该代码包括单隐含层BP和双隐含层BP。建立基于BP神经网络的预测模型，对数据进行随机排列，选取训练样本和测试样本，训练样本训练网络，测试样本进行验证(The code includes single hidden layer BP and double hidden layer BP. Establish a prediction model based on BP neural network, arrange the data randomly, select training sample

针对BP神经网络的初始权值和阈值是随机选取的弊端，采用遗传算法寻优BP的初始权值和阈值，然后进行BP训练和测试。遗传算法包括编码 选择 交叉 和变异等操作(Aiming at the disadvantage that the initial weights and thresholds of BP neural network are randomly selected, genetic algorithm is used to optimize the initial weights and