AI: a manufacturing revolution

The Artificial Intelligence revolution is set to shape the manufacturing landscape forever. But what will this look like?

Artificial Intelligence (AI) is already in effect in the industrial world. From the design process and production floor to the supply chain and administration, AI is destined to change the way we manufacture products and process materials forever.

The effect of things like generative design; Industry 4.0; human-robot collaboration; and smart maintenance are already being felt across the sector – a process that is only going to accelerate over coming years.

Reflecting this sea change, The Alan Turing Institute and the University of Sheffield Advanced Manufacturing Research Centre (AMRC) have signed an agreement to work together to identify opportunities for artificial intelligence (AI) adoption in manufacturing, accelerate research collaboration and boost skills development.

The two organisations have signed a Memorandum of Understanding (MoU) that will draw on their considerable research and development skills across manufacturing, data science, machine learning and AI. Researchers from the Turing and the AMRC hope to identify, and find solutions to, some of the grand challenges facing the manufacturing sector such as meeting increasing demand and the response to Covid-19.

The AMRC is a network of world-leading research and innovation centres working with manufacturing companies of all sizes from around the globe. The AMRC is part of the High Value Manufacturing (HVM) Catapult, a thriving alliance of seven technology and innovation centres that work with industry to help bridge the gap between technology concept and commercialisation.

The Alan Turing Institute is the national institute for data science and artificial intelligence, with headquarters at the British Library in London. The Turing undertakes research which tackles some of the biggest challenges in science, society and the economy.

Mutual research areas of interest in the agreement between the Turing and the AMRC include:Uncertainty quantification; Human-centric design; and Privacy-preserving technologies, including utility and application of synthetic data.

At the Turing, the collaboration will be led by the Institute’s dynamic Data-Centric Engineering research programme, a major £60m research initiative funded by the Lloyd's Register Foundation. The agreement demonstrates an important step for the programme as it seeks to consolidate a research strategy in the domain of manufacturing. Looking forward, it is hoped the new collaboration is the first of many in this research area.

“Establishing ties with the AMRC is essential to furthering our strategy in the area of manufacturing,” said Mark Girolami, the Turing’s Programme Director for Data Centric Engineering. “Having access to a national network of manufacturing research expertise, combined with the unique skill set of Turing researchers, creates an exciting opportunity for innovative, solution-led research outcomes that address key challenges such as maximising automation, integrating intelligent software, increasing capacity, and reshoring, facing the manufacturing sector.”

Professor Rab Scott, Head of Digital at the AMRC, said: “Bringing these world-class organisations together will provide a tremendously valuable resource for the UK’s manufacturing sector. Working together, the AMRC and The Alan Turing Institute will be able to demonstrate how realising greater insights and values from manufacturing data can lead to improvements in productivity, resource utilisation, sustainability and really impact the bottom line.”

Professor Sam Turner, Chief Technology Officer for the HVM Catapult, said the agreement presents a great opportunity for the AMRC and HVM Catapult to build a strong working relationship with The Alan Turing Institute. He added: “AI and machine learning are likely to be at the heart of many manufacturing systems and it is important that the UK harnesses its research and innovation capability to take a leading role in developing solutions.”

Machine learning technology is obviously another key aspect of AI with implications for manufacturing. One example of this can be seen in the fact that it will be used to make the additive manufacturing (AM) process of metallic alloys for aerospace cheaper and faster, encouraging production of lightweight, energy-efficient aircraft to support net zero targets for aviation.

Project MEDAL: Machine Learning for Additive Manufacturing Experimental Design is led by Intellegens, a University of Cambridge spin-out specialising in artificial intelligence, the University of Sheffield AMRC North West, and global aerospace giant Boeing. It aims to accelerate the product development lifecycle of aerospace components by using a machine learning model to optimise additive manufacturing (AM) processing parameters for new metal alloys at a lower cost and faster rate.

AM techniques reduce material waste and energy usage; allow easy prototyping, optimising and improvement of components; and enable the manufacture of components with superior engineering performance over their lifecycle. The global AM market is worth £12bn and that is expected to triple in size over the next five years. Project MEDAL’s research will concentrate on metal laser powder bed fusion - the most widely used AM approach in industry - focussing on key parameter variables required to manufacture high density, high strength parts.

The project is part of the National Aerospace Technology Exploitation Programme (NATEP), a £10 million initiative for UK SMEs to develop innovative aerospace technologies funded by the Department for Business, Energy and Industrial Strategy and delivered in partnership with the Aerospace Technology Institute (ATI) and Innovate UK. Intellegens was a start-up in the first group of companies to complete the ATI Boeing Accelerator last year.

