基于CSO-SVR的气膜钢筋混凝土储仓主体结构施工成本预测研究

为了较准确的预测气膜钢筋混凝土储仓主体结构施工成本,提出一种鸡群算法(CSO)和支持向量回归机(SVR)结合模型,即CSO-SVR,利用CSO算法对SVR进行寻优得到全局最优解,从而得到具有最佳参数的支持向量回归机模型,通过气膜钢筋混凝土储仓主体结构施工成本数据预测仿真,结果显示:CSO-SVR模型预测精度高于PSO-SVR,GA-SVR,SVR,BPNN等方法,是预测气膜钢筋混凝土储仓主体结构施工成本的有效工具.

Research on Construction Cost Prediction of Main structure of Concrete Dome Using Inflated Forms Based on CSO-SVR

In order to predict the construction cost of the main structure of concrete dome using inflated forms more accurately,this article makes a detailed analysis of the factors affecting the cost,and presents a model that combines chicken swarm optimization algorithm (CSO) with support vector regression (SVR),namely CSO-SVR,the CSO algorithm is used to find the optimal solution to the SVR,so as to get the support vector regression machine model with the best parameters.Through the forecast simulation using the construction cost data of main structure of concrete dome using inflated forms,the results demonstrate that the prediction accuracy of CSO-SVR model is higher than PSO-SVR,GA-SVR,SVR,BPNN and so on,it is an effective tool to forecast the construction cost of main structure of concrete dome using inflated forms.