Title :
A design of non-linear electro-pneumatic servo systems by using neural-net based linearizer with off-line learning algorithm
Author :
Oki, Toshitaka ; Tanaka, Kanya ; Yamamoto, Toru ; Uchibori, Akihiko ; Oka, Masato
Author_Institution :
Dept. of Mech. Eng., Ube Nat. Coll. of Technol., Japan
fDate :
6/24/1905 12:00:00 AM
Abstract :
Many electro-pneumatic servo systems have strong nonlinear property because of compressible air in cylinders. To control their systems, a neural network(NN) based linearizer with off line learning is proposed. The augmented system which consists of the controlled object and the linearizer is controlled by a linear controller. The point of the learning algorithm of the NN is to estimate from the actual input of the controlled object to the input of the augmented object directly
Keywords :
control system synthesis; discrete time systems; electropneumatic control equipment; learning (artificial intelligence); linear systems; linearisation techniques; multilayer perceptrons; neurocontrollers; nonlinear control systems; servomechanisms; SISO discrete time linear system; controlled object; learning algorithm; linear controller; neural-net based linearizer; nonlinear electro-pneumatic servo systems; off-line learning algorithm; strong nonlinear property; Adaptive control; Control engineering education; Control systems; Educational technology; Engine cylinders; Linear systems; Neural networks; Nonlinear systems; Servomechanisms; Systems engineering education;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005606
