This project will enhance productivity in construction by using Matta's AI manufacturing copilots for real-time quality assurance and control in cement additive manufacturing (AM). AM has already shown great potential for transforming construction, with a current market size of $310M and trials being carried out for large structures such as houses and bridges. This is an important direction for the construction industry due to major potential benefits in waste reduction, reduced labour requirements, improved environmental sustainability and cost reductions of up to 25%. However, the strict quality control and safety requirements lead to challenges in construction AM adoption. For example, cement materials are ageing from the moment water is added, and so across a printed batch there are inherent changes in extrusion behaviour, and subsequently the porosity and mechanical properties of the finished parts. This opens a significant opportunity for Matta's AI copilots to make construction significantly more efficient. This collaborative project with the University of Cambridge will help Matta realise opportunities in construction firstly, by providing access to a cement AM system and associated expertise to train and test AI models with. Secondly by enabling Matta to address a fundamental challenge with AI systems: they typically need a lot of data. This can be difficult: some defects might be critical but rare; or highly-skilled engineers might be needed to annotate uncountable images. Matta's core patent-pending technology helps address this through automatic data labelling and recognising the causes of defects not just correlations. This allows Matta systems to work with new environments and materials. However, training this foundational AI requires significant initial data. As Matta moves into processes like construction where data is more expensive to gather, Matta will need to train systems with less data. Therefore this project will pioneer new generative and other AI methods to reduce the need for costly experimental training data and enhance the accuracy of its AI systems. TEAM Matta is a venture-backed spin-out from the University of Cambridge developing AI copilots for advanced manufacturing. These copilots are software agents that can monitor, control, and optimise the production of complex parts. With these copilots, manufacturers achieve higher quality, lower waste, and faster innovation. Prof. Ronan Daly, a Professor in the Institute for Manufacturing at the University of Cambridge, has an excellent track record in bringing a detailed scientific understanding to real-world applications involving fluid flow and AM, including studying cement rheology, printing and characterisation.

This project seeks to develop a data-efficient vision-based AI process monitoring system to seamlessly assure additive manufacturing (AM) part quality in real-time, thereby accelerating AM adoption including in our case study of personalised pharmaceuticals. Our key innovation will address a fundamental challenge with AI systems: they typically need a lot of data, which can be difficult in manufacturing. As Matta moves into higher-value processes where data is more expensive to gather yet stakes are higher, we will need to train our systems with less data. This project will therefore pioneer new AI methods to reduce the need for costly experimental training data while enhancing the performance of its AI systems. Pharmaceuticals are an ideal case study because AM has demonstrated great potential to transform medicine by personalisation and rapid prototyping of dosage forms at the point of care. However, strict quality control and specific requirements for every produced batch are required, when releasing pharmaceutical products to patients. This currently prevents the wide adoption of 3D printed pharmaceuticals. Hence, an agile manufacturing technology that can be supervised by artificial intelligence is of critical value to enable applying AM in the pharmaceutical field. The data-efficient AI copilots developed in this project may thereby help vastly more patients access personalised 3D printed medicines and lead to a step change in performance of Matta's AI copilots across all manufacturing. The project is a collaboration between Matta and King's College London. Matta is a start-up company spun out from the University of Cambridge that develops artificial intelligence (AI) copilots for advanced manufacturing processes. These copilots can monitor, control, and optimise production to achieve higher quality, lower waste, and faster innovation. Dr Alhnan at King's College London is a leader in digital tablet fabrication and pharmaceutics and holds four granted patents in the field.

Metal-based additive manufacturing (AM) encompasses a wide range of technologies such as powder bed fusion, binder jetting and direct energy deposition. These processes are primarily used for manufacturing in demanding industries such as aerospace, automotive, medical, and energy. These industries require uniform part quality with properties like those achieved by conventional casting or forging processes. However, metal AM is highly prone to component failure - 3D printed metal parts are susceptible to manufacturing errors (e.g. high porosity, deformation, cracking) during the printing process. Up to 17% materials and valuable time is wasted via failed prints costing the metals manufacturing industry millions of pounds each year. Matta is developing a self-learning universal AI digital platform which leverages the latest AI research and the power of the cloud to bring intelligence to metal AM. Machine Learning is used to detect manufacturing errors and inefficiencies in the printing process, ultimately enabling error correction and prevention to improve resource and energy efficiency over time. Matta's aim is to autonomously detect errors as soon as they occur, stop the printing, and restart the print with automatically corrected settings. Failed prints are an avoidable waste of resources, materials, and energy for a product that is ultimately unviable, and can waste days if not weeks of time. In this project, we will apply our technology to the high-value UK metals manufacturing industry. We will collect diverse datasets of the metal AM process, develop state-of-the-art data science, build self-learning universal AI models to detect errors autonomously and apply them to a live demonstrator. The system will be built as a distributed network of metal printers connected via the cloud so each metal printer can learn from the experiences of others. In this way will create the level of intelligence required to ultimately achieve autonomous error prevention by recognising similarities between manufacturing runs, dramatically improving the productivity of the sector. This project is a natural stepping stone to the development and commercialisation of a total closed-loop AM system where crucial manufacturing parameters are automatically adjusted in real time without human intervention - an industry game changer! Matta is a spin-out from University of Cambridge. This project is critical to our extension from polymer AM to high-value metals manufacturing, where stakes are much higher. Since incorporating in 2021, Matta has also been building relationships with industry leaders such as the Manufacturing Technology Centre, GE, Cambridge, and Stanford.

Approximately 25% of global plastic production is manufactured in China. Reshoring manufacturing to the UK will drive two major impact reductions: carbon emissions and virgin plastic consumption. Batch.works is a UK manufacturer who combines 3D-printing and recycled materials to produce products for UK brands, including lighting, stationery, fashion and homeware. In this project we will integrate AI to reduce the fail-rate of 3D-printing and automate our factor processes to: 1. Increase use of recycled materials 2. Reduce our costly printing fail rate to improve resource efficiency 3. Improve life-cycle circularity for new products 4. Reduce embodied carbon in our products 5. Improve profitability as we scale Building UK manufacturing capability that is inherently adaptable, makes us more resilient and less reliant on global supply chains, which have been vulnerable under COVID.