Hybrid control based on improved CMAC for motor-driven loading system

The motor-driven loading system (MDLS) is highly nonlinear and time variant. It is difficult for the traditional feedforward control method to improve the performance, especially under the disturbance of movement, the so called extraneous torque problem. Aiming at control of MDLS, a hybrid control scheme based on the improved cerebella model articulation controller (CMAC) is proposed. In the controller, CMAC is compound with PID algorithm, the feedforward control is realized by CMAC while the feedback control is realized by PID controller. It absorbs the fast-learning and precise approaching advantages of CMAC to enhance traditional control method. The former learned timers of the assressed hypercubes is used as the credibility in order to eliminate the excess self-learning phenomena. The MDLS's mathematical model is established and the detailed control structure is put forward. Simulation results show that the proposed controller can effectively eliminate the extraneous force and fairly improve the dynamic loading performances of the MDLS. The robustness to unknown external load disturbances is improved.