Corrosion rate prediction for long-distance submarine pipelines based on MWIWOA-SVM

LUO Zhengshan; LYU Haipeng; LUO Jihao

Oil & Gas Storage and Transportation > 2025 >

LUO Zhengshan, LYU Haipeng, LUO Jihao. Corrosion rate prediction for long-distance submarine pipelines based on MWIWOA-SVM[J]. Oil & Gas Storage and Transportation, 2025, 44(5): 1−10.

Citation:

LUO Zhengshan, LYU Haipeng, LUO Jihao. Corrosion rate prediction for long-distance submarine pipelines based on MWIWOA-SVM[J]. Oil & Gas Storage and Transportation, 2025, 44(5): 1−10.

Citation:

LUO Zhengshan, LYU Haipeng, LUO Jihao. Corrosion rate prediction for long-distance submarine pipelines based on MWIWOA-SVM[J]. Oil & Gas Storage and Transportation, 2025, 44(5): 1−10.

PDF (1212 KB)

Corrosion rate prediction for long-distance submarine pipelines based on MWIWOA-SVM

1.
School of Management, Xi’an University of Architecture and Technology
2.
School of Information and Electronics, Beijing Institute of Technology

More Information

Received Date: September 14, 2024
Revised Date: October 20, 2024
Accepted Date: October 20, 2024
Available Online: March 30, 2025

Graphical Abstract

Abstract

Abstract

Objective To ensure the safe operation of long-distance submarine oil and gas pipelines, it is essential to enhance the prediction accuracy of their internal corrosion rates. Most existing models rely on Support Vector Machine (SVM), which has limitations including low convergence accuracy, unbalanced optimization, and a tendency to get stuck in local optima.
Methods To address these issues, Multi-Way Improve the Whale Optimization Algorithm (MWIWOA) was proposed to optimize the SVM-based prediction model for the internal corrosion rate of long-distance submarine pipelines. The population initialization utilized Tent chaotic mapping in conjunction with an opposition-based learning mechanism. Global optimization and local search functions were balanced through the introduction of adaptive weights and nonlinear convergence factors. The extended search mode was refined by integrating the simplex method, while the optimization capability of the Whale Optimization Algorithm (WOA) was enhanced with Levy flight to improve step length. Consequently, the improved WOA facilitated the optimization of kernel function parameters and penalty factors in the SVM-based model, thereby increasing the rigor of parameter selection.
Results Using the corrosion data from the SP74-FPSO pipeline segment as a case study, various algorithm model improvement strategies were applied to construct internal corrosion rate prediction models for long-distance submarine pipelines, including MWIWOA-SVM, WOA-SVM, PSO-SVM, and SVM. These models were trained to predict internal corrosion rates and subsequently compared against one another. The internal corrosion rate prediction model based on MWIWOA-SVM for long-distance submarine pipelines achieved an average absolute percentage error and root mean square error of less than 2％, indicating a very low error level. Both the determination coefficient and fitting degree exceeded 98％, while the relative error between the predicted and actual internal corrosion rates did not exceed 0.99％. These performance metrics significantly outperformed other prediction models, demonstrating higher prediction accuracy.
Conclusion The successful implementation of the Multi-Way Improved Whale Optimization Algorithm enhances prediction accuracy and outperforms comparative models, demonstrating the feasibility of the algorithm improvement. It effectively addresses issues such as low convergence accuracy, tendency to get stuck in local optima, and unbalanced computational power, highlighting the practical significance of the improved model. The experimental results indicate that the MWIWOA-SVM-based prediction model for the internal corrosion rate of long-distance submarine pipelines demonstrates better prediction performance and effectiveness. This model can serve as a valuable reference for future research on risk assessment and maintenance recommendations for submarine pipelines.

