Engineering disaster early warning method and system based on collaborative fusion of multi-physics field monitoring data

Abstract

The invention relates to a multi-physics field monitoring data collaborative fusion engineering disaster early warning method and system, and belongs to the field of hydraulic engineering disaster prevention and control. The method comprises the steps that after multi-sensor real-time monitoring data of a potential dangerous part of an engineering structure is obtained and preprocessed, normalization processing is carried out on multi-physical field monitoring time sequence data, and a normalized sample matrix is constructed; analyzing the sensitivity of each physical field monitoring index to the engineering safety state by adopting a multivariate statistical method, and guiding the initialization training of the long short-term memory network according to the sensitivity to obtain an output result of the long short-term memory network; and taking an output result of the long-short-term memory network as evidence input, obtaining basic probability assignment of each early warning level after fusion according to an evidence theory fusion rule of Chebyshev distance improvement, and determining a disaster danger level of a potential danger part of the engineering structure by adopting a decision-making method of basic probability assignment. By adopting the method and the system, the early warning precision of engineering disasters can be improved.

Description

technical field [0001] The invention relates to the technical field of water conservancy engineering disaster prevention and control, in particular to an engineering disaster early warning method and system for collaborative fusion of multi-physical field monitoring data. Background technique [0002] Water conservancy project disaster monitoring and early warning refers to monitoring the overall water conservancy project or potential disaster body deformation, micro-seismic and other indicators through technical means such as strain sensors, optical fiber sensors, osmometers, acoustic emission, and remote sensing. , pre-alerts a threatened area or group of people. [0003] The responses of different monitoring indicators in the instability process of engineering structures are not synchronized, and the comparison and analysis of a single response indicator or similar signals has a large error in predicting rock mass failure, and the warning time is not uniform. Multi-physi...

AI Technical Summary

Problems solved by technology

The application in early warning of engineering damage is still in its infancy, and a unified fusion rule and effective fusion algorithm have not yet been established, and there is a lack of mature early warning technology for fusion of signals with different physical attributes

Images