Multiobjective Bayesian Optimization for Aeroengine Using Multiple Information Sources

Abstract

Aero-engine performance optimization remains significant for both efficiency and safety during specific operating conditions. Previous works usually solve this optimization problem under a single-objective optimization framework, while multiple objectives need to be optimized simultaneously. Besides, the underlying optimization process requires a variety of function evaluations, and the evaluation cost for an aero-engine is expensive. In reality, the aero-engine model has multiple information sources with different costs and accuracy. The different costs and accuracy of the multiple information sources should be traded off to guide the search for the optimal in a cost-efficient way. Therefore, we propose a multi-information source framework for enabling efficient multi-objective Bayesian optimization. We construct the surrogate model with a multi-fidelity Gaussian process and choose the location-source pair with a modified acquisition function. Finally, we apply the proposed method to improve the performance indexes of the aero-engine, which confirms the efficiency of the proposed algorithm.