CN114792194B - Whole fire control safety intelligent system of building - Google Patents
Whole fire control safety intelligent system of building Download PDFInfo
- Publication number
- CN114792194B CN114792194B CN202210261185.6A CN202210261185A CN114792194B CN 114792194 B CN114792194 B CN 114792194B CN 202210261185 A CN202210261185 A CN 202210261185A CN 114792194 B CN114792194 B CN 114792194B
- Authority
- CN
- China
- Prior art keywords
- fire
- data
- building
- information
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011161 development Methods 0.000 claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 14
- 239000000779 smoke Substances 0.000 claims description 75
- 230000018109 developmental process Effects 0.000 claims description 45
- 239000000463 material Substances 0.000 claims description 38
- 238000012216 screening Methods 0.000 claims description 23
- 238000013528 artificial neural network Methods 0.000 claims description 20
- 238000010276 construction Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 12
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 8
- 238000007667 floating Methods 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000005507 spraying Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 5
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 4
- 238000013210 evaluation model Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 239000002918 waste heat Substances 0.000 claims description 3
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 2
- 230000004913 activation Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 claims description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 2
- 239000001569 carbon dioxide Substances 0.000 claims description 2
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 2
- 229910052760 oxygen Inorganic materials 0.000 claims description 2
- 239000001301 oxygen Substances 0.000 claims description 2
- 230000000737 periodic effect Effects 0.000 claims description 2
- 238000011176 pooling Methods 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims description 2
- 230000003213 activating effect Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000007480 spreading Effects 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000035784 germination Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B1/00—Systems for signalling characterised solely by the form of transmission of the signal
- G08B1/08—Systems for signalling characterised solely by the form of transmission of the signal using electric transmission ; transformation of alarm signals to electrical signals from a different medium, e.g. transmission of an electric alarm signal upon detection of an audible alarm signal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/72418—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality for supporting emergency services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/57—Mechanical or electrical details of cameras or camera modules specially adapted for being embedded in other devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Networks & Wireless Communication (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Primary Health Care (AREA)
- Human Computer Interaction (AREA)
- Emergency Management (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
Abstract
The invention provides an intelligent system for overall fire safety of a building, which comprises a fire situation acquisition module, a cloud platform and a fire situation monitoring module, wherein the fire situation acquisition module is used for acquiring fire situation data based on a plurality of various sensors and uploading the fire situation data to the cloud platform through an internet of things; the intelligent processing module is used for carrying out position positioning and situation evaluation on the fire based on the constructed integral three-dimensional scene of the building according to the fire data to obtain the fire grade and the fire development trend; and the fire handling module is used for executing a handling plan and implementing overall rescue resource scheduling according to the fire grade and the fire development trend. According to the invention, by acquiring and processing fire data, carrying out grade evaluation and development trend judgment on the found fire, executing a disposal plan and implementing overall rescue resource scheduling, the intelligent management level of the overall fire safety of the building can be improved.
Description
Technical Field
The invention relates to the technical field of fire safety, in particular to an intelligent building overall fire safety system.
Background
Along with the continuous development of fire safety technology, the intelligent construction of the whole fire safety of the building is more and more emphasized; particularly, for high-rise buildings, no matter commercial office buildings or houses, the conditions of dense personnel and narrow space exist, the personnel activity forms are various, once a fire disaster happens in a relatively narrow space, the propagation speed is very quick, and huge casualties and property loss are easily caused, so that the overall fire safety of the building is especially important; the existing building is safe in fire fighting, and has the conditions of incomplete fire information acquisition, backward monitoring means and untimely disposal; therefore, a building integrated fire safety intelligent system is needed.
Disclosure of Invention
The invention provides an intelligent system for overall fire safety of a building, which can improve the intelligent management level of the overall fire safety of the building by acquiring and processing fire data, performing grade assessment and development trend judgment aiming at the found fire, executing a disposal plan and implementing overall rescue resource scheduling.
The invention provides an intelligent system for integral fire safety of a building, which comprises:
the fire situation acquisition module is used for acquiring fire situation data based on a plurality of various sensors and transmitting the fire situation data to the cloud platform through the Internet of things;
the intelligent processing module is used for carrying out position positioning and situation evaluation on the fire according to the fire data based on the constructed integral three-dimensional scene of the building to obtain the fire grade and the fire development trend;
and the fire handling module is used for executing a handling plan and implementing overall rescue resource scheduling according to the fire grade and the fire development trend.
Furthermore, the fire acquiring module comprises a plurality of smoke sensors, a plurality of temperature sensors and a plurality of cameras which are arranged in the internal space and the external space of the building, internet of things communication equipment, a cloud platform terminal and a cloud platform database; the smoke sensors are used for collecting smoke concentration data; the temperature sensors are used for collecting temperature data; the cameras are used for collecting image data; integrating the smoke concentration data, the temperature data and the image data to obtain fire data; the Internet of things communication equipment is connected with the cloud platform terminal, and the cloud platform terminal is connected with the cloud platform database through a network.
Further, the fire situation acquisition module comprises a data screening unit, and is used for screening the fire situation data according to preset screening conditions to obtain screening data meeting requirements, and uploading the screening data to a cloud platform; the screening conditions include: the smoke concentration value in the smoke concentration data is larger than or equal to a preset smoke concentration value, the temperature value in the temperature data is larger than or equal to a preset temperature value, and an image in the image data has similarity with a pre-stored image.
Furthermore, the intelligent monitoring module comprises a three-dimensional scene construction unit, a fire positioning unit and a fire evaluation unit;
the three-dimensional scene construction unit is used for constructing an internal three-dimensional scene of an internal space of the building through three-dimensional modeling software according to the integral structure drawing of the building, constructing an external three-dimensional model of an external space of the building through 3DSMAX software, and integrating the internal three-dimensional scene and the external three-dimensional model to obtain the integral three-dimensional scene of the building; the building internal space comprises all rooms, stair corridors and underground spaces in the building; the building external space comprises a building external facade space, a building external wall protruding space and a building top terrace space;
the fire positioning unit is used for positioning the fire occurrence position in the integral three-dimensional scene of the building according to the collected fire data by referring to a fire position positioning library preset in the cloud platform data storage;
the fire evaluation unit is used for evaluating fire according to the smoke concentration data and the temperature data and a preset fire grade evaluation model to obtain a fire grade; and judging the fire according to the image data and a preset fire development trend model to obtain the fire development trend.
