Knowledge-based surrogate modeling in engineering design optimization

Simulations and numerical experiments of engineering problems are often expensive, which may restrict sensitivity analysis and design optimization. Surrogate modeling methodologies are currently being studied to construct approximation models of system responses based on a limited number of the expensive evaluations. The use of surrogate models allows more efficient exploration and exploitation of the system. However, the curse of dimensionality is still an obstacle for large and complex engineering design problems. The required number of high-fidelity evaluations becomes tremendously large in a high-dimensional space. Therefore, it is advisable to adopt knowledge-based surrogate modeling in engineering design optimization. With engineering insight into the system, a high-dimensional design space can be intelligently mapped into system properties, so that better choices of inputs, outputs, and function formulations can be made for surrogate modeling. This chapter covers the methods of embedding engineering knowledge in surrogate modeling for structural mechanical systems and provides application examples in the field of aerospace engineering.