| 215 | 0 | 165 |
| 下载次数 | 被引频次 | 阅读次数 |
针对现有埋地管道点蚀预测模型在特征工程与物理解释性方面存在的双重局限性，研究提出一种融合智能优化与机理驱动分析的预测新范式。该方法通过优化算法提升神经网络性能，并利用特征选择，从复杂的土壤环境数据中识别关键腐蚀驱动因素，有效地规避了信息冗余。结果显示，所提模型的均方误差(Mean Squared Error, MSE)低至0.058 75,预测精度显著提高。此外，可解释性分析证实，该模型的内部决策逻辑与腐蚀理论高度吻合，其将服役年限、土壤pH值和关键侵蚀离子作为核心预测依据，展现出识别冗余特征的学习能力。研究提供了一个兼具高精度、强鲁棒性与物理解释性的预测工具，为实现精准、可靠的管道完整性管理与预测性维护提供了强大的决策支持。
Abstract：This study presents a novel hybrid predictive framework designed to tackle the dual challenges of accuracy and interpretability in modeling pitting corrosion of buried pipelines. The methodology enhances a standard Backpropagation(BP) neural network by first employing and comparing three distinct intelligent optimization algorithms—Particle Swarm Optimization(PSO), Sparrow Search Algorithm(SSA), and Non-dominated Sorting Genetic Algorithm Ⅱ(NSGA-Ⅱ)—to globally optimize the network's initial weights and biases. A key innovation of this study is the development of a Recursive Feature Elimination(RFE) method driven by SHAP values, which systematically evaluated an initial set of 12 input features to identify a more parsimonious and robust optimal subset of 11 variables. The performance of all models was rigorously assessed on a hold-out validation set using a comprehensive suite of metrics(R2, MSE, RMSE, MAE). The results clearly demonstrate the superiority of the optimized models over the baseline network. After feature selection, all three optimized frameworks—PSO-BP, SSA-BP, and NSGA-Ⅱ-BP—achieved significant performance improvements, with their MSE values falling within a low-error range of 6.18% to 14.77% lower than their pre-RFE performance. In stark contrast, the baseline BP model saw its MSE reduced by 83.48% solely due to feature selection. Among the advanced frameworks, the NSGA-Ⅱ-BP model consistently demonstrated the best performance across all evaluation metrics, achieving an exceptionally low final Mean Squared Error(MSE) of 0.058 75, the highest R2 of 0.968 1, and the lowest RMSE of 0.242 3 and MAE of 0.182 3. In addition to its quantitative performance, the SHAP-based interpretability analysis of the top-performing NSGA-Ⅱ-BP model provided strong validation of its scientific soundness. The analysis confirmed that the model's internal logic aligns closely with electrochemical corrosion theories, accurately identifying service life, soil pH, and key corrosive ion concentrations as the most influential predictors. Additionally, the model demonstrated advanced learning capability by recognizing the information redundancy in traditional parameters such as soil resistivity. In conclusion, this research presents a predictive model that is not only highly accurate but also transparent and mechanistically coherent. The comparative analysis further validates the selection of NSGA-Ⅱ as the optimal optimization strategy for addressing this complex engineering challenge.
[1] Ma Duo,Fang Hongyuan,Wang Niannian,et al.The state-of-the-art in pipe defect inspection with computer vision-based methods[J].Measurement,2025:118431.
[2] Wasim M,Djukic M B.External corrosion of oil and gas pipelines:a review of failure mechanisms and predictive preventions[J].Journal of Natural Gas Science and Engineering,2022,100:104467.
[3] Ma Ying,Li Bin,Fang Hongyuan,et al.Fatigue failure behavior of corrosion water supply steel pipes with void around pipes under long-term service load coupling[J].Engineering Failure Analysis,2025,174:109485.
[4] Babu J R,Karve P M,Mahadevan S.Probabilistic prediction of external corrosion fatigue life in buried steel pipes[J].International Journal of Pressure Vessels and Piping,2025,214:105415.
[5] Wasim M,Shoaib S,Mubarak N M,et al.Factors influencing corrosion of metal pipes in soils[J].Environmental Chemistry Letters,2018,16(3):861-879.
[6] Akhlaghi B,Mesghali H,Ehteshami M,et al.Predictive deep learning for pitting corrosion modeling in buried transmission pipelines[J].Process Safety and Environmental Protection,2023,174:320-327.
[7] Capula C S,Terán G,Velázquez J C,et al.Mechanical behavior of X60 pipelines containing pitting corrosion defects based on finite element method[J].Forces in Mechanics,2024,16:100278.
[8] Velázquez J C,Caleyo F,Valor A,et al.Predictive model for pitting corrosion in buried oil and gas pipelines[J].Corrosion,2009,65(5):332-342.
[9] Woldesellasse H,Tesfamariam S.Consequence assessment of gas pipeline failure caused by external pitting corrosion using an integrated Bayesian belief network and GIS model:application with Alberta pipeline[J].Reliability Engineering & System Safety,2023,240:109573.
[10] 李小红，华寅初.用人工神经网络预测评判油气田设备的腐蚀[J].油气储运，1998(8):30-33,64-65.Li Xiaohong,Hua Yinchu.Prediction and evaluation of corrosion of oil and gas field equipment by artificial neural network[J].Oil and Gas Storage and Transportation,1998(8):30-33,64-65.
[11] Du Jian,Zheng Jianqin,Liang Yongtu,et al.Deeppipe:theory-guided prediction method based on automatic machine learning for maximum pitting corrosion depth of oil and gas pipeline[J].Chemical Engineering Science,2023,278:118927.
[12] Miao Xingyuan,Zhao Hong,Song Fulin.Maximum pitting corrosion depth prediction of buried pipeline based on theory-guided machine learning[J].International Journal of Pressure Vessels and Piping,2024,210:105259.
[13] Li Xue,Guo Min,Zhang Ran,et al.A data-driven prediction model for maximum pitting corrosion depth of subsea oil pipelines using SSA-LSTM approach[J].Ocean Engineering,2022,261:112062.
[14] Zheng Qiushuang,Liu Hongbin,Xu Hao,et al.Intelligent prediction model for pitting corrosion risk in pipelines using developed ResNet and feature reconstruction with interpretability analysis[J].Reliability Engineering & System Safety,2025,264(Pt.1):111347.
[15] Velázquez J C,Caleyo F,Valor A,et al.Field study:pitting corrosion of underground pipelines related to local soil and pipe characteristics[J].Corrosion,2010,66(1):016001-1-016001-5.
[16] Zhou Jie,Lin Haifei,Li Shugang,et al.Leakage diagnosis and localization of the gas extraction pipeline based on SA-PSO BP neural network[J].Reliability Engineering & System Safety,2023,232:109051.
[17] Liu Yan,Tang Qiu,Tian Xincheng,et al.A novel offline programming approach of robot welding for multi-pipe intersection structures based on NSGA-Ⅱ and measured 3D point-clouds[J].Robotics and Computer-Integrated Manufacturing,2023,83:102549.
基本信息:
DOI：10.13637/j.issn.1009-6094.2025.1319
中图分类号:TE988.2;TP18
引用信息:
[1]梁瑞,王妮鹏,周文海,等.基于智能优化与特征选择的埋地管道腐蚀深度预测研究[J].安全与环境学报,2026,26(07):2560-2572.DOI:10.13637/j.issn.1009-6094.2025.1319.
基金信息:
甘肃省青年科技基金项目(23JRRA774)
2025-12-31
2025-12-31
2025-12-31