Visual detection method for mechanical component defect

Abstract

The invention discloses a visual detection method for a mechanical component defect. Defect parts in the mechanical component and on the surface of the mechanical component can be continuously scanned, and an acquired image can be processed and analyzed to acquire the area of the surface and internal defects, the barycentric coordinates of the defects and the defect shapes, so that operating personnel can see the defect parts clearly; then a three-dimensional model about the surface texture, color feature and internal structure of the mechanical component is recovered via three-dimensional reconstruction reverse engineering design, and thus the surface and internal defect positions and the defect range of the mechanical component are displayed, and the three-dimensional reconstruction system of the defect is displayed as a three-dimensional PDF document.

Description

technical field [0001] The invention relates to a visual detection method, in particular to a visual detection method for defects of mechanical parts. Background technique [0002] With the development of industrial technology, the processing method of mechanical parts presents a development trend of high precision, high speed and automation. The traditional contact detection method is slow, which is easy to cause damage to the parts and will reduce the measurement accuracy. The measurement technology based on computer vision has the advantages of With the advantages of high speed, good real-time performance, non-touch, low cost, etc., it is widely used in the precise detection of processing defects of various parts. [0003] Testing and inspection is one of the most basic activities in the manufacturing process. Through testing and inspection activities, the quality information of the product and its manufacturing process is provided, and the manufacturing process of the pr...

AI Technical Summary

Problems solved by technology

[0002] With the development of industrial technology, the processing method of mechanical parts presents a development trend of high precision, high speed and automation. The traditional contact detection method is slow, which is easy to cause damage to the parts and will reduce the measurement accuracy. The measurement technology based on computer vision has the advantages of With the advantages of high speed, good real-time performance, non-touch, low cost, etc., it is widely used in the precise detection of processing defects of various parts

[0003] Testing and inspection is one of the most basic activities in the manufacturing process. Through testing and inspection activities, the quality information of the product and its manufacturing process is provided, and the manufacturing process of the product is controlled according to this information—correction and compensation activities are carried out to make waste The rate of products and repaired products is reduced to a minimum, ensuring the stability of the product quality formation process and the consistency of the output products; the traditional inspection and inspection mainly rely on people, and are mainly completed by hand, which is time-consuming and expensive. The production cycle increases and the production cost increases; at the same time, the traditional inspection and testing activities are mainly carried out after the manufacturing process, once the defective products are detected, the loss has already occurred; in addition, the information based on manual inspection often contains human errors According to the influence of such information, the control of the manufacturing process according to such information is not only implemented after the process, but also introduces human errors; therefore, this information cannot be relied on to achieve real-time or on-machine process control; new inspections and inspections often It is based on a variety of advanced sensing technologies and is easy to combine with computer systems; with the support of appropriate software, this type of automatic detection or inspection system can automatically complete data collection, processing, feature extraction and identification, and multiple analysis and calculation

Images