PCE_BO-based structural performance parameter rapid inversion method

Abstract

The invention provides a PCEBO-based structure performance parameter rapid inversion method. The method comprises the following steps of 1, establishing a high-fidelity numerical model capable of representing structure physical model characteristics; 2, selecting structural performance parameters to be inverted as input variables, randomly sampling a finite group of input variable sets through a Latin super-cubic method, substituting the input variable sets into the structural numerical model to solve a corresponding output variable set, and constructing a polynomial chaos expansion agent model capable of representing structural characteristics; and step 3, taking actual measurement data corresponding to engineering demand parameters as an input set in a Bayesian optimizer, and rapidly updating structural performance parameters to be inverted based on a polynomial chaos expansion agent model in combination with a Bayesian optimization algorithm. According to the method, the defects of traditional deterministic back analysis are made up, the limitation that the inversion efficiency is limited by the calculation cost of a complex numerical model in the field of classical back analysis is liberated, the inversion efficiency and the robustness to noise are improved, and the purpose of quick inversion of structural performance parameters is achieved.

Description

technical field [0001] The invention belongs to the field of structural engineering and relates to a fast inversion method of structural performance parameters based on PCE_BO. Background technique [0002] As the main structure of water conservancy and hydropower projects, the safety of the dam is an important issue that people are very concerned about. In the field of dam safety monitoring and health diagnosis, determining the physical parameters of dam concrete and bedrock materials during construction and operation is crucial to predicting the safety of structures. A large part of the current back analysis of dam engineering parameters is based on deterministic analysis or finite probability analysis with engineering judgment. A large number of finite element analyzes are performed on the corresponding numerical models to solve the state equation. However, due to the special nature of the dam Due to the complex coupling between the geometric shape and different material...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems, the present invention provides a PCE_BO-based fast inversion method of dam structural performance parameters. Compared with existing methods, this method can overcome the shortcomings of traditional algorithms such as small application range and low calculation efficiency, and has excellent Robustness of

Images