Further, the construction of the fire location database comprises:
acquiring a historical fire data set based on the cloud platform database, and acquiring fire characteristics corresponding to the historical fire data set; the fire characteristics comprise smoke sensor numbers, temperature sensor numbers and camera numbers;
acquiring a preset interval division table of a building internal space and a building external space, wherein the interval division table comprises a plurality of items of contents; the plurality of items of content distinguish important content from non-important content; the important content corresponds to a key fire monitoring space of the building; the non-important content corresponds to a non-key fire monitoring space of the building;
combining and pairing the smoke sensor numbers with the corresponding non-important contents according to a sequence order to obtain a plurality of first pairing items, and simultaneously obtaining the numbers of the rest smoke sensors; combining and pairing the residual smoke sensor numbers, the temperature sensor numbers and the camera numbers with the important contents simultaneously according to the sequence order to obtain a plurality of second pairing items; and storing the plurality of first pairing items and the plurality of second pairing items into a preset blank library, and taking the blank library as a fire position positioning library to complete the construction of the fire position positioning library.
Further, the fire evaluation unit comprises a fire grade and fire development trend judgment subunit, and is used for determining the fire grade and judging the fire development trend; the fire level and fire development trend judgment subunit comprises a data set acquisition molecular unit, a fire level determination molecular unit and a fire development trend judgment molecular unit;
the data set acquisition molecular unit is used for acquiring a plurality of typical fire data according to the cloud platform database and establishing an initial sample database; the typical fire data comprises typical smoke concentration data, typical temperature data and typical image data; the typical smoke concentration data comprises three types of data of large, medium and small smoke concentration selected according to a preset smoke concentration selection interval; the typical temperature data comprises three types of data of high temperature, medium temperature and low temperature according to a preset temperature selection interval; the typical image data is image data of which the image definition is greater than a preset image definition threshold;
the fire level determining molecular unit is used for obtaining a prediction result by taking the typical smoke concentration data and the typical temperature data as input parameters and the fire level as an output parameter based on a trained neural network, and dividing three fire levels of high, medium and low according to the prediction result;
the fire development trend judgment molecular unit is used for identifying the flame type in the typical image data based on a neural network of rapid target detection and semantic segmentation, and detecting different stages of the flame, thereby judging the development trend of the fire.
Further, the fire handling module comprises a plan execution unit and a rescue resource scheduling unit;
the plan execution unit is used for executing a corresponding disposal scheme according to the fire level; the disposal scheme comprises the steps of starting an alarm device, sending an alarm prompt and starting fire extinguishing operation; the fire extinguishing operation comprises the steps of starting a spraying device and a water cannon device; the spraying device is arranged at the top of the key fire monitoring space in the internal space of the building; the water cannons are arranged in an outer wall protruding space and a top terrace space of an external space of the building;
and the rescue resource scheduling unit is used for calling a corresponding rescue resource scheduling scheme according to the input information of the manpower and material resources and the available information of the manpower and material resources and aiming at the fire level to reinforce and extinguish the fire.
Further, the rescue resource scheduling unit comprises an information acquisition subunit, a disposal judgment subunit and a scheduling replenishment subunit;
the information acquisition subunit is used for acquiring the human and material input information, the available human and material information and the fire condition grade information when a fire disaster occurs;
the disposal judgment subunit is configured to input the human and material input information, the human and material available information, and the fire level information into a preset rescue resource scheduling model, determine whether the disposal work needs to be supplemented with human and material, and obtain a disposal judgment conclusion; the rescue resource scheduling model establishes a data training set according to historical human and material input information, historical human and material available information and historical fire condition grade information stored in a cloud platform database, and trains a deep neural network to obtain the data training set;
and the scheduling and supplying subunit is used for generating a rescue resource scheduling scheme according to the disposal judgment conclusion and performing rescue resource scheduling and supplying work according to the rescue resource scheduling scheme.
The system further comprises a fire safety user side APP, wherein the user side APP is installed on a user mobile phone and used for receiving early warning information and providing escape assistance;
fire control safety user side APP operation interface includes: basic information content, fire early warning information content, safe evacuation content and system basic setting content;
the basic information content includes: time, user position, escape passage position, emergency escape space position and building safety exit position;
the fire early warning information content comprises: the fire position and the fire level;
the safe evacuation content includes: providing corresponding evacuation voice prompt according to the position of the user, and if the position of the user is within a preset refuge needing range and the fire level is higher than the middle level, sending a prompt to the position of the emergency refuge space for refuge; if the position of the user is not in the preset refuge needing range and the fire level is below the middle level, a prompt for escaping is sent to the position of the escape passage;
the basic setting contents include: whether starting is started or not, whether floating display is performed or not and whether an early warning prompting mode is set;
the fire safety user side APP is installed in a mobile phone of a person entering a building in a mobile phone code scanning downloading mode; the basic information content is displayed in real time, and dynamic prompt is carried out periodically; the basic setting content is acquiescently recognized as startup starting, floating display and ring prompting;
when a fire occurs, the fire control command center sends out an alarm prompt, pushes fire position information and fire grade information and sends out an escape prompt according to the position of a user.
Further, still include equipment inspection and change module for carry out the periodic inspection change to the fire data acquisition equipment including smoke transducer and temperature sensor, specifically include: the device comprises a device working state acquisition unit, a device working performance evaluation unit and a device replacement determination unit;
the device working state acquisition unit is used for periodically acquiring the service life of the fire data acquisition device, the acquired data record and the service life information of the device;
the device working performance evaluation unit is used for calling fire data in a cloud platform database to acquire historical fault parameter data of the device and generating a fault rate statistical table according to the historical fault parameter data; the fault rate statistical table comprises a service cycle and a fault rate corresponding to the service cycle, wherein the cycle is in months; matching the service time of the fire data acquisition equipment with the fault rate statistical table to obtain the current fault rate of the fire data acquisition equipment;
if the current fault rate is greater than a preset fault rate value, listing the equipment as a replacement object; if the fault rate is less than a preset fault rate value, detecting a state evaluation value of the fire data acquisition equipment, and if the state evaluation value is less than a preset critical value, listing the equipment as a replacement object;
and the equipment replacement determining unit is used for debugging the equipment listed with the replacement object, and if the performance is not improved after debugging, determining the equipment as the equipment needing to be replaced.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a block diagram of an integrated fire safety intelligent system for a building according to an embodiment of the present invention;
FIG. 2 is a block diagram of an intelligent processing module of the integrated fire safety intelligent system for a building according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an APP operation interface of a fire safety client of the integrated fire safety intelligent system of a building according to an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides an intelligent system for the overall fire safety of a building, which comprises the following components as shown in figure 1:
the fire situation acquisition module is used for acquiring fire situation data based on a plurality of various sensors and transmitting the fire situation data to the cloud platform through the Internet of things;
the intelligent processing module is used for carrying out position positioning and situation evaluation on the fire according to the fire data based on the constructed integral three-dimensional scene of the building to obtain the fire grade and the fire development trend;
and the fire handling module is used for executing a handling plan and implementing the overall scheduling of rescue resources according to the fire grade and the fire development trend.
