CN115394036A - Monitoring and early warning method and system for building fire - Google Patents
Monitoring and early warning method and system for building fire Download PDFInfo
- Publication number
- CN115394036A CN115394036A CN202211019258.7A CN202211019258A CN115394036A CN 115394036 A CN115394036 A CN 115394036A CN 202211019258 A CN202211019258 A CN 202211019258A CN 115394036 A CN115394036 A CN 115394036A
- Authority
- CN
- China
- Prior art keywords
- building
- fire
- early warning
- value
- parameter
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000007613 environmental effect Effects 0.000 claims abstract description 124
- 238000004088 simulation Methods 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 15
- 239000000779 smoke Substances 0.000 claims description 11
- 238000000547 structure data Methods 0.000 claims description 7
- 230000002265 prevention Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000005507 spraying Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims 1
- 238000012549 training Methods 0.000 description 7
- 206010000369 Accident Diseases 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
- G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
- G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/38—Outdoor scenes
- G06V20/39—Urban scenes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method and a system for monitoring and early warning of building fire, which comprises the following steps: simulating the environmental parameters and the fire-fighting equipment state parameters corresponding to various buildings, and analyzing the simulation result to obtain fire disaster factor tables corresponding to various buildings; collecting historical image data of various buildings and constructing a building scene recognition model; identifying a target building according to the building scene identification model to obtain a corresponding building type and determine a corresponding fire disaster factor table; monitoring field parameters in a target building in real time; according to the method and the system, the simulation from the normal range to the early warning range is carried out on the fire related data of various buildings, effective basis is provided for the real occurrence reason of the fire, the accuracy of fire judgment is improved, and professionals can acquire accurate information so as to accurately judge the fire position.
Description
Technical Field
The invention relates to the technical field of fire fighting, in particular to a method and a system for monitoring and early warning of building fire.
Background
A fire refers to a catastrophic combustion event that loses control over time or space. Among various disasters, fire is one of the main disasters which threaten public safety and social development most frequently and most generally, and human beings can utilize and control the fire, which is an important mark of civilized progress. Therefore, the history of using fire and the history of fighting with fire are concomitant, and for fire, people summarize the experience of 'preventing the fire to be the first time, rescuing the second time and giving up the fire to be the next time' in ancient China. With the continuous development of society, the social wealth is increasing, meanwhile, the danger of fire disasters is also increasing, and the hazard of the fire disasters is also increasing. Practice proves that along with the development of society and economy, the importance of fire fighting work is more and more prominent, wherein, because the living density of high-rise buildings is high, and the escape is difficult, one of the difficulties of fire fighting is always difficult, especially fire catching at night, and the rescue difficulty is very large, so the existing building fire research has the following problems:
1. after a building fire accident occurs, a fire investigation department investigates the fire accident, but because the fire accident is caused by a sudden and complex fire accident, field data cannot be monitored, collected and analyzed, and thus systematic review cannot be formed, accurate conclusion may not be drawn about the real occurrence reason of the fire, the same disaster-causing factors cannot be avoided, prevention and processing experience cannot be accumulated, and a vicious circle is formed.
2. The method is used for rapidly and accurately acquiring fire information, fire starting places and peripheral resource information, is the basis for rapidly implementing fire extinguishing rescue, and on the premise that disaster factors cannot be clearly determined in advance, personnel in a building cannot timely obtain accurate information when a fire occurs, and cannot make accurate judgment according to the fire position, so that the optimal rescue opportunity is delayed.
Disclosure of Invention
In view of the above deficiencies of the prior art, the present application provides a method and system for monitoring and early warning of a building fire.
In a first aspect, the present application provides a method for monitoring and early warning of a building fire, comprising:
simulating the environmental parameters and the fire-fighting equipment state parameters corresponding to various buildings, and analyzing the simulation results to obtain fire disaster causing factor tables corresponding to the various buildings;
collecting historical image data of various buildings and constructing a building scene recognition model;
acquiring image data of a target building and inputting the image data into the building scene recognition model for recognition to obtain a corresponding building category;
determining a corresponding fire disaster factor table according to the building type;
monitoring field parameters in a target building in real time;
and comparing and analyzing according to the field parameters and the fire disaster causing factor table corresponding to the target building, and carrying out fire monitoring and emergency treatment according to an analysis result.
