Adaptive neural speed controller for direct drive with PMSM
[ 1 ] Instytut Automatyki i Inżynierii Informatycznej, Wydział Elektryczny, Politechnika Poznańska | [ P ] employee
EN The paper presents selected properties of the adaptive speed neural controller trained online for direct drive during mechanical changes of the object parameters. In the article was compared different algorithms for learning neural networks such as: backpropagation algorithm BP, momentum backpropagation MBP, Quickprop and RPROP. The authors proposed an effective method of supervision of learning neural network, which does not lead to its overfitting. The algorithms were implemented on a laboratory stand.
1144 - 1149