论文部分内容阅读
提出了一种利用遗传算法来优化模糊神经网络的倒立摆智能控制,利用RBF神经网络与模糊推理过程具有函数等价性.设计了基于模糊系统的RBF网络结构。同时采用改进的遗传算法优化了神经网络的参数和权值。其中利用一种动态的交叉率和变异率.有效地加快了收敛的速度。最后,利用Matlab软件对倒立摆进行仿真.仿真结果表明.该控制具有较好的通用性和控制效果。
An intelligent control of inverted pendulum based on genetic algorithm is proposed, which is equivalent to RBF neural network and fuzzy reasoning process. RBF network structure based on fuzzy system is designed. At the same time, the improved genetic algorithm is used to optimize the parameters and weights of the neural network. Which uses a dynamic rate of crossover and mutation, effectively accelerating the rate of convergence. Finally, the inverted pendulum is simulated by using Matlab software.The simulation results show that the control has good versatility and control effect.