INNOVATION | TECHNOLOGY
“The system can be used in-line on any process- ing line to measure volatiles from melt – injection moulding, sheet converting or pelletising, for example. We think this will fill a data gap that currently exists in PCR processing,” said Vorst.
AI in formulation Digital tools for formulation development have been in existence for some time, but it may be that their time in plastics compounding has finally arrived. Premix Group is using a new AI platform to speed its product development process for optimising formulas for electrically conductive compounds. The R&D team developed PERTTI 3.0 in-house, trained on the company’s data. The tool can predict what properties a given formula would have. It can also be used to simulate the cost of different approaches and identify the best solution for each project. “Machine learning itself isn’t new,” said Ville
Mylläri, Product Development Manager of Premix in a blog on the company’s website. “What’s changed is the accessibility. With the rise of open-source tools, even specialised manufacturers like us can now build powerful AI models with relatively low cost and high flexibility.” Mylläri added: “A model for conductive plastics is unique, and the architecture needed to be optimised and tested carefully. The over 40-year history and the huge database of Premix made it possible to develop such a comprehensive model.” Because the platform is built using open-source
frameworks and a modular architecture, it can be adapted to different polymer types and use cases. The company said it sees this tool as key as it
Matmerize’s PolymRize AI polymer software is used in the design of polymers for electronics and energy applications at Asahi Kasei Source Matmerize
continues to diversify its material portfolio and expands into manufacturing in the US, where it opened a new compounding plant in North Carolina in June. “Our next steps involve expanding the support- ed polymer families and scaling the model to support our new regions,” Mylläri said. “The goal is not to replace human expertise, but to give our product developers faster, smarter tools to deliver better outcomes for our customers.” Machine learning could, in the future, be
expanded to optimise processing parameters for the compounding process, he added. Matmerize, a spin-out from the Georgia Institute of Technology in the US, created the PolymRize cloud-based polymer informatics software platform, which uses AI algorithms to identify optimal materials and formulations. The platform can be used by companies to build secure, custom, proprietary models based on the
www.xindacorp.com
info@xindacorp.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50