In some embodiments, before the simulating environmental parameters and fire fighting equipment state parameters corresponding to various buildings and analyzing the simulation result to obtain the fire disaster factor tables corresponding to various buildings, the method includes:
carrying out standardized classification on various buildings according to the building types, and simulating corresponding environmental parameters and fire-fighting equipment state parameters according to classification results;
the environmental parameters comprise a temperature parameter, a smoke concentration parameter and a combustible gas concentration parameter;
the fire-fighting equipment state parameters comprise automatic water spraying fire-extinguishing system state parameters, gas fire-extinguishing system state parameters and smoke prevention and discharge system state parameters.
In some embodiments, the method comprises:
simulating a corresponding number of environment parameter initial values according to the environment parameters, and simulating a corresponding number of fire-fighting equipment state parameter initial values according to the fire-fighting equipment state parameters;
setting an environment parameter standard value and a fire-fighting equipment state parameter standard value;
and adjusting the initial value of the environmental parameter to the standard value of the environmental parameter to obtain an adjusted value of the environmental parameter, and adjusting the initial value of the state parameter of the fire-fighting facility to the standard value of the state parameter of the fire-fighting facility to obtain an adjusted value of the state parameter of the fire-fighting facility.
In some embodiments, the method comprises:
when the environmental parameter adjustment value is smaller than the environmental parameter standard value and the fire fighting equipment state parameter adjustment value is equal to the fire fighting equipment state parameter standard value, recording the current environmental parameter adjustment value as a first low-risk environmental parameter early warning value, and recording the current fire fighting equipment state parameter adjustment value as a first low-risk environmental parameter early warning value;
when the environmental parameter adjustment value is equal to the environmental parameter standard value and the fire fighting equipment state parameter adjustment value is smaller than the fire fighting equipment state parameter standard value, recording the current environmental parameter adjustment value as a second low-risk environmental parameter early warning value, and recording the current fire fighting equipment state parameter adjustment value as a second low-risk environmental parameter early warning value;
when the environmental parameter adjustment value is greater than the environmental parameter standard value and the fire fighting equipment state parameter adjustment value is greater than the fire fighting equipment state parameter standard value, recording the current environmental parameter adjustment value as a high risk environmental parameter early warning value and recording the current fire fighting equipment state parameter adjustment value as a high risk environmental parameter early warning value;
obtaining a low risk environment parameter early warning range according to the first low risk environment parameter early warning value and the second low risk environment parameter early warning value;
obtaining a low-risk fire-fighting facility state early warning range according to the first fire-fighting facility state parameter early warning value and the second fire-fighting facility state parameter early warning value;
and integrating the low-risk environmental parameter early warning range, the low-risk fire-fighting facility state early warning range, the high-risk environmental parameter early warning value and the high-risk environmental parameter early warning value into a fire disaster factor table.
In some embodiments, the collecting of various types of building historical image data and the constructing of the building scene recognition model includes:
building a building scene identification sample data set according to the historical image data;
selecting a set number of building scene identification samples from the building scene identification sample data set;
inputting the building scene identification sample into the convolutional neural network to calculate building general features;
converting the building general characteristics into building characteristics through a full-link neural network;
determining model building characteristics through the minimized error of the building scene identification sample;
and constructing a building scene recognition model according to the building characteristics and the model building characteristics.
In some embodiments, the acquiring image data of the target building and inputting the image data into the building scene recognition model for recognition to obtain a corresponding building category includes:
inputting the image data into the building scene recognition model to obtain a building feature vector of a target building;
and comparing the building feature vector with the building feature vector distance of each type of building in the building scene recognition model, and if the building feature vector distance is smaller than a threshold value, determining that the building is the same building, otherwise, determining that the building is different.
In some embodiments, the determining a corresponding fire disaster causing factor table according to the building category includes:
determining the type of a target building according to the recognition result of the building scene recognition model;
and selecting a corresponding fire disaster causing factor table according to the type of the target building, and acquiring a low-risk environmental parameter early warning range, a low-risk fire-fighting facility state early warning range, a high-risk environmental parameter early warning value and a high-risk environmental parameter early warning value corresponding to the target building.
In some embodiments, the monitoring of site parameters in the target building in real time includes:
determining the type of a target building according to the recognition result of the building scene recognition model;
acquiring corresponding building structure data and building attribute data according to the type of the target building, and setting a real-time monitoring point in the target building according to the building structure data and the building attribute data;
and acquiring corresponding site parameters through the real-time monitoring points, wherein the site parameters comprise actual values of environmental parameters and actual values of state parameters of the fire-fighting equipment.
