基于NSGA-Ⅱ算法的给水管网多目标优化设计

Multi-objective Optimization Design of Water Distribution System Based on Non-dominated Sorting Genetic Algorithms-Ⅱ

为了得到科学合理的给水管网设计方案,在设计时要同时考虑其经济性和可靠性。经济性以"管网建造费用"为目标函数,可靠性以"节点富余水头总和"和"节点富余水头方差"为目标函数,综合这两方面建立了给水管网优化设计的多目标数学模型,并通过MATLAB和EPANET等软件平台,运用带精英策略的非支配排序遗传算法(NSGA-Ⅱ)对该多目标数学模型进行求解分析。最后以纽约隧道(New York Tunnel)工程案例加以验证,结果证明了所采用的基于非支配遗传算法的多目标数学模型在给水管网设计中的合理性和有效性。

In order to obtain a scientific and reasonable design of water distribution system, project economics and reliability should be considered. The cost of pipeline construction is used as one objective function for the economic assessment. The sum of node surplus, head and the node surplus head variance are used as objective functions for the reliability. A multi-objective optimization model for water distribution system was established. The model was solved using MATLAB and EPANET platforms and non-dom- inated sorting genetic algorithm-Ⅱ （ NSGA-Ⅱ ）. The New York Tunnel example network was employed to demonstrate this method＇ s application. It was concluded that the multi-objective optimization model based on the non-dominated sorting genetic algorithm-Ⅱ performed reasonably and effectively to solve op- timization problem for water distribution system.