Multi-fidelity Bayesian Optimization Framework for CFD-Based Non-Premixed Burner Design

2025-11-28

AI Summary

This work addresses the multi-objective trade-off among thermal efficiency improvement, NOₓ emission constraints, and computational cost in hydrogen-fueled non-premixed combustor design. We propose a multi-fidelity Bayesian optimization framework that innovatively introduces a continuous fidelity index to adaptively integrate high- and low-resolution CFD simulations. The method combines a Gaussian process surrogate model with a noisy-constrained expected improvement acquisition function to achieve an efficient accuracy–cost balance. Robustness is enhanced via surrogate-based sensitivity analysis. Experimental results demonstrate that the optimal design achieves an average flame temperature of approximately 2000 K while satisfying stringent NOₓ emission limits. Compared to single-fidelity approaches, the proposed framework reduces total wall-clock time by 57%, significantly accelerating convergence and improving computational resource utilization.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

We propose a multi-fidelity Bayesian optimization (MF-BO) framework that integrates computational fluid dynamics (CFD) evaluations with Gaussian-process surrogates to efficiently navigate the accuracy-cost trade-off induced by mesh resolution. The design vector x = [h, l, s] (height, length, and mesh element size) defines a continuous fidelity index Z(h, l, s), enabling the optimizer to adaptively combine low- and high-resolution simulations. This framework is applied to a non-premixed burner configuration targeting improved thermal efficiency under hydrogen-enriched fuels. A calibrated runtime model t_hat(h, l, s) penalizes computationally expensive queries, while a constrained noisy expected improvement (qNEI) guides sampling under an emissions cap of 2e-6 for NOx. Surrogates trained on CFD data exhibit stable hyperparameters and physically consistent sensitivities: mean temperature increases with reactor length and fidelity and is weakly negative with height; NOx grows with temperature yet tends to decrease with length. The best design achieves T_bar approx 2.0e3 K while satisfying the NOx limit. Relative to a hypothetical single-fidelity campaign (Z = 1), the MF-BO achieves comparable convergence with about 57 percent lower total wall time by learning the design landscape through fast low-Z evaluations and reserving high-Z CFD for promising candidates. Overall, the methodology offers a generalizable and computationally affordable path for optimizing reacting-flow systems in which mesh-driven fidelity inherently couples accuracy, cost, and emissions. This highlights its potential to accelerate design cycles and reduce resource requirements in industrial burner development and other high-cost CFD-driven applications.

Problem

• Optimizing non-premixed burner design for thermal efficiency with hydrogen fuels
• Managing computational cost-accuracy trade-off from mesh resolution in CFD simulations
• Achieving NOx emissions constraints while maximizing thermal performance

Innovation

• Multi-fidelity Bayesian optimization integrates CFD with Gaussian processes
• Continuous fidelity index adaptively combines simulation resolutions
• Constrained noisy expected improvement guides sampling under emissions cap