Fire alarm method and system based on hidden variable model under big data

A technology of hidden variables and big data, applied in the field of fire alarm methods and systems based on hidden variable models under big data, can solve the problems of loss, difficulty in setting boundary values, and high costs, and achieve increased relevance and systematicness, guaranteeing Efficiency and accuracy, the effect of improving accuracy

Pending Publication Date: 2020-05-22
山东睿控电气有限公司
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The alarm mechanism formed by this logic may cause the situation that constitutes a fire alarm to be not alarmed in time, resulting in losses
[0007] (3) It is difficult to set the boundary value: Another huge defect of the traditional alarm mechanism is that it is difficult to set th

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fire alarm method and system based on hidden variable model under big data
  • Fire alarm method and system based on hidden variable model under big data
  • Fire alarm method and system based on hidden variable model under big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] figure 1 The flow chart of the fire alarm method based on the latent variable model under big data of this embodiment is given.

[0070] figure 2 A schematic diagram of the application of the fire alarm method based on the latent variable model under big data in this embodiment in an actual scene is given. exist figure 2 In , "scenario..." indicates an omitted situation.

[0071] Such as figure 1 and figure 2 As shown, a kind of fire alarm method based on the latent variable model under big data of the present embodiment includes:

[0072] Step 1: In each fire scene, receive temperature, smoke concentration and combustible gas concentration in real time, and use the fire event model F: F=a 1 f(T)+a 2 g(S)+a 3 h(X) outputs the probability of fire occurrence in the corresponding fire scene; when the fire probability in the fire scene is greater than the first type error threshold of the statistical hypothesis test, a fire alarm is given to the corresponding fir...

Embodiment 2

[0112] Such as Figure 9 As shown, the fire alarm system based on the latent variable model under big data of the present embodiment includes:

[0113] (1) Fire scene fire alarm module, which is used to receive temperature, smoke concentration and combustible gas concentration in real time in each fire scene, using the fire occurrence event model F: F=a 1 f(T)+a 2 g(S)+a 3 h(X) outputs the probability of fire occurrence in the corresponding fire scene; when the fire probability in the fire scene is greater than the first type error threshold of the statistical hypothesis test, a fire alarm is given to the corresponding fire scene; where f(T) is The implicit function of the single variable of fire and temperature T, g(S) is the implicit function of the single variable of fire and smoke concentration S, h(X) is the implicit function of the single variable of fire and combustible gas concentration X; a 1 、a 2 and a 3 Both are constant coefficients, which are temperature coef...

Embodiment 3

[0144] A computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps in the fire alarm method based on the latent variable model under big data as described in the first embodiment are implemented.

[0145] The beneficial effects produced by this embodiment are:

[0146] Low accuracy: Due to the use of the hidden variable model and the use of the maximum likelihood estimation method, the occurrence of the first type of error and the second type of error is effectively avoided

[0147] For the relative segmentation of the judgment basis: the hidden variable model used not only considers the influence of each judgment basis separately, but also considers the influence of the overall variable on the fire, which increases the correlation and systematization between the judgment basis to a certain extent.

[0148] It is difficult to estimate and determine the boundary value: because in the construction of the hidde...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a fire alarm method and system based on a hidden variable model under big data. The fire alarm method comprises the following steps: in each fire scene, receiving temperature, smoke concentration and combustible gas concentration in real time, and outputting a fire occurrence probability in the corresponding fire scene by utilizing a fire occurrence event model F:F= a1f(T)+a2g(S)+a3h(X); when the fire occurrence probability in the fire scene is greater than a statistical hypothesis test first-class error threshold, performing fire alarm on the corresponding fire scene; solving a fire occurrence probability mean value of all fire scenes, and when the fire occurrence probability mean value is greater than a statistical hypothesis testing second-class error threshold, sending out data exception alarm information and needing human intervention to further judge reasons causing the data exception alarm information; wherein f(T) is an implicit function of a fire and temperature T single variable, g(S) is an implicit function of a fire and smoke single concentration S variable, and h(X) is an implicit function of a fire and combustible gas concentration X single variable; and a1, a2 and a3 are all constant coefficients.

Description

technical field [0001] The invention belongs to the field of fire alarms, and in particular relates to a fire alarm method and system based on a hidden variable model under big data. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] In the field of fire protection, the traditional alarm mechanism is based on sensor alarms, such as alarm information from smoke alarms, temperature alarms and combustible gas sensors, based on simple rules. For example, a boundary value of an alarm temperature is set in advance, and an alarm is issued when the temperature judged by the temperature sensor is greater than the boundary value. Although the traditional method in this fire fighting is simple, it is not necessarily efficient. [0004] The inventor finds that the traditional alarm method mainly has the following problems: [0005] (1) Low accuracy: S...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G08B17/06G08B17/10G08B17/117G06F17/17G06F17/18
CPCG06F17/17G06F17/18G08B17/06G08B17/10G08B17/117
Inventor 金刚王豪井光路张毅骏
Owner 山东睿控电气有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap