Continuous Casting, Computer Vision, Process Automation, Image Metrology, Digital Image Processing
Abstract
In the production process of steel slabs in continuous casting, the manufacture of products outside the specified length limits is a problem that can cause operational problems. Measuring the dimensions produced, such as the length of the board, is essential to ensure quality control and minimize impacts on production. Using image to measure dimensions is a common solution, however, this application in industrial environments with high temperature objects that require high precision is a difficult task. In this sense, this work presents the development of a system, based on computer vision, responsible for automatically measuring the length of steel plates produced in a continuous casting plant. The developed software performs the processing in a few seconds and provides information on measuring the length of the produced plate to field operators. The tests carried out presented results with an average absolute percentage error of 0.23%, showing technical feasibility of the application.
