Special Issue "Machine Learning based Methods for Mechanics"

Deadline: 31 January 2020 (closed)
Guest Editors
Prof. Xiaoying Zhuang, Leibniz Univerisity Hannover, Germany
Prof. Timon Rabczuk, Bauhaus University Weimar, Germany
Prof. Hung Nguyen Xuan, Ho Chi Minh City University of Technology (HUTECH), Vietnam

Summary

In this age of big data, machine learning techniques have been successfully applied in image processing, genomics, financial problems and even medical diagnosis. The emerging application of machine learning and big data analysis has fundamentally influenced and changed our way of how we think, plan, solve and analyze in engineering. Nevertheless, we are faced with many issues and unsolved problems when applying data drive computing and machine learning in engineering analysis.

The objective of the special issue is to invite the submissions of the works of researchers from worldwide and provide a fair overview on the state of the art on theories, methods and techniques contributed to the machine learning for mechanics and applications, and also the remaining issues and limitations, thus promoting further research interests.

Possible topics (inviting more ideas): 
Papers on topics related to new theory, methods and applications related to the machine learning for mechanics not only to theory but also to experiments are encouraged to submit to the special issue. 

We outline the following possible related topics but are not restricted to: 
• Machine learning based solutions of PDEs
• Data driven constitutive modelling
• Visualization and visual analytics of mechanical engineering
• Big data for design and optimization 
• Machine learning assisted high performance computing
• Data-driven computing in dynamics and molecular dynamics
• Machine learning for uncertainties analysis and stochastic model
• Data-driven simulation techniques
• Machine learning for discrete particle-based method


Published Papers