Prediction Model for Pipeline Pitting Corrosion Based on Multiple Feature Selection and Residual Correction

Abstract

The transportation of oil and gas through pipelines is crucial for sustaining energy supply in industrial and civil sectors. However, the issue of pitting corrosion during pipeline operation poses an important threat to the structural integrity and safety of pipelines. This problem not only affects the longevity of pipelines but also has the potential to cause secondary disasters, such as oil and gas leaks, leading to environmental pollution and endangering public safety. Therefore, the development of a highly stable, accurate, and reliable model for predicting pipeline pitting corrosion is of paramount importance. In this study, a novel prediction model for pipeline pitting corrosion depth that integrates the sparrow search algorithm (SSA), regularized extreme learning machine (RELM), principal component analysis (PCA), and residual correction is proposed. Initially, RELM is utilized to forecast pipeline pitting corrosion depth, and SSA is employed for optimizing RELM’s hyperparameters to enhance the model’s predictive capabilities. Subsequently, the residuals of the SSA-RELM model are obtained by subtracting the prediction results of the model from actual measurements. Moreover, PCA is applied to reduce the dimensionality of the original 10 features, yielding 7 new features with enhanced information content. Finally, residuals are predicted by using the seven features obtained by PCA, and the prediction result is combined with the output of the SSA-RELM model to derive the predicted pipeline pitting corrosion depth by incorporating multiple feature selection and residual correction. Case study demonstrates that the proposed model reduces mean squared error, mean absolute percentage error, and mean absolute error by 66.80%, 42.71%, and 42.64%, respectively, compared with the SSA-RELM model. Research findings underscore the exceptional performance of the proposed integrated approach in predicting the depth of pipeline pitting corrosion.

Keywords

Pipeline corrosion / Machine learning / Residual correction / Regularized extreme learning machine / Principal component analysis

References

[1] Al-SabaeeiAM, AlhussianH, AbdulkadirSJ, JagadeeshA. Prediction of oil and gas pipeline failures through machine learning approaches: A systematic review. Energy Reports, 2023, 10: 1313-1338

[2] ArzaghiE, AbbassiR, GaraniyaV, BinnsJ, ChinC, KhakzadN, ReniersG. Developing a dynamic model for pitting and corrosion-fatigue damage of subsea pipelines. Ocean Engineering, 2018, 150: 391-396

[3] Ben SeghierMEA, KeshtegarB, Taleb-BerrouaneM, AbbassiR, TrungNT. Advanced intelligence frameworks for predicting maximum pitting corrosion depth in oil and gas pipelines. Process Safety and Environmental Protection, 2021, 147: 818-833

[4] CadelanoG, BortolinA, FerrariniG, MolinasB, GiantinD, ZontaP, BisonP. Corrosion detection in pipelines using infrared thermography: Experiments and data processing methods. Journal of Nondestructive Evaluation, 2016, 35349

[5] ChouJS, NgoNT, ChongWK. The use of artificial intelligence combiners for modeling steel pitting risk and corrosion rate. Engineering Applications of Artificial Intelligence, 2017, 65: 471-483

[6] De WaardC, MilliamsDE. Carbonic acid corrosion of steel. Corrosion, 1975, 31(5): 177-181

[7] HeC, KangH, YaoT, LiX. An effective classifier based on convolutional neural network and regularized extreme learning machine. Mathematical biosciences and engineering, 2019, 16(6): 8309-8321

[8] HuangGB, ZhuQY, SiewCK. Extreme learning machine: A new learning scheme of feedforward neural networks. 2004 IEEE international joint conference on neural networks, Budapest, Hungary, 2004985990

[9] JiangT, RenL, JiaZG, LiDS, LiHN. Pipeline internal corrosion monitoring based on distributed strain measurement technique. Structural Control and Health Monitoring, 2017, 2411e2016

[10] LiX, GuoM, ZhangR, ChenG. A data-driven prediction model for maximum pitting corrosion depth of subsea oil pipelines using SSA-LSTM approach. Ocean Engineering, 2022, 261112062

[11] LiX, JiaR, ZhangR, YangS, ChenG. A KPCA-BRANN based data-driven approach to model corrosion degradation of subsea oil pipelines. Reliability Engineering & System Safety, 2022, 219108231

[12] LiX, ZhangL, KhanF, HanZ. A data-driven corrosion prediction model to support digitization of subsea operations. Process Safety and Environmental Protection, 2021, 153: 413-421

[13] LiZ, KorovinI, ShiX, GorbachevS, GorbachevaN, HuangW, CaoJ. A data-driven rutting depth short-time prediction model with metaheuristic optimization for asphalt pavements based on RIOHTrack. IEEE-CAA Journal of Automatica Sinica, 2023, 10(10): 1918-1932

