2024-03-29T10:12:34Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/301942019-06-11T06:26:14Zcom_10261_106com_10261_4col_10261_485
Baruch, Ieroham Solomon
Gortcheva, Elena A.
Thomas, Federico
Garrido-Moctezuma, Rubén Alejandro
2010-12-16T10:09:15Z
2010-12-16T10:09:15Z
1999
IASTED International Conference on Modelling and Simulation: 326-331 (1999)
http://hdl.handle.net/10261/30194
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.
eng
openAccess
Automation
A neuro-fuzzy model for nonlinear plants identification
comunicación de congreso