Comprehensive utility tunnel fire early warning method based on fusion of multi-source parameters and their gradient information

Abstract

The invention discloses a comprehensive pipe gallery fire early warning method that integrates multi-source parameters and gradient information, and relates to the field of fire early warning, including S1 establishing a fire risk prediction model; S2 collecting temperature, smoke concentration and carbon monoxide concentration, and importing the fire risk prediction model , and determine the gradient information; S3 determines the fire type and obtains the fire probability through the gradient information and the fire risk prediction model, and performs fire warning; by establishing a fire risk prediction model based on temperature, CO concentration and smoke concentration, through the gradient information of temperature characteristic parameters , and use the continuous state of CO and smoke concentration change rate to make auxiliary judgments, synthesize the environmental changes, and get the fire decision value of the parameter gradient, and then weighted and fuse the multi-source parameter decision probability and fire decision value to get the final fire probability value. The decision-making method is used to judge the current fire situation, and the output value of a single model is no longer used as the basis for judging the fire, which improves the reliability and real-time performance of fire judgment.

Description

technical field [0001] The invention relates to the field of fire early warning, in particular to a fire early warning method for a comprehensive utility gallery that integrates multi-source parameters and gradient information. Background technique [0002] The comprehensive pipe gallery is an underground urban comprehensive pipe corridor that integrates electrical pipelines, gas pipelines, water supply and drainage pipelines, communications, and heating pipelines. In order to ensure the operation safety of the comprehensive pipe gallery, multiple early warning system for disasters. Fire is one of the main monitoring objects for the environmental safety of comprehensive utility corridors, and it is necessary to establish a fire early warning system with early warning capabilities and high accuracy. Most of the traditional fire detectors use a single fire characteristic parameter such as gas concentration, smoke concentration, and temperature as the basis for fire judgment, ...

AI Technical Summary

Problems solved by technology

Most of the traditional fire detectors use a single fire characteristic parameter such as gas concentration, smoke concentration, and temperature as the basis for fire judgment, and are easily affected by external interference, resulting in false alarms and untimely early warning problems.

For example, a fire alarm that uses temperature monitoring only sends out an alarm signal when the temperature exceeds the threshold, and cannot monitor the rapid increase in temperature at the initial stage of a fire, and does not have fire early warning capabilities.

Moreover, if only a single fire characteristic parameter is monitored, it cannot be correlated with other parameters, which is prone to false positives and false negatives. The existing fire early warning algorithm that integrates multiple parameters, but the timeliness and accuracy of fire early warning still need to be improved

Images