Crack damage location method and system based on artificial intelligence and acoustic emission technology

Abstract

The invention relates to a bridge crack damage location method and system based on artificial intelligence and acoustic emission technology. The method includes: S1, obtaining a lead breaking signal, and obtaining a data set through wavelet decomposition; S2, dividing the wavelet decomposition images in the data set into For images of different frequency segments, find out the optimal frequency segment images through preliminary training, and train according to the optimal frequency segment images to obtain the initial convolutional neural network; S3, transfer the trained parameters of the initial convolutional neural network through transfer learning Set as the fixed network parameters of the migrated convolutional neural network, repeat the process of step S2, send the crack acoustic emission signal into the migrated convolutional neural network for training, and obtain a crack damage identification and positioning model; S4, based on the model to be tested Crack damage classification and location judgment. The invention provides an acoustic emission source localization method of a general component, which can realize the acoustic emission source localization with only a few probes, and the localization effect is more accurate.

Description

technical field [0001] The invention relates to the technical field of crack damage location, in particular to a bridge crack damage location method and system based on artificial intelligence and acoustic emission technology. Background technique [0002] Due to untimely monitoring, maintenance and reinforcement, bridge collapse accidents at home and abroad have occurred frequently in recent years. Under the long-term action of external loads and environmental factors, bridges have inherent construction defects and deficiencies. In addition, the late detection, maintenance and reinforcement are not timely, which can easily cause major hidden safety problems. This is a problem that cannot be ignored. Scholars are focusing on research on systems for long-term health monitoring, damage diagnosis and timely early warning of major projects and their key structures. [0003] Acoustic emission technology is a dynamic non-destructive testing technology, which can effectively detec...

AI Technical Summary

Problems solved by technology

[0006] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a crack damage location method and system based on artificial intelligence and acoustic emission technology, which solves the problems of many occupied sensors, location accuracy affected by common components, and lack of suitable noise. Filtering and positioning accuracy can not meet the technical problems required

Images