Method and device for optimizing finite element iteration process based on deep learning

Abstract

The invention provides a method and a device for optimizing a finite element iteration process based on deep learning, and relates to the technical field of civil structure engineering and computers. The method comprises the following steps: establishing a single unit finite element model based on a constitutive relationship; performing iterative calculation solution on the single unit finite element model, and summarizing iteration process data to form a data set; carrying out deep learning on a difficult-to-converge data set of a single unit finite element model; and establishing a real structure finite element model according to the constitutive relationship and the deep learning model, defining a load working condition and a loading and unloading path according to the actual stress condition of the structure, obtaining a finite element simulation result of the real structure, and completing an optimization finite element iteration process based on deep learning. According to the method, prediction of the next state point in iteration is achieved through the deep learning algorithm, the number of iteration steps is reduced, the calculation efficiency and convergence of the finite element model are optimized on the basis that the accuracy of the simulation result is guaranteed, and high universality is achieved.

Description

technical field [0001] The present invention relates to the fields of civil structural engineering and computer technology, in particular to a deep learning-based optimized finite element iterative process method and device. Background technique [0002] In the calculation and analysis of civil and structural engineering, the finite element method is based on the idea of ​​discretization to model and analyze the structure. It has become an important technical means because of its simple and clear physical concept, convenience and practicality, and wide application range. The finite element calculation needs to solve the nonlinear equations. Since the constitutive relationship of materials or components is often complex, it often involves the solution of implicit equations, which needs to be solved by iterative method. [0003] At present, the iterative methods commonly used in finite element calculations in the prior art include secant stiffness iterative method, Newton-Raph...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the iteration speed in the prior art is relatively slow, thereby affecting the calculation efficiency of the finite element, the present invention proposes a method and device for optimizing the iterative process of the finite element based on deep learning

Images