Study Of Controlling Chaos In High-Intensity Accelerator And DC/DC Switching Power Converter By Neural Network

In this paper,we mainly studied on controlling chaos in high-intensity accelerator and DC/DC switching power converter.Those pieces of research results are finished.Better results are obtained. At first,Taking the advantages of neural network control method for nonlinear complex systems, control of beam halo-chaos in the periodic focusing channels of high intensity accelerators is studied by feed-forward back-propagating neural network method. The envelope radius of high-intensity proton beam is reached to the matched beam radius by suitably selecting the control structure of neural network and the linear feedback coefficient, adjusted the right-coefficient of neural network.. The beam halo-chaos is obviously suppressed and shaking size is much largely reduced after the neural network self-adaptation control is applied.After control,the halo intensity factor become zero,other statistical physical quantities and relative average emittances are more than reduced.The beam halo and its regeneration can be eliminated perfectly. Secondly, DC/DC switching power converter is a typical piecewise-smooth dynamical system. In this circuit system, chaotic motion can be generated at certain work and parameters condition. In this paper, the control method based on RBF neural network is proposed for chaos control in DC/DC switching power converter. The control system is Buck power converter. Simulation results show that the chaotic system can be controlled effectively in Buck power converter by this method. The method is still effective when there are parameter perturbation and noise.It makes furter show that the advantages of neural network control method for nonlinear complex systems.