由于BP神经网络初始神经元之间的权值和阈值一般随机选择，因此容易陷入局部最小值。本方法使用遗传算法优化初始神经元之间的权值和阈值，并对比使用遗传算法前后的效果。-Since the initial BP neural network weights between neurons and thresholds generally random selection, it is easy to fall into local minimum. This method uses a genetic algorithm to optimize the initial weights between neurons and thresholds, and compare the results before and after the use of genetic algorithms.