Title :
A comparative case study of direct inverse control and input-output-linearization using a neural plant model
Author_Institution :
Corp. Technol., Inf. & Commun., Siemens AG, München, Germany
fDate :
Aug. 31 1999-Sept. 3 1999
Abstract :
Neural networks can be used as continuous-time models of nonlinear dynamic systems. Based on the neural plant model, various nonlinear control design methodologies may be applied. In this study, direct inverse control and input-output-linearization are used for trajectory tracking of a batch reactor. Given the same approximate neural model, input-output-linearization proves to be superior to direct inverse control.
Keywords :
control system synthesis; neurocontrollers; nonlinear control systems; nonlinear dynamical systems; batch reactor; continuous time model; direct inverse control; input-output-linearization; neural networks; neural plant model; nonlinear control design methodology; nonlinear dynamic systems; trajectory tracking; Approximation methods; Feedforward neural networks; Inductors; Mathematical model; Temperature measurement; Trajectory; Direct Inverse Control; Input-Output-Linearization; Neural Networks;
Conference_Titel :
Control Conference (ECC), 1999 European
Conference_Location :
Karlsruhe
Print_ISBN :
978-3-9524173-5-5
