论文部分内容阅读
为解决逆控制方法较依赖系统精确模型及易受逆误差影响等问题,提出了一类非线性系统基于支持向量回归(Support Vector Regression,SVR)的鲁棒自适应控制方法,该方法通过支持向量回归辨识得到被控对象的逆模型,并构建自适应逆误差补偿环节,在线修正由于逆模型误差、外界干扰等不确定因素对控制系统性能的不良影响,使得系统能够快速、准确的跟踪参考模型输出。导出了支持向量回归的权值自适应调整率,并利用Lyapunov稳定性理论证明了系统闭环渐近稳定。通过对典型非线性模型的仿真研究,证明了此控制方案在解决一类非线性问题上的可行性,且鲁棒性较好。
In order to solve the problem that the inverse control method is more dependent on the exact model of the system and is more susceptible to inverse errors, a robust adaptive control method based on Support Vector Regression (SVR) for a class of nonlinear systems is proposed. The inverse model of the controlled object is obtained by regression identification and the adaptive inverse error compensation is constructed to correct the adverse effect of uncertain factors such as inverse model error and external disturbance on the performance of the control system online so that the system can track the reference model quickly and accurately Output. The adaptive weighting rate of support vector regression is derived. The closed-loop asymptotic stability of the system is proved by the Lyapunov stability theory. Through the simulation research on the typical nonlinear model, the feasibility of this control scheme in solving a class of nonlinear problems is proved and the robustness is better.