Urban underground comprehensive pipe gallery abnormal event early warning method

Abstract

The invention discloses an abnormal event early warning method for an urban underground comprehensive pipe gallery. The method comprises the following steps: acquiring target attribute data through pipe gallery sensing equipment; performing data-level fusion on the data of the homogeneous data sensor by using Kalman filtering; the future pipe gallery data is predicted through an improved and trained TS-Transform model by means of the result of the data level fusion; using a D-S evidence theory to perform decision-level fusion on a data-level fusion result and predicted data; and real-time detection and early warning analysis are realized in parallel by utilizing a decision-making level fusion result. The proposed secondary data fusion model can effectively reduce the redundancy and uncertainty of the pipe gallery data; the provided prediction model solves the problem that a traditional RNN-based time sequence prediction model cannot be trained in parallel and is difficult to process long-term time dependence. According to the abnormal event early warning method, whether the abnormal event occurs in the pipe gallery or not can be detected in real time, possible accidents can be warned in advance, the major accident risk of the pipe gallery is effectively reduced, and economic losses are reduced.

Description

technical field [0001] The invention relates to the field of intelligent operation and maintenance of urban underground utility corridors, in particular to an early warning method for abnormal events of urban underground comprehensive utility corridors. Background technique [0002] The urban underground comprehensive pipe gallery is the underground nerve center of urban management, integrating power, communication, gas, heating, water supply and drainage and other engineering pipelines. It is an important infrastructure and "lifeline" to ensure the normal operation of the city. Centennial plan. In response to the call of the state, scholars and local governments continue to put forward a series of guiding opinions and normative measures for the informatization and intelligent construction of underground comprehensive utility corridors. [0003] Although with the strong support of the state, the smart construction of underground comprehensive utility corridors has attracted...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the technical problems existing in the existing solutions for the intelligent operation and maintenance of pipe corridors, the present invention provides a method for early warning of abnormal events in urban underground comprehensive pipe corridors based on multi-source information fusion

In addition, the Transformer-based deep learning model is used to predict the data in the future pipe corridor environment, which solves the shortcomings of the traditional RNN-based time series prediction model that cannot be trained in parallel and is difficult to deal with long-term time dependence, and embeds it into the pipe corridor In the data fusion model

Images