In some embodiments, the comparing and analyzing according to the field parameter and the fire disaster causing factor table corresponding to the target building, and performing fire monitoring and pre-disaster warning according to the analysis result includes:
comparing the actual values of the environmental parameters and the actual values of the fire fighting equipment state parameters with the corresponding environmental parameters and the corresponding fire fighting equipment state parameters in the fire disaster causing factor table respectively;
when the actual environmental parameter value is within the low-risk environmental parameter early warning range and the actual fire fighting equipment state parameter value is within the low-risk fire fighting equipment state early warning range, marking the real-time monitoring point as a suspected fire point;
when the actual value of the environmental parameter exceeds the high-risk environmental parameter early warning value and the actual value of the fire fighting equipment state parameter is within the low-risk fire fighting equipment state early warning range, or the actual value of the environmental parameter is within the low-risk environmental parameter early warning range and the actual value of the fire fighting equipment state parameter exceeds the high-risk fire fighting equipment state early warning value, the real-time monitoring point sends out alarm information and gives out the position information of the real-time monitoring point;
and when the actual value of the environmental parameter exceeds the high-risk environmental parameter early warning value and the actual value of the state parameter of the fire fighting equipment exceeds the state early warning value of the high-risk fire fighting equipment, the real-time monitoring point sends out alarm information and sends alarm information to nearby rescue units.
In a second aspect, the present application provides a monitoring and early warning system for building fires, comprising:
the parameter simulation module is used for simulating the environment parameters and the fire-fighting equipment state parameters corresponding to various buildings and analyzing the simulation results to obtain fire disaster factor tables corresponding to various buildings;
the building scene recognition model construction module is used for collecting historical image data of various buildings and constructing a building scene recognition model;
the building type identification module is used for acquiring image data of a target building and inputting the image data into the building scene identification model for identification to obtain a corresponding building type;
the fire disaster causing factor table selecting module is used for determining a corresponding fire disaster causing factor table according to the building category;
the field monitoring module is used for monitoring field parameters in the target building in real time;
and the analysis scheduling module is used for comparing and analyzing the scene parameters and the fire disaster factor table corresponding to the target building, and carrying out fire monitoring and emergency treatment according to the analysis result.
The invention has the beneficial effects that:
according to the invention, by simulating the fire related data of various buildings from the normal range to the early warning range, investigators can review systematically, effective basis is provided for the real occurrence reason of the fire, the accuracy of conclusion judgment is improved, the same fire disaster causing factors can be effectively prevented, and the fire prevention and treatment experience can be accumulated.
Drawings
FIG. 1 is a general flow diagram of the present invention.
FIG. 2 is a flow chart of building scene recognition model construction.
Fig. 3 is a block diagram of the system of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In a first aspect, the present application provides a method for monitoring and early warning of a building fire, as shown in fig. 1, including S100 to S600:
s100: simulating the environmental parameters and the fire-fighting equipment state parameters corresponding to various buildings, and analyzing the simulation result to obtain fire disaster factor tables corresponding to various buildings;
carrying out standardized classification on various buildings according to the building types, and simulating corresponding environmental parameters and fire-fighting equipment state parameters according to classification results;
the building models are classified into various building types such as market building buildings, industrial buildings, public entertainment buildings, group renting buildings, hotel buildings, hospital buildings, old-age homes, school buildings, construction sites, cultural relic buildings and the like in a standardized way according to the building types;
the environmental parameters comprise a temperature parameter, a smoke concentration parameter and a combustible gas concentration parameter;
the fire-fighting equipment state parameters comprise automatic water spraying fire-extinguishing system state parameters, gas fire-extinguishing system state parameters and smoke prevention and discharge system state parameters.
Simulating a corresponding number of environment parameter initial values according to the environment parameters, and simulating a corresponding number of fire-fighting equipment state parameter initial values according to the fire-fighting equipment state parameters;
the initial value of the environment parameter is drawn up to include a temperature parameter, the temperature parameter is drawn up according to the indoor normal temperature range, and the temperature parameter range of the initial value of the environment parameter in the embodiment is 0-22 degrees;
the smoke concentration parameter is formulated according to the normal range of smoke shielding degree or light reduction rate, in this embodiment, the range of the smoke concentration parameter of the initial value of the environmental parameter is less than 0.65% OBS/M (% OBS/M refers to the shielding degree or light reduction rate, and refers to the percentage of the light shielded by the smoke particles after passing through the unit length);
the combustible gas concentration parameter is determined according to the non-explosive concentration range of the combustible gas, and in this embodiment, the combustible gas concentration parameter range of the initial value of the environmental parameter is less than 25% LEL (the lowest concentration of the combustible gas which is exploded by an open fire in the air, which is called the lower explosion limit, abbreviated as% LEL);
and the fire fighting equipment state parameters in the fire fighting equipment state parameter initial values are formulated according to the initial values of the fire fighting equipment.
