永磁体的退磁检测方法、电子设备和装置
By using a deep learning model to identify the magnetic field strength distribution image of permanent magnets, the problem of inaccurately judging the demagnetization of permanent magnets in existing technologies has been solved, achieving high-precision and high-speed demagnetization detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI UNIV
- Filing Date
- 2025-03-14
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for detecting demagnetization of permanent magnets cannot accurately determine whether a permanent magnet has demagnetized, nor can they detect the degree of demagnetization.
A deep learning-based demagnetization detection model is used to identify the magnetic field intensity distribution image of a permanent magnet. The model acquires the magnetic field intensity distribution image and uses the DMG-IncepNeXt model to predict the demagnetization state. The model includes an input layer, multiple feature extraction networks, and an output layer. The feature extraction module contains a depthwise separable convolutional layer, a normalization layer, and a multilayer perceptron. Images are acquired by combining an ultrasonic sensor and a visual magnetic field color display.
It achieves higher precision and faster speed in permanent magnet demagnetization detection, with an accuracy of 96.2% and a detection time of 0.02 seconds.
Smart Images
Figure CN120219336B_ABST