改进的BP神经网络在精益建造体系下的施工进度预测
Improved BP Neural Network for Construction Schedule Prediction Under Lean Construction System
张挪威 1林后来 1王广兴 1彭国平 1王玺德 1陈芝琦1
作者信息
- 1. 瑞森新建筑有限公司,山东 济南 250000
- 折叠
摘要
针对基于位置管理系统(LBMS)中预测计划精细化程度低的问题,依靠和声搜索算法(HS)优化BP神经网络的权重和阈值,结合实际施工进度信息,构建了基于HS-BP神经网络的LBMS框架,对施工进度计划精准预测.并以广联达华南总部基地项目中梁板模板施工进度为例,验证了 HS-BP 神经网络的预测精度,同时绘制了梁板模板的实际计划和预测计划的流线图,说明了基于HS-BP神经网络的LBMS框架的可靠性.
Abstract
To address the problem of low accuracy of construction schedule prediction in location-based management systems(LBMS),this paper adopts Harmony Search Algorithm(HS)to optimize the weights and thresholds of BP neural networks.By integrating practical construction information,an LBMS framework based on HS-BP neural networks is constructed to accurately predict the construction schedule.Finally,the prediction accuracy of HS-BP neural network is verified by taking the construction schedule of roof slab formwork of Guangzhou Guanglianda South China Headquarters Base Project as an example.The flow line of the actual and predicted schedules of the beam slab are also drawn to illustrate the reliability of the LBMS framework based on HS-BP neural network.
关键词
精益建造/基于位置管理系统/BP神经网络/和声搜索算法/预测计划Key words
lean construction/location-based management system/BP neural network/harmony search algorithm/construction schedule prediction引用本文复制引用
出版年
2024
NETL
NSTL
万方数据