Water leakage condition reconstruction method of large civil engineering structure based on deep learning

Abstract

The invention provides a water leakage condition reconstruction method for a large civil engineering structure based on deep learning, and the method comprises the steps of obtaining RSSI (Received Signal Strength Indicator) data through measurement according to a radio wave propagation path loss principle, and obtaining a loss factor distribution image through a water leakage condition reconstruction model, wherein the model training process includes: firstly, an RSSI sequence positive problem simulation numerical value is solved and normalized to obtain an RSSI sequence data set and a path loss factor image data set, a positive problem scale, attribute dimensions and label image dimensions are obtained through data to determine a model framework and initialization parameters, and then a water leakage condition reconstruction model is obtained through a training learning algorithm. According to the method, the reconstruction of the water leakage state of the large civil engineering structure can be realized more timely on a larger area and a larger scale through the correlation mapping relationship between the RSSI data and the loss factor distribution image which are easy to obtain, and the structural damage, economic loss and casualties caused by water leakage disasters can be reduced.

Description

technical field [0001] The invention relates to a deep learning-based method for reconstructing leakage water conditions of large civil engineering structures, and relates to the field of wireless monitoring of leakage water of large civil engineering structures. Background technique [0002] In the process of infrastructure construction, the structural safety of the shield tunnel is an important guarantee for the normal operation of the pipe gallery and tunnel construction. Water leakage is the most common and typical structural disaster of shield tunnels. Therefore, the realization of water leakage Detection and real-time monitoring are especially important. At present, the common solutions for water leakage detection of tunnel pipe gallery include manual visual inspection or measurement, infrared thermal imaging detection, laser scanning non-destructive testing, ground radar detection, ultrasonic detection and wireless sensor network data detection. Reconstructing the wa...

AI Technical Summary

Problems solved by technology

Reconstructing the water seepage situation in an area based on wireless sensor network data can be abstracted into an inverse problem in mathematics, and the classic inverse problem mostly uses iterative regularization to solve the inverse problem. Although regularization can improve the discomfort of the inverse problem to a certain extent Qualitative, but relying on more prior knowledge, the effect is still limited in the face of complex data, and needs further improvement

Images