Robust Design Optimization with Limited Data for Char Combustion

TL;DR

This paper introduces a robust optimization method for char combustion that efficiently uses limited data by integrating a polynomial dimensional decomposition surrogate model, enabling high-quality process parameter tuning with reduced computational cost.

Contribution

The study develops a novel surrogate modeling approach that leverages fixed probability measures and sparse regression to optimize char combustion processes with limited high-fidelity simulation data.

Findings

Efficient surrogate model training without additional data generation

Enhanced computational efficiency in process optimization

Successful optimization of char combustion parameters for high energy output

Abstract

This work presents a robust design optimization approach for a char combustion process in a limited-data setting, where simulations of the fluid-solid coupled system are computationally expensive. We integrate a polynomial dimensional decomposition (PDD) surrogate model into the design optimization and induce computational efficiency in three key areas. First, we transform the input random variables to have fixed probability measures, which eliminates the need to recalculate the PDD's basis functions associated with these probability quantities. Second, using the limited data available from a physics-based high-fidelity solver, we estimate the PDD coefficients via sparsity-promoting diffeomorphic modulation under observable response preserving homotopy regression. Third, we propose a single-pass surrogate model training that avoids the need to generate new training data and update the PDD coefficients during the derivative-free optimization. The results provide insights for optimizing process parameters to ensure consistently high energy production from char combustion.