A Feature Selection–Based Intelligent Framework for Predicting Maximum Depth of Corroded Pipeline Defects
Publication: Journal of Performance of Constructed Facilities
Volume 36, Issue 5
Abstract
Corrosion is one of the most common defects of buried pipelines. Accurate prediction of the maximum pitting depth of corroded pipelines is conducive to assessing the remaining strength of the pipeline. In the context of big data, machine learning has been proved to have good results. However, previous studies have less consideration of feature selection in modeling, so that the interpretation of corrosion mechanism in machine learning model is not clear enough. This paper aims to develop a novel intelligent framework to accurately predict the maximum pitting depth of buried pipelines. The framework utilizes correlation analysis to extract features from many factors related to corrosion depth, and then uses a hybrid machine learning tool to predict the maximum pitting depth. Through empirical analysis, it is found that the pipe age of buried pipelines is the leading factor for pipeline corrosion. The prediction model proposed in this paper uses an improved gray wolf optimizer to optimize the support vector machine, and compares the prediction results with eight other benchmark models. It is concluded that the proposed model has the best prediction accuracy and stability. Finally, this paper discusses the influence of feature analysis on the prediction results, showing that this operation can effectively improve the model’s prediction performance and enhance interpretability.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This study was financially supported by the 2022 Open Project of Failure Mechanics and Engineering Disaster Prevention, Key Lab of Sichuan Province (Grant No. FMEDP202212); and the National Key Research and Development Program of China (2019YFE0121900); the Fundamental Research Funds for the Central Universities.
References
ASME. 2012. Manual for determining the remaining strength of corroded pipelines. ASME B31G. New York: ASME.
Ayat, N. E., M. Cheriet, and C. Y. Suen. 2005. “Automatic model selection for the optimization of SVM kernels.” Pattern Recognit. 38 (10): 1733–1745. https://doi.org/10.1016/j.patcog.2005.03.011.
Bors, A. G., and I. Pitas. 1996. “Median radial basis function neural network.” IEEE Trans. Neural Networks 7 (6): 1351–1364. https://doi.org/10.1109/72.548164.
Caleyo, F., J. C. Velázquez, A. Valor, and J. M. Hallen. 2009. “Probability distribution of pitting corrosion depth and rate in underground pipelines: A Monte Carlo study.” Corros. Sci. 51 (9): 1925–1934. https://doi.org/10.1016/j.corsci.2009.05.019.
Cheng, F. 2016. “Monitor safety of aged fuel pipelines.” Nature 529 (7585): 156. https://doi.org/10.1038/529156e.
Chmelko, V., and D. Biro. 2019. “Safety of pressure pipe operation with corrosive defect.” Procedia Struct. Integrity 17 (Jan): 520–525. https://doi.org/10.1016/j.prostr.2019.08.069.
Cook, R. D. 1977. “Detection of influential observation in linear regression.” Technometrics 19 (1): 15–18. https://doi.org/10.1080/00401706.1977.10489493.
Deng, S., X. Wang, Y. Zhu, F. Lv, and J. Wang. 2019. “Hybrid grey wolf optimization algorithm–based support vector machine for groutability prediction of fractured rock mass.” J. Comput. Civ. Eng. 33 (2): 04018065. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000814.
DNV (Det Norske Veritas). 2019. Corroded pipelines. DNV-RP-F101. Norway: DNV.
Erickson, P., and M. Lazarus. 2014. “Impact of the Keystone XL pipeline on global oil markets and greenhouse gas emissions.” Nat. Clim. Change 4 (9): 778–781. https://doi.org/10.1038/nclimate2335.
Frank, E., L. Trigg, G. Holmes, and I. H. Witten. 2000. “Naive Bayes for regression.” Mach. Learn. 41 (1): 5–25. https://doi.org/10.1023/A:1007670802811.
Gogtay, N. J., and U. M. Thatte. 2017. “Principles of correlation analysis.” J. Assoc. Physicians India 65 (3): 78–81.
Hans, C. 2011. “Elastic net regression modeling with the orthant normal prior.” J. Am. Stat. Assoc. 106 (496): 1383–1393. https://doi.org/10.1198/jasa.2011.tm09241.
