A three-layer CMAC is built using the position information of a repairing area obtained from robot teaching as the input vector of CMAC network input space,and using the extended B sample bar function as the basic function of CMAC nonlinear map,and CMAC is trained with a united single variable function exp(),to design and simulate the program with Matlab language tool box and editor.

At the inspiration of the human cranial nerve network and the artificial nerve network, the paper puts forward a structure of the curriculum system using analogue cranial nerve network, which is called the distributed curriculum system.

A new intelligent optimized dispatching method is proposed, and reinforcement learning control is applied in elevator group control system, in which CMAC neural network based on traffic pattern recognition is designed as the controller, in order to optimize the passengers’ average waiting time.

Research about compound control based on CMAC and PID;

Combining characteristics of switched reluctance motors(SRM),this paper presents a controller architecture and learning algorithm for controlling SRM s torque using cerebellar model articulation controller(CMAC) neural network.

This paper presents energy management strategy on the basis of CMAC,and analyzes the influence of CMAC parameters on the performance of controller.

After combining the optimal control theory with Gauss basis function cerebellar model articulation controller(GCMAC) neural network,an optimal control strategy on electro-hydraulic loading system was proposed,which made the closed-loop system gradually stable.

According to the asymmetry and nonlinearity of the symmetrical valve controlled asymmetrical piston system, in order to improve control precision of the system, the work characteristic of the system is analyzed, then a new control method based on the cerebellar model articulation controller(CMAC) is advanced, and the CMAC compound controller is designed.

In order to solve the nonlinearity and the surplus torque disturbance in the rudder load simulator of the unmanned aerial vehicles,a hybrid controller was proposed with the cerebellar model articulation controller(CMAC) network and the traditional proportional-derivative(PD) controller.