Method and system for identifying working mode parameters of time-invariant structure

Abstract

The invention discloses a method and system for identifying working mode parameters of a time-invariant structure. A method with isometric feature mapping and for identifying the working mode parameters of the three-dimensional time-invariant structure is adopted, can well express the nonlinear feature of the three-dimensional structure since the neighbor relation among near-earth distance measurement gauging points is adopted for an isometric feature mapping algorithm, has a good effect of identifying the working mode parameters of the complicated three-dimensional structure, and can be usedfor equipment fault diagnosis, health monitoring and system structure analysis and optimization. The invention further provides a method for identifying the working mode parameters of a Sanger neuralnetwork time-invariant structure. A method for identifying the working mode parameters of parallel pivot element extracting based on the Sanger neural network is used. Multi-order principal componentsare obtained through parallel iteration of the learning rate and the learning rule and easily embedded into multi-core hardware, and the method and system have high engineering value.

Description

technical field [0001] The present invention relates to the field of modal parameter identification, in particular to a method and system for identifying working modal parameters of a time-invariant structure, including a three-dimensional time-invariant structure working modal parameter identification method with equidistant feature mapping, a method based on A time-invariant structure of Sanger neural network work mode parameter identification method, a device fault diagnosis and health status monitoring method based on isometric feature mapping, a device fault diagnosis and health status monitoring method based on Sanger neural network and a A system for identifying operating modal parameters of a time-invariant structure. Background technique [0002] With the development and progress of science and technology, engineering structures in the fields of aerospace, architecture, bridges, oceans, machinery, etc. are gradually developing in the direction of large-scale, comple...

AI Technical Summary

Problems solved by technology

However, the solution of the principal component analysis model based on the method of eigenvalue decomposition may have ill-conditioned problems, and the method of matrix inversion and inverse substitution is used in the solution of the three-dimensional mode shape, so the solution result is likely to cause large errors

In 2017, Wang Jianying and others proposed to use the second-order blind identification to solve the complex three-dimensional structure. Although the ill-conditioned problem solved by the principal component analysis algorithm is avoided, the assembly method of the three-dimensional mode shape follows the method of matrix inversion and inversion

The working modal parameter identification method based on local linear embedding is an algorithm based on nonlinear manifold learning, but it is mainly aimed at the structural nonlinearity caused by the increase of the damping ratio of the structure, and does not dig deep into the 3D modal response data. The nonlinear characteristics of

Images