Asynchronous motor drive system control method based on extreme learning machine

Abstract

The invention discloses an asynchronous motor drive system control method based on an extreme learning machine. According to the control method, aimed at the nonlinear problems existing in an asynchronous motor drive system, a command filtering wave technology is introduced in a traditional backstepping design method, by introducing a compensation mechanism, the error generated by the filtering wave is reduced, and the problem of 'calculating explosion' caused by continuous derivation in a traditional backstepping control is successfully overcome. According to the control method, an extreme learning machine algorithm is utilized to approach a nonlinear function in the system, and the algorithm is combined with a command filtering wave technology and a self-adaption backstepping method. According to the control method, the operation of motor can quickly reach a stable state, the method is more suitable for control objects of an electric automobile drive system and the like which need fast dynamic response, a simulation result shows that the asynchronous motor drive system control method can overcome the influences of the uncertainties of parameters and is beneficial to the guarantee of an ideal control effect, and fast and stable response on the rotating speed is achieved.

Description

technical field [0001] The invention belongs to the technical field of motor speed regulation control, and in particular relates to a control method of an asynchronous motor drive system based on an extreme learning machine. Background technique [0002] Asynchronous motor is a kind of AC motor, also called induction motor, which is mainly used as a motor. Asynchronous motors are widely used in industrial and agricultural production, such as machine tools, water pumps, metallurgy, mining equipment and light industrial machinery, etc., all use it as a prime mover, and its capacity ranges from several kilowatts to several thousand kilowatts. The increasingly popular household appliances, such as washing machines, fans, refrigerators, and air conditioners, use one-way asynchronous motors with a capacity ranging from several watts to several kilowatts. In high-tech fields such as aerospace and computers, asynchronous motors can also be used as generators. For example, small hyd...

AI Technical Summary

Problems solved by technology

Traditional neural network learning algorithms (such as BP algorithm) need to artificially set a large number of network training parameters, and it is easy to generate local optimal solutions

Images