The working principle of the technical scheme is as follows: in order to construct the overall fire safety of a building, active response is carried out from different angles, and the overall fire safety level is improved; the embodiment starts from three aspects of fire acquisition, intelligent treatment and fire treatment, and provides an integral fire safety intelligent system; the system specifically comprises a fire condition acquisition module, a cloud platform and a fire condition monitoring module, wherein the fire condition acquisition module is used for acquiring fire condition data based on a plurality of various sensors and transmitting the fire condition data to the cloud platform through the Internet of things; the intelligent processing module is used for carrying out position positioning and situation evaluation on the fire based on the constructed integral three-dimensional scene of the building according to the fire data to obtain the fire grade and the fire development trend; and the fire handling module is used for executing a handling plan and implementing the overall scheduling of rescue resources according to the fire grade and the fire development trend.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, the fire situation data is collected and processed, the grade evaluation and development trend judgment are carried out according to the found fire situation, the disposal plan is executed, the overall rescue resource scheduling is implemented, and the intelligent management level of the overall fire safety of the building can be improved.
In one embodiment, the fire situation acquisition module comprises a plurality of smoke sensors, a plurality of temperature sensors and a plurality of cameras which are arranged in the internal space and the external space of the building, communication equipment of the internet of things, a cloud platform terminal and a cloud platform database; the smoke sensors are used for collecting smoke concentration data; the temperature sensors are used for acquiring temperature data; the cameras are used for collecting image data; integrating the smoke concentration data, the temperature data and the image data to obtain fire data; the Internet of things communication equipment is connected with the cloud platform terminal, and the cloud platform terminal is connected with the cloud platform database through a network.
The working principle of the technical scheme is as follows: in order to ensure that accurate fire occurrence information is obtained, a certain number of data acquisition devices need to be arranged, and meanwhile, in order to ensure that a large number of data and a large variety of data are stored and called, the data storage quality can be improved by relying on a cloud platform to store the data. The fire situation acquisition module is designed in the embodiment and comprises a plurality of smoke sensors, a plurality of temperature sensors and a plurality of cameras which are arranged in the internal space and the external space of a building, communication equipment of the internet of things, a cloud platform terminal and a cloud platform database; the smoke sensors are used for collecting smoke concentration data; the temperature sensors are used for acquiring temperature data; the cameras are used for collecting image data; integrating the smoke concentration data, the temperature data and the image data to obtain fire data; the Internet of things communication equipment is connected with the cloud platform terminal, and the cloud platform terminal is connected with the cloud platform database through a network.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, the fire data acquisition equipment is arranged and the fire data is stored through the cloud platform, so that the accuracy of fire data information acquisition can be improved, and the intelligent level of data utilization is improved.
In one embodiment, the fire situation acquisition module includes a data screening unit, configured to screen the fire situation data according to a preset screening condition, obtain screening data meeting requirements, and upload the screening data to a cloud platform; the screening conditions include: the smoke concentration value in the smoke concentration data is larger than or equal to a preset smoke concentration value, the temperature value in the temperature data is larger than or equal to a preset temperature value, and an image in the image data has similarity with a pre-stored image.
The more accurate fire data can be obtained, and meanwhile, in order to realize higher utilization value of the data, the fire data needs to be screened; the embodiment designs a data screening unit, which screens the fire data according to preset screening conditions to obtain screening data meeting requirements, and uploads the screening data to a cloud platform; the screening conditions include: the smoke concentration value in the smoke concentration data is larger than or equal to a preset smoke concentration value, the temperature value in the temperature data is larger than or equal to a preset temperature value, and the image in the image data has similarity with a pre-stored image.
The beneficial effects of the above technical scheme are: the scheme that adopts this embodiment to provide through screening the condition of a fire data, can guarantee the accuracy nature of data, improves the value of utilizing of data simultaneously, provides reliable foundation for the later stage judgement condition of a fire.
In one embodiment, as shown in fig. 2, the intelligent processing module includes a three-dimensional scene construction unit, a fire location unit, and a fire evaluation unit;
the three-dimensional scene construction unit is used for constructing an internal three-dimensional scene of an internal space of the building through three-dimensional modeling software according to the integral structure drawing of the building, constructing an external three-dimensional model of an external space of the building through 3DSMAX software, and integrating the internal three-dimensional scene and the external three-dimensional model to obtain the integral three-dimensional scene of the building; the building internal space comprises all rooms, stair corridors and underground spaces in the building; the building external space comprises a building external facade space, a building external wall protruding space and a building top terrace space;
the fire positioning unit is used for positioning the fire occurrence position in the integral three-dimensional scene of the building according to the collected fire data by referring to a fire position positioning library preset in the cloud platform data storage;
the fire evaluation unit is used for evaluating fire according to the smoke concentration data and the temperature data and a preset fire grade evaluation model to obtain a fire grade; and judging the fire according to the image data and a preset fire development trend model to obtain the fire development trend.
The working principle of the technical scheme is as follows: in order to better realize the monitoring of the fire, the three-dimensional scene of the building can be established, each space position is marked in the three-dimensional scene, the external space of the building is also included, the fire condition of each space position can be monitored, the fire can be positioned in time after the fire happens, the fire condition is researched and judged by analyzing the fire condition data, and a foundation is provided for pertinently developing the disposal work. The intelligent processing module designed in the embodiment comprises a three-dimensional scene construction unit, a fire positioning unit and a fire evaluation unit;
the three-dimensional scene construction unit is used for constructing an internal three-dimensional scene of an internal space of the building through three-dimensional modeling software according to the integral structure drawing of the building, constructing an external three-dimensional model of an external space of the building through 3DSMAX software, and integrating the internal three-dimensional scene and the external three-dimensional model to obtain the integral three-dimensional scene of the building; the building internal space comprises all rooms, stair corridors and underground spaces in the building; the building external space comprises a building external facade space, a building external wall protruding space and a building top terrace space;
the fire positioning unit is used for positioning the fire occurrence position in the integral three-dimensional scene of the building according to the collected fire data by referring to a fire position positioning library preset in the cloud platform data storage;
the fire evaluation unit is used for evaluating fire according to the smoke concentration data and the temperature data and a preset fire grade evaluation model to obtain a fire grade; and judging the fire according to the image data and a preset fire development trend model to obtain the fire development trend.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, the fire occurrence position can be accurately positioned by establishing the three-dimensional scene of the building and marking the spatial position of the building, the severity of the fire can be timely researched and judged, and a foundation is provided for pertinently developing rescue work.
In one embodiment, the construction of the fire location database comprises:
acquiring a historical fire data set based on the cloud platform database, and acquiring fire characteristics corresponding to the historical fire data set; the fire characteristics comprise smoke sensor numbers, temperature sensor numbers and camera numbers;
acquiring a preset interval division table of a building internal space and a building external space, wherein the interval division table comprises a plurality of items of contents; the plurality of items of content distinguish important content from non-important content; the important content corresponds to a key fire monitoring space of the building; the non-important content corresponds to a non-key fire monitoring space of the building;
combining and pairing the smoke sensor numbers with the corresponding non-important contents according to a sequence order to obtain a plurality of first pairing items, and simultaneously obtaining the numbers of the rest smoke sensors; combining and pairing the residual smoke sensor numbers, the temperature sensor numbers and the camera numbers with the important contents simultaneously according to the sequence order to obtain a plurality of second pairing items; and storing the plurality of first pairing items and the plurality of second pairing items into a preset blank library, and taking the blank library as a fire position positioning library to complete the construction of the fire position positioning library.
