论文部分内容阅读
使用径向基函数(Radial Basis Function,RBF)神经网络为桥式起重机设计一种防摇摆控制器,并采用遗传算法(Genetic Algorithm,GA)与粒子群优化算法(Particle Swarm Optimization,PSO)相结合的混合进化算法(Hybrid Evolutionary Algorithm,HEA)作为神经网络的学习算法.RBF神经网络用于生成台车运动的光滑轨迹,而混合进化算法以台车遵循所生成轨迹到达目标位置时起重机系统的机械能为优化目标,对神经网络的参数进行优化调整,从而达到抑制负载残余摆动的目的.最后通过仿真验证了所提出的混合进化算法相对于遗传算法和粒子群优化算法的优越性以及所设计的防摇摆控制器的正确性和有效性.
An anti-sway controller for overhead traveling crane was designed by Radial Basis Function (RBF) neural network and was combined with Particle Swarm Optimization (PSO) using genetic algorithm (GA) Hybrid Evolutionary Algorithm (HEA) is used as the learning algorithm of neural network.The RBF neural network is used to generate the smooth trajectory of the trolley movement, while the hybrid evolutionary algorithm uses the mechanical energy of the crane system when the trolley follows the generated trajectory to reach the target position In order to optimize the target, the parameters of the neural network are optimally adjusted to achieve the purpose of restraining the residual swing of the load.Finally, the simulation results show the superiority of the proposed hybrid evolutionary algorithm over the genetic algorithm and the particle swarm optimization algorithm, Swing controller correctness and effectiveness.