Steel structure damage detection method based on full-connection neural network and transmissibility function

Abstract

The invention discloses a steel structure damage detection method based on combination of a full-connection neural network and a transmissibility function, and the method comprises the steps: carryingout the transient analysis of a steel structure frame structure model through ANSYS software, obtaining the node accelerations of a steel structure frame structure under different damage positions and damage degrees, and obtaining the variable quantity of the transmissibility function through MATLAB software; obtaining a damage index value of each detection position of the steel structure by taking the variable quantity of the transmissibility function as an input parameter of the full-connection neural network; furthermore, carrying out experimental verification through a steel structure frame damage detection experiment. Results show that compared with a traditional transmissibility function method, the new method has the advantages that the steel structure damage recognition rate of all the positions is averagely improved by 26.3%, the damage conditions of all the positions of the steel structure can be recognized more accurately and comprehensively, and the damaged positions of the steel structure are accurately positioned.

Description

technical field [0001] The invention belongs to the field of steel structure damage detection, and in particular relates to a steel structure damage detection method based on the combination of a fully connected neural network and a transfer rate function. Background technique [0002] Large-scale steel structures (such as bridges or multi-storey buildings) are prone to cracks due to internal stress at the welds of steel structures during their service life, and bolts are prone to loosening at the joints of steel structures due to impact loads. In order to ensure the safety and reliability of these structures To prevent catastrophic accidents, early and reliable damage detection and health assessment are extremely important, while ultrasonic, eddy current, X-ray and magnetic flux leakage testing may involve high cost and intermittent exploration. [0003] The transmissibility function refers to the ratio of the frequency domain response or the energy ratio between two differ...

AI Technical Summary

Problems solved by technology

[0004] In the author's previous research, a steel structure damage detection method based on the transfer rate function and wavelet analysis successfully identified the damage at a specific location of the steel structure, but the existing transfer rate function method is not comprehensive enough for steel structure damage detection. accurate

Images