Parameter identification system and method of induction motor

Abstract

The invention discloses a parameter identification system and method of an induction motor. The invention comprises a test system for on-line identification on a parameter of the induction motor, a reinforcement learning framework suitably used for identifying the motor parameter and a q-learning-based parameter identification method of the induction motor, wherein the test system can be used for acquiring data such as a real-time voltage, a real-time current, a real-time temperature and a real-time torque, which are needed by an on-line identification algorithm, of the motor, the data is used for identifying the parameter, the reinforcement learning framework comprises a state variable in a reinforcement learning environment, an award value and selection of an action mode, and by the q-learning-based parameter identification method, a data set is generated in real time and the parameter is identified during the running process of the test system. By the parameter identification system and method, the conflict problem of difficulty in acquiring identification accuracy and a training set is solved, a special motor mathematical model is not depended, high universality is achieved, and the data set can be generated in real time and is not needed to be prepared in advance; the identified parameter takes optimal output performance as priority and is free from influence of change of an actual physical parameter, and the identification accuracy is high; and the rotor resistance of the induction motor can be identified, and the excitation inductance of the induction motor can also be identified.

Description

Technical field [0001] The invention relates to the technical field of motor control, in particular to a system and method for identifying parameters of induction motors. Background technique [0002] The parameter identification of induction motors is an important and difficult problem in the field of motor control. The accuracy of parameter identification directly affects the output performance of the motor. In the parameter identification of induction motors, the most important identification parameters are rotor resistance and magnetizing inductance, because the temperature of the rotor changes constantly during the operation of the motor, which leads to the constant change of the rotor resistance value, and the identification accuracy of the rotor resistance directly affects the motor The size of the output torque; Similarly, during the field weakening operation of the induction motor, the value of the excitation inductance will also change from time to time, and the identi...

AI Technical Summary

Problems solved by technology

Its disadvantage is that it relies on the motor model, and the inaccuracy of the motor model will lead to serious errors in the results

Patent: A method for identifying rotor resistance parameters of induction motors based on ELman neural network (public number: CN102937670A) discloses a method for identifying rotor resistance parameters of induction motors based on neural networks. This method belongs to the online identification method driven by data, and its advantages It does not require a clear motor model and can realize online parameter identification, but its disadvantages are also very obvious: it needs a data set to train the neural network, and it is very difficult to obtain a reliable data set

Patent: A high-speed train traction induction motor parameter identification method (public number: CN104201962A) discloses an identification method based on a motor flux observer. This method belongs to a model-driven online identification method. The amount is small, but the disadvantages are also extremely obvious: the model-driven method greatly depends on the mathematical model of the motor, but the mathematical model of the motor does not consider the nonlinear loss of the motor, so there is a large error in actual use

[0006] In summary, the parameter identification of induction motors is a key issue in the field of motor control. The previous identification methods of induction motors have contradictions between the identification accuracy and the difficulty of obtaining training sets, that is, the motor model-driven method is used, and such methods do not require Data set, but the inaccuracy of the model leads to low identification accuracy and poor versatility; or use the motor data-driven method, which has high versatility and accurate identification accuracy, but it needs to obtain the data set in advance, and the acquisition of the data set is relatively difficult. difficulty

Images