FullText(HTML)

References (28)

References

[1]	徐学武. 海底油气管道内腐蚀分析与防护[J]. 腐蚀与防护,2014,35(5):500−504. XU X W. Analysis and protection of internal corrosion for submarine pipelines of oil and gas[J]. Corrosion & Protection, 2014, 35(5): 500−504.
[2]	COLE I S, MARNEY D. The science of pipe corrosion: a review of the literature on the corrosion of ferrous metals in soils[J]. Corrosion Science, 2012, 56: 5−16. DOI: 10.1016/j.corsci.2011.12.001.
[3]	王英波,殷振兴,胡浩,唐晓. 海洋大气环境中架空管道保温层下腐蚀的调研及防护对策[J]. 腐蚀与防护,2021,42(7):53−58. DOI: 10.11973/fsyfh-202107011. WANG Y B, YIN Z X, HU H, TANG X. Investigation and protection of corrosion under insulation of overhead pipeline in marine atmospheric environment[J]. Corrosion Science, 2021, 42(7): 53−58. doi: 10.11973/fsyfh-202107011
[4]	骆正山,宋莹莹,毕傲睿. 基于GRA-RFR的油气集输管道内腐蚀速率预测[J]. 材料保护,2020,53(3):95−100. DOI: 10.16577/j.cnki.42-1215/tb.2020.03.017. LUO Z S, SONG Y Y, BI A R. Prediction model of internal corrosion rate in oil and gas gathering pipelines based on GRA-RFR[J]. Materials Protection, 2020, 53(3): 95−100. doi: 10.16577/j.cnki.42-1215/tb.2020.03.017
[5]	张梁,高源,杨光,李民强. BP神经网络模型的改进及其在海底管道外腐蚀速率预测中的应用[J]. 安全与环境学报,2023,23(11):3882−3888. DOI: 10.13637/j.issn.1009-6094.2022.1608. ZHANG L, GAO Y, YANG G, LI M Q. Improvement of the BP neural network model and its application in the prediction of the external corrosion rate of submarine pipeline[J]. Journal of Safety and Environment, 2023, 23(11): 3882−3888. doi: 10.13637/j.issn.1009-6094.2022.1608
[6]	肖荣鸽,王栋,王勤学. 基于ASO-BP神经网络的海底油气管道腐蚀速率预测[J]. 化学工业与工程,2022,39(6):109−116. DOI: 10.13353/j.issn.1004.9533.20216004. XIAO R G, WANG D, WANG Q X. Prediction of corrosion rate of submarine oil and gas pipelines based on ASO-BP neural network[J]. Chemical Industry and Engineering, 2022, 39(6): 109−116. doi: 10.13353/j.issn.1004.9533.20216004
[7]	ZHI Y J, FU D M, YANG T, ZHANG D W, LI X G, PEI Z B. Long-term prediction on atmospheric corrosion data series of carbon steel in China based on NGBM(1, 1) model and genetic algorithm[J]. Anti-Corrosion Methods and Materials, 2019, 66(4): 403−411. DOI: 10.1108/ACMM-11-2017-1858.
[8]	贾海韵,胡丽华,李夏侨,曲志豪,王竹,常炜,等. 基于核主成分分析算法的海底管道内腐蚀风险预测[J]. 腐蚀与防护,2023,44(3):82−87. DOI: 10.11973/fsyfh-202303012. JIA H Y, HU L H, LI X Q, QU Z H, WANG Z, CHANG W, et al. Internal corrosion risk prediction of submarine pipeline based on kernel principal component analysis[J]. Corrosion and Protection, 2023, 44(3): 82−87. doi: 10.11973/fsyfh-202303012
[9]	TIAN L, LUO Y. A study on the prediction of inherent deformation in fillet-welded joint using support vector machine and genetic optimization algorithm[J]. Journal of Intelligent Manufacturing, 2020, 31(3): 575−596. DOI: 10.1007/s10845-019-01469-w.
[10]	HATAMI S, GHADERI-ARDAKANI A, NIKNEJAD-KHOMAMI M, KARIMI-MALEKABADI F, RASAEI M R, MOHAMMADI A H. On the prediction of CO₂ corrosion in petroleum industry[J]. The Journal of Supercritical Fluids, 2016, 117: 108−112. DOI: 10.1016/j.supflu.2016.05.047.
