Controle inteligente de sistemas eletroidráulicos utilizandoredes neurais artificiais

摘要

This work describes the development of a nonlinear control strategy for an electro-hydraulicactuated system. The system to be controlled is represented by a third order ordinarydifferential equation subject to a dead-zone input. The control strategy is based on a nonlinearcontrol scheme, combined with an artificial intelligence algorithm, namely, the method offeedback linearization and an artificial neural network. It is shown that, when such a hardnonlinearity and modeling inaccuracies are considered, the nonlinear technique alone is notenough to ensure a good performance of the controller. Therefore, a compensation strategybased on artificial neural networks, which have been notoriously used in systems that requirethe simulation of the process of human inference, is used. The multilayer perceptron networkand the radial basis functions network as well are adopted and mathematically implementedwithin the control law. On this basis, the compensation ability considering both networks iscompared. Furthermore, the application of new intelligent control strategies for nonlinear anduncertain mechanical systems are proposed, showing that the combination of a nonlinearcontrol methodology and artificial neural networks improves the overall control systemperformance. Numerical results are presented to demonstrate the efficacy of the proposedcontrol system