Fast and robust parametric and functional learning with Hybrid Genetic Optimisation (HyGO)

2025-10-10

AI Summary

To address the lack of an efficient, unified framework for joint parameter and functional optimization in complex engineering problems—particularly the slow convergence in late-stage derivative-free global optimization (e.g., evolutionary algorithms)—this paper proposes HyGO, a hybrid global optimization framework. HyGO innovatively integrates global exploration (via genetic algorithms or genetic programming) with an enhanced Downhill Simplex Method (DSM) for local refinement, employing a two-stage adaptive strategy to balance exploration and exploitation: in the parameter optimization stage, GA and DSM operate in tandem; in the functional optimization stage, GP and DSM alternate iteratively. Validated through RANS-based numerical simulations, HyGO demonstrates superior convergence speed and robustness across multiple benchmark problems. Applied to aerodynamic shape optimization of the Ahmed body, HyGO achieves over 20% drag reduction while significantly improving flow attachment and suppressing separation bubble formation.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization
• Machine Learning: Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

The Hybrid Genetic Optimisation framework (HyGO) is introduced to meet the pressing need for efficient and unified optimisation frameworks that support both parametric and functional learning in complex engineering problems. Evolutionary algorithms are widely employed as derivative-free global optimisation methods but often suffer from slow convergence rates, especially during late-stage learning. HyGO integrates the global exploration capabilities of evolutionary algorithms with accelerated local search for robust solution refinement. The key enabler is a two-stage strategy that balances exploration and exploitation. For parametric problems, HyGO alternates between a genetic algorithm and targeted improvement through a degradation-proof Dowhill Simplex Method (DSM). For function optimisation tasks, HyGO rotates between genetic programming and DSM. Validation is performed on (a) parametric optimisation benchmarks, where HyGO demonstrates faster and more robust convergence than standard genetic algorithms, and (b) function optimisation tasks, including control of a damped Landau oscillator. Practical relevance is showcased through aerodynamic drag reduction of an Ahmed body via Reynolds-Averaged Navier-Stokes simulations, achieving consistently interpretable results and reductions exceeding 20% by controlled jet injection in the back of the body for flow reattachment and separation bubble reduction. Overall, HyGO emerges as a versatile hybrid optimisation framework suitable for a broad spectrum of engineering and scientific problems involving parametric and functional learning.

Problem

• HyGO addresses slow convergence in evolutionary optimization algorithms
• It integrates global exploration with accelerated local search methods
• The framework solves both parametric and functional engineering optimization problems

Innovation

• Hybrid Genetic Optimisation combines evolutionary algorithms with local search
• Two-stage strategy balances exploration and exploitation phases
• Alternates genetic algorithm with degradation-proof Dowhill Simplex Method