Quality monitoring in industrial painting through image processing in the context of digitalization

• Grant number: 21/00745-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2021
• End date: July 31, 2022
• Field of knowledge: Engineering - Mechanical Engineering - Manufacturing Processes
• Principal Investigator: Sidney Bruce Shiki
• Grantee: Matheus Chiaramonte Rocha
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

Monitoring the quality of industrial paint is very important to avoid future wear on the paint as well as to increase the quality of the final finish. However, such monitoring usually requires the use of sensors and other high-cost elements, so its use is discarded as it is not a financially viable option. In this sense, the present research will study the possibility of using low-cost components, such as a camera and a Raspberry Pi hardware, to make the function of more expensive sensors. Thus, with the use of the mentioned components, an analysis will be made on specimens with defective paint and also with paint without defects, so that later the comparison between the two can be made. The images will be processed using an algorithm in Python, which will apply an edge identification method called Local Binary Pattern. Once this processing is done, metrics will be calculated on the defect(s) found, such as aspect ratio, thickness, area, and others. To determine the type of defect found and also check if there is a difference between the images of defective and non-defective specimens, a statistical method will be used, obtaining the mean and standard deviation and then a hypothesis test will be carried out. Finally, the results obtained will be uploaded to a Thing Speak server using IoT techniques, and with the data obtained, a database will be built in SQL to store and organize all search results. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

PEREIRA, FRANCO ROCHA; RODRIGUES, CAIO DIMITROV; DA SILVA E SOUZA, HUGO; NETO, JOSE OLIVEIRA CRUZ; ROCHA, MATHEUS CHIARAMONTE; BARBOSA, GUSTAVO FRANCO; SHIKI, SIDNEY BRUCE; INOUE, ROBERTO SANTOS. Force and vision-based system for robotic sealing monitoring. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, v. N/A, p. 13-pg., 2023-02-27. (19/22115-0, 21/00367-8, 21/00745-2)