The content on this page was translated automatically.
Invitation to the research colloquium - lecture by Prof. Dr.-Ing. Fadi Aldakheel, Hanover
In the context of the research colloquium for final year students, doctoral students and postdoctoral students we cordially invite you to the lecture
EfficientMultiscale Modeling of Heterogeneous Materials Using Deep Neural Networks,
Professor Dr.-Ing. Fadi Aldakheel, Gottfried Wilhelm Leibniz University Hannover, Institute of Structural Mechanics and Computational Mechanics (IBNM)
Material modeling using modern numerical methods accelerates the design process and reduces the costs of developing new products. However, for multiscale modeling of heterogeneous materials, the well-established homo-genization techniques remain computationally expensive for high accuracy levels. In this contribution, a machine learning approach, convolutional neural networks (CNNs), is proposed as a computationally efficient solution method that is capable of providing a high level of accuracy. In this work, the data-set used for the training process, as well as the numerical tests, consists of artificial/real microstructural images ("input"). Whereas, the output is the homogenized stress of a given representative volume element. The model performance is demonstrated by means of examples and compared with traditional homogenization methods. As the examples illustrate, high accuracy in predicting the homogenized stresses, along with a significant reduction in the computation time, were achieved using the developed CNN model.
The colloquium will take place on 04.07.23 at 14:00 in the Campus Center, Lecture Hall 4. We look forward to seeing you there.