The working principle of the technical scheme is as follows: in order to ensure that accurate and precise positioning information is obtained, fire collecting equipment is matched and corresponds to partitioned areas inside and outside a building space, and a fire position positioning library is established; in the embodiment, a historical fire data set is obtained based on the cloud platform database, and fire characteristics corresponding to the historical fire data set are obtained; the fire characteristics comprise smoke sensor numbers, temperature sensor numbers and camera numbers;
acquiring a preset interval division table of a building internal space and a building external space, wherein the interval division table comprises a plurality of items of contents; the plurality of items of content distinguish important content from non-important content; the important content corresponds to a key fire monitoring space of the building; the non-important content corresponds to a non-key fire monitoring space of the building;
combining and pairing the smoke sensor numbers with the corresponding non-important contents according to a sequence order to obtain a plurality of first pairing items, and simultaneously obtaining the numbers of the rest smoke sensors; combining and pairing the residual smoke sensor numbers, the temperature sensor numbers and the camera numbers with the important contents simultaneously according to the sequence order to obtain a plurality of second pairing items; and storing the plurality of first pairing items and the plurality of second pairing items into a preset blank library, and taking the blank library as a fire position positioning library to complete the construction of the fire position positioning library.
The beneficial effects of the above technical scheme are: adopt the scheme that this embodiment provided, through establishing building condition of a fire position location storehouse, can fix a position the conflagration place of occurrence position more accurately, be favorable to improving the level that intelligent processing was handled.
In one embodiment, the fire evaluation unit comprises a fire grade and fire development trend judgment subunit, configured to determine a fire grade and judge a fire development trend; the fire level and fire development trend judgment subunit comprises a data set acquisition molecular unit, a fire level determination molecular unit and a fire development trend judgment molecular unit;
the data set acquisition molecular unit is used for acquiring a plurality of typical fire data according to the cloud platform database and establishing an initial sample database; the typical fire data comprises typical smoke concentration data, typical temperature data and typical image data; the typical smoke concentration data comprises three types of data of large, medium and small smoke concentration selected according to a preset smoke concentration selection interval; the typical temperature data comprises three types of data of high temperature, medium temperature and low temperature according to a preset temperature selection interval; the typical image data is image data of which the image definition is greater than a preset image definition threshold;
the fire level determining molecular unit is used for obtaining a prediction result by taking the typical smoke concentration data and the typical temperature data as input parameters and the fire level as an output parameter based on a trained neural network, and dividing three fire levels of high, medium and low according to the prediction result;
the fire development trend judgment molecular unit is used for identifying the flame type in the typical image data based on a neural network of rapid target detection and semantic segmentation, and detecting different stages of the flame, thereby judging the development trend of the fire.
The working principle of the technical scheme is as follows: in order to more accurately evaluate the fire, the relationship between the fire size and the smoke concentration and the fire temperature can be determined, and a fire grade model can be constructed.
The uncontrollable factors of the fire are many, once the fire breaks out, the violent combustion conditions such as flashover and the like are easy to happen, so that the extinguishing is difficult to carry out, and at the moment, the fire needs to be controlled in a certain area to prevent the further spreading of the fire and help people in the building to escape. To achieve this, it is necessary to determine the fire class from the fire data, and a space with a high fire class is likely to be an object of spreading, and to extinguish the space by concentrating the force, and it is possible to control the fire in a small area and prevent further spreading.
For the fire grade evaluation, multiple types of information are required to be fused for comprehensive judgment, five items of data of the obtained temperature, carbon dioxide concentration, carbon monoxide concentration, oxygen concentration and smoke density are selected as the input of a neural network, three result values of large, medium and small are output according to the influence degree of the data on the human body, and the three result values are corresponding to the mild, medium and high grades of the fire;
in this embodiment, a ReLU activation function is used to activate neurons of a neural network, and a forward transfer process thereof is calculated as follows:
in the above formula, d β Is an input vector of dimensionality sequence number beta, p is the dimensionality of the input vector, alpha and beta are both the dimensionality sequence numbers, beta =0,1,2 …, p-1,u βα And representing the weight between the beta-th neuron of the next layer and the alpha-th neuron of the previous layer. N is a radical of α For the corresponding bias of the alpha-th neuron, M α Outputting the result corresponding to the alpha-th neuron; the fire level can be judged according to the size of the output result.
In the process of monitoring the fire, real-time flame detection is required, and the algorithm speed is high. However, for the analysis of the actual scene of a fire, it is not necessary to detect each frame of image, and the detection can be performed at a certain time interval, and then the detection accuracy is improved, for this fact, this embodiment is completed by adopting Fast R-CNN neural network, and the working process is that, firstly, VGG-16 and ResNet50 are used as feature extraction networks to perform feature extraction to obtain feature maps, and the feature maps are input to the RPN network to obtain region candidate frames and region scores, and simultaneously, ROI pooling is performed in combination with candidate frame information output by the RPN, and then the features are subjected to full connection processing, and classification scores and regression bounding boxes are output; and through target identification, flame type information is obtained, identification results of smoldering, flame, small fire, big fire and waste heat are distinguished, and the development trend of the fire is judged according to the identification structure.
The fire evaluation unit comprises a fire grade and fire development trend judgment subunit, and is used for determining the fire grade and judging the fire development trend; the fire level and fire development trend judgment subunit comprises a data set acquisition molecular unit, a fire level determination molecular unit and a fire development trend judgment molecular unit;
the data set acquisition molecular unit is used for acquiring a plurality of typical fire data according to the cloud platform database and establishing an initial sample database; the typical fire data comprises typical smoke concentration data, typical temperature data and typical image data; the typical smoke concentration data comprises three types of data of large, medium and small smoke concentration selected according to a preset smoke concentration selection interval; the typical temperature data comprises three types of data of high temperature, medium temperature and low temperature according to a preset temperature selection interval; the typical image data is image data of which the image definition is greater than a preset image definition threshold;
the fire level determining molecular unit is used for obtaining a prediction result by taking the typical smoke concentration data and the typical temperature data as input parameters and the fire level as an output parameter based on a trained neural network, and dividing three fire levels of high, medium and low according to the prediction result;
the fire development trend judgment molecular unit is used for identifying the flame type in the typical image data based on a neural network of rapid target detection and semantic segmentation, and detecting different stages of the flame, thereby judging the development trend of the fire.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, the fire evaluation can be accurately performed by constructing the fire grade model, so that the quality of the fire evaluation is improved, and the pertinence of fire disposal is improved; by utilizing the flame type identification in the image by the Faster R-CNN neural network, different stages of flame can be effectively distinguished, and the fire can be restrained in the germination stage by effectively detecting the smoldering state or the waste heat state.
