A Recurrent Neural Multi-Model for Mechanical Systems Dynamics Compensation
Ieroham Baruch*, Rafael Beltran*, Ruben Garrido*,
Boyka Nenkova**
* Department of Automatic Control, CINVESTAV-IPN, 07360 Mexico D.F., Mexico
** Institute of Information Technologies, 1113 Sofia
Abstract:
The paper proposed a new fuzzy-neural recurrent multi-model for systems identification and states estimation of complex nonlinear mechanical plants with backlash. The parameters and states of the local recurrent neural network models are used for a local direct and indirect adaptive control systems design. The de-signed local control laws are coordinated by a fuzzy rule based control system. Simulation results confirm the applicability of the proposed intelligent control system, where a good convergence of all recurrent neural networks, is obtained.
Keywords: Recurrent neural networks, back propagation learning, fuzzy-neural multi-model, systems identification, adaptive control, mechanical system with backlash.