Defect unit clustering method and its device
A clustering method and unit location technology, applied in electrical components, image data processing, instruments, etc., to achieve accurate defect clustering results and reduce computing load
Active Publication Date: 2018-05-04
SAMSUNG SDS CO LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, conventional clustering methods simply generate groups based on the distance between defect occurrence locations
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The advantages, features and methods for realizing the advantages and features of the present invention can be clearly understood with reference to the accompanying drawings and the embodiments described in detail later. However, the present invention is not limited to the following embodiments, but can be realized in various forms within the scope of the claims. This embodiment is provided to fully disclose the present invention and fully inform those skilled in the art of the scope of the invention, and the present invention is limited only by the scope of the claims. The same reference numerals denote the same structural elements throughout the specification.
[0037] Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used as meanings that can be commonly understood by those...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention provides a defect unit clustering method and its device, which further reflect the suspected defective equipment information of each product selected through the manufacturing history information of each product to cluster the defects. The present invention includes the steps of: generating a sample defect map, the sample defect map represents the distribution of defective units of defective samples according to unit positions, and the defective samples are composed of products that contain more than one defective unit among products that are divided into multiple units; in the sample defect map In , select at least a part of the unit positions with more than one defective unit as clustering objects; use the passing equipment information by product to select more than one suspected defective equipment for each unit position contained in the clustering objects; and The clustering objects are classified into more than one group so that the first unit location and the second unit location contained in one group have at least one suspected defective device, and a location is established between the first unit location and the second unit location relationship.
Description
technical field [0001] The invention relates to a device and method for clustering defects (defects) occurring in different positions of a product. In more detail, it relates to a method and an apparatus thereof for clustering defects of defective samples appearing on a defect map of defective samples composed of defective products by unit. Background technique [0002] When defects occur at different positions of the product, it is necessary to perform analysis on the stability of the product / process / equipment, such as Commonality analysis, History analysis, and Delay Time analysis, etc. Defects are clustered. [0003] However, the conventional clustering method is a method of generating groups simply based on the distance between defect occurrence positions. That is, in the conventional defect clustering method, short-distance defects are designated as one group regardless of the cause of occurrence of each defect. [0004] Patent Document: Korean Patent No. 0742425 C...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06K9/62
CPCG06T7/0004G06T2207/20072G06T2207/30121G06T7/45H01L22/20H01L22/00
Inventor 申启荣安大中朴志英姜智民
Owner SAMSUNG SDS CO LTD