A robotic inspection system with 3D vision and machine learning will monitor and correct defects in glass, metal, and ceramic production in real time. Current manufacturing in these "foundation industries" relies on rigid, pre-programmed methods that cannot adapt to errors or changing conditions. This makes it difficult for UK manufacturers to cut energy use and CO₂ emissions while staying competitive against countries with lower labour costs and weaker environmental rules. The project addresses this by using multi-axis robots, bespoke sensors, and AI to digitise inspection and adjust production on the fly. If successful, the system could reduce energy costs and improve production yields across tempered glass, kiln-fired ceramics, and foundry castings. These are materials that go into windows, tiles, pipes, and engine blocks—everyday objects whose manufacture currently wastes significant energy and material. The impact would be a quieter, more efficient industrial backbone, not a visible consumer product.
View original technical description
This collaborative, cross sector R&D demonstration project furthers previous industrial research to advance & showcase novel technology developed to support transformation of Foundation Industry production process optimisation. The primary aim is to increase efficiency to achieve greater productivity by increased energy and resource efficiency. This will be achieved by using advanced robotics integrated with 3D machine vision systems which are augmented with bespoke sensors creating a data rich environment. The robotic, vision and sensory technology will be applied and demonstrated with foundation industry production processes building on previous R&D to digitally inspect defects in metals, glass and ceramics. With additional utilisation of machine learning (ML) on data collected, the advacned artificial intelligence (AI) developed can begin to enhance these traditional Foundation Industry production processes to enabling greater industrial productivity whilst significantly reducing energy consumption and CO2 emissions in both glass, metals, and ceramic manufacturing. Current manufacturing methods are inflexible, often requiring the time-intensive pre-programming or manual intervention of production tasks responding to unexpected occurrences or production errors. This means that foundation industries are unable to respond to the demands of future environmental targets and cannot make further improvements within the manufacturing process until the production methods are updated. This is critical to address; success will allow UK manufacturing to remain competitive when facing increasing global competition where labour rates and emissions regulations are significantly lower. This project aims to use advanced 3D vision sensor data to produce ML and AI algorithms to monitor and improve the metals, glass and ceramic production process. To guarantee the repeatability and accuracy of measurement, automation through the flexibility offered by modern multi-axis robotic systems will be demonstrated. The ultimate output of the system will result in foundation industry-wide benefits in glass, ceramics, and metals production. This project will address specific needs in these foundation industries by offering an augmented, existing manufacturing process brought about by digitised inspection & intelligent machine learning. It is anticipated that a reduction in energy costs and improved production yields associated with the manufacture of tempered glass & kiln fired ceramic materials will be significantly and positively impacted, as is the case in the foundry castings industries.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know