Setting an environment parameter standard value and a fire-fighting equipment state parameter standard value;
the environmental parameter standard value is set according to the lowest lower limit of national regulation temperature alarm, smoke alarm and combustible gas alarm; and the standard value of the state parameter of the fire fighting equipment is drawn up according to the rated value of the fire fighting equipment.
And adjusting the initial value of the environmental parameter to the standard value of the environmental parameter to obtain an adjusted value of the environmental parameter, and adjusting the initial value of the state parameter of the fire-fighting facility to the standard value of the state parameter of the fire-fighting facility to obtain an adjusted value of the state parameter of the fire-fighting facility.
When the environmental parameter adjustment value is smaller than the environmental parameter standard value and the fire fighting equipment state parameter adjustment value is equal to the fire fighting equipment state parameter standard value, recording the current environmental parameter adjustment value as a first low-risk environmental parameter early warning value, and recording the current fire fighting equipment state parameter adjustment value as a first low-risk environmental parameter early warning value;
when the environmental parameter adjustment value is equal to the environmental parameter standard value and the fire fighting equipment state parameter adjustment value is smaller than the fire fighting equipment state parameter standard value, recording the current environmental parameter adjustment value as a second low-risk environmental parameter early warning value, and recording the current fire fighting equipment state parameter adjustment value as a second low-risk environmental parameter early warning value;
because the condition that the data is misreported due to the fire-fighting equipment faults can occur, the condition that a single item of the environmental parameter/the fire-fighting equipment state parameter exceeds the early warning value is classified as low-risk early warning.
When the environment parameter adjustment value is larger than the environment parameter standard value and the fire fighting equipment state parameter adjustment value is larger than the fire fighting equipment state parameter standard value, recording the current environment parameter adjustment value as a high risk environment parameter early warning value, and recording the current fire fighting equipment state parameter adjustment value as a high risk environment parameter early warning value;
the situation that the environmental parameter and the state parameter of the fire-fighting equipment exceed the early warning value at the same time and the fire-fighting equipment has fewer faults occurs, so that the situation that the two parameters exceed the early warning value at the same time is classified as a high-risk early warning value.
Obtaining a low risk environmental parameter early warning range according to the first low risk environmental parameter early warning value and the second low risk environmental parameter early warning value;
obtaining a low-risk fire fighting equipment state early warning range according to the first fire fighting equipment state parameter early warning value and the second fire fighting equipment state parameter early warning value;
and integrating the low-risk environmental parameter early warning range, the low-risk fire-fighting facility state early warning range, the high-risk environmental parameter early warning value and the high-risk environmental parameter early warning value into a fire disaster factor table.
S200: collecting historical image data of various buildings and constructing a building scene recognition model;
the process of specifically constructing the building scene recognition model is shown in fig. 2, and includes steps S210 to S260:
s210: building a building scene identification sample data set according to the historical image data;
in the stage of constructing a building scene recognition sample data set, training sample data needs to be prepared, wherein the training sample data includes a large amount of multi-channel data, such as thousands of orders of magnitude of historical image data, and a correct recognition result corresponding to each sample needs to be marked. In this embodiment, the constructed building scene identification sample data set includes a building scene retrieval formula, building pictures of the same type, and building pictures of different types;
s220: selecting a given number of building scene identification samples from the building scene identification sample data set;
the method includes the steps that a model used for analyzing whether a building in two different pictures is the same building or not needs to be trained through deep learning calculation, a large number of pictures are needed for training the model, the pictures belong to the same building are marked, the larger the data volume is, the more accurate the data marking is, the higher the precision of the trained model is, and high-quality standard data can be selected from a building scene recognition sample data set through a crawler program.
S230: inputting the building scene identification sample into the convolutional neural network to calculate building general features;
the general features comprise image line trends, image inflection points, image fixed point features, image categories and styles.
S240: converting the building general characteristics into building characteristics through a full-link neural network;
s250: determining model building characteristics through the minimized error of the building scene recognition sample;
the model building characteristic algorithm comprises the following steps:
L(T，Y，N)＝max(||f(T)-f(Y)||∧2-||f(T)-f(N)||∧2+a，0)
l (T, Y, N) is an error caused by the building scene identification sample; f (T), f (Y) and f (N) respectively represent building scene search formulas, building pictures of the same type and training building feature vectors obtained after different types of building pictures are trained; and a and 0 are positive numbers and are used for increasing the discrimination.
