Search

A new type of wavelet neural network and grey prediction control strategy is proposed for the complex nonlinearity of some artillery servo system of electric load simulator and the influence of extra torque on the system. The control strategy is mainly composed of a variable structure wavelet neural network controller with particle swarm optimization and a grey prediction compensator( GPC). The variable structure wavelet neural network controller optimizes the parameters of wavelet neural network with particle swarm optimization( PSO) to speed up the convergence of the system, and changes the number of hi-den neurons using the self-learning algorithm dynamically to reduce the calculation complexity and improve the dynamic and static performances of the system. The grey prediction compensator is constructed based on the stability of the system in the sense of Lyapunov, which predicts the input torque deviation and further improves the stability and accuracy of the system. The hardware-in-the-loop simulation results show that the hybrid control strategy has strong robustness and high control precision and ensures the stability and anti-interference ability of the system under dynamic load. [ABSTRACT FROM AUTHOR]

An adaptive fuzzy wavelet neural network fast terminal sliding mode control (AFWN-FTSMC) approach is proposed to control the position of high power AC servo system in a certain weapon. An adaptive fuzzy wavelet neural network controller (AFWNC) is introduced to approach the equivalent control of sliding mode control, which solves the problem that the equivalent control can not be obtained accurately because of the uncertain parameter and external disturbances of the system. The controller can be designed without accurate mode. An adaptive proportional-integral (A-PI) law is used to eliminate system chattering. The stability of the closed loop system is guaranteed by using the Lyapunov method. Simulation results show that the proposed approach can not only improve the steady state performance and control accuracy, but also avoid the chattering problem effectively, and the structural parameter uncertainty has strong robustness. [ABSTRACT FROM AUTHOR]

A novel fractional order neural sliding mode control (FNSMC) strategy is proposed for the nonlinearities of a gun control system (GCS) which is used to control the elevation of a certain top-mounted gun. A fractional order PID type sliding surface is especially designed by introducing the fractional order calculus, and an equivalent control discipline with fractional order dynamics is induced. The saturation function is employed as switch function. To achieve the best control performances, a dynamic adjustment approach of the switch gain is introduced based on RBF neural network. The dynamic and static characteristics of the fractional order sliding mode control (FSMC) system are analyzed by numerical simulation, demonstrating that FSMC can reach up to the steady state more smoothly, which significantly suppresses the chatter effects and enhances the response rate of the control system. Finally, a series of experiments on a semi-physics simulation platform are conducted to investigate the performances of control system. The results show that the proposed FNSMC is of more excellence than the conventional integer order neural SMC (CNSMC). The FNSMC-based control system is of better tracking accuracy as well as high robustness, and the fast, smooth and accurate adjustments of the gun can be achieved. [ABSTRACT FROM AUTHOR]