基于离散变量遗传算法的注塑模浇口位置优化设计

Gate location optimization of plastic injection molding based on genetic algorithm with discrete variables

建立了一个注塑模浇口位置设计的多目标优化模型,以浇口位置作为设计变量,优化充填过程中入口压力、温度分布等主要工艺参数以减小制品的翘曲程度.将拟精确罚函数和基于信息熵的多种群离散变量遗传算法相结合,发展了一种求解注塑模浇口位置多目标优化问题的迭代格式.在遗传进化中采用了多种群遗传策略和基于信息熵的空间减缩搜索技术,从而大大提高了遗传进化的效率.将该算法与注塑模流动数值模拟程序结合进行浇口位置优化设计.算例表明所提出的方法适用于注塑模浇口位置优化,并且有较好的计算效率和精度.

A multi-objective optimization model for the gate location design of plastic injection molding is constructed. The problem is to design the gate location by optimizing the main process parameters in filling phase such as the inlet pressure, distribution of temperature and so on, reducing warping of plastics. A new iteration scheme in conjunction with the pseudo-excitation method and multi-population genetic algorithm with discrete variables based on information entropy is developed to solve the multi-objective optimization model for the gate location design of plastic injection molding. Multi-population genetic strategy and information entropy-based searching technique with narrowing down space are employed in the method, making the efficiency of genetic evolution very high. The method is combined with the flow numerical simulation program to search the optimum location of the gate. Numerical examples show that the method is suitable for designing optimal gate location and gives high efficiency and accuracy.