Objective
The project aims to develop a guaranteed and reliable on-line quality assurance system using artificial intelligence, which will detect defective joints during the resistance spot welding process. Resistance spot welding is relatively easy to integrate in automatic plants. Therefore it is one of the most important welding methods used in industrial series and mass production with welding machines and welding robots. It is also used in manual single-piece production in the workshop sector, when sheet-sheet, wire-wire or wire-sheet joints are to be made. The spectrum of applications includes car body construction in the automotive industry, apparatus engineering, production of electrical appliances and household devices, as well as the production of small electrical components. Unfortunately, up to now, security aspects forbid the general usage of resistance spot welding as the quality of the joint cannot be guaranteed. At the moment quality variations of the welding joints realised by resistance spot welding are observed, due e.g. to voltage fluctuations or wear of electrodes. Currently it is impossible to control during the welding process (on-line) the quality of the welding joint. Even at the end of the welding process, the quality of the welding joint cannot be verified in a reliable way by non-destructive test methods using ultrasonic waves or x-rays. For this reason, at the moment random destructive testing is the only reliable method. Furthermore additional ,,safety points" are welded in order to guarantee that the overall strength of the joint is sufficient. This quality assurance method is timeconsuming and leads to extremely high production costs in safety relevant areas. Through the new control system with neural networks developed in the project, it will be possible for example to use resistance spot welding also for assembling very stressed parts of the car body. The industrial objectives to be achieved in this project are: - The quality evaluation time has to be < 200 ms, in order to not lower the welding speed. - Various estimations assume that up to now 1-2% of the welding spots, which are of non-sufficient quality, are not detected. Therefore quality reliability shall be >99%. - The on-line quality control system developed in this project will be cost effective and capable of being integrated in future control systems without expensive sensor technology. The increase in the price of the welding control system due to the integration of the quality insurance should not be more than approximatively 2.500 ECU, in order to obtain a good market acceptance. - It is expected to reduce the quality control costs bv at least 20 to 30%. - The control system will be tested on strategical important advanced materials categories for the automotive and electrical engineering industries, like coated steel, aluminium and non-ferrous metals. This new technology will allow the combination of high quality welding joints with low production costs. At the end of the project two precompetitive prototypes of quality control systems using artificial intelligence for the automotive industry and the electrical industry respectively will be available. About one or two years of additional testing will be necessary to bring this new quality control system of resistance spot welding on the market. The aims of the project are focused on the area 2.3 ,,Reliability and quality of materials and products" and area l . l "Incorporation of new technologies into production systems of the workprogramme. Especially relevant are the research tasks 2.3.1 .S, 2.3.4.M and l . l . l .M.
Fields of science
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringcontrol systems
- engineering and technologymechanical engineeringvehicle engineeringautomotive engineering
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensors
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectrical engineering
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
Call for proposal
Data not availableFunding Scheme
CSC - Cost-sharing contractsCoordinator
HAMBURG
Germany