论文部分内容阅读
提出了一种智能融合自适应控制策略用于带外部干扰及模型不确定性的漂浮基空间机器人系统.首先建立不确定空间机器人动力学模型,利用径向基神经网络在逼近域内来补偿模型中出现的未知非线性部分,为保证权值及网络参数在线调节,采用线性化技术将非线性的RBF网络部分线性化,其高阶项量及逼近误差通过自适应鲁棒控制器消除,无须预先估计系统的不确定性程度和外部干扰,包括网络权值和基函数宽度及中心在内的所有参数均能在线实时调整,从而提高了控制精度.该控制器在神经网络控制器的暂时失效的情况下也能保证系统鲁棒性,基于李雅普诺夫理论证明了整个闭环系统信号一致最终有界(UUB).仿真结果表明该智能融合控制器能够达到很好的控制精度.
A smart fusion adaptive control strategy is proposed for a floating base space robot system with external disturbances and model uncertainties.First, a dynamic model of an uncertain space robot is established and the radial basis function neural network is used to compensate the model in an approximation domain In order to ensure that the weights and network parameters are adjusted online, the nonlinear RBF network is partially linearized by linearization. The high-order terms and the approximation errors are eliminated by the adaptive robust controller without prior It is estimated that the degree of system uncertainty and external disturbances, including network weights and the width and center of the basis functions, all the parameters can be adjusted online in real time to improve the control accuracy of the controller in the temporary failure of neural network controller In addition, the robustness of the system is guaranteed, and the UUB is proved based on the Lyapunov theory.The simulation results show that the intelligent fusion controller can achieve good control accuracy.