In this paper we attempt to apply some neural networks based methods in order to solve a control benchmark problem. The goal is to control an electro hydraulic velocity servomotor system. Firstly, some ordinary neural networks have been employed as a controller and simulation results are shown. Secondly, the FEL method is employed and the advantages are mentioned. Both "Dynamic" and "CMAC" neural networks are employed in FEL scheme.
In this paper, robust controllers have been proposed for oscillation suppression in the RTAC benchmark problem. A nominal plant and an uncertainty model are extracted out of varieties of linear models, identified for the nonlinear system and the generalized plant for the unstructured uncertainty problem has been presented. Based on passivity, a cascade controller has been designed to reduce amount of uncertainty in lower frequencies. It is verified that through a nonlinear feedback controller in the inner loop, the uncertainty of linear estimates of the system reduces significantly, and becomes plausible to use linear robust techniques such as mixed sensitivity and H 2 /H to design controller for the system. Finally H and H 2 /H controllers have been designed for new generalized plant and results are compared with the previous reports in literature.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.