English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The ∞ux and torque of switched reluctance motor (SRM) have a highly nonlinear functional relationship with rotor position and phase current, as a consequence of the double-salient structure of the stator and rotor pole and highly magnetic saturation, which is di-cult to build an accurate analytic model. In order to achieve the SRM high-performance control, it is necessary to build an accurate nonlinear model for SRM. On the basis of the adequate and precise sample data, by taking advantage of neural network that has outstanding nonlinear mapping capability, this paper adopts the Back Propagation (BP) based on Levenberg-Marquardt (LM) algorithm and Radial Basis Function (RBF) neural network to build o†ine models for SRM respectively. Under difierent requirements of model accuracy, two kinds of network are studied and compared with each other on accuracy, scale and other aspects. The research results indicate that the network scale built as SRM nonlinear model by BP neural network based on LM algorithm is smaller than the one built by RBF. Additionally, the model accuracy is higher. In terms of the Switched Reluctance Drive (SRD) which requires real-time controller, reducing the network scale will be beneflcial to the online real-time control of the system.

THE RESEARCH ON FLUX LINKAGE CHARACTERISTIC BASED ON BP AND RBF NEURAL NETWORK FOR SWITCHED RELUCTANCE MOTOR