In this paper,a method of reducing the tracking error in CNC machining is proposed.The structured neural network is used to approximate the discontinuous friction in CNC machining,which has jump points and uncertainti...In this paper,a method of reducing the tracking error in CNC machining is proposed.The structured neural network is used to approximate the discontinuous friction in CNC machining,which has jump points and uncertainties.With the estimated nonlinear friction function,the reshaped trajectory can be computed from the desired one by solving a second order ODE such that when the reshaped trajectory is fed into the CNC controller,the output is the desired trajectory and the tracking error is eliminated in certain sense.The proposed reshape method is also shown to be robust with respect to certain parameters of the dynamic system.展开更多
基金partially supported by a National Key Basic Research Project of Chinaa USA NSF grant CCR-0201253the Foundation of UPC for the Author of National Excellent Doctoral Dissertation under Grant No.120501A
文摘In this paper,a method of reducing the tracking error in CNC machining is proposed.The structured neural network is used to approximate the discontinuous friction in CNC machining,which has jump points and uncertainties.With the estimated nonlinear friction function,the reshaped trajectory can be computed from the desired one by solving a second order ODE such that when the reshaped trajectory is fed into the CNC controller,the output is the desired trajectory and the tracking error is eliminated in certain sense.The proposed reshape method is also shown to be robust with respect to certain parameters of the dynamic system.
