A method and system for visual inspection of defects in CNC machine tool castings
CN118982539BActive Publication Date: 2024-12-31ZHANGJIAGANG HONGYI DUCTILE IRON CO LTD
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202411463220.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-21
- Publication Date
- 2024-12-31
- Estimated Expiration
- 2044-10-21
AI Technical Summary
Technical Problem
The existing CNC machine tool casting defect detection methods in factory assembly line environments have reduced image quality and low detection accuracy due to uneven surface reflection and light of castings.
Method used
By acquiring multiple segmented areas in the target casting image, dividing them into noise interference areas and casting structure areas according to the solid-state structural factor, the structural defect coefficient and structural information loss rate are calculated, and the image is adjusted to improve detection accuracy.
Benefits of technology
It effectively improves the image quality of castings, improves the accuracy of casting defect detection, and reduces the impact of noise interference on the detection results.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN118982539B_ABST
Abstract
The invention discloses a method and system for visual detection of defects in CNC machine tool castings, and relates to the field of image processing technology. The method comprises: obtaining multiple segmented areas in a target casting image; dividing each segmented area into a noise interference area or a casting structure area according to a solid structure factor of each segmented area, wherein the solid structure factor is used to characterize the probability factor that the segmented area is a solid structure; calculating the structural defect coefficient of each casting structure area to obtain the defective structure area in each casting structure area; determining the structural information loss rate of the defective structure area by using the structural richness coefficient, the structural defect coefficient and each noise interference area of the defective structure area; adjusting the target casting image according to the structural information loss rate of the defective structure area, so that casting defect detection is performed according to the adjusted target casting image.
Need to check novelty before this filing date? Find Prior Art