基于人工智能算法的氯盐侵蚀混凝土预测模型

摘要/Abstract

摘要： 本文基于机器学习算法建立了输电塔桩基混凝土氯离子浓度预测模型,通过相关系数、均方根误差、绝对平均误差和方差比对模型进行检验,并根据蒙特卡洛模拟对模型的稳健性进行分析,同时基于海马优化器对模型进行优化。结果表明,支持向量机(SVM)模型、随机森林(RF)模型和梯度提升树(GBDT)模型都可以准确预测输电塔桩基混凝土中氯离子浓度,相关系数R²均大于0.880,均方根误差小于0.009,绝对平均误差小于0.006,方差比大于0.890。根据误差和稳健性分析结果,建议混凝土中氯离子浓度的预测计算优先使用GBDT模型和SVM模型。根据优化结果,海马优化器能显著提升模型的性能。

关键词: 机器学习算法, 氯离子浓度, 预测模型, 稳健性, 海马优化器

Abstract: Some prediction models of chloride ion concentration in concrete of the transmission tower pile foundations were established based on machine learning algorithm. These models were tested through correlation coefficient, root mean square error, mean absolute error and variance ratio, and the robustness of the models were analyzed according to Monte Carlo simulation. At the same time, the models were optimized based on sea-horse optimizer. The results show that the support vector machine (SVM) model, the random forest (RF) model and the gradient boosting decision tree (GBDT) model can accurately predict the chloride ion concentration in the concrete of the transmission tower pile foundations. The correlation coefficient R² is greater than 0.880, the root mean square error is less than 0.009, the mean absolute error is less than 0.006, and the variance ratio is greater than 0.890 for all these prediction models. According to the results of error and robustness analysis, it is recommended to prioritize the use of the GBDT model and SVM model for the prediction of chloride ion concentration in concrete. According to the optimization results, the sea-horse optimizer can significantly improve performance of model.

Key words: machine learning algorithm, chloride ion concentration, prediction model, robustness, sea-horse optimizer

中图分类号:

TU528

崔纪飞, 柏林, 饶平平, 康陈俊杰, 张锟. 基于人工智能算法的氯盐侵蚀混凝土预测模型[J]. 硅酸盐通报, 2024, 43(2): 439-447.

CUI Jifei, BAI Lin, RAO Pingping, KANG Chenjunjie, ZHANG Kun. Prediction Model of Chloride Erosion Concrete Based on Artificial Intelligence Algorithm[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2024, 43(2): 439-447.

