Method for detecting defects of bearing sealing element based on vision

Abstract

The invention discloses a method for detecting defects of a bearing sealing element based on vision. The method includes the steps: obtaining a bearing sealing element image; treating the bearing sealing element image by using an image segmentation and target association method, to obtain a workpiece image of the bearing sealing element; calculating the workpiece image by using a workpiece range, to obtain an effective workpiece image of the bearing sealing element; treating the effective workpiece image by using a workpiece range comparison and direction difference judgment method, to obtain a burr defect; treating the effective workpiece image by using a histogram analysis method, to obtain a right-side workpiece image and a reverse-side workpiece image; treating the right-side workpiece image by using a color significance and rectangle feature judging method, to obtain a chromatic aberration defect; calculating the reverse-side workpiece image by using a metal range, to obtain a workpiece metal part image; and treating the workpiece metal part image by using a brightness significance and color transformation method, to obtain glue overflow and corrosion defects. The method solves the problem of on-line detection of the bearing sealing element, and improves the automation level.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of machine vision, and in particular, to a vision-based defect detection method for a bearing seal. Background technique [0002] At present, my country's bearing manufacturing industry is still dominated by traditional products, and the technical level is not high. The impact of this is that domestic bearing production is still mainly labor-intensive, with high overall output, but low technical content, low precision, The added value of the product is low, and the quality cannot be guaranteed. Although a few domestic bearing manufacturers have introduced some automatic and semi-automatic bearing manufacturing equipment from abroad, and formed the production capacity of some high-precision bearing products, the quality of products cannot be guaranteed because the detection methods are mainly manual detection and offline random inspection. , unable to meet the quality requirements of for...

AI Technical Summary

Problems solved by technology

However, the existing visual inspection system cannot be applied to the on-line detection of bearing seals. The main reasons are: 1) The pattern of bearing seals is relatively complex, with various colors, and there are front and back sides, and the area of ​​the metal area of ​​the back seal The difference is very large. 2) There are many types of defects on the bearing seals, including burrs, color difference, glue overflow, rust, etc. 3) The accuracy of the detection of bearing seal defects is very high, and the detection accuracy of burrs is usually required to be 0.1mm 2 Even higher, so it is necessary to use a high-resolution image sensor (3 million pixels or 5 million pixels), which puts forward higher requirements for the efficiency of visual image processing methods

Images