M.R. Gouvêa, E.S. Figueiredo, B.R. Menezes, L.M.R. Baccarini, A.V. Pires, and W.M. Caminhas (Brazil)
Fuzzy logic, neural network, neurofuzzy controller, vector control
: The purpose of this paper is to present a new online learning controller based on the Neo Fuzzy Neuron structure. The Online Neurofuzzy Controller (ONFC) proposed in this work has as main contribution the fact that its neurofuzzy structure uses the process error not only to correct the network parameters, but also as network input. The ONFC has a very simple structure with only one input, two membership functions and one output and, on the other hand, the network parameters are corrected through the gradient method. The control system is evaluated through digital simulations and experimental implementation applied to an induction motor vector control structure with stator field orientation – FOVS. Simulation and experimental results are presented which demonstrate the effectiveness of the online neurofuzzy controller. Moreover, the proposed controller is able to adapt its learning to a wide ranges of motors and loads.
Important Links:
Go Back
