Modeling method for dynamic model of data-driven asynchronous motor

Abstract

The invention relates to a modeling method for a dynamic model of a data-driven asynchronous motor, and the method comprises the following steps of: establishing a dynamic model of an asynchronous motor by using actual operation data of the asynchronous motor, and identifying coefficients in the dynamic model by using a data-driven nonlinear dynamic sparse representation method; compared with a traditional asynchronous motor dynamic modeling method based on an equivalent circuit, the asynchronous motor dynamic model established by the method is not affected by model errors, and the robustness to noise is higher; and on the other hand, compared with other data-driven dynamic modeling methods, such as a neural network, a support vector machine and the like, the asynchronous motor dynamic model established by the method is simpler in structure and more interpretable.

Description

technical field [0001] The invention relates to the technical field of motor control, in particular to a data-driven asynchronous motor dynamic model modeling method. Background technique [0002] The primary problem of motor control is the modeling of the motor. The mathematical model of the motor is the most important tool in the research of motor control theory and the development of motor control system products. In the field of motor control, scholars and engineers often establish two motor mathematical models according to different application scenarios: one is a steady-state model, or a static model; the other is a dynamic model, or a dynamic model Model. The steady-state model only considers the steady-state process of the motor and does not consider the dynamic process of the motor. This model is generally in the form of y=f(u), where y is the output variable and u is the input variable. The modeling method of the steady-state model is often relatively simple, eit...

AI Technical Summary

Problems solved by technology

However, the research on the data-driven motor dynamics model modeling method is still in a blank state.

The reason is that the research on the dynamic model modeling method of the data-driven system is still not deep enough at this stage, especially the construction of a simple and interpretable data-driven dynamic model cannot be established. model method

For example, the differential neural network is a data-driven dynamic model modeling method proposed in the past two years. This method can establish a systematic neural network-type dynamic model. However, this model structure is often too complex and lacks interpretability. Meet the requirements of high real-time performance, high reliability and high robustness in the motor field

Images