Standardized detection system and method for postures of parts in semi-closed cavity

Abstract

The invention discloses a standardized detection system and method for postures of parts in a semi-closed cavity. The standardized detection system comprises a material conveying module (1), an image acquisition module (2), an image analysis module (3) and a material screening module (4), wherein the material conveying module (1) conveys materials in the semi-closed cavity into an image acquisition area of the image acquisition module (2); the image acquisition module (2) is used for performing image acquisition on parts in the semi-closed cavity material when the semi-closed cavity material reaches a specified position; the image analysis module (3) analyzes the image received by the image acquisition module (2) and judges whether the image is qualified or not; and the material screening module (4) is used for respectively collecting qualified or unqualified semi-closed cavity materials in the material conveying module (1).

Description

technical field [0001] The invention relates to the application of deep learning in industrial inspection, in particular to a part attitude standardization detection system based on deep learning. Background technique [0002] In the actual production process, equipment is often assembled from parts of different structures, and in many cases the parts will be assembled in the structure of a semi-closed cavity. There is a need to detect whether the part has defects, but it cannot be directly observed from outside the structure The state of the part. Such as: the production and assembly of ballpoint pens. [0003] A ballpoint pen is a writing instrument in which ink is brought out by a ball rolling on the tip of the pen and transferred to paper. There are many types of ballpoint pens in terms of appearance and structure, such as: plug-in ballpoint pen, which is a ballpoint pen appearance structure. It is divided into two parts: the pen holder and the pen cap in appearance. ...

AI Technical Summary

Problems solved by technology

And in practical applications, due to different light intensity, dust interference, or slightly different part postures from the template, good products will be misjudged as defective products. The machine vision template matching method has cumbersome operations, low versatility, and is greatly affected by environmental factors. and other shortcomings

Images