Automatic surface quality inspection for quantitative evaluation of stamped parts ...
Grant number: | 18/22005-8 |
Support Opportunities: | Research Grants - Innovative Research in Small Business - PIPE |
Duration: | July 01, 2019 - August 31, 2021 |
Field of knowledge: | Engineering - Mechanical Engineering - Manufacturing Processes |
Convênio/Acordo: | FINEP - PIPE/PAPPE Grant |
Principal Investigator: | Enivaldo Amaral de Souza |
Grantee: | Enivaldo Amaral de Souza |
Host Company: | Autaza Tecnologia S/A |
CNAE: |
Fabricação de máquinas e equipamentos para uso industrial específico não especificados anteriormente Fabricação de automóveis, camionetas e utilitários |
City: | São José dos Campos |
Abstract
The automotive industry manufactures the car body using metal sheets that are shaped by the stamping process. The quality control of these parts is of extreme importance, since the first impression the consumer has of a car is by observing the exterior appearance. An unmarked and smoothly contoured exterior surface suggests technical superiority of the manufacturer over its competitors. In the early stages of production, irregularities often go undetected to the human eye due to the lusterless appearance of the unpainted metal. These same undulations with millimetric depth, however, become visible and disturbing when the automotive parts are painted and become mirrored. To inspect unpainted parts by comparing the lamp reflection, a reflective oil is used on them. However, the oil application and removal process is not suitable for mass production, making it difficult to visualize body defects prior to painting. As at every stage of the production process, the added value of the parts increases, the later the defects are identified, the more expensive the costs are to repair them, wasting millions of dollars in the automotive industry. This project presents an automated quality inspection solution for unpainted automotive parts using three-dimensional scanning, which will improve the objectivity and reproducibility of the inspection. The product of this project is a Robotic 3D Scanner, containing equipment and software to assist the automotive industry to ensure the quality of their products during manufacture. Cameras are used to capture images of the body of the car, which is illuminated with a special light projector that projects a zebra pattern on the body. The software reconstructs the three-dimensional surface of the car, performs the analysis and creates an automatic report that shows the defects identified and their classification using colors, facilitating communication for the correction teams. The company AUTAZA is a startup in the field of computer vision and quality inspection for the industry, started in 2016 from a project between university (Instituto Tecnológico de Aeronáutica) and automotive industry (General Motors). In 2017 and 2018 Autaza obtained PIPE Phases 1 and 3 projects for the creation of an equipment for the inspection of defects in painted automotive parts. The main differential of its products is to deliver, not only the metrology, but a recommendation of the severity of the defects. (AU)
Articles published in Agência FAPESP Newsletter about the research grant: |
TITULO |
Articles published in other media outlets (0 total): |
More itemsLess items |
VEICULO: TITULO (DATA) |
VEICULO: TITULO (DATA) |