Structural anomaly monitoring data reconstruction method and device with environment temperature correlation

Abstract

The invention provides a structural anomaly monitoring data reconstruction method and device with environment temperature correlation, electronic equipment and a storage medium. The structural anomaly monitoring data reconstruction method with environment temperature correlation comprises the following steps: obtaining to-be-reconstructed structural anomaly monitoring data; inputting the to-be-reconstructed structural anomaly monitoring data and the environment temperature data corresponding to the to-be-reconstructed structural anomaly monitoring data into the trained structural anomaly monitoring data reconstruction model to obtain a prediction data sequence output by the structural anomaly monitoring data reconstruction model, wherein the prediction data sequence is a missing part in the structural anomaly monitoring data predicted by the model; and based on the generated prediction data sequence, reconstructing the structure anomaly monitoring data sequence to obtain a complete structure monitoring data sequence, wherein the structure anomaly monitoring data reconstruction model is obtained by training based on the sample anomaly data and a complete sample structure monitoring data sequence corresponding to the sample anomaly data.

Description

technical field [0001] The present invention relates to the field of structural anomaly data reconstruction methods based on deep learning, in particular to a structural anomaly monitoring data reconstruction method, device, electronic equipment and storage medium with environmental temperature correlation. Background technique [0002] Usually, during the construction of hydraulic structures such as dams and sluices, as well as industrial and civil structures such as tunnels, bridges, and civil foundation pits, due to water pressure, backfilling soil behind walls, and other external loads, the main structure of the building cannot be avoided. Therefore, it is necessary to pay close attention to the deformation and stability of the building structure during the construction process and later operation, so it is necessary to monitor the changes of the building structure in real time. Long-term monitoring data can provide a reference for the status assessment and safety evalua...

AI Technical Summary

Problems solved by technology

[0004] However, the application of deep learning methods for single-dimensional input and one-way prediction to abnormal data reconstruction still faces two difficulties: (1) the sequence accuracy predicted by the neural network model will decrease with the increase of the sequence length of the backward prediction; and (2) The input sequence is the single-dimensional input network model of the structural monitoring data sequence itself, which is difficult to meet the accuracy requirements of data reconstruction.

Images