论文部分内容阅读
为科学合理地测算建筑工程安全施工费费率,考虑数据时效性和施工环境差异性对费率的重要影响,提出精细化限时测算方法。将建筑工程安全施工费划分为固定费用和变动费用2部分,构建基于粒子群优化算法(PSO)的误差BP神经网络模型,以此预测工程结算造价,分析费用后得到与实际安全施工费对应的费率计费基数,进而得到费率。选取41个已完工样本项目进行网络训练,确定模型最优网络结构。对武汉市15个典型在建项目进行实证分析。结果表明,在限定时间以及调研采集数据时效性约束条件下,用该模型算得的费率能反映不同地域施工环境对安全施工费动态需求。
In order to scientifically and reasonably calculate the safety construction fee rate of construction projects and to consider the significant impact of the data timeliness and construction environment difference on the rates, a refined time limit calculation method is proposed. The safety construction cost of construction engineering is divided into two parts: fixed cost and variable cost, and an error BP neural network model based on Particle Swarm Optimization (PSO) is constructed to predict the settlement cost of the project. After analyzing the cost, the construction cost corresponding to the actual safety construction cost Rate billing base, and then get the rate. Select 41 completed sample project network training to determine the model optimal network structure. 15 typical projects under construction in Wuhan are empirically analyzed. The results show that the rate calculated by this model can reflect the dynamic demand for safety construction costs in different construction environments in a limited time and under the time constraint of collecting and collecting data.