南通大学学报（自然科学版）2025，Vol.24Issue(4)：30-35,6.DOI:10.12194/j.ntu.20250114001
基于SVR-SSA组合模型的水下桩基混凝土耐久性研究
Study on durability of underwater pile foundation concrete based on SVR-SSA combined model
康峰沂 1杜仲宝 1陈志明 1钱光耀 1祁浩东1
作者信息
- 1. 南通市公路事业发展中心,江苏南通 226007
- 折叠
摘要
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 limita-tions 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 river-side and coastal waters of Nantong City,the model was constructed and training and prediction experiments were con-ducted.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 pre-diction 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 devia-tion confirms that this method can provide effective support for durability research on underwater pile foundation con-crete in small-sample scenarios within the water level fluctuation zone.关键词
水下桩基混凝土/樽海鞘算法/支持向量回归/耐久性/水位变动区/氯离子渗透Key words
underwater pile foundation concrete/salp swarm algorithm/support vector regression/durability/water level fluctuation zone/chloride ion penetration分类
信息技术与安全科学引用本文复制引用
康峰沂,杜仲宝,陈志明,钱光耀,祁浩东..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(4):30-35,6.