S260: and constructing a building scene recognition model according to the building characteristics and the model building characteristics.
And when the distance between the feature vectors of f (T) and f (Y) is smaller than that of f (T) and f (Y), ending the training, or when the distance between the feature vectors of f (T) and f (Y) is larger than or equal to that of f (T) and f (N), increasing the number of sample pictures corresponding to each picture type to perform the training again. And when the calculated loss degree (loss) is small enough or the loss degree is not changed for a long time, ending the training process to obtain the building scene recognition model.
S300: acquiring image data of a target building and inputting the image data into the building scene recognition model for recognition to obtain a corresponding building category;
inputting the image data into the building scene recognition model to obtain a building feature vector of a target building;
the image data is a building scene retrieval type, i.e. a building picture, and may also be a description of the picture or a part of the whole building picture.
And comparing the building feature vector with the building feature vector distance of each type of building in the building scene recognition model, and if the building feature vector distance is smaller than a threshold value, determining that the building is the same building, otherwise, determining that the building is different.
The threshold value can be randomly set, and calculation and judgment are carried out through calculation to obtain the optimal threshold value. For example, different thresholds are randomly selected, the accuracy of the threshold in the test set is calculated, and the threshold which can lead the accuracy of the test set to be the highest is selected. Wherein, the test set is a building scene identification sample data set, and the precision is as follows: correctly distinguish the number/total number of the same building.
S400: determining a corresponding fire disaster causing factor table according to the building category;
determining the type of a target building according to the recognition result of the building scene recognition model;
and selecting a corresponding fire disaster causing factor table according to the type of the target building, and acquiring a low-risk environmental parameter early warning range, a low-risk fire-fighting facility state early warning range, a high-risk environmental parameter early warning value and a high-risk environmental parameter early warning value corresponding to the target building.
S500: monitoring field parameters in a target building in real time;
determining the type of a target building according to the recognition result of the building scene recognition model;
acquiring corresponding building structure data and building attribute data according to the type of the target building, and setting a real-time monitoring point in the target building according to the building structure data and the building attribute data;
the building structure data comprises building size, building floor number, room position, door and window position, fire fighting equipment number, fire fighting equipment type and the like, and the building attribute data comprises building age, building strength grade, building material attribute and the like.
The mode of setting the real-time monitoring points is as follows: establishing a fire fighting equipment database, wherein the establishing process of the fire fighting equipment database specifically comprises the following steps: building information sub-libraries and fire fighting equipment sub-libraries are respectively established, and building data of various building models are led into the building information sub-libraries; importing fire fighting equipment information in a fire fighting equipment sublibrary according to fire fighting equipment data in the building data; therefore, the real-time monitoring points needing to be set are marked in the building.
And acquiring corresponding field parameters through the real-time monitoring points, wherein the field parameters comprise actual values of environmental parameters and actual values of state parameters of the fire-fighting equipment.
S600: and comparing and analyzing according to the field parameters and the fire disaster factor table corresponding to the target building, and carrying out fire monitoring and emergency treatment according to the analysis result.
Comparing the actual values of the environmental parameters and the actual values of the fire fighting equipment state parameters with the corresponding environmental parameters and the fire fighting equipment state parameters in the fire disaster causing factor table respectively;
when the actual value of the environmental parameter is within the low-risk environmental parameter early warning range and the actual value of the fire fighting equipment state parameter is within the low-risk fire fighting equipment state early warning range, marking the real-time monitoring point as a suspected fire point;
at the moment, the actual values of the environmental parameters and the actual values of the state parameters of the fire-fighting facilities do not reach the high-risk early warning values, so that whether a fire disaster occurs or not can be rechecked through a monitoring video of a monitoring camera in an area where a suspected fire disaster point is located, and/or the fire disaster occurs can be rechecked in a mode that a fire inspection worker goes to the site of the suspected fire disaster point to confirm.
