Purpose and goal
Surface treatment (production) of commercial (trucks, cars, busses etc.) bodies is highly automated except for the inspection and evaluation of what to repair and adjust. Volvo Group has together with Umeå University and Volvo Cars identified a need for a real-time automated quality inspection and repair system for painted vehicle bodies. This is to reduce production costs, reduce environmental impact and create long-term cooperation between Umeå University and the Swedish automotive industry.
Expected results and effects
The project has developed a pilot system to automatically detect and classify defects on a painted surface and a test system for automated alarm and root case analysis. The systems have been tested at Volvo Trucks production plant in Umeå. The solution includes camera systems, algorithms for image analysis, alarm and root cause analysis as well as logic for communication and structuring of data.
Planned approach and implementation
The project has been carried out in close collaboration between the academia and industry, mainly at Volvo Trucks production plant in Umeå and Umeå University. The following activities have been carried out: - Evaluation of camera techniques. - Logics for data structuring. - Collection of production data. - Development of methods for image processing. - Development of classification methods. - Development of methods for alarms and root cause systems. Within the project, eight master thesis and one bachelor thesis work has been completed.