Harvey, D., S. Leybourne, and P. Newbold. 1997. “Testing the equality of prediction mean squared errors.” Int. J. Forecasting 13 (2): 281–291. https://doi.org/10.1016/S0169-2070(96)00719-4.
Hssina, B., A. Merbouha, H. Ezzikouri, and M. Erritali. 2014. “A comparative study of decision tree ID3 and C4. 5.” Int. J. Adv. Comput. Sci. Appl. 4 (2): 13–19. https://doi.org/10.14569/SpecialIssue.2014.040203.
Hwang, Y.-S., and S.-Y. Bang. 1997. “An efficient method to construct a radial basis function neural network classifier.” Neural Networks 10 (8): 1495–1503. https://doi.org/10.1016/S0893-6080(97)00002-6.
Khalajestani, M. K., M. R. Bahaari, A. Salehi, and S. Shahbazi. 2015. “Predicting the limit pressure capacity of pipe elbows containing single defects.” Appl. Ocean Res. 53 (Oct): 15–22. https://doi.org/10.1016/j.apor.2015.07.002.
Lam, C., and W. Zhou. 2016. “Statistical analyses of incidents on onshore gas transmission pipelines based on PHMSA database.” Int. J. Press. Vessels Pip. 145 (Sep): 29–40. https://doi.org/10.1016/j.ijpvp.2016.06.003.
Lee, D.-M., S.-J. Kim, H.-J. Lee, and Y.-J. Kim. 2021. “Fatigue life evaluation of socket welded pipe with incomplete penetration defect: I-test and FE analysis.” Nucl. Eng. Technol. 53 (11): 3852–3859. https://doi.org/10.1016/j.net.2021.05.033.
Li, W., R. K. Mazumder, and Y. Li. 2021. “Time-dependent reliability analysis of buried water distribution network: Combined finite-element and probabilistic approach.” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part A: Civ. Eng. 7 (4): 04021064. https://doi.org/10.1061/AJRUA6.0001178.
Lu, H., S. Behbahani, X. Ma, and T. Iseley. 2021a. “A multi-objective optimizer-based model for predicting composite material properties.” Constr. Build. Mater. 284 (May): 122746. https://doi.org/10.1016/j.conbuildmat.2021.122746.
Lu, H., T. Iseley, S. Behbahani, and L. Fu. 2020b. “Leakage detection techniques for oil and gas pipelines: State-of-the-art.” Tunnelling Underground Space Technol. 98 (Apr): 103249. https://doi.org/10.1016/j.tust.2019.103249.
Lu, H., T. Iseley, J. Matthews, W. Liao, and M. Azimi. 2021b. “An ensemble model based on relevance vector machine and multi-objective salp swarm algorithm for predicting burst pressure of corroded pipelines.” J. Pet. Sci. Eng. 203 (Aug): 108585. https://doi.org/10.1016/j.petrol.2021.108585.
Lu, H., and X. Ma. 2020. “Hybrid decision tree-based machine learning models for short-term water quality prediction.” Chemosphere 249 (Jun): 126169. https://doi.org/10.1016/j.chemosphere.2020.126169.
Lu, H., J. C. Matthews, M. Azimi, and T. Iseley. 2020c. “Near real-time HDD pullback force prediction model based on improved radial basis function neural networks.” J. Pipeline Syst. Eng. Pract. 11 (4): 04020042. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000490.
Lu, H., Z.-D. Xu, M. Azimi, L. Fu, and Y. Wang. 2022. “An effective data-driven model for predicting energy consumption of long-distance oil pipelines.” J. Pipeline Syst. Eng. Pract. 13 (2): 04022005. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000637.
Lu, H., Z.-D. Xu, T. Iseley, and J. C. Matthews. 2021c. “Novel data-driven framework for predicting residual strength of corroded pipelines.” J. Pipeline Syst. Eng. Pract. 12 (4): 04021045. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000587.
Mangalathu, S., and J. S. Jeon. 2019. “Machine learning–based failure mode recognition of circular reinforced concrete bridge columns: Comparative study.” J. Struct. Eng. 145 (10): 04019104. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002402.
