Hardware part defect detecting system and method

Abstract

The invention provides a hardware part defect detecting system and a method. The hardware part defect detecting system comprises an image acquisition module, a defect information extraction module, a artificial neural network training module, and a defect identification module; the image acquisition module is used for acquiring standard images of hardware parts and corresponding defect sample images, performing image gray-scale treatment and image de-noising processing, and obtaining standard images and defect sample image gray-scale treated images; the defect information extraction module is used for extracting defect characteristic values of defect sample images using a defect minimum bounding box position extraction unit and a defect characteristic extraction unit; the artificial neural network training module is used for training artificial neural network via BP algorithm and the defect characteristic values of the defect sample images. According to the hardware part defect detecting system, the trained artificial neural network is used for identifying the defect kinds and defect positions of the hardware parts to be detected, hardware part surface defect automatic detection is realized, hardware part surface defect detection efficiency is increased, and manpower, material resources, and financial resources are saved.

Description

technical field [0001] The invention relates to the technical field of component defect detection, in particular to a hardware component defect detection system and method. Background technique [0002] In modern society, hardware parts are ubiquitous in life, and have been widely used in various industries such as electronics, chemical industry, and aerospace. Since the contour, shape, and size of each part in the hardware parts must be consistent with the accuracy of the original design to meet the production requirements, in the rapidly developing industrial environment, detecting part defects is one of the indispensable links in the processing industry. At present, most factories mainly rely on artificial naked eyes to detect surface defects of hardware parts. This method is not only inefficient but also prone to false detection or missed detection due to the visual fatigue of the staff. Even if the staff finds the surface defects of hardware parts , and can only rely o...

AI Technical Summary

Problems solved by technology

At present, most factories mainly rely on artificial naked eyes to detect surface defects of hardware parts. This method is not only inefficient but also prone to false detection or missed detection due to the visual fatigue of the staff. Even if the staff finds the surface defects of hardware parts , and can only rely on naked eye positioning for reprocessing, which can easily cause secondary processing defects. If the workpiece is discarded directly, it will cause waste of resources

Therefore, manual detection of component defects not only consumes a lot of human resources, but also has low detection efficiency and poor effect

Images