Nut defect detection method and device based on machine vision

Abstract

The invention relates to the field of part defect detection, in particular to a nut defect detection method and a device based on machine vision, and aims to improve the defect detection efficiency ofnuts. The method comprises the following steps that firstly, a top view image, a side view image and a squint image of the nuts are acquired, and binarization processing is carried out on the three images; and then the characteristic parameters of the nuts to be detected are extracted on the image subjected to binarization processing, compared with a preset characteristic parameters, whether theinner diameter of the nuts to be detected is too large or too small, the upper groove is cut over, the upper groove is not opened, the upper groove is opened reversely, the number of the outer groovesis not consistent, the outer grooves are arranged upside down, the inner threads are not opened, the nuts are in lap joint with other nuts or not are judged, and then the to-be-detected nut is classified, so that waste products, secondary products, abnormal products and qualified products can be distinguished. Compared with the traditional manual detection, the method and device can efficiently detect all nuts one by one, the production efficiency is greatly improved, and the qualified rate of the delivery nut is remarkably improved.

Description

technical field [0001] The invention relates to the field of component defect detection, in particular to a machine vision-based nut defect detection method and device. Background technique [0002] Nut is a basic part that tightly connects mechanical equipment. It has been widely used in many fields such as automobile manufacturing, construction, machinery, rail transit, public facilities, and foundry industry. Due to different materials, specifications, technical requirements, etc., there are various types of nut products on the market. Affected by the complex and changeable production process, different equipment operation and maintenance conditions, and improper manual setting operations, there is a certain proportion of defective products in the nuts produced by the automated assembly line. Typical defects are: [0003] 1) The inner diameter of the nut is too large or too small, so that the nut and the bolt or screw cannot be screwed together or the bite force cannot ...

AI Technical Summary

Problems solved by technology

[0003] 1) The inner diameter of the nut is too large or too small, so that the nut and the bolt or screw cannot be screwed together or the bite force cannot reach the corresponding standard after screwing together

Such nuts are generally treated as scrap as defects are difficult to resolve with simple rework;

[0004] 2) Lack of craftsmanship, typical examples include unopened internal threads, unopened upper grooves, etc. Such defects are mainly caused by missing specific processing steps during production and processing

[0005] 3) The upper groove is reversed, and the nut is not placed correctly on the production line, for example, the bottom is facing upwards, resulting in the subsequent processing. The groove process that should be performed on one side of the nut is wrongly implemented on the other side, and the entire nut becomes a waste product

However, nut production has the characteristics of low single product value and large quantity base. It is unrealistic to realize comprehensive nut quality inspection manually

At present, nut production enterprises usually adopt the quality inspection method of manual random inspection. This method can find a large number of continuous nut quality problems, but it has no obvious effect on sporadic quality problems, and the latter is not used in actual production. rare

Images