Mariano, R. S., and D. Preve. 2012. “Statistical tests for multiple forecast comparison.” J. Econom. 169 (1): 123–130. https://doi.org/10.1016/j.jeconom.2012.01.014.
Masoumi, F., S. Masoumzadeh, N. Zafari, and M. Javad Emami-Skardi. 2021. “Optimum sanitary sewer network design using shuffled gray wolf optimizer.” J. Pipeline Syst. Eng. Pract. 12 (4): 04021055. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000597.
Mazumder, R. K., A. M. Salman, and Y. Li. 2021. “Failure risk analysis of pipelines using data-driven machine learning algorithms.” Struct. Saf. 89 (Mar): 102047. https://doi.org/10.1016/j.strusafe.2020.102047.
Metropolo, P. L., and A. E. P. Brown. 2004. “Natural gas pipeline accident consequence analysis.” Process Saf. Prog. 23 (4): 307–310. https://doi.org/10.1002/prs.10054.
Meyer, D., F. Leisch, and K. Hornik. 2003. “The support vector machine under test.” Neurocomputing 55 (1–2): 169–186. https://doi.org/10.1016/S0925-2312(03)00431-4.
Mirjalili, S., S. M. Mirjalili, and A. Lewis. 2014. “Grey wolf optimizer.” Adv. Eng. Software 69 (Mar): 46–61. https://doi.org/10.1016/j.advengsoft.2013.12.007.
Miyamoto, A., J. Puttonen, and A. Yabe. 2017. “Long term application of a vehicle-based health monitoring system to short and medium span bridges and damage detection sensitivity.” Engineering 9 (2): 68. https://doi.org/10.4236/eng.2017.92005.
Nadimi-Shahraki, M. H., S. Taghian, and S. Mirjalili. 2021. “An improved grey wolf optimizer for solving engineering problems.” Expert Syst. Appl. 166 (Mar): 113917. https://doi.org/10.1016/j.eswa.2020.113917.
Noble, W. S. 2006. “What is a support vector machine?” Nat. Biotechnol. 24 (12): 1565–1567. https://doi.org/10.1038/nbt1206-1565.
Ossai, C. I. 2020. “Corrosion defect modelling of aged pipelines with a feed-forward multi-layer neural network for leak and burst failure estimation.” Eng. Fail. Anal. 110 (Mar): 104397. https://doi.org/10.1016/j.engfailanal.2020.104397.
Pal, M. 2005. “Random forest classifier for remote sensing classification.” Int. J. Remote Sens. 26 (1): 217–222. https://doi.org/10.1080/01431160412331269698.
Phan, H. C., and A. S. Dhar. 2021. “Predicting pipeline burst pressures with machine learning models.” Int. J. Press. Vessels Pip. 191 (Jun): 104384. https://doi.org/10.1016/j.ijpvp.2021.104384.
Phan, H. C., and H. T. Duong. 2021. “Predicting burst pressure of defected pipeline with principal component analysis and adaptive neuro fuzzy inference system.” Int. J. Press. Vessels Pip. 189 (Feb): 104274. https://doi.org/10.1016/j.ijpvp.2020.104274.
Phan, H. C., T.-T. Le, N. D. Bui, H. T. Duong, and T. D. Pham. 2021. “An empirical model for bending capacity of defected pipe combined with axial load.” Int. J. Press. Vessels Pip. 191 (Jun): 104368. https://doi.org/10.1016/j.ijpvp.2021.104368.
Prasad, A. M., L. R. Iverson, and A. Liaw. 2006. “Newer classification and regression tree techniques: Bagging and random forests for ecological prediction.” Ecosystems 9 (2): 181–199. https://doi.org/10.1007/s10021-005-0054-1.
Rachman, A., T. Zhang, and R. C. Ratnayake. 2021. “Applications of machine learning in pipeline integrity management: A state-of-the-art review.” Int. J. Press. Vessels Pip. 193 (Oct): 104471. https://doi.org/10.1016/j.ijpvp.2021.104471.
