Materials Processing Institute to use AI to transform AM in the UK | VoxelMatters


Stay up to date with everything that is happening in the wonderful world of AM via our LinkedIn community.

The Materials Processing Institute is leading a £600,000 research collaboration to develop SMART-APP, an AI-based tool capable of creating greater efficiencies within the Additive Manufacturing (AM) sector.

Working in partnership with Additive Manufacturing Solutions Ltd and AMFG, it aims to provide a versatile, commercial, predictive material reuse management tool enabling AM to expand by introducing greater cost efficiencies.

SMART-APP aims to enable the production of AM components, using Laser Powder Bed Fusion by introducing smart predictive models for resource efficiency and waste reduction.

Materials Processing Institute to leverage AI on SMART-APP tool to transform additive manufacturing material reuse in the UKNick Parry, Industrial Digitalisation Group Manager at the Teesside-based Materials Processing Institute, said: “SMART-APP is the next logical step to continue the work the Institute has already undertaken in powder characterization. By developing an artificial intelligence tool that can help AM users create faster and cheaper ways of maximizing powder reuse, the AM industry, especially those needing to maximize the operational effectiveness of their machines.

“This predictive tool will develop and enable world-class production of AM components, with smart solutions for resource efficiency and providing longer use of materials feedstock and reducing wastage.”

SMART-APP predicts the quality change of the powder after each process and proposes alternative process parameters on used powder to extend its lifespan with a minimal or an in-specification impact on product quality.

The project is funded by Innovate UK, part of UK Research and Innovation (UKRI), the UK’s innovation agency, which drives productivity and economic growth by supporting businesses to develop and realise the potential of new ideas.

One area of particular interest is the growth of metal AM which is not yet cost-effective due to a development gap in the level of powder waste and length of processing time.

The research will feature state-of-the-art materials characterization, and mechanical testing, investigating shelf life and the processability envelope of environmentally affected common stainless steel, titanium and superalloy base feedstock. It will also examine methods of reclaiming the powders and the effect on the final product.

The resulting outputs will be fed into an advanced database linking powder input properties against AM part performance to provide a predictive tool that will be available for the industry to use.

Rob Higham, CEO of Additive Manufacturing Solutions, added: “AMS is delighted to have the support of Innovate UK to continue developing our world-leading powder and AM process optimization capability portfolio.

“This marks our first step toward a ground-breaking approach to dynamic materials management. The potential of the AM process remains a potential in many people’s eyes. It could be realized with the development of a versatile and smart predictive tool for tracking powder quality after each reuse.”

Alexander Grimmer, Technical Consultant at London-headquartered AMFG, a market-leading software company providing MES and workflow automation for manufacturing, said: “This initiative aims to transform additive manufacturing towards more resource-efficient methods.

“SMART-APP aims to instill trust in the additive manufacturing realm by forecasting powder quality and recommending processes to restore desired powder properties for reuse. AMFG eagerly anticipates contributing to a cutting-edge material management system in this project, poised to deliver substantial environmental and economic benefits to the industry. This endeavor is set to expedite the widespread adoption of additive manufacturing.”

Latest articles

spot_imgspot_img

Related articles

Leave a reply

Please enter your comment!
Please enter your name here

spot_imgspot_img