IASTED International Conference on Modelling and Simulation (MS), 1999, Filadelfia (EE.UU.) ; A improved parallel Recurrent Neural Network (RNN) model and an improved dynamic Back-propagation (BP) method of its learning, are proposed. The RNN model is given as a two layer Jordan canonical architecture for both continuous and discrete-time cases. The output layer is of Feedforward type. The hidden layer is a recurrent one with self-feedbacks and full forward connections with the inputs. A linearisation of this RNN model is performed and the stability, observability and controllability conditions, are studied. To preserve the RNN stability, sigmoid activation functions are introduced in RNN feedback loops. The paper suggests to improve RNN realisation using saturation function instead of a sigmoid one. A new improved RNN learning algorithm of dynamic BP-type containing momentum term, is proposed. For a complex non-linear plants identification, a fuzzy-rule-based system and a neuro-fuzzy model, are proposed. The proposed neuro-fuzzy model is applied for identification of a mechanical system with friction. ; Peer Reviewed
A neuro-fuzzy model for nonlinear plants identification
1999-01-01
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
DDC: | 629 |
Identification of MIMO Neuro-fuzzy Hammerstein Model with Noises
British Library Conference Proceedings | 2014
|Identification of MIMO Neuro-fuzzy Hammerstein Model with Noises
Springer Verlag | 2014
|Adaptive Neuro-Fuzzy Model with Fuzzy Clustering for Nonlinear Prediction and Control
BASE | 2014
|Neuro-fuzzy approach for non-linear system identification and control
Kraftfahrwesen | 1998
|