基于神经网络滑模的采摘机械臂控制设计

针对二自由度采摘机械臂的位置跟踪控制问题,设计了一种基于神经网络的滑模控制器。其中,神经网络控制器用来估计含有不确定性的滑模控制的等效控制律;鲁棒控制器用来使动态系统始终保持在滑模面上,保证了系统的渐近稳定性,进而实现了采摘机械臂的高精度位置跟踪控制。基于李亚普诺夫稳定性理论设计了自适应律来在线估计系统的不确定性。仿真结果表明:设计的控制器能够实现采摘机械臂对期望位置的精确跟踪,可以满足实际工程的需要。

Sliding mode control for picking manipulators based on neural-network

Sliding mode controller based on neural-network is presented.The controller drives the picking manipulator of two degrees of freedom to achieve position control.The neural-network controller mimics an equivalent control law in the sliding mode control.A robust controller is chosen to curb the system dynamics on the sliding surface,thus the asymptotic stability can be guaranteed and high-accuracy position tracking control can be achieved.An adaptive law based on Lyapunov stability theory is employed to estimate the uncertainties of the system.Numerical simulations illustrate the excellent position control performance of the picking manipulators,which can fulfill the requirements of engineering application.