Detection method and device of surface defect of mechanical part based on machine vision

Abstract

The invention discloses a detection method and device of surface defect of a mechanical part based on machine vision. The detection method comprises the steps of: carrying out positioning, filtration, enhancement, binaryzation, morphological treatment, boundary tracing, characterization extraction and the like on the collected surface images of the mechanical part; and judging whether a defect exists through the size of a defect area or not. The detection device comprises a position transmission module, a position control module, a clamp, an image collecting module and an upper computer for processing the image and sending a position control instruction, wherein under the control of the upper computer and the position control module, the position transmission module can move in an X direction, a Y direction and a Z direction, and can rotate around a Z axis; the image collecting module comprises a camera and a light source; and the camera and the position control module are respectively connected with the upper computer. By using the detection method and device, nondestructive detection is carried out based on the machine vision, irregular parts can be detected, no demagnetization problem exists; and the detection method and device have the advantages of high detection precision and high efficiency.

Description

technical field [0001] The invention relates to the field of surface detection research, in particular to a method and device for detecting surface defects of mechanical parts based on machine vision. Background technique [0002] During the processing and production of mechanical parts, it is often necessary to detect and measure them, because most of the mechanical parts are used to bear a certain pressure or perform a large amount of reciprocating motion, so once the produced mechanical parts are abnormal, it may cause The entire system collapses, even with catastrophic consequences. For example, the crankshaft is the main rotating part of the engine. After the connecting rod is installed, the up and down (reciprocating) motion of the connecting rod can be changed into a circular (rotating) motion, which is an important part of the engine. As a power connector of various engines, if there is an abnormality, it may cause serious consequences. Therefore, the roughness dete...

AI Technical Summary

Problems solved by technology

For the testing of mechanical parts, there are generally two methods at present, one is ultrasonic testing, and the other is magnetic testing. However, since ultrasonic testing is suitable for testing relatively regular tubular parts, although the detection speed of magnetic testing can basically reach Requirements, but can not be completely demagnetized, which may have a huge impact on the performance of the engine, and the process is more complicated

At present, the traditional detection method usually judges the surface defects of the crankshaft manually based on its experience and visual observation, which is not only inefficient, but also high in labor costs, labor-intensive, and error-prone, which cannot meet the needs of today's high-speed production

Images