说明：  针对BP神经网络存在的缺点，本文利用遗传算法能够收敛到全局最优解而 且遗传算法鲁棒性强的特点将遗传算法同神经网络结合起来，不仅能发挥神经网 络的泛化映射能力，而且使神经网络具有很快的收敛性以及较强的学习能力。为 了验证遗传算法优化BP神经网络的有效性，本文将此算法应用到直线一级倒立 摆的稳定控制中，同时利用UbVIEW语言界面开发能力强，并且数据输入、网 络通信、硬件控制简单的优点，制作了倒立摆的仿真控制和实时控制软件。仿真 研究表明，遗传算法优化BP神经网络的控制器设计是可行的，可以很好的实现倒 立摆的稳定控制。
(BP neural network for the shortcomings, this paper genetic algorithm can converge to global optimal solution and And genetic algorithm robustness characteristics of the genetic algorithm combined with neural networks, neural networks can not only play The generalization ability of network mapping, and the neural network with fast convergence and a strong ability to learn. As The validation of genetic algorithm to optimize the effectiveness of BP neural network, this algorithm is applied to this line a handstand Put stability control, and interface development using UbVIEW language ability, and data entry, network Network communications, hardware, the advantages of simple control, produced a simulation of the inverted pendulum control and real-time control software. Simulation Studies have shown that genetic algorithm BP neural network controller design is feasible, can achieve a good fall Li put stability control. )