Efficient approximate optimization method for aircraft driven by heterogenous data

Abstract

The invention discloses an efficient approximate optimization method for aircraft driven by heterogenous data, and belongs to the technical field of aircraft engineering optimization. A fuzzy clustering point selection strategy based on distance identification is adopted to select high-quality local high / low-precision sample points with better feasibility and optimality from an alternative sample point set, and the optimization process is guided to rapidly converge to a global feasible optimal point; and a Co-kriging agent model of an aircraft system analysis model is constructed through selected high / low-precision sample points, and multi-source simulation analysis models with different precisions in engineering are fully utilized to realize guaranteed-precision fast-response prediction of a complex aircraft engineering system, the solving efficiency and robustness of an aircraft system optimization problem related to a high-time-consuming analysis model are improved, and the performance of a complex aircraft system is improved. The method is suitable for being applied to the field of aircraft complex engineering system optimization containing a high-precision analysis model, and corresponding related engineering problems are solved.

Description

technical field [0001] The invention relates to an efficient approximate optimization method for aircraft driven by heterogeneous data, and belongs to the technical field of aircraft engineering optimization. Background technique [0002] With the development of subject modeling technology, numerical computing technology and computer hardware and software, high-precision analysis models are widely used in the engineering practice of aircraft optimization, such as Computational Fluid Dynamics (Computational Fluid Dynamics, CFD) model of aerodynamics, structural discipline Finite Element Analysis (FEA) model, etc. Applying a high-precision analysis model can improve the confidence of the results and improve the quality of the vehicle, but at the same time it increases the computational cost. In addition, in the process of aircraft optimization, the high-precision analysis model is repeatedly called to find the optimal solution, which further increases the computational comple...

AI Technical Summary

Problems solved by technology

[0035] Aiming at the problem that the existing peak-chasing sampling method and its derivative algorithm are difficult to use heterogeneous data in engineering, the technical problem to be solved by the heterogeneous data-driven aircraft efficient approximate optimization method disclosed in the present invention is: through high / low precision sample points Construct a co-kriging proxy model of high-precision analysis model, make full use of the multi-source simulation model with different precision in the project, realize the accuracy-preserving and fast-response prediction of the complex engineering system of the aircraft, and effectively improve the aircraft engineering involving the high-time-consuming analysis model Optimizing problems to optimize efficiency and improve the quality of aircraft complex engineering systems

The present invention is suitable for use in the optimization field of aircraft complex engineering systems including high-precision analysis models, and solves corresponding related engineering problems

Images