Ryu, K., T. Lee, D. C. Baek, and J. W. Park. 2020. “Pipe thinning model development for direct current potential drop data with machine learning approach.” Nucl. Eng. Technol. 52 (4): 784–790. https://doi.org/10.1016/j.net.2019.10.004.
Seghier, M. E. A. B., B. Keshtegar, M. Taleb-Berrouane, R. Abbassi, and N. T. Trung. 2021. “Advanced intelligence frameworks for predicting maximum pitting corrosion depth in oil and gas pipelines.” Process Saf. Environ. Prot. 147 (Mar): 818–833. https://doi.org/10.1016/j.psep.2021.01.008.
Seghier, M. E. A. B., B. Keshtegar, K. F. Tee, T. Zayed, R. Abbassi, and N. T. Trung. 2020. “Prediction of maximum pitting corrosion depth in oil and gas pipelines.” Eng. Fail. Anal. 112 (May): 104505. https://doi.org/10.1016/j.engfailanal.2020.104505.
Shin, Y., D. W. Kim, J. Y. Kim, K. I. Kang, M. Y. Cho, and H. H. Cho. 2009. “Application of AdaBoost to the retaining wall method selection in construction.” J. Comput. Civ. Eng. 23 (3): 188–192. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000001.
Sudheer, K. P., and S. K. Jain. 2003. “Radial basis function neural network for modeling rating curves.” J. Hydrol. Eng. 8 (3): 161–164. https://doi.org/10.1061/(ASCE)1084-0699(2003)8:3(161).
Suykens, J. A., and J. Vandewalle. 1999. “Least squares support vector machine classifiers.” Neural Process. Lett. 9 (3): 293–300. https://doi.org/10.1023/A:1018628609742.
Tee, K. F., and A. H. Wordu. 2020. “Burst strength analysis of pressurized steel pipelines with corrosion and gouge defects.” Eng. Fail. Anal. 108 (Jan): 104347. https://doi.org/10.1016/j.engfailanal.2019.104347.
Velázquez, J. C., F. Caleyo, A. Valor, and J. M. Hallen. 2009. “Predictive model for pitting corrosion in buried oil and gas pipelines.” Corrosion 65 (5): 332–342. https://doi.org/10.5006/1.3319138.
Velázquez, J. C., F. Caleyo, A. Valor, and J. M. Hallen. 2010. “Field study—Pitting corrosion of underground pipelines related to local soil and pipe characteristics.” Corrosion 66 (1): 016001. https://doi.org/10.5006/1.3318290.
Vt, S. E., and Y. C. Shin. 1994. “Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems.” IEEE Trans. Neural Networks 5 (4): 594–603. https://doi.org/10.1109/72.298229.
Wang, N., and M. S. Zarghamee. 2014. “Evaluating fitness-for-service of corroded metal pipelines: Structural reliability bases.” J. Pipeline Syst. Eng. Pract. 5 (1): 04013012. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000148.
Wang, Q., and W. Zhou. 2019. “A new burst pressure model for thin-walled pipe elbows containing metal-loss corrosion defects.” Eng. Struct. 200 (Dec): 109720. https://doi.org/10.1016/j.engstruct.2019.109720.
Xu, H., and S. K. Sinha. 2019. “A framework for statistical analysis of water pipeline field performance data.” In Pipelines 2019: Multidisciplinary topics, utility engineering, and surveying, 180–189. Reston, VA: ASCE.
Xu, H., and S. K. Sinha. 2021. “Modeling pipe break data using survival analysis with machine learning imputation methods.” J. Perform. Constr. Facil. 35 (5): 04021071. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001649.
Xu, Z. D., Y. Yang, and A. N. Miao. 2021a. “Dynamic analysis and parameter optimization of pipelines with multidimensional vibration isolation and mitigation device.” J. Pipeline Syst. Eng. Pract. 12 (1): 04020058. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000504.
Xu, Z.-D., C. Zhu, and L.-W. Shao. 2021b. “Damage identification of pipeline based on ultrasonic guided wave and wavelet denoising.” J. Pipeline Syst. Eng. Pract. 12 (4): 04021051. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000600.
