Image-processing-based automatic micro part sorting system

Abstract

The invention provides an image-processing-based automatic micro part sorting system. The system comprises a workpiece screening module, a detection module, a software control system and a detection postprocessing module, wherein the detection module is positioned on the two sides of a rail of the workpiece screening module and connected with the software control system on a computer through a data line; and the detection postprocessing module is directly connected with the detection module and controlled by the software control system of the computer. By the system, the problems of low part surface quality detection efficiency, a high omission factor and high labor cost in the conventional micro part production process are mainly solved; and micro cylinder parts can be detected and sorted on line, particularly defects such as bumps, scratches, cracks and pits on the surfaces of the parts can be accurately distinguished and removed, the yield of the sorted products is ensured, and high sorting speed is achieved.

Description

technical field [0001] The invention relates to a fast sorting system, in particular to an automatic sorting system for tiny parts based on image processing. Background technique [0002] Tiny parts refer to parts whose outer geometric dimension is less than 5mm. Due to the wide application of tiny parts in military, civilian and industrial products, the surface defect detection of parts is an important part of part quality inspection and precision control in part production. The traditional detection of small parts still relies on manual detection. Due to the small size of the detected parts, manual detection is labor-intensive, and the efficiency is low, and the missed detection rate is high, which will inevitably cause defects in the quality control of parts. Therefore, an online automatic detection is urgently needed. system. Although image processing technology is used in many inspection fields, most of them are for the detection of larger parts, or for the detection ...

AI Technical Summary

Problems solved by technology

In the production of small parts, the general production cycle is short and the number of products is large, but the current detection methods are difficult to meet the detection accuracy and resolution requirements, and the detection speed requirements, especially when the detection speed is required to reach More than 3000 pieces per minute

[0003] Among the existing patents, the invention patent CN101832951A discloses an "on-line detection method for surface defects of PVC circular pipes based on machine vision system", which is mainly aimed at detecting the surface quality of large pipes, and its detection method is limited to large sizes Parts, and do not need to detect the work of automatic screening and sorting in the early stage and automatic rejection in the later stage, it cannot meet the requirements of the sorting speed proposed in the detection of small parts, so it is not suitable for the sorting of small parts

[0004] From the currently published literature "Automatic detection device for the geometric size of tiny parts" ("Ordnance Industry Automation" in December 2009), it can be seen that it mainly detects the size of tiny parts, but cannot realize the unevenness and pitting in the end face circle. , crack detection, etc.

[0005] In summary, in order to overcome the problems of difficult screening of tiny cylindrical parts, large mutual interference and high detection resolution, and at the same time need to detect defects such as unevenness, scratches, cracks, pitting and other defects on the surface of parts, it is necessary to develop a A new type of sorting system for tiny parts

Images