A Online Detection Method for Surface Defects of Bushing Parts Based on Compressive Sensing

Abstract

An online detection method for surface defects of shaft sleeve parts based on compressed sensing. This method adopts machine vision and compressed sensing methods to establish a compressed sensing description of surface defect images of parts, and establishes optical imaging and defect detection models that highlight surface defects; collect typical Denoising and necessary image preprocessing are performed on the sample image of the defective part, then the sampling frequency is adjusted and the size is normalized, the training sample is established and a redundant dictionary is established; an appropriate orthogonal basis decomposition matrix and random observation matrix are designed, and the joint Orthogonal matching pursuit algorithm converts solving the minimum norm into a suboptimal solution problem to reconstruct the defect image, calculates the sparse representation of the image to be tested, and identifies the defect of the part to be tested according to the established judgment and recognition standard. Construct an online inspection system with functions of feeding, positioning and adjustment, image acquisition, image processing, defect detection and discrimination, parts sorting, etc., to realize rapid detection of surface defects of shaft sleeve parts.

Description

technical field [0001] The invention relates to an online detection method for surface defects of shaft sleeve parts based on compressed sensing, and belongs to the technical field of online nondestructive detection of mechanical parts. Background technique [0002] With the gradual transfer of the global manufacturing center to my country, while the production and manufacturing capacity continues to expand, people also put forward higher and higher requirements for product quality. Product surface quality is an important part of it, and it has an important impact on the direct use or deep processing of the product. The existence of surface defects in some application fields may cause huge losses to users, and strict detection and control must be carried out. [0003] Shaft sleeve parts are mainly used for supporting, guiding and positioning. They are widely used in various machines and instruments. They are generally made of steel, cast iron, bronze or brass. During the p...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose an online detection method for surface defects of shaft sleeve parts based on compressed sensing, according to the problems of large amount of collection, low data utilization rate, and poor real-time performance in the detection of surface defects of existing mechanical parts.

Images