optimize the hyper-parameters of the RF model in order to improve the prediction performance. The results show that the main controlling factors of internal corrosion of Tahe oil pipeline were partial pressure of CO₂, temperature, Cl^- concentration and partial pressure of H₂S. After the RF model was optimized with the PSO algorithm, the coefficient of determination R² was 0.97, and the root mean square error and the mean absolute error was 0.161 and 0.027, respectively, which were better than the other three regression models. As a result, the PSO optimized RF model had high accuracy in predicting corrosion rate of pipelines. It can provide reference and support for corrosion early warning and protection of oil and gas pipelines.
- CO₂-H₂S corrosion,
- machine learning,
- random forest (RF),
- particle swarm optimization (PSO),
- corrosion rate

FullText(HTML)

References (22)

References

[1]	肖雯雯, 李俊, 梁婷婷, 等. BP神经网络模型在管道腐蚀风险智能预测中的应用[J]. 石油管材与仪器, 2021, 7(6): 56-61. XIAO W W, LI J, LIANG T T, et al. Application of BP neural network model in intelligent prediction of pipeline corrosion risk[J]. Petroleum Tubular Goods & Instruments, 2021, 7(6): 56-61.
[2]	麦小琴管道缺陷智能识别的研究沈阳沈阳工业大学2005麦小琴. 管道缺陷智能识别的研究[D]. 沈阳: 沈阳工业大学, 2005. MAI X QResearch intelligent identification of defect profile in the system of magnetic flux leakage detectingShenyangShenyang University of Technology2005MAI X Q. Research intelligent identification of defect profile in the system of magnetic flux leakage detecting[D]. Shenyang: Shenyang University of Technology, 2005.
[3]	BERGHOUT T, BENBOUZID M. A systematic guide for predicting remaining useful life with machine learning[J]. Electronics, 2022, 11(7): 1125.
[4]	SMITH M, BARTON L, PESINIS K, et alIntelligent corrosion prediction using Bayesian networksProceeding of the Corrosion 2019HoustonNACE International20191337SMITH M, BARTON L, PESINIS K, et al. Intelligent corrosion prediction using Bayesian networks[C]//Proceeding of the Corrosion 2019. Houston: NACE International, 2019: 1337.
[5]	凌晓, 徐鲁帅, 余建平, 等. 基于改进的BP神经网络的输油管道内腐蚀速率预测[J]. 传感器与微系统, 2021, 40(2): 124-127. LING X, XU L S, YU J P, et al. Prediction of corrosion rate in oil pipeline based on improved BP neural network[J]. Transducer and Microsystem Technologies, 2021, 40(2): 124-127.
[6]	NYBORG RCO₂ corrosion models for oil and gas production systemsProcedding of the Corrosion 2010HoustonNACE International201010371NYBORG R. CO₂ corrosion models for oil and gas production systems[C]//Procedding of the Corrosion 2010. Houston: NACE International, 2010: 10371.
[7]	PENG Z G, LV F L, FENG Q, et al. Enhancing the CO₂-H₂S corrosion resistance of oil well cement with a modified epoxy resin[J]. Construction and Building Materials, 2022, 326: 126854.
[8]	SKILBRED E S, PALENCSÁR S, DUGSTAD A, et al. Hydrogen uptake during active CO₂-H₂S corrosion of carbon steel wires in simulated annulus fluid[J]. Corrosion Science, 2022, 199: 110172.
[9]	ABD A A, NAJI S Z, HASHIM A S. Failure analysis of carbon dioxide corrosion through wet natural gas gathering pipelines[J]. Engineering Failure Analysis, 2019, 105: 638-646.
[10]	SUN Y H, NEŠIĆ SA parametric study and modeling on localized CO₂ corrosion in horizontal wet gas flowProceeding of the Corrosion 2004HoustonNACE International200404380SUN Y H, NEŠIĆ S. A parametric study and modeling on localized CO₂ corrosion in horizontal wet gas flow[C]//Proceeding of the Corrosion 2004. Houston: NACE International, 2004: 04380.
[11]	MORAES F D, SHADLEY J, CHEN J F, et alCharacterization of CO₂ corrosion product scales related to environmental conditionsProceeding of the Corrosion 2000HoustonNACE international200000030MORAES F D, SHADLEY J, CHEN J F, et al. Characterization of CO₂ corrosion product scales related to environmental conditions[C]//Proceeding of the Corrosion 2000, Houston: NACE international, 2000: 00030.
[12]	EBERHART R, KENNEDY JA new optimizer using particle swarm theoryMhs’95 Proceeding of the Sixth International Symposium on Micro Machine & Human ScienceIEEE19953943EBERHART R, KENNEDY J. A new optimizer using particle swarm theory[C]//Mhs’95 Proceeding of the Sixth International Symposium on Micro Machine & Human Science. [S. l.]: IEEE, 1995: 39-43.
[13]	易文周. 混沌鲶鱼粒子群优化和差分进化混合算法[J]. 计算机工程与应用, 2012, 48(15): 54-58.
[14]	HO T KRandom decision forestsProceedings of 3rd International Conference on Document Analysis and RecognitionAugust 14-16,1995Montreal, QC, CanadaIEEE1995278282HO T K. Random decision forests[C]//Proceedings of 3rd International Conference on Document Analysis and Recognition. August 14-16,1995, Montreal, QC, Canada. [S. l.]: IEEE, 1995: 278-282.
[15]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
[16]	MBARAK W K, CINICIOGLU E N, CINICIOGLU O. SPT based determination of undrained shear strength: regression models and machine learning[J]. Frontiers of Structural and Civil Engineering, 2020, 14(1): 185-198.
[17]	LI X H, ZHANG L Y, KHAN F, et al. A data-driven corrosion prediction model to support digitization of subsea operations[J]. Process Safety and Environmental Protection, 2021, 153: 413-421.
[18]	KESHTEGAR B, EL AMINE BEN SEGHIER M. Modified response surface method basis harmony search to predict the burst pressure of corroded pipelines[J]. Engineering Failure Analysis, 2018, 89: 177-199.
[19]	骆正山, 秦越, 张新生, 等. 基于LASSO-WOA-LSSVM的海洋管线外腐蚀速率预测[J]. 表面技术, 2021, 50(5): 245-252. LUO Z S, QIN Y, ZHANG X S, et al. Prediction of external corrosion rate of marine pipelines based on LASSO-WOA-LSSVM[J]. Surface Technology, 2021, 50(5): 245-252.
[20]	白鹤, 张章, 刘亚明, 等. 基于灰色关联分析的FDM工艺参数与制件精度关系研究[J]. 工程塑料应用, 2020, 48(11): 80-84,94. BAI H, ZHANG Z, LIU Y M, et al. Research on the relationship between FDM process parameters and part accuracy based on grey relational analysis[J]. Engineering Plastics Application, 2020, 48(11): 80-84,94.
[21]	RODRIGUEZ-GALIANO V, GHIMIRE B, ROGAN J, et al. An assessment of the effectiveness of a random forest classifier for land-cover classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 67: 93-104.
[22]	XUE L, LIU Y T, XIONG Y F, et al. A data-driven shale gas production forecasting method based on the multi-objective random forest regression[J]. Journal of Petroleum Science and Engineering, 2021, 196: 107801.

Cited By

Get Citation

PDF

XML

Article views (14) PDF downloads (6)

Turn off MathJax

Article Contents

Abstract

References

Pipeline Corrosion Risk Prediction Based on Particle Swarm Optimized Random Forest Model

Abstract

References

Catalog

Export File

Citation

Format

Content