About this Research Topic
Shape optimization, inverse analysis, and uncertainty qualification are pacesetting technologies in computer-aided engineering. Shape optimization provides a powerful tool to automate the engineering design process and search for the optimal solution in a large design space. Inverse analysis enables the identification of mechanical parameters and defects of structures. Uncertainty qualification enhances structural reliability by considering various sources of uncertainties, such as material distribution, loading and manufacturing errors. As an enormous progress in computational science, machine learning has a significant impact on structural engineering. Particularly, machine learning is closely linked to structural optimization, inverse analysis, and uncertainty qualification. The introduction of machine learning techniques will enhance the credibility, efficiency, generality, and robustness of these advanced numerical methods.
The aim of this Research Topic is to investigate how machine learning techniques can be applied to structural optimization, inverse analysis or uncertainty qualification. We are interested in both, theoretical innovation in modeling and simulation, and practical applications in structural engineering. In addition, we are intended to improve the algorithms of machine learning by incorporating prior knowledge of physical models.
The Research Topic scope includes but is not limited to the following areas in structural engineering in combination with machine learning:
• Shape optimization, topology optimization, size optimization, and material distribution optimization.
• Stochastic reliability modeling of the uncertainty problems associated with loading, materials, and geometries.
• Inverse analysis for parameter identification, non-destructive testing and structural health monitoring.
• Acceleration techniques or Model Order Reduction for large scale problems in structural engineering.
• Integration of Computer-Aided Design (CAD) and Computer-Aided Engineering (CAE).
• Physics-informed machine learning.
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.