C.T. Wu, ANSYS
Wing Kam Liu, Northwestern
J.S. Chen, University of California, San Diego
WaiChing Sun, Columbia University
In recent years, the intelligent model reduction via mathematical, numerical and statistical approaches to reveal the high-dimensional multiscale data in low-dimensional industrial scale has played a crucial role in the efficient design of advanced materials, processes, structures and complex mechanical systems. New and exciting developments of intelligent model reduction methods often go beyond classical theories and incorporate more profound physical mechanisms, machine learning techniques, sensors, data storage, parallel and high performance computing. They are becoming the exclusive numerical tools in addressing the computational challenges which were difficult or impossible to solve by conventional methods. These new developments are increasingly important in improving safety, quality and productivity for future innovative industrial design and manufacturing. The goal of this mini-symposium is to bring together experts working on these methods, share research results and identify the emergent needs towards more rapid progress in advancing the important fields for engineering applications. Topics of interest for this mini-symposium include, but are not limited to the following:
- Advanced and data-driven constitutive modeling
- Big data in design and manufacturing engineering
- Computational homogenization and RVE analysis
- Data-driven analyses and forecasting
- Domain decomposition, parallel computing with TPUs and GPUs
- Machine (deep, manifold, reinforcement and transfer) learning
- Meta-modeling and meta-learning for applications with limited data
- Geometric learning with Euclidean and Non-Euclidean data
- Multi-scale, coupling and upscaling techniques
- Object/event detection, recognition and reconstruction
- Reduced-order and surrogate modeling
- Software development • Industrial applications
- The link of CAE to CAD and CAM
- Verification, validation, uncertainty quantification and adversarial attack