Optimization design of fuzzy neural network controller in direct torque control system

How to correctly select the voltage space vector in a direct torque control system is one of the key techniques to get over the shortcoming of the DTC system at low speed. We introduce the intelligent optimization algorithm to the fuzzy neural network controller adopted by the direct torque control system. Adopting the immune genetic algorithm to optimize the weights and grade of the membership function of the fuzzy neural network can get over the defects that are easy to get in the local minima of BP. It can infer with the stator voltage vector reasonably. It has an easy control system, a dynamic torque response, and a fast rotation speed. It improves the low speed performances of the direct torque system.

[1]  Dipankar Dasgupta,et al.  Artificial immune systems in industrial applications , 1999, Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296).

[2]  J.N. Nash.  Direct torque control, induction motor vector control without an encoder , 1996, Conference Record of 1996 Annual Pulp and Paper Industry Technical Conference.

[3]  Kazuhiko Takahashi,et al.  Adaptive learning method of neural network controller using an immune feedback law , 1999, 1999 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (Cat. No.99TH8399).

[4]  J Timmis,et al.  An artificial immune system for data analysis. , 2000, Bio Systems.

[5]  Li Jian-zhen.  A learning algorithm of artificial neural network based on genetic algorithm , 2002 .

[6]  Kwee-Bo Sim,et al.  Realization of cooperative strategies and swarm behavior in distributed autonomous robotic systems using artificial immune system , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).