In one embodiment, the fire handling module comprises a plan execution unit and a rescue resource scheduling unit;
the plan execution unit is used for executing a corresponding disposal scheme according to the fire level; the disposal scheme comprises the steps of starting an alarm device, sending an alarm prompt and starting fire extinguishing operation; the fire extinguishing operation comprises the steps of starting a spraying device and a water cannon device; the spraying device is arranged at the top of the key fire monitoring space in the internal space of the building; the water cannons are arranged in an outer wall protruding space and a top terrace space of an external space of the building;
and the rescue resource scheduling unit is used for calling a corresponding rescue resource scheduling scheme according to the input information of the manpower and material resources and the available information of the manpower and material resources and aiming at the fire level to reinforce and extinguish the fire.
The working principle of the technical scheme is as follows: in the process of fire disposal, on one hand, fire disposal is carried out according to a formulated disposal scheme, on the other hand, a standby scheme is needed to deal with unpredictable fire, and therefore scheduling and supplying work needs to be prepared, and under the necessary condition, manpower and material resources are timely supplemented, and the aid-adding work is developed. The embodiment comprises a plan execution unit and a rescue resource scheduling unit;
the plan execution unit is used for executing a corresponding disposal scheme according to the fire level; the disposal scheme comprises the steps of starting an alarm device, sending an alarm prompt and starting fire extinguishing operation; the fire extinguishing operation comprises the steps of starting a spraying device and a water cannon device; the spraying device is arranged at the top of the key fire monitoring space in the internal space of the building; the water cannons are arranged in an outer wall protruding space and a top terrace space of an external space of the building;
and the rescue resource scheduling unit is used for calling a corresponding rescue resource scheduling scheme according to the input information of manpower and material resources and the available information of the manpower and material resources and aiming at the fire level to reinforce and extinguish fire.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, the fire evaluation can be accurately carried out by constructing the fire grade model, the quality of the fire evaluation is improved, and the pertinence of the fire disposal is improved.
In one embodiment, the rescue resource scheduling unit comprises an information acquisition subunit, a disposal judgment subunit and a scheduling replenishment subunit;
the information acquisition subunit is used for acquiring the human and material input information, the available human and material information and the fire situation grade information when a fire disaster occurs;
the disposal judgment subunit is used for inputting the human and material input information, the available human and material information and the fire condition grade information into a preset rescue resource scheduling model, determining whether the disposal work needs to be supplemented with human and material, and obtaining a disposal judgment conclusion; the rescue resource scheduling model establishes a data training set according to historical human and material input information, historical human and material available information and historical fire condition grade information stored in a cloud platform database, and trains a deep neural network to obtain the data training set;
and the scheduling and supplying subunit is used for generating a rescue resource scheduling scheme according to the disposal judgment conclusion and performing rescue resource scheduling and supplying work according to the rescue resource scheduling scheme.
The working principle of the technical scheme is as follows: in order to ensure the scientific and reasonable scheduling of the rescue resources, a rescue resource scheduling model can be constructed according to historical data and based on a deep neural network, the human and material resource supplement condition is determined through the model, and the design and implementation of a rescue resource scheduling scheme are carried out according to a judgment conclusion. The embodiment comprises an information acquisition subunit, a disposal judgment subunit and a scheduling replenishment subunit;
the information acquisition subunit is used for acquiring the human and material input information, the available human and material information and the fire situation grade information when a fire disaster occurs;
the disposal judgment subunit is used for inputting the human and material input information, the available human and material information and the fire condition grade information into a preset rescue resource scheduling model, determining whether the disposal work needs to be supplemented with human and material, and obtaining a disposal judgment conclusion; the rescue resource scheduling model establishes a data training set according to historical human and material input information, historical human and material available information and historical fire condition grade information stored in a cloud platform database, and trains a deep neural network to obtain the data training set;
and the scheduling and supplying subunit is used for generating a rescue resource scheduling scheme according to the disposal judgment conclusion and performing rescue resource scheduling and supplying work according to the rescue resource scheduling scheme.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, the rescue resource scheduling and supplying scheme can be scientifically and reasonably formulated by constructing the rescue resource scheduling model, so that the rescue resource scheduling and supplying work can be effectively carried out, and the efficient treatment of the fire can be ensured.
In one embodiment, as shown in fig. 3, the system further comprises a fire safety user side APP, where the user side APP is installed on a user mobile phone and is used for receiving early warning information and providing escape assistance;
fire control safety user side APP operation interface includes: basic information content, fire early warning information content, safe evacuation content and system basic setting content;
the basic information content includes: time, user position, escape passage position, emergency refuge space position and building safety exit position;
the fire early warning information content comprises: the fire position and the fire level;
the safe evacuation content includes: providing corresponding evacuation voice prompts according to the positions of the users, and if the positions of the users are within a preset refuge range required and the fire level is above the middle level, sending out prompts for refuge to the positions of the emergency refuge space; if the position of the user is not in the preset refuge needing range and the fire level is below the middle level, a prompt for escaping is sent to the position of the escape passage;
the basic setting contents include: whether starting is started or not, whether floating display is performed or not and whether an early warning prompting mode is set;
the fire safety user side APP is installed in a mobile phone of a person entering a building in a mobile phone code scanning downloading mode; the basic information content is displayed in real time and is dynamically prompted at regular intervals; the basic setting content is acquiescently recognized as startup starting, floating display and ring prompting;
when a fire occurs, the fire control command center sends out an alarm prompt, pushes fire position information and fire grade information, and sends out an escape prompt according to the position of a user.
The working principle of the technical scheme is as follows: in order to better realize the purpose of overall fire safety, and enable personnel in a building to timely and accurately know and master fire information and a safe escape and danger avoiding process, a mobile phone user side APP can be designed and installed on a user mobile phone for receiving early warning information and providing escape help; this embodiment fire safety user side APP operation interface includes: basic information content, fire early warning information content, safe evacuation content and system basic setting content;
the basic information content includes: time, user position, escape passage position, emergency refuge space position and building safety exit position;
the fire early warning information content comprises: the fire position and the fire level;
the safe evacuation content comprises: providing corresponding evacuation voice prompt according to the position of the user, and if the position of the user is within a preset refuge needing range and the fire level is higher than the middle level, sending a prompt to the position of the emergency refuge space for refuge; if the position of the user is not in the preset refuge needing range and the fire level is below the middle level, a prompt for escaping is sent to the position of the escape passage;
the basic setting contents include: whether starting is started or not, whether floating display is performed or not and whether an early warning prompting mode is set;
the fire safety user side APP is installed in a mobile phone of a person entering a building in a mobile phone code scanning downloading mode; the basic information content is displayed in real time and is dynamically prompted at regular intervals; the basic setting content is acquiescently recognized as startup starting, floating display and ring prompting;
when a fire occurs, the fire control command center sends out an alarm prompt, pushes fire position information and fire grade information, and sends out an escape prompt according to the position of a user.
