基于多源数据的水利工程施工复合地基承载力估算研究

Research on Bearing Capacity Estimation of Composite Foundation for Hydraulic Engineering Construction Based on Multi-source Data

为得出水利工程复合地基承载力的最优估算模型,以实测承载力为基础,基于人工神经网络模型(ANN),以3种优化算法(布谷鸟算法CSA、粒子群算法PSO、遗传算法GA)构建了3种优化模型,以多源数据为输入组合方式,比较了不同模型精度,结果表明:影响复合地基承载力的因素由高到低依次为桩径、桩长、置换率、施工工艺、孔隙比,CSA-ANN模型在所有模型中精度最高,可推荐估算水利工程复合地基承载力。

To obtain the optimal estimation model of the bearing capacity of the composite foundation of hydraulic engineering,based on the measured bearing capacity,based on the artificial neural network model(ANN),and uses three optimization algorithms(cuckoo algorithm CSA,particle swarm algorithm PSO,genetic algorithm GA).We built 3 optimization models and used multi-source data as input combination to compare the accuracy of different models.The results showed that:the factors affecting the bearing capacity of composite foundations are pile diameter,pile length,replacement rate,construction technology,void ratio from high to low.The CSA-ANN model has the highest accuracy among all models.