[14] LiuG, AyelloF, VeraJ, EckertR, BhatP. An exploration on the machine learning approaches to determine the erosion rates for liquid hydrocarbon transmission pipelines towards safer and cleaner transportations. Journal of Cleaner Production, 2021, 295126478

[15] LiuH, ChenC. Data processing strategies in wind energy forecasting models and applications: A comprehensive review. Applied Energy, 2019, 249: 392-408

[16] LiuH, ZhangL, LiuHF, ChenS, WangS, WongZZ, YaoK. High-frequency ultrasonic methods for determining corrosion layer thickness of hollow metallic components. Ultrasonics, 2018, 89: 166-172

[17] MaH, ZhangW, WangY, AiY, ZhengW. Advances in corrosion growth modeling for oil and gas pipelines: A review. Process Safety and Environmental Protection, 2023, 171: 71-86

[18] MayZ, AlamMK, NayanNA. Recent advances in nondestructive method and assessment of corrosion undercoating in carbon - steel pipelines. Sensors, 2022, 22176654

[19] MousaviSS, MoghaddamAS. Failure pressure estimation error for corroded pipeline using various revisions of ASME B31G. Engineering Failure Analysis, 2020, 109104284

[20] OssaiCI. A data-driven machine learning approach for corrosion risk assessment—A comparative study. Big Data and Cognitive Computing, 2019, 3228

[21] OssaiCI. Corrosion defect modelling of aged pipelines with a feed-forward multi-layer neural network for leak and burst failure estimation. Engineering Failure Analysis, 2020, 110104397

[22] PengS, ChenQ, ZhengC, LiuE. Analysis of particle deposition in a new-type rectifying plate system during shale gas extraction. Energy Science & Engineering, 2019, 8(3): 702-717

[23] PengS, ZhangZ, LiuE, LiuW, QiaoW. A new hybrid algorithm model for prediction of internal corrosion rate of multiphase pipeline. Journal of Natural Gas Science and Engineering, 2021, 85103716

[24] RenCY, QiaoW, TianX. Natural gas pipeline corrosion rate prediction model based on BP neural network. Fuzzy Engineering and Operations Research, Berlin Heidelberg, Germany, 2012449455

[25] ShiF, LiuZ, LiE. Prediction of pipe performance with ensemble machine learning based approaches. 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control, Shanghai, China, 2017408414

[26] SongY, WangQ, ZhangX, DongL, BaiS, ZengD, XiY. Interpretable machine learning for maximum corrosion depth and influence factor analysis. npj Materials Degradation, 2023, 7(1): 1-15

[27] SunY, ZhangS. A multiscale hybrid wind power prediction model based on least squares support vector regression-regularized extreme learning machine-multi-head attention-bidirectional gated recurrent unit and data decomposition. Energies, 2024, 17122923

[28] TanX, FanL, HuangY, BaoY. Detection, visualization, quantification, and warning of pipe corrosion using distributed fiber optic sensors. Automation in Construction, 2021, 132103953

[29] VelazquezJC, CaleyoF, ValorA, HallenJM. Field study—Pitting corrosion of underground pipelines related to local soil and pipe characteristics. Corrosion, 2010, 661016001

[30] WangJ, WangX, ZhangJ, ShangX, ChenY, FengY, TianB. Soil salinity inversion in Yellow River Delta by regularized extreme learning machine based on ICOA. Remote Sensing, 2024, 1691565

[31] WeiB, ChenL, LiH, YuanD, WangG. Optimized prediction model for concrete dam displacement based on signal residual amendment. Applied Mathematical Modelling, 2020, 78: 20-36

[32] XuB, ChenZ, WangX, BuJ, ZhuZ, ZhangH, LuJ. Combined prediction model of concrete arch dam displacement based on cluster analysis considering signal residual correction. Mechanical Systems and Signal Processing, 2023, 203110721

[33] XuB, WangS, XiaH, ZhuZ, ChenX. A global sensitivity analysis method for safety influencing factors of RCC dams based on ISSA-ELM-Sobol. Structures, 2023, 51: 288-302

[34] YinS, LiuH. Wind power prediction based on outlier correction, ensemble reinforcement learning, and residual correction. Energy, 2022, 250123857

[35] ZhangM, GuoY, XieQ, ZhangY, WangD, ChenJ. Defect identification for oil and gas pipeline safety based on autonomous deep learning network. Computer Communications, 2022, 195: 14-26

[36] ZhengQ, WangC, LiuW, PangL. Evaluation on development height of water-conduted fractures on overburden roof based on nonlinear algorithm. Water, 2022, 14233853

RIGHTS & PERMISSIONS

Harbin Engineering University and Springer-Verlag GmbH Germany, part of Springer Nature