Title :
Multiple interconnected Hopfield networks for intelligent global linearising control
Author :
Dimopoulos, K.P. ; Kambhampati, C.
Author_Institution :
Dept. of Cybern., Reading Univ., UK
Abstract :
A combination of multiple interconnected Hopfield networks is proposed to identify and control a class of control affine nonlinear systems, and is compared with two other single Hopfield networks each with different number of neurons. The control strategy is based on global linearising control in which the network models is used to synthesise a state feedback that will cancel out the nonlinearities yielding a linear model on which standard PID control can then be applied
Keywords :
Hopfield neural nets; control nonlinearities; linearisation techniques; neurocontrollers; nonlinear control systems; state feedback; three-term control; Hopfield neural networks; PID control; affine nonlinear systems; global linearisation; intelligent control; nonlinearities; state feedback; Control nonlinearities; Control system synthesis; Control systems; Intelligent networks; Linear feedback control systems; Network synthesis; Neurons; Nonlinear control systems; Nonlinear systems; State feedback;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.832718
