基于改进粒子群算法的施工可靠度优化  

Optimization of Construction Reliability Based on Improved Particle Swarm Algorithm

作　　者：邵必林[1] 裴明洋 SHAO Bilin;PEI Mingyang(School of Management,Xi’an University of Architecture and Technology,Xi’an 710055,China)

机构地区：[1]西安建筑科技大学管理学院,陕西西安710055

出　　处：《土木工程与管理学报》2021年第5期29-34,48,共7页Journal of Civil Engineering and Management

基　　金：陕西省创新能力计划软科学研究计划(2019KRM195);住房和城乡建设部软科学研究项目(2019-R-022)。

摘　　要：针对建筑工程施工管理过程中目标控制失衡、不全面的问题,提出一种基于施工可靠度的建筑工程项目多目标优化方法。将施工期的建筑工程项目抽象为一个串–并联复杂网络并引入可靠度理论。分析管控建筑工程项目工期、成本、质量和安全四个目标的必要性,建立四大目标可靠度定量模型并提出了新的施工可靠度计量模型。采用Tanh函数改善粒子群算法的搜索能力,通过实验仿真和统计分析表明,改进后粒子群算法的优化能力显著提高。最后运用改进的粒子群算法优化施工可靠度及工程成本。实际案例分析表明,所提出的方法既有利于工程成本的有效控制,又有利于施工可靠度的提升,对实施建筑工程项目的事前控制有较好的借鉴价值并且为施工管理提供了一条新的思路。Aiming at the problem of unbalanced and incomplete target control in construction management, a multi-objective optimization method for construction projects based on construction reliability was proposed. Abstracted the construction project during the construction period as a series-parallel complex network and introduced reliability theory. Analyzed the necessity of controlling the four goals of construction project duration, cost, quality and safety, established the four major target reliability quantitative models and proposed a new construction reliability measurement model. The Tanh function was used to improve the searchability of PSO. Experimental simulation and statistical analysis show that the optimization ability of PSO is significantly improved after the improvement. Finally, the improved particle swarm optimization algorithm is used to optimize the construction reliability and project cost. The actual case analysis shows that the proposed method is not only conducive to the effective control of engineering cost, but also conducive to the improvement of construction reliability, which has a good reference value for the implementation of construction project control in advance and provides a new idea for construction management.

关 键 词：施工可靠度 PSO 施工管理 

分 类 号：TU71[建筑科学—建筑技术科学] F416.9[经济管理—产业经济]