Switched reluctance motor on-line modeling method based RBF neural network

Abstract

The invention discloses a switched reluctance motor on-line modeling method based a RBF (Radial Basis Function) neural network, belonging to the technical field of intelligent control on the switched reluctance motor. The method is used for establishing an off-line model of the switched reluctance motor through a RBF neural network method based on the static data of the switched reluctance motor. On that basis, an error regulation method is designed, the on-line model of the switched reluctance motor is established, and the on-line model has the real-time on-line regulation function and can describe the dynamic characteristics of the switched reluctance motor more accurately. In an experimental process, a method of establishing an input-output mapping relation is used in the on-line modeling method, the problem of overlong operation time of the Gaussian function in a DSP (Digital Signal Processor) is solved, and the realizability of a simulation model in engineering application is ensured, wherein the simulation model is designed based the RBF neural network.

Description

technical field [0001] The invention relates to an online modeling method for switched reluctance motors based on RBF neural network, belonging to the field of intelligent control of switched reluctance motors. Background technique [0002] Due to the double salient pole structure of SRM and the highly saturated magnetic circuit, the calculation of the magnetization curve of flux linkage-current-rotor position as the basis of various characteristics of SRM is quite complicated, and it is difficult to obtain the analytical formula of flux linkage ψ, so it is difficult to establish SRM precise mathematical model. Traditional methods for modeling SRM include: linear method, function analysis method, and finite element analysis method. However, due to the above reasons, the models established using these traditional methods have gradually been unable to meet the accuracy requirements of complex control methods. [0003] With the development and mature application of intelligent...

AI Technical Summary

Problems solved by technology

The following deficiencies can be summarized from the published literature: 1. Some models do not take into account the situations that may be encountered in the actual engineering application of the motor, and they can only be applied to the simulation environment; 2. Although some models are in the actual control platform of the motor However, this part of the model is all based on the static measurement data of the motor, that is, offline data, so it cannot accurately describe the dynamic characteristics of the motor; 3. Some models have a dynamic adjustment function, and the actual motor control platform It has been verified, but this part of the model has high requirements for the prior knowledge of the simulation or the prior conditions of the experiment, the application range of the algorithm is narrow, and the portability is not strong

Images