Infrastructure intelligent monitoring method of skin-like structure

By constructing a spatiotemporal correlation model and data fusion technology, combined with a multi-grained perceptual map adjustment strategy, data understanding and prediction problems in structural health monitoring are solved, and high-precision and low-energy monitoring effects are achieved.

CN119646930AActive Publication Date: 2025-03-18TONGJI UNIV
7 Cites 0 Cited by

Patent Information

Application Number
CN202411673510.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-21
Publication Date
2025-03-18
Estimated Expiration
2044-11-21

AI Technical Summary

Technical Problem

The prior art is difficult to meet the needs of comprehensive understanding and accurate prediction of complex structural data in structural health monitoring, and it faces problems such as difficulty in sensor installation, high long-term operation energy consumption, and strong data heterogeneity.

Method used

A time series expansion convolutional network and dimensional isolation graph attention network are used to construct a spatiotemporal correlation model, combined with a conditional variational autoencoder for data fusion, and a multi-grained sensing map adjustment strategy is proposed to adapt to monitoring needs under different security conditions.

Benefits of technology

It realizes high-precision structural health assessment, is characterized by intuitiveness and low energy consumption, extends the service life of the sensor network, and improves monitoring flexibility and adaptability.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an infrastructure intelligent monitoring method of a skin-like structure, and relates to the technical field of civil engineering Internet of Things. The method comprises the following steps: acquiring infrastructure data of a plurality of sensor nodes in a sensor network; constructing a space-time correlation model according to the infrastructure data of the plurality of sensor nodes, and distinguishing the property of each sensor node in the sensor network according to the space-time correlation model; inputting the time features and the space features of the time-space correlation model into a conditional variational auto-encoder (CVAE) model, and determining a danger coefficient of each sensor node; and according to the danger coefficient of each sensor node, performing visualization processing on the structure health state of the infrastructure, and according to the danger coefficient of each sensor node and the property of each sensor node, adjusting the infrastructure monitoring work of the sensor network. By adopting the method, the monitoring precision can be ensured, the system energy consumption is effectively reduced, and the service life of the sensor network is prolonged.
Need to check novelty before this filing date? Find Prior Art