坦克稳定器的神经滑模控制方法

针对坦克稳定器这一类非线性和不确定性的复杂控制对象,提出一种神经滑模控制方法。该方法将滑模控制与神经网络相结合,解决了控制系统跟踪性能和鲁棒性能之间的矛盾。系统中的滑模控制器保证了系统的快速跟踪性能;而神经网络具有很强的自学习功能,通过学习能够保证系统的稳定性,同时可对扰动和参数变化进行有效的抑制补偿,从而在不牺牲系统鲁棒性的同时达到削弱抖振的目的。从理论上证明了滑动平面的稳定性,并且通过仿真验证了该结果。仿真结果表明该设计方法优于经典设计,为实际设计提供了一种可行的新方法。

Method of Neural Network Sliding Mode Control of Tank Stabilizer

A new method of neural network sliding mode control for tank stabilizer, which contains nonlinearity and uncertainty, is presented. In this method, the sliding mode control and the neural network control are integrated. It solves the conflict between tracking and robustness of the control system. The sliding mode tracking controller is designed to ensure that the system has fast tracking characteristic, while neural network has stronger function of self-learning. It can ensure stability of the system by learning online, and suppress resistance perturbation and parameter variations, thus reducing the chattering without decreasing the robustness of system. This paper theoretically proves the asymptotic stability of the sliding plane, and the simulation results are valid. Simulation results show this is superior to the classical design, and thus a realistic new technique is provided for the design.