SMART MANUFACTURING
INSPECTING WELDED CONNECTIONS IN THE AUTOMOTIVE INDUSTRY – USING AI
Machine vision combined with artificial intelligence makes it possible: the technology automatically inspects welded connections in body shells and identifies anomalies. The Spanish automation specialist DGH has developed such an application for the automotive industry. It improves the consistency, speed, reliability, and accuracy of the entire inspection process – and does so completely autonomously. The machine vision solution was developed by DGH using the software products MVTec HALCON and the Deep Learning Tool from MVTec.
H
igh quality standards are required in automotive production. This naturally also applies to welding processes on the body-in-white (BIW). The importance of body stability is self-explanatory. More exciting is the question of how the high quality of welded connections can be ensured – automatically and seamlessly. The challenge is that many different defects can occur which impair the quality of the bodywork. For example, cracks, incomplete weld seams and irregular welding patterns must be precisely identified. DGH tackled exactly this challenge. The Spanish company, which has its main headquarter in Valladolid and recently has been integrated in GROUPE ADF, supports a wide range of industry segments with innovative solutions for process automation. The result is an inspection system that automatically captures images of welded joints. These are then immediately checked by the MVTec HALCON AI algorithms and DGH machine vision software. It sends the results – OK or NOK – to the PLC. This controls how to proceed with the bodywork accordingly. MVTec HALCON is the standard software for machine vision from MVTec. The Munich-based family business has been developing hardware-independent machine
vision software for industrial applications since it was founded in 1996 and is one of the technology leaders in this field – partly because the company offers various powerful deep learning algorithms.
DEEP LEARNING IN PRODUCTION: OPTICAL INSPECTION OF WELDED CONNECTIONS Deep learning is a type of artificial intelligence. In machine vision, deep learning enables the implementation of more and more applications, including those that were previously not possible. In addition, the performance of existing applications can be significantly improved. DGH has also taken advantage of these developments. On behalf of a large French automotive group, DGH’s team of experts developed an automated system for inspecting welded connections between metal parts for inert gas welding (MIG welding) processes. “Previously, the inspection was always carried out by long-serving employees. This is because it is not always easy to recognise whether the quality of the welded connection from the different processes is OK. When implementing the new system, we therefore incorporated the experience of such employees. We have trained the underlying deep learning networks with their knowledge. The required
robust recognition rates are only possible using deep learning,” explains Guillermo Martín, innovation and technology director at DGH. The primary aim of the implementation was to achieve a very high-quality standard for all weld seams. In addition, the new, autonomous quality inspection was intended to bring the fundamental advantages of automation to bear. Namely, greater speed, reliability, accuracy and clear consistency in decision-making – in contrast to the subjectivity of human decision-making.
DGH ACHIEVES CLEAN PROCESS INTEGRATION OF MACHINE VISION Implementing such a system involved several challenges. “It was clear to us that we had to implement the system based on machine vision. Sensors or classic 2D/3D vision systems fail due to the complexity of the weld seams. The first challenge was therefore to develop a viable solution and reliably detect the different types of defects. Additionally, the second challenge involved transferring the expertise of experienced employees into the deep learning application. Finally, the third challenge was to carry out the inspection processes in a short time. The reason for this is the tight cycle times,” explains Martín. The system that has now been implemented at the French car manufacturer works as follows: When a body arrives at the inspection station, the PLC triggers various inspection processes. When the station receives a trigger, the attached 2D cameras take photos of the welded connections individually or one after the other and transmit them via GigE Vision protocol to the machine vision software, where they are processed. The system checks whether anomalies can be detected around the weld seams. It can reliably inspect different weld joints, seams, and spots created during various welding processes. The data is then sent to the PLC
18 Autumn2025 UKManufacturing
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48
