Permanent magnet synchronous motor online efficiency optimization method

By optimizing the control of permanent magnet synchronous motors using a current prediction model, the problem that existing efficiency optimization methods cannot cover complex operating conditions is solved. This enables efficient and real-time optimization of the motor in dynamic scenarios and improves the motor's energy feedback efficiency.

CN122268230APending Publication Date: 2026-06-23CHONGQING VEHICLE TEST & RES INST CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610277874.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-09
Publication Date
2026-06-23

AI Technical Summary

Technical Problem

Existing efficiency optimization methods for permanent magnet synchronous motors are insufficient to cover the complex and ever-changing dynamic operating conditions in actual vehicle operation, resulting in a significant decrease in efficiency optimization under non-standard operating conditions and an inability to achieve adaptive optimization under all operating conditions.

Method used

A pre-trained current prediction model is used. The motor battery state parameters are obtained through the input layer, the first hidden layer, the second hidden layer and the output layer. After preprocessing, the parameters are input into the model and processed using Swish and Tanh activation functions to determine the current values ​​of the d-axis and q-axis, thereby achieving efficient control of the motor controller.

Benefits of technology

Under any combination of speed, torque, battery status, and temperature, it can quickly provide the optimal current distribution command, significantly improving motor efficiency. It is suitable for dynamic and severe braking scenarios, ensuring the smoothness of the braking process and real-time optimization capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122268230A_ABST
    Figure CN122268230A_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of electric machines, and relates to an online efficiency optimization method for a permanent magnet synchronous motor. For each preset fixed control period of a motor controller of a target vehicle, a motor battery state parameter in the fixed control period is acquired. The motor battery state parameter is preprocessed. The preprocessed motor battery state parameter is input into an input layer of a current prediction model, and then sequentially passes through a first hidden layer, a second hidden layer and an output layer to obtain a predicted current instruction. According to the predicted current instruction and a preset current constant, current values of d-axis and q-axis are determined, so as to control the motor controller according to the current values of d-axis and q-axis. Through the trained current prediction model, the best current distribution instruction can be quickly given under any combination of speed, torque, battery state and temperature, and the motor efficiency is significantly improved.
Need to check novelty before this filing date? Find Prior Art