Partial least square Kriging model-assisted aviation reducer efficient global optimization method

Abstract

The invention provides a partial least square Kriging model-assisted aviation speed reducer efficient global optimization method. The method comprises the following steps: carrying out initial test design; a computer is used for achieving simulation calculation, a target response value of the total weight of the gearbox and constraint response values of gear, tooth root and tooth surface strength are obtained, and a DS database is established; performing normalization processing and partial least square transformation on the DS database, determining the number of principal components, and constructing a partial least square Kriging kernel function; constructing a feasibility probability strategy to realize sample filling, or constructing a maximization partial least square constraint weight expectation improvement criterion to realize space sample filling, and placing filled sample data and a simulation output target value and a response value corresponding to the filled sample data in a DS database; and iteratively updating the DS database until the maximum number of iterations is reached or a threshold value meeting the maximum constraint expectation improvement criterion is met. According to the method, efficient construction and self-adaptive adjustment of the Kriging proxy model under the multivariable condition can be achieved, rapid convergence of the globally optimal solution is achieved, and the expensive simulation cost is reduced.

Description

technical field [0001] The invention relates to computer simulation and engineering optimization calculation, and in particular relates to an efficient global optimization method for an aviation reducer assisted by a partial least squares Kriging model. Background technique [0002] Under the background of global competition, enterprise product development and product verification rely more and more on computer experiments. Efficient design methods, simulation technologies and optimization methods have become a strong support for enterprises to occupy the market. Although the application of high-precision simulation technology has effectively improved the quality and reliability of computer experiments, complex product design and system optimization problems often consume a lot of simulation time. In addition, the complex inner code of the high-precision simulation model and the closedness of commercial simulation software make the input and output show a "black box" functio...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a partial least squares Kriging model-assisted high-efficiency global optimization method for aviation reducers to solve the problems of long training time, expensive simulation and time-consuming problems in the high-dimensional data modeling process existing in the design of aviation reducers. Low utilization of computing resources

Images