用遗传算法求解排水管道造价公式参数  

Optimizing Parameters in Investment Formulation of Drainage Pipe Using Genetic Algorithms

作　　者：伊学农[1] 刘遂庆[1] 徐峰 

机构地区：[1]同济大学环境科学与工程学院,上海200092 [2]莱芜市规划勘察设计院,山东莱芜271100

出　　处：《同济大学学报（自然科学版）》2004年第1期20-23,共4页Journal of Tongji University:Natural Science

摘　　要：排水管道造价公式的型式有多种,各公式中分别含有多个地方参数,用传统方法难以直接优化求解.因此以公式均方差最小为目标函数,利用遗传算法优化计算造价公式中各参数.遗传算法的全局随机搜索技术和对目标函数的直接操作方法,避免了直接推导使用多阶导数和高阶方程的麻烦,提高了公式的精度.It is difficult to optimize the parameters in investment formulation directly with conventional methods because there are seven parameters in it. With minimizing objective function, the mean square deviation of investment formulation and the parameters are optimized directly by the application of genetic algorithms (GAs). It can overcome the trouble of application of pluri-derivative and high order equations in solving the investment formulation using global random search theory and applying the objective function information directly in GAs. The proposed methods in this paper can reduce the mean square deviation and optimize the parameters of investment formulation effectively. This is a part of optimal design for drainage systems.

关 键 词：造价公式 费用函数 优化 遗传算法 

分 类 号：TU992.2[建筑科学—市政工程]