基于神经网络的不确定非线性时滞系统保成本控制

Guaranteed cost control for uncertain time-delay nonlinear systems based on neural networks

保成本控制问题受到了人们的关注,并取得了很多的研究成果,但这些研究均未考虑提高系统动态特性的问题,且很少涉及非线性系统。为此,将神经网络和控制理论相结合,针对一类不确定非线性时滞系统,结合系统动态特性以及非线性扰动抑制问题,提出了新的控制算法。通过将稳定度引入保成本控制中,可以在保成本控制的基础上提高系统的动态特性;利用神经网络良好的非线性逼近能力,很好地解决了系统存在任意非线性扰动时的控制问题。

In recent years guaranteed cost control has been concerned by people, but these researches have not considered improving the system dynamic performance and seldom have related to nonlinear system. Being aimed at the problem blank connecting the neural network with H_∞ control theory for the uncertain time-delay nonlinear systems in connection with the problems of system dynamic performance and offsetting nonlinear disturbance the control algorithm is proposed. Based on guaranteed cost control the system can raise its dynamic performance by adding α-stability to the gnaranteed cost control and using nonlinear appreximate ability of neural network the system control problem is solved very well in existing unrestricted nonlinear disturbance.