| 78 | 0 | 23 |
| 下载次数 | 被引频次 | 阅读次数 |
针对水位变动区水下桩基混凝土因氯离子侵蚀致耐久性劣化的寿命预测问题，传统基于Fick定律的方法因假设理想化、难以涵盖复杂因素而存在局限性。本文提出采用支持向量回归（support vector regression,SVR）与樽海鞘算法（salp swarm algorithm,SSA）结合的SVR-SSA组合模型，实现氯盐环境下该场景混凝土寿命精准预测。以南通市滨江临海水域实测样本数据为基础，构建模型并开展训练与预测实验，并将本文模型与单一SVR模型、SVR和飞蛾扑火算法组合模型对比。结果表明，SVR-SSA模型预测精度显著更优，平均均方误差低至0.145，精度较其他模型最少提升95.87%，标准偏差为0.056。均方误差与标准偏差的综合表现，证实该方法在水位变动区小样本场景下，可为水下桩基混凝土耐久性研究提供有效支撑。
Abstract：For the service life prediction problem of durability degradation of underwater pile foundation concrete in the water level fluctuation zone caused by chloride ion erosion, traditional methods based on Fick′s law have limitations due to idealized assumptions and difficulty in covering complex factors. This paper proposes a hybrid SVR-SSA model combining support vector regression(SVR) with the salp swarm algorithm(SSA) to achieve accurate prediction of concrete service life in chloride environments under this scenario. Based on measured sample data from the riverside and coastal waters of Nantong City, the model was constructed and training and prediction experiments were conducted. The proposed model was compared with the single SVR model and the hybrid model combining SVR and moth-flame optimization algorithm. The results indicate that the SVR-SSA model exhibits significantly superior prediction accuracy, with a mean squared error(MSE) as low as 0.145, representing at least 95.87% improvement over other models, and a standard deviation of 0.056. The comprehensive performance in terms of MSE and standard deviation confirms that this method can provide effective support for durability research on underwater pile foundation concrete in small-sample scenarios within the water level fluctuation zone.
[1]GJORV O E. Durability design and quality assurance of major concrete infrastructure[J]. Advances in Concrete Construction, 2013, 1(1):45-63.
[2]LEONOVICH S N, SHALYI E E, KIM L V. Reinforced concrete under the action of carbonization and chloride aggression:a probabilistic model for service life prediction[J].Science&Technique, 2019, 18(4):284-291.
[3]FELIX E F, POSSAN E. Modeling the carbonation front of concrete structures in the marine environment through ANN[J]. IEEE Latin America Transactions, 2018, 16(6):1772-1779.
[4]覃源，薛存，李遥，等.盐冻耦合作用下水工混凝土耐久性及寿命预测[J].水力发电学报，2024(2):110-122.QIN Y, XUE C, LI Y, et al. Durability and lifespan predictions of hydraulic concrete under salt freezing coupling effect[J]. Journal of Hydroelectric Engineering, 2024(2):110-122.(in Chinese)
[5]徐国会.硫酸盐干湿循环作用下废水混凝土寿命预测模型[J].公路交通科技，2024, 41(6):36-45.XU G H. Service life prediction model for wastewater concrete under sulfate dry-wet cycle[J]. Journal of Highway and Transportation Research and Development, 2024, 41(6):36-45.(in Chinese)
[6]杨冬鹏，郭卫民，王宝民.基于Weibull模型的混凝土冻融损伤寿命预测及应用[J].水利学报，2022, 53(8):977-983.YANG D P, GUO W M, WANG B M. Prediction and application of freezing-thawing damage life of concrete based on Weibull model[J]. Journal of Hydraulic Engineering ,2022, 53(8):977-983.(in Chinese)
[7]LOUNIS Z. Uncertainty modeling of chloride contamination and corrosion of concrete bridges[M]//Applied Research in Uncertainty Modeling and Analysis. Boston, MA:Springer US, 2007:491-511.
[8]GJØRV O E. Durability of concrete structures[J]. Arabian Journal for Science and Engineering, 2011, 36(2):151-172.
