Details

Autor(en) / Beteiligte

• Kellner, Leon
• Stender, Merten
• von Bock und Polach, Rüdiger U. Franz
• Herrnring, Hauke
• Ehlers, Sören
• Hoffmann, Norbert
• Høyland, Knut V.

Titel

Establishing a common database of ice experiments and using machine learning to understand and predict ice behavior

Ist Teil von

• Cold regions science and technology, 2019-06, Vol.162, p.56-73

Ort / Verlag

Elsevier B.V

Erscheinungsjahr

2019

Quelle

Elsevier ScienceDirect Journals

Beschreibungen/Notizen

• Ice material models often limit the accuracy of ice related simulations. The reasons for this are manifold, e.g. complex ice properties. One issue is linking experimental data to ice material modeling, where the aim is to identify patterns in the data that can be used by the models. However, numerous parameters that influence ice behavior lead to large, high dimensional data sets which are often fragmented. Handling the data manually becomes impractical. Machine learning and statistical tools are applied to identify how parameters, such as temperature, influence peak stress and ice behavior. To enable the analysis, a common and small scale experimental database is established. •The results based on a large data set agree with the majority of state-of-the-art understanding of ice mechanics.•Temperature and strain rate are the most important features regarding the prediction of ductile or brittle behavior.•The most important features for the prediction of peak stress and ice behavior are not necessarily the same.•The identified patterns can be used in ice material modeling.