The beneficial effects of the above technical scheme are: adopt the scheme that this embodiment provided, through design fire control safety user side APP, can in time transmit the personnel in the building with condition of a fire information, in time help personnel flee and keep away the danger, can promote whole fire control safety's intelligent level.
In one embodiment, the fire detection system further comprises an equipment inspection and replacement module, which is used for periodically inspecting and replacing the fire data acquisition equipment comprising the smoke sensor and the temperature sensor, and specifically comprises: the device comprises a device working state acquisition unit, a device working performance evaluation unit and a device replacement determination unit;
the device working state acquisition unit is used for periodically acquiring the service life of the fire data acquisition device, the acquired data record and the service life information of the device;
the device working performance evaluation unit is used for calling fire data in a cloud platform database to acquire historical fault parameter data of the device and generating a fault rate statistical table according to the historical fault parameter data; the fault rate statistical table comprises a service cycle and a fault rate corresponding to the service cycle, wherein the cycle is in months; matching the service duration of the fire data acquisition equipment with the fault rate statistical table to obtain the current fault rate of the fire data acquisition equipment;
if the current fault rate is greater than a preset fault rate value, listing the equipment as a replacement object; if the fault rate is less than a preset fault rate value, detecting a state evaluation value of the fire data acquisition equipment, and if the state evaluation value is less than a preset critical value, listing the equipment as a replacement object;
and the equipment replacement determining unit is used for debugging the equipment listed as the replacement object, and if the performance is not improved after debugging, determining the equipment as the equipment to be replaced.
The working principle of the technical scheme is as follows: in order to ensure the working performance of the smoke sensor and the temperature sensor and the accuracy of the acquired data, the fire data acquisition equipment needs to be regularly detected and replaced so as to ensure the accuracy of the fire data acquisition. The embodiment comprises the following steps: the device comprises a device working state acquisition unit, a device working performance evaluation unit and a device replacement determination unit;
the device working state acquisition unit is used for periodically acquiring the service life of the fire data acquisition device, the acquired data record and the service life information of the device;
the device working performance evaluation unit is used for calling fire data in a cloud platform database to acquire historical fault parameter data of the device and generating a fault rate statistical table according to the historical fault parameter data; the fault rate statistical table comprises a service cycle and a fault rate corresponding to the service cycle, wherein the cycle is in months; matching the service time of the fire data acquisition equipment with the fault rate statistical table to obtain the current fault rate of the fire data acquisition equipment;
if the current fault rate is greater than a preset fault rate value, listing the equipment as a replacement object; if the fault rate is less than a preset fault rate value, detecting a state evaluation value of the fire data acquisition equipment, and if the state evaluation value is less than a preset critical value, listing the equipment as a replacement object;
and the equipment replacement determining unit is used for debugging the equipment listed as the replacement object, and if the performance is not improved after debugging, determining the equipment as the equipment to be replaced.
The beneficial effects of the above technical scheme are: adopt the scheme that this embodiment provided, inspect the change through regularly to fire data acquisition equipment, can guarantee the good performance of equipment performance to ensure the degree of accuracy of the fire data who obtains, help improving whole fire safety's management level.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (7)
1. The utility model provides an intelligent system of whole fire control safety of building which characterized in that includes:
the fire situation acquisition module is used for acquiring fire situation data based on a plurality of various sensors and transmitting the fire situation data to the cloud platform through the Internet of things;
the intelligent processing module is used for carrying out position positioning and situation evaluation on the fire according to the fire data based on the constructed integral three-dimensional scene of the building to obtain the fire grade and the fire development trend;
the fire handling module is used for executing a handling plan and implementing overall rescue resource scheduling according to the fire grade and the fire development trend;
the system also comprises a fire safety user side APP, wherein the user side APP is installed on a user mobile phone and is used for receiving early warning information and providing escape help;
fire control safety user side APP operation interface includes: basic information content, fire early warning information content, safe evacuation content and system basic setting content;
the basic information content includes: time, user position, escape passage position, emergency refuge space position and building safety exit position;
the fire early warning information content comprises: the fire position and the fire level;
the safe evacuation content includes: providing corresponding evacuation voice prompt according to the position of the user, and if the position of the user is within a preset refuge needing range and the fire level is higher than the middle level, sending a prompt to the position of the emergency refuge space for refuge; if the position of the user is not in the preset refuge-needing range and the fire level is below the middle level, a prompt for escaping is sent to the position of the escape passage;
the basic setting contents include: whether starting is started or not, whether floating display is performed or not and whether an early warning prompting mode is set;
the fire safety user side APP is installed in a mobile phone of a person entering a building in a mobile phone code scanning downloading mode; the basic information content is displayed in real time and is dynamically prompted at regular intervals; the basic setting content is acquiescently recognized as startup starting, floating display and ring prompting;
when a fire occurs, the fire control command center sends out an alarm prompt, pushes fire position information and fire grade information, and sends out an escape prompt according to the position of a user;
the intelligent processing module comprises a three-dimensional scene construction unit, a fire positioning unit and a fire evaluation unit;
the three-dimensional scene construction unit is used for constructing an internal three-dimensional scene of an internal space of the building through three-dimensional modeling software according to the integral structure drawing of the building, constructing an external three-dimensional model of an external space of the building through 3DSMAX software, and integrating the internal three-dimensional scene and the external three-dimensional model to obtain the integral three-dimensional scene of the building; the building internal space comprises all rooms, stair corridors and underground spaces in the building; the building external space comprises a building external facade space, a building external wall protruding space and a building top terrace space;
the fire positioning unit is used for positioning the fire occurrence position in the integral three-dimensional scene of the building according to the collected fire data by referring to a fire position positioning library preset in the cloud platform data storage;
the fire evaluation unit is used for evaluating fire according to the smoke concentration data and the temperature data and a preset fire grade evaluation model to obtain a fire grade; judging the fire according to the image data and a preset fire development trend model to obtain a fire development trend;
the fire evaluation unit comprises a fire grade and fire development trend judgment subunit, and is used for determining the fire grade and judging the fire development trend; the fire level and fire development trend judgment subunit comprises a data set acquisition molecular unit, a fire level determination molecular unit and a fire development trend judgment molecular unit;
