TECHNOLOGY | MATERIALS SIMULATION AI helps to develop better materials


Spanish research organisation Aimplas has launched the Poly-ML project, which applies machine learning to predict material proper- ties based on their composition and processing conditions. The techniques make it possible to optimise formulations, reduce the need for experimental testing and improve the efficiency of R&D processes, it says. The project focuses on the development of predictive models that can anticipate the mechanical, thermal or physical properties of materials, to enable faster, more accurate decisions to be made in early development. This approach helps reduce costs, time and waste generation, while improving trace- ability and sustainability, says Aimplas. Partners include Tyris AI, which specialises in AI applied to industry, and Faperin, a plastic processing company. On one hand, Faperin provides data from its processes to


BIOPLASTICS Bio-based foam replaces oil-based materials


The Fraunhofer Institute in Germany has developed a bio-based extruded foam that can be made on existing equipment. The foam, made of polybutylene


succinate (PBS), addresses CO2 reduction, regulatory compliance and economic efficiency, says Fraunhofer. The PBS Extrusion Foam (xPBS)


can replace conventional polyethyl- ene (PE) foams in key applications such as packaging, protective and transport solutions and construction. In these markets, regulatory require- ments and high sustainability demands are driving the need for bio-based materials, it says.


42


A key factor for industry is that xPBS functions as a so-called drop-in solution. The foam can be processed on existing extrusion lines without requiring major investments in retrofitting. This gives companies the opportunity to make their products


FILM & SHEET EXTRUSION | May/June 2026


more sustainable in the short term without fundamentally changing existing processes. The project was a collaboration between several Fraunhofer institutes including ICT (which drove formula- tion and process development of the foaming process) and IAP, which focused on polymer synthesis and the adjustment of material properties. “Our goal was to develop a material solution that can be used directly in industry,” said Anja Dennard, project manager at Fraunhofer ICT. “The fact we can now produce PBS foams with properties comparable to PE on an industrial scale is a first.” � www.ccpe.fraunhofer.de


www.filmandsheet.com


train models and draw conclusions, while Tyris AI contributes its knowl- edge in the application of AI in the industrial sector. The project focuses on a tool that allows models to be developed, even without programming knowledge, in order to facilitate the adoption of artificial intelligence in the plastics sector, promoting its digitalisation and competitiveness. “With Poly-ML, we are taking a step towards the real application of


artificial intelligence in the design of plastic materials,” said Joan Giner, a researcher at Aimplas. From an environmental perspec-


tive, Poly-ML contributes to reducing laboratory waste and the use of hazardous solvents and additives by avoiding inefficient formulations. In occupational health, it cuts the exposure of technical staff to chemi- cals and reduces the risks associated with experimental testing. � www.aimplas.es


IMAGE: FRAUNHOFER ICT


IMAGE: AIMPLAS


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