Prediction method for residual bearing capacity and crack propagation path of crack-containing structure based on LSTM-cGAN

Abstract

The invention discloses a prediction method for the residual bearing capacity and the crack propagation path of a crack-containing structure based on LSTM-cGAN. The method comprises the following steps: at a training stage, firstly, obtaining the strength of a structure containing cracks of different degrees and a crack propagation path of the structure under a loading condition through finite element calculation or field actual measurement; and based on a conditional generative adversarial network model and a long-short-term memory method, simultaneously training four deep neural networks including a generation network G and a judgment network D, an LSTM network for processing a time sequence and a convolutional neural network CNN for judging crack structure strength; after the training is completed, inputting the structure crack propagation history measured on site into the generation network G and the LSTM network to obtain the prediction of the corresponding structure strength andcrack propagation path. According to the method, the strength and the crack propagation path of the crack-containing structure can be efficiently predicted, and the in-situ nondestructive monitoring of the crack-containing structure can be effectively realized.

Description

technical field [0001] The invention belongs to the intersecting field of civil structural engineering and computer vision, and in particular relates to a method for predicting the remaining bearing capacity of a crack-containing structure and a crack propagation path based on LSTM-cGAN. Background technique [0002] The occurrence and expansion of cracks are important hidden dangers that lead to the decline and failure of structural durability, and may lead to structural catastrophe accidents. In actual engineering, most reinforced concrete structures are in a working state with cracks during the operation period. Therefore, monitoring the cracked structure and predicting its crack propagation path and structural strength are important contents of the monitoring of civil structures during the operation period. [0003] In the traditional crack propagation path and strength prediction method, a physical model is often established according to the current mechanical state, an...

AI Technical Summary

Problems solved by technology

[0003] In the traditional crack propagation path and strength prediction method, a physical model is often established according to the current mechanical state, and the crack propagation path and strength at the next moment are obtained by iteratively solving the structural control equations. However, when the structural performance degrades, or When the internal structure of the composite material is unknown, the assumed physical model is often incorrect and the simulation results are not satisfactory

Images