基于先进计算模型的深基坑钢板桩围堰施工成本预测  

Cost Prediction of Deep Foundation Pit Steel Sheet Pile Cofferdam Construction Based on Advanced Computing Model

作　　者：吴家锐 WU Jiarui(China Railway 18th Bureau Group the Fifth Engineering Co.,Ltd.,Tianjin 300451)

机构地区：[1]中铁十八局集团第五工程有限公司,天津300451

出　　处：《湖北理工学院学报》2025年第2期54-60,共7页Journal of Hubei Polytechnic University

摘　　要：为了提高深基坑开挖钢板桩围堰施工成本预测的精确性,开发了一种基于先进计算模型的预测方法,即先结合现场具体条件制定详细的深基坑开挖钢板桩围堰施工方案,配置相应的劳动力资源和材料等关键施工要素,再用鸡群算法对极限学习机(ELM)的权重和偏置进行优化,形成高性能预测模型。将该模型应用于太平湾合作创新区原水管线工程的顶管穿越G15沈海高速项目工作坑和接收坑深基坑钢板桩围堰施工成本预测,结果显示能够准确预测钢板桩围堰打入、基坑清淤及支撑等关键施工阶段的直接人力和材料成本,预测的残差及相对误差均保持在较低水平,在施工成本预测领域具有高效性和可靠性。In order to improve the accuracy of cost prediction for steel sheet pile cofferdam construction in deep foundation pit excavation,an advanced computational model based prediction method has been developed.Firstly,a detailed construction plan for steel sheet pile cofferdam construction in deep foundation pit excavation is formulated based on specific site conditions,and corresponding key construction elements such as labor resources and materials are configured.Then,the chicken swarm algorithm is used to optimize the weights and biases of the extreme learning machine(ELM),forming a high-performance prediction model.The model is applied to predict the construction cost of steel sheet pile cofferdam in the deep foundation pit of the G15 Shenhai Expressway project for the top pipe crossing of the original water pipeline project in Taiping Bay Cooperation Innovation Zone.The results show that it can accurately predict the direct labor and material costs of key construction stages such as steel sheet pile cofferdam driving,foundation pit dredging,and support.The residuals and relative errors of the prediction are kept at a low level,and it has high efficiency and reliability in the field of construction cost prediction.

关 键 词：深基坑 钢板桩 围堰施工 成本预测 极限学习机 

分 类 号：TU473[建筑科学—结构工程]