School of Engineering Science
Since inspecting the quality of die-cast and hot-pressed metal components is mostly done manually, increased automation in this step would substantially increase the competitiveness of die-casting foundries and hot-pressed metal component manufacturers. The project therefore intends to develop, test, and evaluate vision systems for automating the quality inspection of die-cast and hot-pressed metal components.
By introducing automated inspection, companies could cut lead times, decrease waste, and make it easier for these companies to recruit new personnel, since it would eliminate a monotonous task prone to inducing repetitive stress injuries.
The customers of metal processing industries place very high demands on the quality of metal components, from the cosmetic perspective as well as dimensions, durability and safety. This in turn imposes very high demands on the industrial production processes and quality inspection methods used, because a metal component can have many different types of defects that can have a negative impact on its quality. Defects may be found inside the component, on its surface, or be of a geometric nature.
Due to these high demands from customers, there is great interest in the industry in being able to automate the quality inspection process. In this project, various camera systems for automated vision systems for the quality inspection of surface and geometric defects will be developed, tested and evaluated in order to arrive at the level of technical maturity required to enable the commercialisation and implementation of these systems at manufacturers of die-cast and hot-pressed metal components.
This scenario is assessed to be fully realistic in light of the fact that the automated detection of external (and for transparent materials also internal) defects has been implemented in other manufacturing industries, for example the plastics industry, and that both hardware and software development in automated quality inspections systems is moving rapidly forward.
The project will be carried out in two main steps. In the first step, a test bed will be set up at Swerea SWECAST, where the two vision system companies can gather image data and test their systems under production-like conditions. A third system that is based on cheap web cameras and open source code will also be developed in this project by RISE SICS, with some guidance from the University of Skövde. RISE SICS are currently running another project in which they are developing a similar system aimed at other businesses.
In the second step, tests will be carried out on the factory floor. The goal is to develop solutions that are close to a state where they can be implemented in die-casting foundries and at hot-pressed metal component manufacturers. This project is also important for the vision system companies, who will acquire generic knowledge that can be used for development aimed at other businesses and industries.