一种基于模式识别的电感磁芯分类筛选方法
By constructing a network model of the air pore connectivity of inductor cores through multi-layer resolution scanning and graph theory analysis, the problem of evaluating the impact of air pore defects on magnetic properties was solved, and high-precision performance prediction and quality control were achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGDONG HUAYU TECH CO LTD
- Filing Date
- 2025-08-11
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to accurately assess the impact of internal porosity defects in inductor cores on magnetic properties. In particular, they lack the flexibility and depth of analysis capabilities to address the multi-scale characteristics of porosity distribution and complex network structures, leading to inaccurate performance predictions.
The image set is acquired by multi-resolution scanning, and a network model of pore connectivity is constructed by combining graph theory analysis. The connection strength and distribution density of key nodes are extracted, the magnetic permeability prediction feature vector is adjusted, and the performance level is predicted by pattern recognition. When there is a deviation, the image segmentation threshold is backtracked to optimize the accuracy.
It achieves high-precision prediction of inductor core performance, provides efficient quality control and material design support, and improves the accuracy of performance prediction through multi-scale analysis and dynamic calibration mechanisms.
Smart Images
Figure CN120976645B_ABST