针对应用遗传算法进行给水管网优化设计中惩罚系数难以确定的问题,提出了一种应用给水管网技术经济参数来计算惩罚系数的新方法。数值模拟结果表明,采用该方法计算惩罚系数是可行的,能以较高的概率搜索到最优解,减小了确定惩罚系数的随意性和盲目性,提高了遗传算法的进化效率和收敛性,对于工程优化设计具有一定的参考价值。
Aimed at the problem that the penalty factor is difficult to be determined in the optimal design of water pipe network using genetic algorithms, a new method for calculating the penalty factor by the technological and economic parameters of the water pipe network was put forward. The numerical simulation results show that it is feasible to adopt this method to calculate the penalty factor. The optimal solution can be searched at higher probability. The randomness and blindness in determining the penalty factor are reduced, and the evolution efficiency and convergence of the genetic algorithms are improved. The method has a reference value for engineering optimization design.