Reduced-Space Multi-Fidelity Bayesian Optimization
Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models
This research provides a scalable method for optimizing complex industrial processes, which could be relevant for industries looking to improve efficiency and reduce costs.
A new framework called RS-MFBO is designed to optimize industrial process simulations. It uses Global Sensitivity Analysis to reduce dimensionality and a cost-aware acquisition strategy to guide sampling. The method was validated on two simulators, SuperPro Designer and Aspen HYSYS, and showed it can reduce the number of expensive high-fidelity evaluations while maintaining performance.
Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models
Optimizing industrial process flowsheets is often computationally prohibitive due to the high cost of rigorous simulations and the curse of dimensionality inherent in complex design spaces. To address these challenges, we present a reduced-space multi-fidelity Bayesian optimization (RS-MFBO) framework designed for high-dimensional, expensive black-box functions. The approach integrates Global Sensitivity Analysis (GSA) for dimensionality reduction with a fidelity-augmented Gaussian process that captures correlations between low-cost approximations and expensive high-fidelity evaluations. A cost-aware acquisition strategy, augmented with cooldown and promotion mechanisms, adaptively guides the allocation of samples across fidelities. The framework is validated on two distinct industrial process simulators: a plasmid DNA bioprocess in SuperPro Designer and a green fuel synthesis plant in Aspen HYSYS. Results across diverse economic and physical objectives demonstrate that the proposed method substantially reduces the number of high-fidelity simulator evaluations while maintaining competitive optimization performance compared to single-fidelity baselines. These results highlight RS-MFBO as a scalable, simulator-agnostic approach for cost-constrained black-box optimization.