A finite element analysis parameter Bayesian optimization method and device
A technology for analyzing parameters and optimization methods, applied in design optimization/simulation, special data processing applications, calculations, etc., can solve problems such as limited optimization effects and large calculation costs, and achieve the effects of saving energy, improving efficiency, and ensuring optimization effects
Active Publication Date: 2022-02-22
FUDAN UNIV
View PDF10 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, random search is still a brute force search method in the parameter space, the optimization effect is limited in the case of limited computing resources, and it still requires a large computational cost
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0019] In order to make the technical means, creative features, goals and effects of the present invention easy to understand, a Bayesian optimization method and device for finite element analysis parameters of the present invention will be described in detail below in conjunction with the embodiments and accompanying drawings.
[0020]
[0021] The specific implementation platform of a Bayesian optimization method and device for finite element analysis parameters in this embodiment: the operating system is windows 7, implemented with Python 3.7 language, and the version of Unigraphics NX used is 12.0.
[0022] The Bayesian optimization in this embodiment is a heuristic search method, and its basic idea is to use Bayesian theorem to estimate the posterior distribution of the objective function, sample in this distribution and input the objective black-box function to update the distribution. That is to first determine the prior distribution of the model (generally set to obey...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a Bayesian optimization method and device for finite element analysis parameters, which optimizes the multidimensional heat conduction parameters involved in the finite element model to obtain the optimal thermal analysis result, and is characterized in that it includes the following steps: setting the multidimensional heat conduction parameters Input the initial value of the finite element analysis software with the finite element model; set Bayesian optimization information in the secondary development program; retrieve the thermal analysis temperature; obtain sample points, and update the initial Gaussian process model; use the acquisition function to obtain The evaluation point, and update the thermal analysis file according to the evaluation point to obtain the updated thermal analysis file; use the finite element analysis software to perform thermal analysis on the updated thermal analysis file to obtain the optimized thermal analysis result; judge whether the number of iterations has been reached, and when the judgment is no, set The optimized thermal analysis result is used as the new initial thermal analysis result, and the updated thermal analysis file is used as the new thermal analysis file for further optimization; when the judgment is yes, the optimal thermal analysis result is output.
Description
technical field [0001] The invention belongs to the field of electrical digital data processing, and in particular relates to a Bayesian optimization method and device for finite element analysis parameters. Background technique [0002] Finite element analysis simulates and analyzes real physical systems through mathematical approximation to obtain analysis results, which can be applied to heat conduction analysis. The finite element analysis requires a lot of calculations in the analysis process, and the calculations are generally completed with the aid of computer software. Unigraphics NX is an efficient computer software for finite element thermal analysis. When using the finite element analysis method for heat conduction analysis, it is necessary to provide relevant parameters such as thermo-optical properties, density, and thickness. These related parameters will directly affect the analysis results, and usually need to be continuously optimized according to actual n...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/23G06F119/08
CPCG06F30/23G06F2119/08
Inventor 李洪毅薛恩晓冯瑞
Owner FUDAN UNIV