Ben Pellegrini, CEO of Intellegens, said: “We are very excited to be launching this project in conjunction with the AMRC. The intersection of machine learning, design of experiments and additive manufacturing holds enormous potential to rapidly develop and deploy custom parts not only in aerospace, as proven by the involvement of Boeing, but in medical, transport and consumer product applications.”

James Hughes, Research Director for University of Sheffield AMRC North West, said the project will build the AMRC’s knowledge and expertise in alloy development so it can help other UK manufacturers.

“At the AMRC we have experienced first-hand, and through our partner network, how onerous it is to develop a robust set of process parameters for AM. It relies on a multi-disciplinary team of engineers and scientists and comes at great expense in both time and capital equipment,” said Hughes. “It is our intention to develop a robust, end-to-end methodology for process parameter development that encompasses how we operate our machinery right through to how we generate response variables quickly and efficiently. Intellegens’ AI-embedded platform Alchemite will be at the heart of all of this.

“There are many barriers to the adoption of metallic AM but by providing users, and maybe more importantly new users, with the tools they need to process a required material should not be one of them. With the AMRC’s knowledge in AM, and Intellegens’ AI tools, all the required experience and expertise is in place in order to deliver a rapid, data-driven software toolset for developing parameters for metallic AM processes to make them cheaper and faster.”

Sir Martin Donnelly, president of Boeing Europe and managing director of Boeing in the UK and Ireland, said the project shows how industry can successfully partner with government and academia to spur UK innovation.

“We are proud to see this project move forward because of what it promises aviation and manufacturing, and because of what it represents for the UK’s innovation ecosystem,” Donnelly said. “We helped found the AMRC two decades ago, Intellegens was one of the companies we invested in as part of the ATI Boeing Accelerator and we have longstanding research partnerships with Cambridge University and the University of Sheffield. We are excited to see what comes from this continued collaboration and how we might replicate this formula in other ways within the UK and beyond.”

Aerospace components have to withstand certain loads and temperature resistances, and some materials are limited in what they can offer. There is also simultaneous push for lower weight and higher temperature resistance for better fuel efficiency, bringing new or previously impractical-to-machine metals into the aerospace material mix.

One of the main drawbacks of AM is the limited material selection currently available and the design of new materials, particularly in the aerospace industry, requires expensive and extensive testing and certification cycles which can take longer than a year to complete and cost as much as £1 million to undertake. Project MEDAL aims to accelerate this process, using Machine Learning (ML) to rapidly optimise AM processing parameters for new metal alloys, making the development process more time and cost efficient.

Pellegrini said experimental design techniques are extremely important to develop new products and processes in a cost-effective and confident manner. The most common approach is Design of Experiments (DOE), a statistical method that builds a mathematical model of a system by simultaneously investigating the effects of various factors.

“DOE is a more efficient, systematic way of choosing and carrying out experiments compared to the Change One Separate variable at a Time (COST) approach. However, the high number of experiments required to obtain a reliable covering of the search space means that DOE can still be a lengthy and costly process, which can be improved,” explained Pellegrini.

“The machine learning solution in this project can significantly reduce the need for many experimental cycles by around 80%. The software platform will be able to suggest the most important experiments needed to optimise AM processing parameters, in order to manufacture parts that meet specific target properties. The platform will make the development process for AM metal alloys more time and cost efficient. This will in turn accelerate the production of more lightweight and integrated aerospace components, leading to more efficient aircrafts and improved environmental impact.”

Intellegens will produce a software platform with an underlying machine learning algorithm based on its Alchemite platform. It has already been used successfully to overcome material design problems in a University of Cambridge research project with a leading OEM where a new alloy was designed, developed and verified in 18 months rather than the expected 20-year timeline, saving about $10m.

Ian Brooks, AM technical fellow at University of Sheffield North West, said by harnessing two key technologies - artificial intelligence and additive manufacturing - Project MEDAL hopes to unlock big benefits aligned to the Aerospace Technology Institute’s strategic themes on aerostructures, propulsion and power, and systems.

“It targets future integrated structures by accelerating development of new metal alloys and optimising an AM process to create lightweight components; its key driver is to protect the environment by reducing material usage and waste; and it looks to minimise fuel consumption through lightweighting of components for flight controls and potentially landing gear systems,” said Brooks.

While this new method is being developed with aerospace in mind, the team believes it will have applications for other sectors too. Brooks said: “The opportunity for this project is to provide end users with a validated, economically viable method of developing their own powder and parameter combinations. Research findings from this project and the project output will have applications for other sectors including automotive, space, construction, oil and gas, offshore renewables and agriculture.”