CMAC Neural Network Control Research Articles

PID+CMAC Neural Network Control of Micro Positioning Platform

Because of some intrinsic properties of the PZT actuator, such as hysteresis, creep and nonlinearity effect, it’s difficult to achieve satisfactory results and control precision for conventional PID controller. In order to improve the control precision of the PZT driven of micro positioning platform, we proposed a CMAC neural network based on PID control scheme, which has the characteristics of realizing feed-forward control and obtaining the inverse dynamic model of controlled object by the CMAC neural network controller, and realizing feedback control by conventional controller, which can ensure the system stability and suppress disturbance. Form MATLAB simulation results, it demonstrates that the CMAC+PID control algorithm can be able to improve the control precision and response time of the system, and enhance the anti-interference ability and robustness, comparing with the traditional digit PID control algorithms.

Neural Network Control of EPS Based on the Cerebellum Model

A mathematical model of vehicle electronic power steering system (EPS)is established. To meet the response speed and real-time requirements of the EPS control, A neural network control strategy of EPS based on the cerebellar model is designed, steering system dynamic response is analyzed and EPS controller based on a single-chip computer with ARM kernel is developed, On the basis of the simulation road test of vehicle is carried out. The results show that the CMAC neural network control of EPS can well coordinate the contradiction between portability and flexibility, It can improve vehicle handling stability and the comprehensive performance of the vehicle.

Fast tool servo control for ultra-precision machining at extremely low feed rates

Diamond turning of brittle materials such as glass, ceramic, germanium and zinc sulfide has been of considerable research interest in recent years due to applications in optics and precision engineering systems. When diamond turning brittle materials, material removal should be kept within the ductile regime to avoid subsurface damage [1, 2]. It is generally accepted that ductile regime machining of brittle materials can be accomplished using extremely low depth of cut and feed rates. Nanometric level positioning accuracy of the machine tool axes is difficult particularly at low feed rates due to friction and backlash. Friction at extremely low feed rates is highly nonlinear due to the transition from stiction to coulomb friction, and as such is very difficult to model. In order to compensate the effect of friction and backlash of a machine tool stage, a nano-metric precision three degrees of freedom (DOF) positioner is designed and fabricated as a fast tool servo. The fast tool servo, which is an independently operated positioning device, would have a small range but high bandwidth and accuracy compared to the conventional lead-screw mechanism. The nano positioner as a fast tool servo and motor-driven feedback controller were combined in order to obtain large motion with high positioning accuracy. A CMAC neural network control algorithm was applied in order to provide on-line learning and better tracking capability compared to standard PID control algorithm. The learning controller was implemented using “C” language on DSP based PC-bus board to control both diamond turning machine and nano positioner.

CMAC Neural Network Control for High Precision Motion Control in the Presence of Large Friction

Precision requirements in ultra-precision machining are often given in the order of micrometers or sub-micrometers. Machining at these levels requires precise control of the position and speed of the machine tool axes. Furthermore, in machining of brittle materials, extremely low feed rates of the machine tool axes are required. At these low feed rates there is a large and erratic friction characteristic in the drive system which standard PID controllers are unable to deal with. In order to achieve the desired accuracies, friction must be accurately compensated in the real-time servo control algorithm. A learning controller based on the CMAC algorithm is studied for this task.