SUMMARY

The design of strongly coupled multidisciplinary engineering systems is challenging since it is characterized by the complex interaction of different disciplines. Such complexity cannot be easily captured by explicit analytical solutions. This deficiency motivates the development of surrogate modeling that enables the prediction of the systems' behavior without analytical formulations. Among existing surrogate modeling techniques, deep learning has gained significant interest because of the flexibility of non-linear formulation and applicability to data-driven analysis. Notably, a deep surrogate model augments the precision of prediction and estimation of system behavior once image-based inputs that represent physical experiments and simulation are employed. Nevertheless, the deep surrogate model's feasibility is often flawed due to massive training costs and complicated network structures. To address those issues, in the proposed research, physics-informed artificial image (PiAI) is constructed and utilized to train deep neural networks in strongly coupled multidisciplinary domains. To further improve the credibility of deep surrogate models, a statistical calibration process is proposed to match the data distributions of the training and test sets. The calibration process can resolve the covariate shift that occurs when the data distributions are heterogeneous. Lastly, multi-fidelity deep surrogate modeling is proposed to enhance computational productivity. The efficacy and applicability of the proposed framework are also addressed in practical engineering design applications: cantilever beam and stretchable strain sensor.