基于粒子群-神经网络的风景园林施工项目工期压缩方法  

A Time Compression Method for Landscape Architecture Construction Projects Based on Particle Swarm Optimization Neural Network

作　　者：姚勇强 YAO Yongqiang(School of Culture and Tourism,Huangshan Vocatinal Technical College,Tunxi 245031,China)

机构地区：[1]黄山职业技术学院文化与旅游学院,安徽屯溪245031

出　　处：《徐州工程学院学报(自然科学版)》2025年第1期49-57,共9页Journal of Xuzhou Institute of Technology(Natural Sciences Edition)

摘　　要：风景园林施工项目管理过程中依靠单一神经网络求解工期压缩模型,容易陷入局部最优,导致压缩费用过高,因此提出基于粒子群-神经网络的风景园林施工项目工期压缩方法.该方法充分考虑风景园林施工涉及的众多施工环节,建立施工项目子网络,并通过引入工期压缩机理搭建项目群网络计划框架;从赶工费用、索赔费用等方面入手,构建以压缩费用最低为目标的项目工期压缩数学模型,给出资源约束条件、工期压缩约束条件和关键路径不变约束条件;运用粒子群算法优化神经网络,在避免陷入局部最优的同时,分析多种工期压缩方案模拟实施后产生的数据,更准确预测压缩费用变化,且以此项目工期压缩数学模型的求解,得到最优压缩策略.实验结果表明:依托该方法对某风景园林施工项目进行工期压缩处理,产生的总压缩费用仅为55万元,极大降低了施工成本.In the process of landscape architecture construction project management,reliance upon a single neural network to address the duration compression model can readily result in the system attaining a local optimum,thereby engendering elevated compression costs.To solve the problem,a time compression method for landscape construction projects based on a particle swarm optimization neural network is proposed.It is imperative to acknowledge the intricacies of construction processes in landscape architecture construction,necessitating the establishment of a sub-network of construction projects.This sub-network can then be subjected to a schedule compression mechanism to construct a project group network planning framework.From a cost perspective,encompassing both rush and claim costs,a mathematical model for project duration compression is constructed with the objective of minimizing compression costs.The model also take into account resource constraints,duration compression constraints,and key path invariant constraints.The particle swarm optimization algorithm is employed to optimize neural networks and circumvent local optima.The data generated after simulating the implementation of multiple schedule compression schemes is analyzed,enabling more accurate predictions of changes in compression costs.Furthermore,the mathematical model of project schedule compression is solved to obtain the optimal compression strategy.The experimental results demonstrate that reliance on this method to compress the construction period of a specific landscape construction project resulted in a total compression cost of 550,000 yuan,which is a significant reduction in construction costs.

关 键 词：粒子群-神经网络 风景园林 施工项目 子网络 工期压缩 资源约束 

分 类 号：TU386.3[建筑科学—结构工程]