Integrated coupling model generation method for multi-source monitoring detection data

Abstract

The invention discloses an integrated coupling model generation method for multi-source monitoring detection data. Safety monitoring data and manual detection information are processed and analyzed byapplying data-level fusion and feature-level fusion in an information fusion technology; a reliable basic data source is provided for safety risk evaluation of a long-distance water diversion engineering structure; the evaluation result can truly reflect the structure safety state of the engineering operation period, long-term stable operation of the engineering is guaranteed, and the problem that the evaluation result deviates from the reality due to the fact that a single data source is used for evaluating the structure safety state of the long-distance water diversion engineering in the prior art is effectively solved.

Description

technical field [0001] The invention relates to the technical field of safety detection data processing, and more specifically relates to a method for generating an integrated coupling model of multi-source monitoring and detection data. Background technique [0002] The long-distance water diversion project is an important means to solve the uneven spatial distribution of water resources in my country and realize the optimal allocation of water resources. Therefore, it is particularly important to ensure that the structure of the water diversion project is in a safe and stable state. However, long-distance water diversion projects are generally linear projects, which have the characteristics of long water delivery lines, wide cross-domain ranges, various types and quantities of buildings, and complex geographical environments. Here comes the great challenge. Therefore, how to effectively process and analyze the actual measurement data of the original project, and accurate...

AI Technical Summary

Problems solved by technology

[0004] First, the reliability of the monitoring data is not high: due to the complexity of the long-distance water diversion project itself and its environment, as well as the limitations of sensor accuracy, quality and service life, there are inevitably errors in the monitoring data, that is, the collected Data is often incomplete, noisy or inconsistent

Errors include both data single-point errors and continuous data errors, so the authenticity and reliability of monitoring data needs to be improved

[0005] Second, the availability of detection information is poor: the environment of long-distance water diversion projects is relatively complex, and there are many types of diseases, and the content of manual inspection information is complex and diverse. Contains quantitative indicators (such as crack length and width, carbonization depth, corrosion area, etc.) with specific numerical results. If they are not structured, they cannot be used as an ideal data source for safety risk assessment of engineering structures

[0006] Third, the data source is single: simply using safety monitoring data or manual inspection information to evaluate the structural safety status of long-distance water diversion projects, resulting in the lack of basic data resources, making the evaluation results deviate from reality

[0007] To sum up, how to solve the problem that the evaluation results deviate from reality due to the evaluation of the structural safety status of long-distance water diversion projects mainly based on a single data source is an urgent problem to be solved by those skilled in the art

Images