[11]	梁昌晶,谢波,刘延庆,刘志娟,郭自强,任春燕,等. 基于KPCA-GWO-SVM的埋地管道土壤腐蚀速率预测[J]. 油气储运,2021,40(8):938−944. DOI: 10.6047/j.issn.1000-8241.2021.08.016. LIANG C J, XIE B, LIU Y Q, LIU Z J, GUO Z Q, REN C Y, et al. Prediction of soil corrosion rate of buried pipeline based on KPCA-GWO-SVM[J]. Oil & Gas Storage and Transportation, 2021, 40(8): 938−944. doi: 10.6047/j.issn.1000-8241.2021.08.016
[12]	王盼锋,王寿喜,马钢,全青. 基于PCA-PSO-SVM模型的海底多相流管道内腐蚀速率预测[J]. 安全与环境工程,2020,27(2):183−189. DOI: 10.13578/j.cnki.issn.1671-1556.2020.02.025. WANG P F, WANG S X, MA G, QUAN Q. Prediction of internal corrosion rate of submarine multiphase flow pipelines based on PCA-PSO-SVM model[J]. Safety and Environmental Engineering, 2020, 27(2): 183−189. doi: 10.13578/j.cnki.issn.1671-1556.2020.02.025
[13]	李响,余建星,苗春生,郭帅,齐凯,陈达兴. 基于遗传算法SVM的海洋环境腐蚀速率预测[J]. 中国海洋平台,2018,33(5):56−62. DOI: 10.3969/j.issn.1001-4500.2018.05.008. LI X, YU J X, MIAO C S, GUO S, QI K, CHEN D X. Prediction of corrosion rate in marine environment based on support vector machine combining with genetic algorithm[J]. China Offshore Platform, 2018, 33(5): 56−62. doi: 10.3969/j.issn.1001-4500.2018.05.008
[14]	MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51−67. DOI: 10.1016/j.advengsoft.2016.01.008.
[15]	师国东,胡明茂,宫爱红,龚青山,郭庆贺,谭浩. 基于XGBoost-MSIWOA-LSTM的车辆油耗优化预测模型[J/OL]. 计算机集成制造系统:1−24[2024-09-11]. http://kns.cnki.net/kcms/detail/11.5946.TP.20230724.1508.002.html. SHI G D, HU M M, GONG A H, GONG Q S, GUO Q H, TAN H. Optimal prediction model of vehicle fuel consumption based on XGBoost-MSIWOA-LSTM[J/OL]. Computer Integrated Manufacturing Systems: 1−24[2024-09-11]. http://kns.cnki.net/kcms/detail/11.5946.TP.20230724.1508.002.html.
[16]	VAPNIK V N. 统计学习理论[M]. 许建华,张学工,译. 北京:电子工业出版社,2004:1-559. VAPNIK V N. Statistical learning theory[M]. XU J H, ZHANG X G, translated. Beijing: Publishing House of Electronics Industry, 2004: 1-559.
[17]	刘昆. 粒子群算法优化支持向量机的网络流量混沌预测[J]. 现代电子技术,2019,42(2):120−123. DOI: 10.16652/j.issn.1004-373x.2019.02.028. LIU K. Chaotic prediction of network traffic based on particle swarm algorithm optimization and support vector machine[J]. Modern Electronics Technique, 2019, 42(2): 120−123. doi: 10.16652/j.issn.1004-373x.2019.02.028
[18]	梁文娟,李雪艳. 基于ARIMA、LS-SVM和BP神经网络组合模型的航空运输飞行事故征候预测[J]. 安全与环境工程,2018,25(1):130−136. DOI: 10.13578/j.cnki.issn.1671-1556.2018.01.023. LIANG W J, LI X Y. Flight incidents prediction of air transportation based on the combined model of ARIMA, LS-SVM and BPNN[J]. Safety and Environmental Engineering, 2018, 25(1): 130−136. doi: 10.13578/j.cnki.issn.1671-1556.2018.01.023
[19]	单梁,强浩,李军,王执铨. 基于Tent映射的混沌优化算法[J]. 控制与决策,2005,20(2):179−182. DOI: 10.13195/j.cd.2005.02.60.shanl.013. SHAN L, QIANG H, LI J, WANG Z Q. Chaotic optimization algorithm based on Tent map[J]. Control and Decision, 2005, 20(2): 179−182. doi: 10.13195/j.cd.2005.02.60.shanl.013
