Research Interests: Surrogate Modelling, Uncertainty Quantification, Stochastic Optimisation, Machine Learning

Research project title: Robust Design under Uncertainty

Project description: The goal of engineering design is to create technological systems that satisfy specific performance objectives and constraints over a period of time. However, modern engineering systems are inherently complex, and this complexity means that endogenous (geometry, material properties) and exogenous (loads) information is never complete. This lack of information can be captured by modeling uncertainties as random variables, whose distributions can in principle be obtained from expert opinion, literature or test data. The objective of performance-based design is therefore to determine the optimal design that minimizes an expected loss function which depends on both the characteristics of the design space and the model parameters that encode the characteristics of the system under study. However, simply optimizing for nominal performance usually results in a suboptimal design, as this approach fails to take into account the uncertainties that arise in modeling, manufacturing and operation. Moreover, once in operation, such designs usually suffer a sharper decline in performance due to degradation compared to other suboptimal designs. The aim of this project is to take all forms of uncertainty into account to perform robust optimization; obtaining a set of solutions with high performance and low variability in the face of uncertainty.

Supervisory team: Dr Francisco Alejandro Diaz De la O, Dr Peter Green

ORCID: 0000-0002-9018-7993