论文部分内容阅读
针对实际导弹系统存在气动系数不确定量和外界干扰的问题,提出了采用最小二乘支持向量机(LSSVM)对汇总不确定量进行估计和补偿的方法。采用输出重定义技术克服了导弹过载输出的非最小相位特性,利用容易测量的过载和角速度相组合重新定义了新输出量。设计了基于LS-SVM的滑模控制器使导弹过载控制系统的跟踪误差最终收敛到零。以某型超声速反舰导弹为研究对象进行了仿真分析,仿真结果表明,基于LS-SVM的滑模控制器具有很好的控制效果,LS-SVM实现了对汇总不确定量的准确估计。
In order to solve the problem that the actual missile system has uncertainties of aerodynamic coefficients and external disturbances, a method of estimating and compensating the aggregate uncertainties by using least squares support vector machines (LSSVM) is proposed. The output redefinition technique is used to overcome the non-minimum phase characteristics of the missile overload output and to redefine the new output with a combination of easily measured overload and angular velocity. The sliding mode controller based on LS-SVM is designed to make the tracking error of missile overload control system finally converge to zero. The simulation results show that the sliding mode controller based on LS-SVM has a good control effect, and the LS-SVM achieves an accurate estimation of the aggregate uncertainty.