Modelling and predicting of a switched reluctance motor drive using radial basis function network-based adaptive fuzzy system

A novel fuzzy-neural system, which is referred to as a radial basis function network-based adaptive fuzzy system (RBFN-AFS), is presented, to model the switched reluctance machine (SRM) and predict the dynamic performances in an SRM drive system. First, we use an indirect method to measure the phase flux linkage of a 6/4 SRM and then use the co-energy method to calculate phase torque characteristics. Secondly, the RBFN-AFS is designed to learn and train the SRM in the knowledge of the electromagnetic characteristics by using the hierarchically self-organising learning algorithm. This modelling scheme does not require any prior information about the SRM system apart from the input and output signals, and has good capability of generalisation and excellent convergent speed. Then, an RBFN-AFS current-dependent inverse flux linkage model and an RBFN-AFS torque model are used to simulate the various transient and steady-state performances of the 6/4 0.55kW SRM. The simulation and experimental results based on a DSP drive platform are reported to show that the modelling scheme has good estimation performance under different operation conditions of the SRM.