Back To Schedule
Wednesday, June 2 • 16:50 - 17:15
Applying machine learning to process and characterisation data of nanoenhanced composites: a means for prediction

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

  • Machine Learning
  • Characterisation
  • Nanoindentation

This work describes a novel methodology of data documentation in materials characterisation, which has as starting point the creation and usage of any Data Management Plan (DMP) for scientific data in the field of materials science and engineering, followed by the development and exploitation of ontologies for the harnessing of data created through experimental techniques. The case study that is discussed here is nanoindentation, a widely used method for the experimental assessment of mechanical properties on a small scale. Except for technology development and synthesis of new materials and hybrid composite structures, the need of developing new evaluation methodologies is highlighted to assist and accelerate developments. Artificial Intelligence (AI) is a promising candidate to bridge the gap between Research and Development (R&D) and industry by establishing unbiased relations between microstructure and properties. This is majorly appreciated in case of Safe-by-Design requirements regarding mechanical performance, and real-time characterisation. Being representative, k-means, Random Forrest (RF), Support Vector Machines (SVM), k-Nearest Neighbors (KNN) are common Machine Learning (ML) algorithms used in multiclass classification problems for automated classification of microstructures.
This work contributes to nanocomposites design and quality control associated with identifying the optimum inclusion in nanomaterials reinforcement by microstructure assessment. In this direction, Artificial Intelligence can provide a module for enabling fast, in-line, and real-time metrological characterisation of nanoindentation data.
This work has been partially supported by the EU Horizon 2020 Programmes: MODCOMP (GA No 685844), SMARTFAN (GA No 760779), OYSTER (GA No 760827) and REPAIR3D (GA No 814588).

Speakers, Jury Members & Final...
avatar for Elias KOUMOULOS


Dr. Elias P. Koumoulos holds a BSc in Chemical Engineering, followed by MSc in Materials Science and Technology and PhD in nanomechanics. To date, he has the authorship of over 70 published papers in ISI journals, 6 book chapters, 90 participations in national/international conferences... Read More →

Wednesday June 2, 2021 16:50 - 17:15 CEST
Conferences (Hall 6 - Room 611)