19th Presentation | Bio-inspired Discontinuous Composite Materials with a Machine Learning Driven Optimized Architecture | Athanasios Oikonomou

19th Presentation | Bio-inspired Discontinuous Composite Materials with a Machine Learning Driven Optimized Architecture | Athanasios Oikonomou

NanoAI welcomes Athanasios Oikonomou  who will present his work, titled “Bio-inspired Discontinuous Composite Materials with a Machine Learning Driven Optimized Architecture”.

As always, an open discussion will follow.

When? June 6th, 15:00 Greece

Description:

Βio-inspired hierarchical discontinuous fibrous composite materials are investigated with an aim of achieving enhanced pseudo-ductility and elevated toughness. A novel methodology is proposed to search fast and efficiently the vast design space of the geometrical parameters of the discontinuities that combines advanced numerical simulations of the material’s mechanical behavior as well as state-of-the-art Machine Learning approaches such as Active Learning. A continuum mesoscale-based numerical scheme is developed to simulate the mechanical behavior of discontinuous fibrous composites under three-point bending loading and is utilized in a sequential Bayesian optimization scheme that iteratively searches for the material architecture that achieves maximum toughness. Five independent geometrical variables related to the size and the exact topology of the discontinuities form a vast five-dimensional design space of more than 2.6×106 possible combinations in which the proposed methodology moves quickly and efficiently to identify after only 100 iterations the optimal configuration that increases the material’s toughness more than 100% with a knock-down effect on the ultimate bending strength of less than 10%.

Mr. Athanasios Oikonomou is a young engineer, motivated by innovative concepts in machine learning with practical applications in the field of additive manufacturing. He has acquired his Engineering Diploma from the University of Patras, where he is currently pursuing his Ph.D. in Data Driven Bio-fabrication, utilizing Advanced Additive Manufacturing Techniques, Machnine Learning, and Physics Informed Neural Networks. Furthermore, he is currently working as an Additive Manufacturing Engineer in BIOG3D.

He has more than three years of academic experience, along with two years of industrial experience as a system development, additive manufacturing, and machine learning engineer, with participation in biomedical and composites manufacturing projects. Participating in several EU projects and publishing in internationally renowned journals, he is interested in system development with embedded novel machine learning techniques, for process optimization.

Speaker links:

Subscribe to our mailing list: https://lists.iit.demokritos.gr/mailman/listinfo/nanoai
You can find more info on this upcoming talk as well as on our previous talks at http://nano-ai.iit.demokritos.gr/