Statistical process control method based on image-data variable window defect monitoring

Abstract

The invention discloses a statistical process control method based on image-data variable window defect monitoring. The method comprises the following steps of step1, acquiring an image; step2, carrying out image preprocessing; step3, acquiring an ideal image; step4, performing variable window monitoring; step5, calculating a maximum likelihood ratio statistic amount; step6, determining an upper bound of a control chart; and step7, drawing the control chart. The method has advantages that before the maximum likelihood ratio statistic amount is calculated, division and extraction of a variable area where variation is possible to generate are performed, calculation of most of normal areas is eliminated and a calculation amount is greatly reduced; and simultaneously, instead of using a fixed block to divide a whole image, the areas where variation is possible to generate are marked so that a monitored variable area range is a real variable area range and monitoring accuracy is increased.

Description

technical field [0001] The invention relates to a statistical process control method based on variable window defect monitoring of image data, which belongs to the field of quality control in the product manufacturing process. Background technique [0002] During the manufacturing process of the product, there will be many factors that lead to the variation of the manufacturing process state and the decline of product quality. In the traditional product quality inspection, the quality inspection is usually carried out after the product manufacturing process is over, and the unqualified products are scrapped or recycled, which not only takes up effective manufacturing time, wastes resources, but also reduces the yield rate. In order to solve this problem, the statistical process control method can be used to monitor the product manufacturing process in real time. [0003] Statistical process control is a series of methods that apply mathematical statistics tools to deal with...

AI Technical Summary

Problems solved by technology

Megahed (Megahed, F.M "The Use of Image and Point Cloud Data in Statistical Process Control," (the use of image data and point cloud data in statistical process control) PhD Thesis, Virginia Polytechnic Institute and State University, 2012.) The image is divided into multiple small areas according to a fixed window, and statistics are calculated and compared for different areas of each image, and finally the region where the variation occurs and the image sequence number are located. However, this method requires a large amount of calculation and the accuracy of locating defects Poor, with a fixed window, which prevents it from matching defect areas well

The surface image of the product contains a lot of information about the quality of the product, the graphics are diverse, and the graphics of each layer may be different, and the existing methods cannot be directly applied to the statistical process control

Images