Title :
On-line training algorithms for an induction motor stator flux neural observer
Author :
Nied, Ademir ; Seleme, I.S. ; Parma, Gustavo G. ; De Menezes, Benjamim R.
Author_Institution :
Centro de Pesquisa e Desenvolvimento em Engenharia Electrica, Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil
Abstract :
This work presents a neural network based stator flux observer. Although the network topology is a standard multilayer perceptron network, the training algorithms are new. This paper presents two on-line training algorithms, which are based on Variable Structure Systems (VSS) theory and Sliding Mode Control (SMC). The resulting observer shows good convergence velocity and robustness with respect to the induction motor parameters for both training algorithms tested.
Keywords :
induction motors; learning (artificial intelligence); multilayer perceptrons; network topology; observers; robust control; stators; variable structure systems; convergence velocity; induction motor parameters; induction motor stator flux neural observer; multilayer perceptron network; network topology; neural network; online training algorithms; robustness; sliding mode control; variable structure systems theory; Convergence; Induction motors; Multilayer perceptrons; Network topology; Neural networks; Robustness; Sliding mode control; Stators; Testing; Variable structure systems;
Conference_Titel :
Industrial Electronics Society, 2003. IECON '03. The 29th Annual Conference of the IEEE
Print_ISBN :
0-7803-7906-3
DOI :
10.1109/IECON.2003.1279967
