Flux linkage characteristics on-line modeling of switched reluctance motor based on boundary constraints RBF

The switched reluctance motor (SRM) has received extensive attention from researchers for its inherent advantages, and it has become a popular research topic in the field of variable-speed drives. Due to saliency of SRM mechanical structure and principle of reluctance torque production, strong nonlinear flux linkage characteristics on-line modeling method of SRM is studied. On the basis of analyzing boundary constraints RBF neural network topology and training algorithm, flux linkage characteristics on-line modeling method based on DSP is proposed. Sampling and transmission method of SRM operating data using serial communication interface (SCI) module is discussed. Utilizing SRM controller, on-line modeling experimental platform is set up. Experiment results of 18.5 kW and 132 kW SRM shows that the method can realize flux linkage characteristics on-line modeling under different power rating, the modeling error is less than 0.01Wb. The proposed method is feasible and portable for SRM modeling and provides an easy way to implement.