Zhang, L., W. Zhou, and L. Jiao. 2004. “Wavelet support vector machine.” IEEE Trans. Syst. Man Cybern. Part B Cybern. 34 (1): 34–39. https://doi.org/10.1109/TSMCB.2003.811113.
Zhu, C., Z.-D. Xu, H. Lu, and Y. Lu. 2022. “Evaluation of cross-sectional deformation in pipes using reflection of fundamental guided-waves.” J. Eng. Mech. 148 (5): 04022016. https://doi.org/10.1061/(ASCE)EM.1943-7889.0002095.
Information & Authors
Information
Published In
Journal of Performance of Constructed Facilities
Volume 36 • Issue 5 • October 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Feb 7, 2022
Accepted: May 12, 2022
Published online: Jul 29, 2022
Published in print: Oct 1, 2022
Discussion open until: Dec 29, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Qinci Li, Zhaokun Li, Tingting Xie, Ye Ding, Nan Gan, Yahui Tan, Chong Zhang, Analysis of Natural Groundwater Flowing into the Flow Field of In Situ Leaching Mining, Processes, 10.3390/pr11020471, 11, 2, (471), (2023).
- Hongfang Lu, Haoyan Peng, Zhao-Dong Xu, Guojin Qin, Mohammadamin Azimi, John C. Matthews, Li Cao, Theory and Machine Learning Modeling for Burst Pressure Estimation of Pipeline with Multipoint Corrosion, Journal of Pipeline Systems Engineering and Practice, 10.1061/JPSEA2.PSENG-1481, 14, 3, (2023).
- Hongfang Lu, Zhao-Dong Xu, Xulei Zang, Dongmin Xi, Tom Iseley, John C. Matthews, Niannian Wang, Leveraging Machine Learning for Pipeline Condition Assessment, Journal of Pipeline Systems Engineering and Practice, 10.1061/JPSEA2.PSENG-1464, 14, 3, (2023).
- Haoyan Peng, Hongfang Lu, Zhao-Dong Xu, Yijia Wang, Zhenwu Zhang, Predicting Solid-Particle Erosion Rate of Pipelines Using Support Vector Machine with Improved Sparrow Search Algorithm, Journal of Pipeline Systems Engineering and Practice, 10.1061/JPSEA2.PSENG-1367, 14, 2, (2023).
- Xiaojiang Liu, Bin Sun, Zhao-Dong Xu, Xuanya Liu, Dajun Xu, A Data-Driven Danger Zone Estimation Method Based on Bayesian Inference for Utility Tunnel Fires and Experimental Verification, Journal of Performance of Constructed Facilities, 10.1061/JPCFEV.CFENG-4280, 37, 1, (2023).
- Hongfang Lu, Xinmeng Jiang, Zhao-Dong Xu, Houming Ni, Lingdi Fu, Mechanical behavior of high-pressure pipeline installed through horizontal directional drilling under seismic loads, Tunnelling and Underground Space Technology, 10.1016/j.tust.2023.105073, 136, (105073), (2023).
- Yihuan Wang, Ruiling Li, Ailin Xia, Pingan Ni, Guojin Qin, An integrated modeling method of uncertainties: application-orientated fuzzy random spatiotemporal analysis of pipeline structures, Tunnelling and Underground Space Technology, 10.1016/j.tust.2022.104825, 131, (104825), (2023).
- Hongfang Lu, Dongmin Xi, Guojin Qin, Environmental risk of oil pipeline accidents, Science of The Total Environment, 10.1016/j.scitotenv.2023.162386, 874, (162386), (2023).
- Guojin Qin, Ailin Xia, Hongfang Lu, Yihuan Wang, Ruiling Li, Chengtao Wang, A hybrid machine learning model for predicting crater width formed by explosions of natural gas pipelines, Journal of Loss Prevention in the Process Industries, 10.1016/j.jlp.2023.104994, 82, (104994), (2023).
- Xin Ma, Hongfang Lu, Minda Ma, Lifeng Wu, Yubin Cai, Urban natural gas consumption forecasting by novel wavelet-kernelized grey system model, Engineering Applications of Artificial Intelligence, 10.1016/j.engappai.2022.105773, 119, (105773), (2023).
- See more