利用遗传算法优化BP神经网络权值和阈值，然后进行训练，利用训练好的模型进行预估。附实例-The use of genetic algorithm to optimize BP neural network weights and thresholds, and then training, training a good use of forecast models. Attached examples

针对目前自动称重配料系统中采用传统PID控制的不足、系统误差不稳定、动态特性不理想，提出了一种基于神经网络PID控制的算法。该系统传递函数为 ,本文设计BP神经网络为三层，输入层4个节点,隐层为5个节点，输出层为3个节点。-For automatic weighing batching system currently used in traditional PID control deficiencies, systematic errors unstable dynamics is not

基于BP算法的神经网络对一个非线性系统进行辨识，最终辨识达到稳定并有较小的辨识误差。-BP neural network algorithm is based on a nonlinear system identification, and ultimately to identify stable and has a small identification error.