Offline and Online Modelling of Switched Reluctance Motor Based on RBF Neural Networks
Abstract
Due to the highly nonlinearity of the flux-linkage characteristics of Switched Reluctance Motor drives (SRM), accurately modelling is cumbersome. In this paper, the offline- trained and the online-trained Radial Basis function (RBF) neural network model are proposed for estimating the SRM flux-linkage under running conditions. To investigate the performance of the modelling schemes, the simulation and experiments have been implemented in a 12/8 structure SRM prototype. The results show that the online-trained model exhibits much better estimation accuracy and robustness than the offline-trained model. Thus, the online-trained RBF model is more suitable for SRM performance prediction and analyzing.
© 2013 Jun Cai, Zhiquan Deng, published by Slovak University of Technology in Bratislava
This work is licensed under the Creative Commons License.