the data set acquisition molecular unit is used for acquiring a plurality of typical fire data according to the cloud platform database and establishing an initial sample database; the typical fire data comprises typical smoke concentration data, typical temperature data and typical image data; the typical smoke concentration data comprises three types of data of large, medium and small smoke concentration selected according to a preset smoke concentration selection interval; the typical temperature data comprises three types of data of high temperature, medium temperature and low temperature according to a preset temperature selection interval; the typical image data is image data of which the image definition is greater than a preset image definition threshold;
the fire level determining molecular unit is used for obtaining a prediction result by taking the typical smoke concentration data and the typical temperature data as input parameters and the fire level as an output parameter based on a trained neural network, and dividing three fire levels of high, medium and low according to the prediction result;
the fire development trend judgment molecular unit is used for identifying the flame type in the typical image data based on a neural network of rapid target detection and semantic segmentation, and detecting different stages of the flame, so as to judge the development trend of the fire;
for the fire grade evaluation, multi-class information is required to be fused for comprehensive judgment, five items of data of the obtained temperature, carbon dioxide concentration, carbon monoxide concentration, oxygen concentration and smoke density are selected as the input of a neural network, three result values of large, medium and small are output according to the influence degree of the data on the human body, and the three result values correspond to three classes of mild, medium and high of the fire;
activating the neurons of the neural network by using a ReLU activation function, wherein the calculation formula of the forward transfer process is as follows:
in the above formula, d β Is an input vector of dimensionality sequence number beta, p is the dimensionality of the input vector, alpha and beta are both the dimensionality sequence numbers, beta =0,1,2 …, p-1,u βα Representing the weight between the beta-th neuron of the next layer and the alpha-th neuron of the previous layer; n is a radical of α For the corresponding bias of the alpha-th neuron, M α Corresponding to the alpha-th neuronThe output result of (1); the fire level can be judged according to the size of the output result;
in the process of monitoring the fire, real-time flame detection is required, and the algorithm speed is higher; for the analysis of the actual scene of the fire, however, detection does not need to be carried out on each frame of image, detection can be carried out at a certain time interval, then the detection precision is improved, fast R-CNN neural network is adopted for completion, the working process is that firstly, VGG-16 and ResNet50 are used as feature extraction networks for feature extraction to obtain feature maps, the feature maps are input to an RPN network to obtain regional candidate frames and regional scores, meanwhile, ROI pooling is carried out by combining with candidate frame information output by the RPN, then the features are subjected to full connection processing, and classification scores and regression bounding boxes are output; and through target identification, flame type information is obtained, identification results of smoldering, flame, small fire, big fire and waste heat are distinguished, and the development trend of the fire is judged according to the identification structure.
2. The intelligent fire safety system for the whole building as recited in claim 1, wherein the fire situation acquisition module comprises a plurality of smoke sensors, a plurality of temperature sensors and a plurality of cameras which are arranged in the internal space and the external space of the building, internet of things communication equipment, a cloud platform terminal and a cloud platform database; the smoke sensors are used for collecting smoke concentration data; the temperature sensors are used for acquiring temperature data; the cameras are used for collecting image data; integrating the smoke concentration data, the temperature data and the image data to obtain fire data; the Internet of things communication equipment is connected with the cloud platform terminal, and the cloud platform terminal is connected with the cloud platform database through a network.
3. The intelligent system for the overall fire safety of the building according to claim 1, wherein the fire acquisition module comprises a data screening unit, and is used for screening the fire data according to preset screening conditions to obtain screening data meeting requirements and uploading the screening data to a cloud platform; the screening conditions include: the smoke concentration value in the smoke concentration data is larger than or equal to a preset smoke concentration value, the temperature value in the temperature data is larger than or equal to a preset temperature value, and an image in the image data has similarity with a pre-stored image.
4. The intelligent system for integrated fire safety of buildings according to claim 1, wherein the construction of the fire location database comprises:
acquiring a historical fire data set based on the cloud platform database, and acquiring fire characteristics corresponding to the historical fire data set; the fire characteristics comprise smoke sensor numbers, temperature sensor numbers and camera numbers;
acquiring a preset interval division table of a building internal space and a building external space, wherein the interval division table comprises a plurality of items of contents; the plurality of items of content distinguish important content from non-important content; the important content corresponds to a key fire monitoring space of the building; the non-important content corresponds to a non-key fire monitoring space of the building;
combining and pairing the smoke sensor numbers with the corresponding non-important contents according to a sequence order to obtain a plurality of first pairing items, and simultaneously obtaining the numbers of the rest smoke sensors; combining and pairing the residual smoke sensor numbers, the temperature sensor numbers and the camera numbers with the important contents simultaneously according to the sequence order to obtain a plurality of second pairing items; and storing the plurality of first pairing items and the plurality of second pairing items into a preset blank library, and taking the blank library as a fire position positioning library to complete the construction of the fire position positioning library.
5. The intelligent fire safety system for the whole building of claim 1, wherein the fire handling module comprises a plan execution unit and a rescue resource scheduling unit;
the plan execution unit is used for executing a corresponding disposal scheme according to the fire level; the disposal scheme comprises the steps of starting an alarm device, sending an alarm prompt and starting fire extinguishing operation; the fire extinguishing operation comprises the steps of starting a spraying device and a water cannon device; the spraying device is arranged at the top of the key fire monitoring space in the internal space of the building; the water cannons are arranged in an outer wall protruding space and a top terrace space of an external space of the building;
and the rescue resource scheduling unit is used for calling a corresponding rescue resource scheduling scheme according to the input information of manpower and material resources and the available information of the manpower and material resources and aiming at the fire level to reinforce and extinguish fire.
6. The intelligent fire safety system for the whole building of claim 5, wherein the rescue resource scheduling unit comprises an information acquisition subunit, a disposal judgment subunit and a scheduling supply subunit;
the information acquisition subunit is used for acquiring the human and material input information, the available human and material information and the fire situation grade information when a fire disaster occurs;
the disposal judgment subunit is used for inputting the human and material input information, the available human and material information and the fire condition grade information into a preset rescue resource scheduling model, determining whether the disposal work needs to be supplemented with human and material, and obtaining a disposal judgment conclusion; the rescue resource scheduling model establishes a data training set according to historical human and material input information, historical human and material available information and historical fire condition grade information stored in a cloud platform database, and trains a deep neural network to obtain the data training set;
and the scheduling and supplying subunit is used for generating a rescue resource scheduling scheme according to the disposal judgment conclusion and performing rescue resource scheduling and supplying work according to the rescue resource scheduling scheme.
