Neural network inverse system-based internal model control method for five-phase fault-tolerant permanent magnet motor

Abstract

The invention discloses a neural network inverse system-based internal model control method for a five-phase fault-tolerant permanent magnet motor. The invertibility of the controlled five-phase fault-tolerant permanent magnet motor is proved according to the invertibility principle and the Interactor algorithm; a training sample set of a neural network is built; samples become standardized data for training a neural network; the neural network is trained in Matlab offline; when the training accuracy reaches a set value 0.001, training is stopped; the static neural network which is trained offline and a preposed integrator form a neural network inversion; the trained static neural network inverse system and the preposed integral link are connected with each other in series in front of an original system, so as to form a pseudo-linear composite system; and finally, supplementary controllers are designed for the obtained two pseudo-linear sub-systems to achieve closed-loop control on the overall system according to the internal model control principle. Therefore, the anti-jamming capability and the robust performance of the system are improved.

Description

technical field [0001] The invention relates to the field of five-phase fault-tolerant permanent magnet motors, in particular to a decoupling control method for five-phase fault-tolerant permanent magnet motors, which is suitable for electric vehicles, aerospace and other places with high reliability requirements. Background technique [0002] In recent years, due to the advantages of high efficiency, high energy density, and high reliability of the five-phase motor and its drive system, it has developed rapidly in the field of electric vehicles. Therefore, being able to reliably and stably control the five-phase motor has become the key to ensuring the reliability of the drive system. However, since the five-phase motor is a multivariable, strongly coupled nonlinear system, it is difficult for the general control strategy to meet the requirements of the drive system. Therefore, decoupling and linearization become the key to control the five-phase motor. [0003] Such as ...

AI Technical Summary

Problems solved by technology

However, both the differential geometry method and the inverse system method need to obtain an accurate mathematical model of the controlled object, and the five-phase motor is a multivariable nonlinear system, and its accurate mathematical model is difficult to obtain

In addition, the physical meaning of differential geometry is difficult to express clearly

Although the theoretical analysis of the inverse system method is relatively simple, its anti-interference ability and robust performance are difficult to meet the system requirements

Images