A new method of neural network adaptive sliding mode control for tank gun control system that contains time varying and nonlinearity is presented. Based on the advantage of strong robustness of sliding mode control,adaptive approximation for system perturbation parameters and unmodeled dynamics can effectively reduce the switch gain and restrain the system chattering,which uses RBF neural network. The combinationof sliding mode control and neural network approximation can guarantee the robustness and weaken the chattering of the system.Simulation results show that the design can effectively improve the dynamic and static performance of system,which is superior to the classical control method and provides a feasible design method for the design of tank gun control system.%针对坦克炮控系统的时变性和非线性,设计一种神经网络自适应滑模控制方法.基于滑模控制强鲁棒性的优点,用RBF神经网络对系统摄动参数和未建模动态进行自适应逼近,可有效地降低切换增益,抑制系统的抖振.将滑模控制和神经网络逼近相结合,既保证了系统的鲁棒性又削弱了系统的抖振.仿真结果表明该设计能够有效地提高系统的动静态性能,优于经典的控制方法,为坦克炮控系统的设计提供了一种可行的设计方法.
展开▼