论文部分内容阅读
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.
In order to predict the construction cost of CFR CFO more accurately, a combination model of CSO and SVR (CSO-SVR) is proposed, and the CSO algorithm is used to optimize SVR SVR model and the global optimal solution, the SVR model with the best parameters is obtained and the simulation data of the construction cost of the main structure of CFR storage warehouses is used to predict the simulation results. The results show that the prediction accuracy of CSO-SVR model is higher than that of PSO-SVR and GA- SVR, SVR, BPNN and other methods are effective tools for predicting the construction cost of the main structure of gas-membrane concrete storage silos.