Construction method of flux linkage observing device of electric automobile induction motor

Abstract

The invention discloses a construction method of a flux linkage observing device of an electric automobile induction motor based on an inverse system of a support vector machine. The construction method comprises the following steps of firstly, constructing a flux linkage-containing subsystem of an electric automobile induction motor prime system, establishing an electric automobile induction motor flux linkage inverse system of the flux linkage-containing subsystem, adopting a support vector machine and a differentiator to establish the inverse system of the support vector machine, training the support vector machine to obtain the vector coefficients and threshold values of the support vector machine to realize the electric automobile induction motor flux linkage inverse system, and finally, serially connecting the inverse system of the support vector machine with the electric automobile induction motor prime system to form the flux linkage observing device. The construction method has the advantages that the on-line and real-time detection of the flux linkage of the electric automobile induction motor is realized, the accurate flux linkage information is provided for the vector control of the induction motor, and the working performance of the electric automobile induction motor is improved.

Description

technical field [0001] The present invention relates to the field of electric vehicles, in particular to a construction method of an electric vehicle induction motor flux linkage observer based on a support vector machine inverse, which provides a new identification method for the flux linkage detection of electric vehicle induction motors, and is suitable for electric vehicles. High-performance real-time control of automotive induction motors. Background technique [0002] In order to realize the high-performance control of induction motors used in driving electric vehicles, vector control strategies are usually adopted. In order to take advantage of the excellent dynamic and static characteristics of vector control, the dependence of electric vehicle induction motors on parameters must be solved. Among many parameters, the vector control strategy directly affects the The control effect is the flux link identification link. Induction motor flux detection can be divided int...

AI Technical Summary

Problems solved by technology

The stator voltage and current flux linkage model method uses the stator back electromotive force to obtain the stator flux linkage, which can obtain higher detection accuracy at high speeds, but is easily affected by the deviation of motor parameters at low speeds, and the error does not converge. At zero speed, Since the stator voltage is zero, this method cannot be used; the stator current speed flux linkage model method uses the rotor flux equation to establish the relationship between the stator current, rotational speed and flux linkage, so as to obtain the flux linkage. The voltage-current flux linkage model method is easily affected by parameter deviation, but due to the introduction of parameters such as rotor resistance, stator inductance and leakage inductance, the robustness of the method is reduced; the hybrid flux linkage model method combines the stator voltage The advantages of the current flux linkage model method and the stator current speed flux linkage model method make the induction motor use the stator voltage current flux linkage model method at high speeds, and use the stator current speed flux linkage model method at low speeds, but this brings The problem of model switching in the operation of induction motors; the extended Kalman filter flux linkage observation model method is essentially a full-state or dimensionality reduction observation model, which has the characteristics of anti-parameter change and strong ability to measure noise, but the state matrix in the model error It is closely related to the motor parameters, and an accurate noise matrix needs to be set

It can be seen that the flux linkage obtained by the indirect method is related to the parameters of the induction motor, and the parameters of the induction motor are easily affected by the working environment, load changes, noise interference, etc., which makes it very difficult to accurately obtain the flux linkage of the induction motor

Images