Battery connector quality detecting method based on machine vision

Abstract

The invention discloses a battery connector quality detecting method based on machine vision. A connector template data set is built; images of detected connectors are acquired; acquired original images of the battery connectors are cut to obtain images of rectangular window areas; the cut images are aslant corrected to obtain corrected images; the images are reconstructed until the images finishpretreatment; after the images are pretreated, positions of the connectors, connector FPC substrate copper exposure, connector central area defects, connector hardware part defects and connector plastic part detects are respectively detected by adopting independent detecting methods; detecting templates are updated in real time by adopting dynamic template update mechanisms; a coordinate system isbuilt based on the corrected images; the defects are classified, positioned and marked; detecting results are output; common quality problems of inclination / deflection, FPC plate copper exposure, hardware defects, plastic defects and central area defects of the connectors can be detected; and excellent instantaneity and higher detecting rate are achieved.

Description

technical field [0001] The invention belongs to the technical field of machine vision automatic surface defect detection, and in particular relates to a machine vision-based battery connector quality detection method. Background technique [0002] Detecting the battery protection board connector is an important step in the battery assembly process. The battery FPC connector is affected by the incoming material itself or the battery assembly process, which will cause poor appearance, such as connector offset / skew, connector welding Less tin / more tin, damaged and deformed connector plastic body, deformed / missing hardware parts, dirty connector, etc. These defects can directly lead to poor product functionality and affect product performance. Therefore, this process has become an important link in product quality monitoring. [0003] At present, domestic products still use traditional manual inspection methods, that is, use simple CCD projection equipment or magnifying glasses...

AI Technical Summary

Problems solved by technology

However, the technology is not yet free from human intervention and is slow, so its application is limited

For the application of automatic visual inspection, some inspection systems have appeared in China, but they are mainly used for low-end inspection, while some advanced automatic inspection equipment abroad are expensive, making it difficult for many domestic enterprises to accept

Images