Fire alarm method based on olfaction chip and big data

By adopting fire alarm methods based on olfactory chips and big data in large storage centers, using sensor networks and advanced data analysis technology to identify and locate fire sources, the shortcomings of traditional methods in early fire detection are solved, and more efficient fire response and disposal are achieved.

CN119672892AInactive Publication Date: 2025-03-21BEIJING GUODING HUAJIAN TECH CO LTD
0 Cites 1 Cited by

Patent Information

Application Number
CN202411877737.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-19
Publication Date
2025-03-21
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

It is difficult to detect fires in large storage centers in the early stages, and traditional smoke detectors and temperature sensors cannot trigger alarms in time in the early stages of the fire, resulting in slow response.

Method used

The fire alarm method based on olfactory chips and big data is adopted to collect environmental data through a sensor network, including chemical molecular concentration, smoke particle concentration and ambient temperature, combined with the Krigin interpolation method to generate a visual model of gas distribution, local outlier factor LOF algorithm and convolutional neural network CNN are used to identify abnormal patterns, and the fire source is located through infrared thermal imaging equipment, and the hierarchical early warning mechanism is activated.

Benefits of technology

It significantly improves the accuracy and response speed of early fire detection, reduces the rate of false alarms and missed alarms, and improves the efficiency of fire disposal.

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

Abstract

The invention discloses a fire alarm method based on an olfactory chip and big data, and relates to the technical field of fire monitoring, and the method comprises the steps: collecting storage environment data through the olfactory chip, a smoke sensor and a temperature detector, and generating a three-dimensional visual model of gas distribution in combination with a diffusion equation and a Kriging interpolation method; a local outlier factor LOF algorithm is adopted to eliminate interference signals such as dust or harmless smoke, and a convolutional neural network CNN is adopted to identify fire feature modes such as high-risk gas combination, rapid increase of smoke concentration and abnormal temperature distribution; infrared thermal imaging equipment is adopted to scan an abnormal area, and spatial heat map information at the initial stage of a fire disaster is verified, so that the accuracy of fire source positioning is enhanced; and according to the abnormal mode and the positioning result, a grading early warning mechanism is carried out, a random forest algorithm is combined with environmental data after fire extinguishing to assess a re-combustion risk, and the future fire prevention and control capability is optimized by dynamically adjusting a sensor response threshold.
Need to check novelty before this filing date? Find Prior Art