44 n TRANSPORT July/August 2025 www.drivesncontrols.com AI and 3D are helping car-makers with QC I recently heard a podcaster interviewing the CEO of one of the biggest tech companies in the world. He made a good point: it is the companies and industries that use AI to boost productivity and grow the economy that will be the real winners from AI, not the tech companies and supply-side hype that we’re drowning in today. Some automotive manufacturers are further ahead than others, but everyone is looking for advice and partners who can help turn AI investments into real value – and they’re turning to machine-builders and SIs (systems integrators) for answers. 2D and 3D data for AI As the pace of AI in vehicle manufacturing speeds up and the requirement to use operational data becomes more urgent, leaders in engineering and quality inspection need expertise. But a lot of data is being missed – generated on the frontline and then locked up and siloed in devices, systems, sites and workflows. This data offers huge potential for AI model testing and training, especially more advanced deep learning models that improve and adjust over time – known as intelligent automation. According to a study of attitudes to manufacturing vision conducted by Zebra Technologies, industrial leaders say their most significant quality management issues are real-time visibility (28%), integrating data (26%), and maintaining traceability (23%). These all relate to the ability to capture, share, and analyse data using the most appropriate scanning, camera, and 3D sensing hardware and software. Machine vision specialists are using increasingly smarter cameras and sensors to build intelligently automated solutions that capture much higher quality 2D and 3D visual data at high speed for deep learning model training, testing and deployment on the frontline via devices and PCs. Automotive successes I recently read a good example of how manufacturing data is being used to great effect in an AI application. Some automotive OEMs have been able to cut defect rates by 10-15% in their quality inspection processes for items as complex as car doors, which can contain up to 80 components. They are also simplifying production lines, cutting maintenance costs and system complexity. One machine vision SI has created a system based on dualcamera, single-laser 3D sensor hardware integrated with AI software. The 3D sensor scans items such as car doors, capturing thousands of data points, and turns them into detailed point cloud and depth map representations for the AI software to inspect for defects. This scalable, adaptable technology is now also being used in other sectors such as pharmaceuticals and food. In another example, a supplier of surface treatment technologies collaborated with a machine vision SI to improve the production quality of caps that car-makers use to protect high-voltage batteries from external influences. The system consists of vision-guided robots using no-code, flowchart-based machine vision software with deep learning. A robot arm manoeuvres the battery caps through various stages of inspection, guided by a camera system to check for defects that could affect quality and performance. The SIs highlight the software’s development speed and rapid execution times when analysing many – and sometimes large – image files simultaneously, as well as the ability for continual improvement across the manufacturing process using deep learning models. This is the result of extensive training using a large, annotated dataset to recognise and classify certain types of defects using images. As automotive OEMs continue to transition to electric vehicle manufacturing, we are seeing how machine vision, 3D sensing and AI are supporting other frontline operations. For example, detecting defects in battery cells and assessing the size and integrity of tabs and connectors, which can be problematical because of reflections from the metallic surfaces. Using 3D sensors can help combat the lack of contrast by scanning surfaces accurately to reveal surface imperfections. 3D profilers and sensors can also inspect welding and sealing areas and bead thickness, dimensions, and position with micron-level accuracy. It can be difficult to image seals and welds, but with 3D sensors and advanced imaging software, users can capture all of a battery cell’s dimensions, leaving no potential flaw undetected and supporting accurate module assembly. n Car-makers are merging machine vision, 3D sensing, deep learning and vision-guided robotics technologies to enhance the production of traditional and electric vehicles. Stephan Pottel, Zebra Technologies’ manufacturing strategy director for the EMEA region, explains how they are doing this, with the help of some real applications. Automotive manufacturers and suppliers are combining machine vision with technologies such as AI and deep learning to improve quality inspection performance.
RkJQdWJsaXNoZXIy MjQ0NzM=