【作者】 姚慰炜；

【导师】 马孝义；

【作者基本信息】 西北农林科技大学 ， 水利水电工程， 2011， 硕士

【摘要】 环状管网优化设计是供水工程的重要组成部分。在供水工程中管网部分的投资一般要占到工程总投资的50%~80%,而且影响管道系统的能耗和运行管理费用。因此,在工程资金投入有限的情况下,进行管网系统的优化设计、寻求能满足水量和水压要求,且能使整个系统的造价最低或年费用最小、系统可靠性最高的设计方案,对节约投资、降低能耗、提高经济效益和社会效益有着重要的现实意义。本文以环状供水管网为研究对象,在总结国内外管网优化研究和最优化技术成果的基础上,针对目前研究中存在的问题与不足,采取理论研究、计算机模拟计算和实例分析相结合的方法,应用聚类分类算法和遗传算法最优化理论,以投资最小为目标,对环状管网布置和在满足压力、流速、闭合差、流量平衡等约束条件下水流分配和管径选择的同步优化遗传算法整数编码方法自动计算方法进行了研究。建立了基于K-Means聚类算法与Hopfield神经网络的管网布置方案和基于整数遗传算法的环状管网流量分配与管径同步优化模型。本文的研究主要取得了以下成果:(1)用连续型Hopfield神经网络结合聚类算法解决环状管网的布置问题,提出一种环状给水管网布置优化设计的方法,先用聚类解决了环状管网基环的确定,再用Hopfield神经网络以较大的概率得到最优路径。(2)用遗传算法解决环状管网水力计算及管径选择的同步优化设计。解该模型的算法为一种不依赖于问题本身而从全局空间出发搜索问题的最优解。研究中应用采用了整数编码的方法,避免了二进制遗传编码冗余问题。(3)本文在布置段编码设计中,根据设计人员的经验确定出各个管道的流量范围和管径的选择,将设计经验有机的融入到优化计算的初始阶段,同时也有效地减少了优化计算中不可行解的数目,提高了优化计算的计算效率和可行性。(4)解决了管网布置优化,环状管网水力计算及管径优化,实现管网的全局最优化。对降低工程投资具有较大的参考价值,也对丰富环状管网设计理论有重要的意义。更多还原

【Abstract】 The irrigation of water-delivery with pipelines is an important way to develop the water-saving agriculture, and its tendency is the pipeline irrigation system. In the whole pipe irrigation network system, the pipe network investment usually contains 50-80% of the total investment. Moreover, water delivery system affects the energy consumption and operational management costs of the pipeline system. Therefore, in the situation of the limited project fund, it has significant meaning to perform the optimal design for reducing the investment, reducing the energy consumption, enhancing the economic and social benefits. The guiding principle of optimal design is to satisfy the water volume and irrigation pressure request, seek the lowest cost or the smallest yearly operation expense and have the highest system reliability.The research is focus on the loop pipe network, based on the summarization of the previous pipe network optimization and the optimized technology achievement. In view of the existing problems and shortcomings, combing theoretical study with analysis of computer and case, this thesis optimize the loop pipe network layout and diameter simultaneous optimization design coding method based on the integer code genetic algorithm, automatically method for identifying water flow route of different pipe layouts, and an automatically calculating program of water pressure of nodes and flow velocity of different pipes, put forward a pipe layout and diameters simultaneous optimization model and algorithm of loop pipe network, combining theoretical study and optimization algorithm with computer analysis and case analysis, adopting Genetic Algorithm(GA) optimization theory. This thesis achieves integration of software and program of pipe network layout and diameter simultaneous optimization design based on the MATLAB integer code genetic algorithm.This thesis mainly achieved the following results:(1) Using a continuous Hopfield neural network clustering algorithm to solve loop pipe network layout problem and optimized the allocation of water supply looped network design.(2) Using Genetic Algorithm for Pipe Network Hydraulic Calculation and Optimal Design of Synchronous diameter selection. Solution of the model is not dependent on the problem itself but from the global space search problem the optimal solution. Application of research methods used integer encoding, to avoid redundant genetic coding of binary problems.(3) This section of code in the layout design based on the experience of the designer and determines the flow of each pipe diameter range and choice of design experience into organic optimization of the initial stage. The code design method can effective in reducing the number of infeasible solutions and improve the computational efficiency of optimization and feasibility.(4) Solve the optimization of the network layout, ring diameter hydraulic calculation and optimization of the network to achieve global optimization. Reducing investment has significant meaning. This thesis also enrich network design theory.更多还原