7. The intelligent fire safety system for the whole building as claimed in claim 1, further comprising an equipment inspection and replacement module for performing periodic inspection and replacement on fire data acquisition equipment including a smoke sensor and a temperature sensor, specifically comprising: the device comprises a device working state acquisition unit, a device working performance evaluation unit and a device replacement determination unit;
the device working state acquisition unit is used for periodically acquiring the service life of the fire data acquisition device, the acquired data record and the service life information of the device;
the device working performance evaluation unit is used for calling fire data in a cloud platform database to acquire historical fault parameter data of the device and generating a fault rate statistical table according to the historical fault parameter data; the fault rate statistical table comprises a service cycle and a fault rate corresponding to the service cycle, wherein the cycle takes months as a unit; matching the service duration of the fire data acquisition equipment with the fault rate statistical table to obtain the current fault rate of the fire data acquisition equipment;
if the current fault rate is greater than a preset fault rate value, listing the equipment as a replacement object; if the fault rate is less than a preset fault rate value, detecting a state evaluation value of the fire data acquisition equipment, and if the state evaluation value is less than a preset critical value, listing the equipment as a replacement object;
and the equipment replacement determining unit is used for debugging the equipment listed as the replacement object, and if the performance is not improved after debugging, determining the equipment as the equipment to be replaced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210261185.6A CN114792194B (en) | 2022-03-16 | 2022-03-16 | Whole fire control safety intelligent system of building |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210261185.6A CN114792194B (en) | 2022-03-16 | 2022-03-16 | Whole fire control safety intelligent system of building |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114792194A CN114792194A (en) | 2022-07-26 |
| CN114792194B true CN114792194B (en) | 2023-04-18 |
Family
ID=82459416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210261185.6A Active CN114792194B (en) | 2022-03-16 | 2022-03-16 | Whole fire control safety intelligent system of building |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114792194B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115619609B (en) * | 2022-09-27 | 2024-02-27 | 无锡布塔信息科技有限公司 | Fire-fighting warning method and system based on three-dimensional visual data |
| CN115310882B (en) * | 2022-10-12 | 2023-01-24 | 北京晨豪科技有限公司 | Visual fire-fighting strategy planning method and system |
| CN116363825B (en) * | 2023-06-02 | 2023-08-29 | 北京利达华信电子股份有限公司 | Method and device for displaying fire spreading trend, electronic equipment and medium |
| CN116757437B (en) * | 2023-07-07 | 2024-01-30 | 浙江警正安全科技有限公司 | Intelligent fire emergency alarm system |
| CN116800801B (en) * | 2023-08-24 | 2023-11-07 | 北京天恒安科集团有限公司 | Intelligent fire control scheduling method and system based on NB-Iot |
| CN116884167B (en) * | 2023-09-08 | 2023-12-05 | 山东舒尔智能工程有限公司 | Intelligent fire control video monitoring and alarm linkage control system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800961A (en) * | 2018-12-27 | 2019-05-24 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire rescue decision-making technique, device, storage medium and terminal device |
| CN113936239A (en) * | 2021-10-19 | 2022-01-14 | 山东华尔泰建筑工程有限公司 | Intelligent fire fighting condition identification method and system based on neural network algorithm |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107564231B (en) * | 2017-09-15 | 2020-09-04 | 山东建筑大学 | Building fire early warning and fire situation assessment system and method based on Internet of things |
| CN107818420A (en) * | 2017-11-07 | 2018-03-20 | 博康智能信息技术有限公司 | Application process is commanded in a kind of fire-fighting fire extinguishing rescue under battle conditions |
| CN108538038A (en) * | 2018-05-31 | 2018-09-14 | 京东方科技集团股份有限公司 | fire alarm method and device |
| CN111489006A (en) * | 2019-01-29 | 2020-08-04 | 深圳富桂精密工业有限公司 | Fire development situation prediction method and device and computer-readable storage medium |
| CN110853137A (en) * | 2019-11-18 | 2020-02-28 | 河海大学常州校区 | Guiding fire prevention and fire fighting rescue system and method based on three-dimensional scene reduction |
| CN111401581A (en) * | 2020-03-11 | 2020-07-10 | 中煤航测遥感集团有限公司 | Building operation and maintenance management method, system, equipment and storage medium |
| CN112686399B (en) * | 2020-12-24 | 2024-07-05 | 国网上海市电力公司 | Distribution room fire emergency repair method and system based on augmented reality technology |
-
2022
- 2022-03-16 CN CN202210261185.6A patent/CN114792194B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800961A (en) * | 2018-12-27 | 2019-05-24 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire rescue decision-making technique, device, storage medium and terminal device |
| CN113936239A (en) * | 2021-10-19 | 2022-01-14 | 山东华尔泰建筑工程有限公司 | Intelligent fire fighting condition identification method and system based on neural network algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114792194A (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114792194B (en) | Whole fire control safety intelligent system of building | |
| US12033492B2 (en) | Intelligent emergency response for multi-tenant dwelling units | |
| CN111754715B (en) | Fire-fighting emergency response method, device and system | |
| CN109215285A (en) | The intelligent fire-pretection system and method for fire behavior monitoring and rescue run based on WiFi probe | |
| CN108648402A (en) | intelligent fire alarm method, terminal and storage medium | |
| CN113936239A (en) | Intelligent fire fighting condition identification method and system based on neural network algorithm | |
| CN115392708A (en) | Fire risk assessment and early warning method and system for building fire protection | |
| CN114971409B (en) | Smart city fire monitoring and early warning method and system based on Internet of things | |
| CN112578690B (en) | Intelligent building energy consumption management and control system and method | |
| CN112885021B (en) | Multi-sensor fire prediction method and system based on composite algorithm | |
| KR102213204B1 (en) | Method and apparatus for managing firefighting facilities and preventing fires based on gis using artificial neural networks | |
| CN111640280A (en) | Subway station pollutant early warning method based on multi-source information fusion | |
| CN114997754B (en) | Emergency plan analysis method and device based on cloud model and entropy weight method | |
| CN113990022A (en) | Fire fighting monitoring method, device, equipment and storage medium based on edge calculation | |
| CN115394036A (en) | Monitoring and early warning method and system for building fire | |
| CN117592768B (en) | Fire disaster management method and system for internal places of enterprises based on big data processing | |
| CN114187728A (en) | Fire monitoring method and system based on artificial intelligence and digital twin technology | |
| CN114005236A (en) | Forest fire detection method and system based on Internet of things and readable storage medium | |
| CN111359132B (en) | Intelligent fire-fighting alarm method and system based on artificial intelligence | |
| CN117180687A (en) | Intelligent fire-fighting remote monitoring system and method | |
| CN111815893A (en) | Fire-fighting early warning method based on Internet of things and storage medium | |
| KR20100074445A (en) | System reponding to emergency | |
| CN114462974A (en) | Intelligent fire-fighting full-chain prevention and control system and multi-source information fusion decision-making method | |
| CN114157836A (en) | Forest fire prevention scheduling system based on candidate frame fusion | |
| CN117935021B (en) | Scene fire image analysis model training method and system based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230327 Address after: 518000 1804, building C, Xiangnian Plaza, 4060 Qiaoxiang Road, Gaofa community, Shahe street, Nanshan District, Shenzhen, Guangdong Applicant after: Shenzhen Senlei Hongtai Fire Technology Co.,Ltd. Address before: Room 2402, No. 13-1, Hai'an Road, Tianhe District, Guangzhou, Guangdong 510000 (office only) Applicant before: Guangdong Yongyao fire protection Electromechanical Engineering Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |