A Dynamic Fuzzy Neural Networks Controller for Dynamic Load Simulator

This paper presents the design, development of dynamic load simulator based on dynamic fuzzy neural networks (D-FNNs) controller. Dynamic load simulator (DLS) can reproduce desired load torque acting on loaded object to test its performance and stability. In DLS, the redundancy torque caused by the motion of loaded object has a very poor effect on the loading accuracy. So a simplified dynamic model is derived to clarify the causation of redundancy torque, and an inverse model controller based on D-FNNs is implemented to compensate redundancy torque and improve the accuracy of load torque despite the nonlinearity and uncertainties in the DLS system. The effectiveness of D-FNNs controller for DLS is verified by numerical simulation and experiment

[1]  Yoonsu Nam.  QFT force loop design for the aerodynamic load simulator , 2001 .

[2]  Meng Joo Er,et al.  A fast learning algorithm for parsimonious fuzzy neural systems , 1999, 1999 European Control Conference (ECC).

[3]  Li-Xin Wang,et al.  A Course In Fuzzy Systems and Control , 1996 .

[4]  Metin Gokasan,et al.  A nonlinear load simulator for robot manipulators , 2001, IECON'01. 27th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.37243).

[5]  Meng Joo Er,et al.  A fast learning algorithm for parsimonious fuzzy neural systems , 1999 .