参考文献

[1] MEHTA P K. Durability of concrete: fifty years of progress?[C]//Durability of Concrete: Second International Conference, Montreal, Canada 1991. American Concrete Institute, 1991.
[2] 李镜培, 赵高文, 李林, 等. 硫酸盐渍土中灌注桩竖向承载力演变规律[J]. 哈尔滨工业大学学报, 2017, 49(6): 84-89.
LI J P, ZHAO G W, LI L, et al. Bored piles' vertical bearing strength evolution in sulfate saline soil[J]. Journal of Harbin Institute of Technology, 2017, 49(6): 84-89 (in Chinese).
[3] 李镜培, 谢峰, 李亮, 等. 硫酸盐侵蚀下混凝土灌注桩的损伤效应[J]. 哈尔滨工业大学学报, 2019, 51(6): 89-94.
LI J P, XIE F, LI L, et al. Damage effect of concrete cast-in-situ piles under sulfate attack[J]. Journal of Harbin Institute of Technology, 2019, 51(6): 89-94 (in Chinese).
[4] 李镜培, 李林, 陈浩华, 等. 腐蚀环境中混凝土桩基耐久性研究进展[J]. 哈尔滨工业大学学报, 2017, 49(12): 1-15.
LI J P, LI L, CHEN H H, et al. Advances in concrete pile durability in corrosive environment[J]. Journal of Harbin Institute of Technology, 2017, 49(12): 1-15 (in Chinese).
[5] 杨威, 吉学宽, 蒋琼明. 北部湾海域混凝土结构中氯离子扩散模型研究[J]. 山西建筑, 2021, 47(6): 51-56.
YANG W, JI X K, JIANG Q M. Study on chloride diffusion model of concrete structure eroded by seawater in Beibu Gulf[J]. Shanxi Architecture(Natural Science Edition), 2021, 47(6): 51-56 (in Chinese).
[6] 王家滨, 王斌, 张凯峰, 等. 盐冻损伤喷射混凝土衬砌结构氯离子扩散及其模型[J]. 材料导报, 2020, 34(16): 16055-16061.
WANG J B, WANG B, ZHANG K F, et al. Chloride diffusion and its model of shotcrete lining structure with salt-frost degradation[J]. Materials Reports, 2020, 34(16): 16055-16061 (in Chinese).
[7] 马亚涛, 郭细伟, 方智勇, 等. 氯离子在混凝土桩基中扩散过程的有限元分析[J]. 武汉理工大学学报(交通科学与工程版), 2022, 46(3): 477-482.
MA Y T, GUO X W, FANG Z Y, et al. Finite element analysis of chloride ion diffusion process in concrete pile foundation[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering), 2022, 46(3): 477-482 (in Chinese).
[8] 喻宣瑞, 刘慧平. 基于贝叶斯机械算法探究氯离子在钢筋混凝土结构中的扩散规律[J]. 建筑材料学报, 2022, 25(12): 1248-1254.
YU X R, LIU H P. Chloride Ion Diffusion in Reinforced Concrete Structure Based on Bayesian Mechanical Algorithm[J]. Journal of Building Materials(Natural Science Edition), 2022, 25(12): 1248-1254 (in Chinese).
[9] 余红发, 孙伟. 混凝土氯离子扩散理论模型[J]. 东南大学学报(自然科学版), 2006, 36(增刊2): 68-76.
YU H F, SUN W. Model research on chlorine ion diffusion in concretes[J]. Journal of Southeast University (Natural Science Edition), 2006, 36(supplement 2): 68-76 (in Chinese).
[10] WANG H L, LU C H, JIN W L, et al. Effect of external loads on chloride transport in concrete[J]. Journal of Materials in Civil Engineering, 2011, 23(7): 1043-1049.
[11] RIBEIRO D V, PINTO S A, JÚNIOR N S A, et al. Effects of binders characteristics and concrete dosing parameters on the chloride diffusion coefficient[C]//Congreso Latino-Americano De Patología De Construcción. Alconpat, 2021, 122: 14.
[12] FARAHANI A, TAGHADDOS H, SHEKARCHI M. Prediction of long-term chloride diffusion in silica fume concrete in a marine environment[J]. Cement and Concrete Composites, 2015, 59: 10-17.
[13] REAL S, BOGAS J A, PONTES J. Chloride migration in structural lightweight aggregate concrete produced with different binders[J]. Construction and Building Materials, 2015, 98: 425-436.
[14] 吴贤国, 刘茜, 王洪涛, 等. 基于随机森林和支持向量机的高性能混凝土抗渗性预测研究[J]. 硅酸盐通报, 2021, 40(3): 829-835+844.
WU X G, LIU X, WANG H T, et al. Prediction of impermeability of concrete based on random forest and support vector machine[J]. Bulletin of the Chinese Ceramic Society, 2021, 40(3): 829-835+844 (in Chinese).
[15] VAN Q T. Machine learning approach for investigating chloride diffusion coefficient of concrete containing supplementary cementitious materials[J]. Construction and Building Materials, 2022, 328: 127103.
[16] 鲁先龙, 程永锋. 我国输电线路基础工程现状与展望[J]. 电力建设, 2005, 26(11): 25-27+34.
LU X L, CHENG Y F. Current status and prospect of transmission tower foundation engineering in China[J]. Electric Power Construction, 2005, 26(11): 25-27+34 (in Chinese).
[17] 刘晓, 王思迈, 卢磊, 等. 机器学习预测混凝土材料耐久性的研究进展[J]. 硅酸盐学报, 2023, 51(8): 2062-2073.
LIU X, WANG S M, LU L, et al. Development on machine learning for durability prediction of concrete materials[J]. Journal of the Chinese Ceramic Society, 2023, 51(8): 2062-2073 (in Chinese).
[18] 倪沙沙, 迟世春. 基于粒子群支持向量机的高心墙堆石坝渗透系数反演[J]. 岩土工程学报, 2017, 39(4): 727-734.
NI S S, CHI S C. Back analysis of permeability coefficient of high core rockfill dam based on particle swarm optimization and support vector machine[J]. Chinese Journal of Geotechnical Engineering, 2017, 39(4): 727-734 (in Chinese).
[19] 王一清. 基于机器学习的纯电动二手车价格预测: 以蔚来公司为例[D]. 济南: 山东大学, 2022.
WANG Y Q. Price prediction of pure electric used-car based on machine learning: take Nio for example[D]. Jinan: Shandong University, 2022 (in Chinese).
[20] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.
ZHOU Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2016 (in Chinese).
[21] PHAM B T, LE L M, LE T T, et al. Development of advanced artificial intelligence models for daily rainfall prediction[J]. Atmospheric Research, 2020, 237: 104845.
[22] SOIZE C. Stochastic models of uncertainties in computational mechanics[M]. Reston, VA: American Society of Civil Engineers, 2012.
[23] ABEDINI M, GHASEMIAN B, SHIRZADI A, et al. A novel hybrid approach of Bayesian Logistic Regression and its ensembles for landslide susceptibility assessment[J]. Geocarto International, 2018, 34: 1427-1457.
[24] 王才进, 张涛, 骆俊晖, 等. 神经网络反馈分析方法预测土体热阻系数研究[J]. 岩土工程学报, 2019, 41(增刊2): 109-112.
WANG C J, ZHANG T, LUO J H, et al. Utilization of neural network feedback method to prediction of thermal resistivity of soils[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(supplement 2): 109-112 (in Chinese).
[25] 王才进, 蔡国军, 武猛, 等. 基于人工智能算法预测土体导热系数[J]. 岩土工程学报, 2022, 44(10): 1899-1907.
WANG C J, CAI G J, WU M, et al. Prediction of thermal conductivity of soils based on artificial intelligence algorithm[J]. Chinese Journal of Geotechnical Engineering(Natural Science Edition), 2022, 44(10): 1899-1907 (in Chinese).
[26] ZHAO S J, ZHANG T R, MA S L, et al. Sea-horse optimizer: a novel nature-inspired meta-heuristic for global optimization problems[J]. Applied Intelligence, 2023, 53(10): 11833-11860.