[20]	TIZHOOSH H R. Opposition-Based learning: a new scheme for machine intelligence[C]. Vienna: International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06), 2005: 695−701.
[21]	林娟,钟一文,马森林. 改进的反向蛙跳算法求解函数优化问题[J]. 计算机应用研究,2013,30(3):760−763. DOI: 10.3969/j.issn.1001-3695.2013.03.030. LIN J, ZHONG Y W, MA S L. Improved opposition-based shuffled frog leaping algorithm for function optimization problems[J]. Application Research of Computers, 2013, 30(3): 760−763. doi: 10.3969/j.issn.1001-3695.2013.03.030
[22]	RANA N, ABD LATIFF M S, ABDULHAMID S M, MISRA S. A hybrid whale optimization algorithm with differential evolution optimization for multi-objective virtual machine scheduling in cloud computing[J]. Engineering Optimization, 2022, 54(12): 1999−2016. DOI: 10.1080/0305215X.2021.1969560.
[23]	任小康,郝瑞芝,孙正兴,史变霞. 基于单纯形法的量子粒子群优化算法[J]. 微电子学与计算机,2010,27(1):154−157. DOI: 10.19304/j.cnki.issn1000-7180.2010.01.041. REN X K, HAO R Z, SUN Z X, SHI B X. Quantum_ behaved particle swarm optimization algorithm based on simplex method[J]. Microelectronics & Computer, 2010, 27(1): 154−157. doi: 10.19304/j.cnki.issn1000-7180.2010.01.041
[24]	张潮,冯锋. 混沌策略和单纯形法改进的鲸鱼优化算法[J]. 中国科技论文,2020,15(3):293−299. DOI: 10.3969/j.issn.2095-2783.2020.03.007. ZHANG C, FENG F. Whale optimization algorithm based on chaotic strategy and simplex method[J]. China Sciencepaper, 2020, 15(3): 293−299. doi: 10.3969/j.issn.2095-2783.2020.03.007
[25]	王秋萍,丁成,王晓峰. 一种基于改进KH与KHM聚类的混合数据聚类算法[J]. 控制与决策,2020,35(10):2449−2458. DOI: 10.13195/j.kzyjc.2019.0086. WANG Q P, DING C, WANG X F. A hybrid data clustering algorithm based on improved krill herd algorithm and KHM clustering[J]. Control and Decision, 2020, 35(10): 2449−2458. doi: 10.13195/j.kzyjc.2019.0086
[26]	雍欣,高岳林,赫亚华,王惠敏. 多策略融合的改进萤火虫算法[J]. 计算机应用,2022,42(12):3847−3855. DOI: 10.11772/j.issn.1001-9081.2021101830. YONG X, GAO Y L, HE Y H, WANG H M. Improved firefly algorithm based on multi-strategy fusion[J]. Journal of Computer Applications, 2022, 42(12): 3847−3855. doi: 10.11772/j.issn.1001-9081.2021101830
[27]	骆正山,马昌宝,王小完. 基于RS-MSWOA-LSSVM的油气管道失效压力预测[J]. 安全与环境工程,2022,29(4):163−171. DOI: 10.13578/j.cnki.issn.1671-1556.20211155. LUO Z S, MA C B, WANG X W. Prediction of oil and gas pipeline failure pressure based on RS-MSWOA-LSSVM[J]. Safety and Environmental Engineering, 2022, 29(4): 163−171. doi: 10.13578/j.cnki.issn.1671-1556.20211155
[28]	RASMUSSEN C E, WILLIAMS C K I. Gaussian processes for machine learning[M]. Cambridge: MIT Press, 2005: 79-102.

Supplements (0)

Cited By

Get Citation

PDF

XML

Article views (0) PDF downloads (0)

Turn off MathJax

Article Contents

Abstract

References

Corrosion rate prediction for long-distance submarine pipelines based on MWIWOA-SVM

Abstract

References

Catalog

Export File

Citation

Format

Content