[9]MIRJALILI S, GANDOMI A H, MIRJALILI S Z, et al.Salp swarm algorithm:a bio-inspired optimizer for engineering design problems[J]. Advances in Engineering Software, 2017, 114:163-191.
[10]FARIS H, MAFARJA M M, HEIDARI A A, et al. An efficient binary salp swarm algorithm with crossover scheme for feature selection problems[J]. Knowledge-Based Systems, 2018, 154:43-67.
[11]ZHAO X Q, YANG F, HAN Y Z, et al. An oppositionbased chaotic salp swarm algorithm for global optimization[J]. IEEE Access, 2020, 8:36485-36501.
[12]MAJHI S K, BHATACHHARYA S, PRADHAN R, et al.Fuzzy clustering using salp swarm algorithm for automobile insurance fraud detection[J]. Journal of Intelligent&Fuzzy Systems, 2019, 36(3):2333-2344.
[13]MASDARI M, TAHANI M, NADERI M H, et al. Optimization of airfoil Based Savonius wind turbine using coupled discrete vortex method and salp swarm algorithm[J].Journal of Cleaner Production, 2019, 222:47-56.
[14]BABAEI F, LASHKARI Z B, SAFARI A, et al. Salp swarm algorithm-based fractional-order PID controller for LFC systems in the presence of delayed EV aggregators[J].IET Electrical Systems in Transportation, 2020, 10(3):259-267.
[15]SMOLA A J, SCH魻LKOPF B. A tutorial on support vector regression[J]. Statistics and Computing, 2004, 14(3):199-222.
[16]KAZEM A, SHARIFI E, HUSSAIN F K, et al. Support vector regression with chaos-based firefly algorithm for stock market price forecasting[J]. Applied Soft Computing,2013, 13(2):947-958.
[17]ALJARAH I, AL-ZOUBI A M, FARIS H, et al. Simultaneous feature selection and support vector machine optimization using the grasshopper optimization algorithm[J].Cognitive Computation, 2018, 10(3):478-495.
[18]ZHANG X L, CHEN X F, HE Z J. An ACO-based algorithm for parameter optimization of support vector machines[J]. Expert Systems with Applications , 2010 , 37(9):6618-6628.
[19]LI S, FANG H J, LIU X Y. Parameter optimization of support vector regression based on sine cosine algorithm[J].Expert Systems with Applications, 2018, 91:63-77.
[20]邱敬怡，赵璇.基于SVR-BP算法的江苏省空气质量指数预测[J].南通大学学报（自然科学版），2020, 19(1):42-47.QIU J Y, ZHAO X. Air quality index prediction in Jiangsu Province based on SVR-BP[J]. Journal of Nantong University(Natural Science Edition), 2020, 19(1):42-47.(in Chinese)
[21]SOLLICH P. Bayesian methods for support vector machines:evidence and predictive class probabilities[J]. Machine Learning, 2002, 46(1):21-52.
[22]华设检测科技有限公司. 2023—2024年南通市普通国省道“三特”等重要桥梁、桥梁水下桩基及中小桥涵检查服务项目[R].南通：华设检测科技有限公司，2024.
[23]XU X Q, LI Q, DU Z B, et al. Recognition of concrete imperfections in underwater pile foundation based on binocular vision and YOLOv8[J]. KSCE Journal of Civil Engineering, 2025, 29(6):100075.
[24]周明.氯盐环境下混凝土耐久性分析与定量设计[D].南宁：广西大学，2016.ZHOU M. Analysis and quantitative design of concrete durability in chloride environment[D]. Nanning:Guangxi University, 2016.(in Chinese)
基本信息:
DOI：10.12194/j.ntu.20250114001
中图分类号:U445.551
引用信息:
[1]康峰沂,杜仲宝,陈志明,等.基于SVR-SSA组合模型的水下桩基混凝土耐久性研究[J].南通大学学报(自然科学版),2025,24(04):30-35.DOI:10.12194/j.ntu.20250114001.