University of Cambridge, UK, spin-out machine learning company, Intellegens, has partnered with Ansys, based in Canonsburg, Pennsylvania, USA, to integrate machine learning methods into Additive Manufacturing workflows, hoping to facilitate the development of reliable, repeatable processes.
The companies hope that the gathering of technology from this collaboration will make it faster and easier for AM project teams to analayse data from experiment, simulation or production-generating models, capturing vital insights which can be used to optimise process parameters and powders, simultaneously improving the quality of the parts and cutting time to market.
“Intellegens’ machine learning technology offers a ready-made solution to key data analysis challenges faced by our Additive Manufacturing customers,” stated Rob Davis, Director of Product Management, Ansys. “Integration with Ansys Granta MI creates a unified workflow for capturing and applying results from AM testing, simulation, and production.”
The agreement means Intellegens’ Alchemite™, a machine learning platform, will be embedded into Ansys’ materials data management software, Granta MI™.
Alchemite utilises deep learning algorithms to quickly find relationships within complex datasets, even when that data may have many empty values. This, reportedly, makes Alchemite ideal for AM teams seeking to utilise data drawn from a variety of sources: it extracts any possible knowledge to identify the critical combinations of factors which ultimately control the performance of AM parts. Alchemite needs no prior knowledge of which parameters are of import, an advantage in this emerging technology area.
Alchemite has the following potential applications throughout the AM workflow: process parameter optimisation, computational design, failure analysis & QC, data validation & gap filling and assisted design of experiments (DoE).
Granta MI is said to be de facto for materials data management in engineering enterprises, as it is able to be applied to capture all of a company’s AM data into a single place, including data on the properties of powders & raw materials, machine build parameters, post-build processing data, test results for parts and simulation data from the Ansys AM simulation suite. Integrating Alchemite into this system will allow the straightforward analysis of a full range of data in the search for key process/property relationships and to allow the continuous improvement of models as the data is updated.
“Merging the data management capabilities of Ansys’ Granta MI with the machine learning prowess of Alchemite is a perfect fit, promising to deliver deep insights to Additive Manufacturing workflows,” commented Dr Gareth Conduit, CTO at Intellegens. “We look forward to working with the global Ansys network to deliver the benefits of machine learning to many more AM project teams.”