Research On The FAST Node Displacements Control Based On Improved PSO_BP

FAST (Five-hundred-meter Aperture Spherical Radio Telescope), the most sensitive and internationally largest spherical radio telescope, has significant impact on deep space exploration, environmental research and national security. Since researching on the FAST node displacement control theoretically and practically impact the design and implementation of FAST in industrial control fields, efficient utilization of the FAST node displacement control to realize deformation adjustment and the whole network has been the focus of much of the research.Section 1 summarizes the theory of neural network control and analyzes FAST active reflecting surface deformation, more emphasis was put on the analysis of the FAST node displacement control principle and factors influencing the accuracy of the displacement control, then it decide the inputs and outputs of the control model. Section 2 explains the related theories of particle swarm algorithm and BP neural network algorithm and illustrate the advantages and disadvantages of the two algorithms. In this paper, the limitations of the particle swarm algorithm, slow convergence speed and easy to premature, using genetic manipulation and adaptive inertia weight are improved. And it illustrates the concrete implementation steps and process of the improved algorithm. By analyzing the simulation results, it is concluded that the effectiveness of the improved PSO algorithm. Aiming at the disadvantages of BP neural network algorithm, slow convergence speed and easy to fall into local minimum, using the improved particle swarm optimization algorithm to optimizing the BP neural network, the network optimization precision, generalization capacity and speed are improved. Then it shows the concrete implementation steps and process of the improved PSO_BP algorithm; Section 3 establishes the simulation model of improved particle swarm algorithm, verifies that the optimization ability of the improved particle swarm algorithm is better than the traditional algorithms.The main contribution of the paper is to establish the FAST node displacement control model based on improved PSO_BP algorithm. The results of simulation have verified the effectiveness and feasibility of the improved PSO_BP algorithms and the control model based on improved PSO_BP. It has important practical significance to the research of the entire network adjustment of FAST active reflector.