Optimal Design Of Water Supply System Based On Improved Genetic Algorithm

The water supply network system is an important infrastructure for cities and towns.With the progress of urbanization in China,the scale of urban areas has been continuously expanded,and the scale of water supply networks has also increased.The problem of low investment efficiency in water supply network has become prominent.By optimizing the design of the pipe diameter scheme in the water supply network,the investment cost can be reduced while ensuring the water supply demand.Therefore,scientific and rational optimization of the water supply network has great economic and practical significance.Using the intelligent optimization algorithm to design the optimal diameter scheme is the research direction of water supply network design in recent years.According to the characteristics of the water supply network optimization problem,an improved genetic algorithm is designed to optimize complex,multidimensioned and nonlinear economical objective function about water supply network construction and operation.The design of the classic network case and actual case is optimized using the improved algorithm and the optimization results show that the improved algorithm has certain advantages in solving the network optimization problem.Based on the analysis of the characteristics of the water supply network optimization problem,the genetic algorithm is improved,and a real-coded genetic algorithm using the auxiliary individual oriented crossover operator is proposed.The improved crossover operator adopts the oriented crossover framework and the auxiliary individual technology to realize the fast optimization for multi-dimensional function,which makes the algorithm adjust to the multi-dimensional characteristics of the water supply network optimization problem.At the same time,in order to enhance the robustness of the convergence process and improve algorithm the success rate in searching the optimal diameter combination scheme,the parents-center crossover strategy and k-bit-swap operator are adopted,which reduces the risk of convergence to the local optimum.The proposed algorithm is tested by multiple complex test functions.The experimental results show that the improved algorithm has better performance than the existing algorithms.The proposed algorithm is applied to the optimization of water supply network,and the constraints are solved by integer coding and penalty function method.The performance of the improved algorithm is verified by the classic water supply network case.The optimization results show that the improved algorithm has better global search ability,and can obtain the global optimal solution satisfying the constraint condition with acceptable convergence speed and better success rate which shows that the adaptability of the improved algorithm for pipe network optimization is better.The improved genetic algorithm is used to optimize the design of a town's water supply network rebuilding project,which provides decision-making suggestions for the network rebuilding.To solve the problems of poor reliability of water supply network and insufficient long-term water demand in this town,the improved algorithm is used to calculate the optimal diameter scheme,and a proposal for rebuilding network is given.The hydraulic simulation software is used to verify that the renovation scheme meets the water demand.In addition four kinds of accident conditions are designed to verify the renovation scheme and the results show that the renovation scheme improves the reliability of water supply in the town's water supply network.