Ingot surface defect detection method, device and electronic equipment
By using a dual defect identification model and deep learning algorithms, the problem of misjudgment in the surface inspection of semiconductor ingots has been solved, and efficient and accurate defect type identification has been achieved.
CN119780091BActive Publication Date: 2026-09-04BYD CO LTD
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202411149736.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2026-09-04
- Estimated Expiration
- 2044-08-20
AI Technical Summary
Technical Problem
In existing technologies, semiconductor ingot surface inspection suffers from misjudgment of non-surface structural defect types, resulting in low accuracy and low efficiency.
Method used
A dual defect identification model is adopted. First, the surface defects are identified by the first defect identification model. If defects are found, the second defect identification model is used to further identify some surface data. Combined with deep learning and small-scale local point cloud processing algorithms, quality grade data is generated.
Benefits of technology
It improves the accuracy of defect detection, avoids misjudgment of non-surface structural defect types, and ensures the accuracy and efficiency of defect judgment.
✦ Generated by Eureka AI based on patent content.
Abstract
The application relates to a material ingot surface defect detection method and device and electronic equipment. The material ingot surface defect detection method comprises the following steps: inputting surface data of a to-be-detected material ingot into a first defect identification model to enable the first defect identification model to output a first defect identification result; when the first defect identification result indicates that the to-be-detected material ingot has a surface defect, inputting part of the surface data of the to-be-detected material ingot into a second defect identification model to enable the second defect identification model to output a second defect identification result; and generating quality grade data of the to-be-detected material ingot according to the first defect identification result or the second defect identification result. The detection method is accurate.
Need to check novelty before this filing date? Find Prior Art