Bayesian Optimization of a Lightweight and Accurate Neural Network for Aerodynamic Performance Prediction

2025-03-25

AI Summary

In multidisciplinary design optimization for aerospace applications, balancing accuracy and efficiency in aerodynamic performance prediction remains challenging. This paper proposes a Bayesian optimization–based automated hyperparameter tuning method for lightweight neural networks. Innovatively, it constructs a hybrid Gaussian process surrogate model by integrating hierarchical and categorical kernels to explicitly capture the heterogeneous structure of aerodynamic design variables. Coupled with lightweight neural architecture search, the method jointly optimizes predictive accuracy and parameter efficiency. On drag coefficient prediction, the proposed approach achieves a mean absolute percentage error (MAPE) of 0.0163%, improving upon baseline methods by nearly an order of magnitude. For aircraft self-noise prediction, it attains a MAPE of 0.82%, substantially outperforming existing methods (2–3%) while significantly reducing computational cost. The framework establishes a new paradigm for high-fidelity, low-overhead aerodynamic modeling.

Technology Category

• Machine Learning: Auto ML and Hyperparameter Tuning
• Search and Optimization: Mixed Discrete/Continuous Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Ensuring high accuracy and efficiency of predictive models is paramount in the aerospace industry, particularly in the context of multidisciplinary design and optimization processes. These processes often require numerous evaluations of complex objective functions, which can be computationally expensive and time-consuming. To build efficient and accurate predictive models, we propose a new approach that leverages Bayesian Optimization (BO) to optimize the hyper-parameters of a lightweight and accurate Neural Network (NN) for aerodynamic performance prediction. To clearly describe the interplay between design variables, hierarchical and categorical kernels are used in the BO formulation. We demonstrate the efficiency of our approach through two comprehensive case studies, where the optimized NN significantly outperforms baseline models and other publicly available NNs in terms of accuracy and parameter efficiency. For the drag coefficient prediction task, the Mean Absolute Percentage Error (MAPE) of our optimized model drops from 0.1433% to 0.0163%, which is nearly an order of magnitude improvement over the baseline model. Additionally, our model achieves a MAPE of 0.82% on a benchmark aircraft self-noise prediction problem, significantly outperforming existing models (where their MAPE values are around 2 to 3%) while requiring less computational resources. The results highlight the potential of our framework to enhance the scalability and performance of NNs in large-scale MDO problems, offering a promising solution for the aerospace industry.

Problem

• Optimize neural network for aerodynamic prediction accuracy
• Reduce computational cost in aerospace design optimization
• Improve performance in large-scale multidisciplinary optimization

Innovation

• Bayesian Optimization for Neural Network hyper-parameters
• Hierarchical and categorical kernels in BO
• Lightweight NN for aerodynamic performance prediction