[15p-S2_204-1~18] 23.1 Joint Session N "Informatics"

2:45 PM - 3:00 PM JST(5:45 AM - 6:00 AM UTC)

[15p-S2_204-6] Development of Multimodal Deep Learning Technologies to promote green transformation in resin plastic compounding and injection molding processes

〇Shigeru Kojima¹, Ko Osawa¹, Yukako Taka¹, Michihiro Okuyama¹, Akihiro Naruke¹, Miyuki Okaniwa¹, Daisuke Kimura², Kenji Hata², Shun Muroga² (1.KONICA MINOLTA, INC., 2.AIST)

Keywords:

deep learning,plastic molding

We have been studying the application of Multimodal AI to complex resin systems such as fiber-reinforced plastics. In this report, we examine its applicability to another type of complex resin system, polymer blends. We present results on AI-based property prediction and state visualization for resin alloys. Furthermore, Konica Minolta is engaged in the resin recycling business, and the insights gained from this research will contribute to promoting Green Transformation (GX) initiatives.