Flexible neural network adaptive control based on the particle swarm optimization algorithm

A flexible neural network adaptive controller based on particle swarm optimization algorithm is proposed for the trajectory tracking control of manipulator robots with model errors and uncertain disturbances. The flexible neural network with adjustable nonlinear degree by parameter variation is used as controller. The particle swarm algorithm is used to optimize the initial weights and thresholds because of its powerful search performance. The method can overcome the defect that the neural network is easy to fall into local extremum and has slow convergence speed in the training. The neural network controller based on the particle swarm optimization algorithm to optimize has better learning and adaptive ability. The simulation results show that the system has fast convergence and high precision, good network generalization and adaptability, and is suitable for the real-time control.