摘要
随着顶推施工在桥梁工程中的广泛应用,桥梁顶推施工对桥墩位移影响及预测亟待深入。为提高桥墩位移预测精度,提出一种基于混沌映射和余弦适应因子优化的改进麻雀搜索算法(ISSA),用于优化门控循环单元(GRU)神经网络的超参数,构建ISSA-GRU预测模型。以南河大桥为工程依托,发现改进后的ISSA算法通过混沌映射增强初始种群多样性,结合余弦适应因子动态调整搜索策略,有效避免局部最优,收敛速度较传统SSA算法显著提升。ISSA-GRU模型在桥墩位移预测中表现优异,其均方误差(MSE)较传统SSA-GRU模型降低93.65%,预测值与实际值的离散度大幅减小,验证了模型的高精度与鲁棒性。
With the wide application of jacking construction in bridge engineering,the influence and prediction of bridge jacking construction on pier displacement need to be further studied.In order to improve the prediction accuracy of bridge pier displacement,an improved sparrow search algorithm(ISSA)based on chaotic mapping and cosine adaptation factor optimization is proposed to optimize the hyperparameters of the gated recurrent unit(GRU)neural network and construct the ISSA-GRU prediction model.Based on the Nanhe Bridge project,it is found that the improved ISSA algorithm enhances the diversity of the initial population through chaotic mapping,and dynamically adjusts the search strategy in combination with the cosine adaptation factor to effectively avoid local optimization.The convergence speed is significantly improved compared with the traditional SSA algorithm.The ISSA-GRU model performs well in the prediction of pier displacement.Its mean square error(MSE)is 93.65%lower than that of the traditional SSA-GRU model,and the dispersion between the predicted value and the actual value is greatly reduced,which verifies the high accuracy and robustness of the model.
作者
郭波
GUO Bo(China Railway 18th Bureau Group Third Engineering Co.,Ltd.,Zhuozhou,Hebei 072750,China)
出处
《施工技术(中英文)》
2025年第10期95-99,112,共6页
Construction Technology
基金
中国铁建股份有限公司2024年度科技研究开发计划及资助课题(2024-C1)
中铁十八局集团有限公司2022年度科研创新项目(C2022-051)。
关键词
桥梁工程
桥墩
顶推
位移
预测
bridges
bridge pier
jacking
displacement
prediction