When the actual value of the environmental parameter exceeds the high-risk environmental parameter early warning value and the actual value of the fire fighting equipment state parameter is within the low-risk fire fighting equipment state early warning range, or the actual value of the environmental parameter is within the low-risk environmental parameter early warning range and the actual value of the fire fighting equipment state parameter exceeds the high-risk fire fighting equipment state early warning value, the real-time monitoring point sends out alarm information and gives out the position information of the real-time monitoring point;
the step is that the environmental parameter actual values and the fire fighting equipment state parameter actual values of all the collected real-time monitoring points are respectively judged, when one of the environmental parameter actual values and the fire fighting equipment state parameter actual values exceeds an early warning value, the monitoring point is indicated to possibly have a fire disaster, the judgment can improve the judgment accuracy, and the probability of occurrence of misjudgment is reduced. Furthermore, each real-time monitoring point sends out alarm information and gives out the position of the abnormal real-time monitoring point, so that the coverage area of the notification can be increased as much as possible, and the escape personnel can plan a proper escape route according to the position of the escape personnel and the relative position of the abnormal real-time monitoring point during escape, so that the escape rate can be effectively increased.
And when the actual value of the environmental parameter exceeds the high-risk environmental parameter early warning value and the actual value of the state parameter of the fire fighting equipment exceeds the state early warning value of the high-risk fire fighting equipment, the real-time monitoring point sends out alarm information and sends alarm information to nearby rescue units.
Because the environmental parameter and the fire-fighting equipment state parameter exceed the early warning value simultaneously and the condition of the fire-fighting equipment fault is less, when two actual values exceed the early warning value, it is indicated that a fire disaster occurs at the monitoring point probably, at the moment, the real-time monitoring point is required to send out alarm information and a rescue preparation is required to be made, so that alarm information is required to be sent to nearby rescue units, the alarm information comprises a fire starting place, an alarm personnel contact mode, the existence of trapped personnel and burning substance information, the information is provided, so that the rescue units improve the field information acquisition efficiency, and the effective rescue time is ensured.
In a second aspect, the present application provides a monitoring and early warning system for building fires, as shown in fig. 3, comprising:
the parameter simulation module is used for simulating the environmental parameters and the fire-fighting equipment state parameters corresponding to various buildings and analyzing the simulation results to obtain fire disaster causing factor tables corresponding to the various buildings;
the building scene recognition model building module is used for collecting historical image data of various buildings and building a building scene recognition model;
the building type identification module is used for acquiring image data of a target building and inputting the image data into the building scene identification model for identification to obtain a corresponding building type;
the fire disaster causing factor table selecting module is used for determining a corresponding fire disaster causing factor table according to the building category;
the field monitoring module is used for monitoring field parameters in the target building in real time;
and the analysis scheduling module is used for carrying out comparison analysis according to the field parameters and the fire disaster causing factor table corresponding to the target building, and carrying out fire monitoring and emergency treatment according to the analysis result.
The above is only a preferred embodiment of the present invention, and it should be noted that several modifications and improvements made by those skilled in the art without departing from the technical solution should also be considered as falling within the scope of the claims.
Claims (10)
1. A monitoring and early warning method for building fire is characterized in that: the method comprises the following steps:
simulating the environmental parameters and the fire-fighting equipment state parameters corresponding to various buildings, and analyzing the simulation result to obtain fire disaster factor tables corresponding to various buildings;
collecting historical image data of various buildings and constructing a building scene recognition model;
acquiring image data of a target building and inputting the image data into the building scene recognition model for recognition to obtain a corresponding building category;
determining a corresponding fire disaster factor table according to the building type;
monitoring field parameters in a target building in real time;
and comparing and analyzing according to the field parameters and the fire disaster causing factor table corresponding to the target building, and carrying out fire monitoring and emergency treatment according to an analysis result.
2. A method for monitoring and forewarning of a building fire as claimed in claim 1, wherein: before simulating the environmental parameters and the fire-fighting equipment state parameters corresponding to various buildings and analyzing the simulation results to obtain the fire disaster factor tables corresponding to various buildings, the method comprises the following steps:
carrying out standardized classification on various buildings according to the building types, and simulating corresponding environmental parameters and fire-fighting equipment state parameters according to classification results;
the environmental parameters comprise a temperature parameter, a smoke concentration parameter and a combustible gas concentration parameter;
the fire-fighting equipment state parameters comprise automatic water spraying fire-fighting system state parameters, gas fire-fighting system state parameters and smoke prevention and discharge system state parameters.
3. A method for monitoring and forewarning of a building fire as claimed in claim 2, wherein: the simulation of the environmental parameters and the fire fighting equipment state parameters corresponding to various buildings comprises the following steps:
simulating a corresponding number of environment parameter initial values according to the environment parameters, and simulating a corresponding number of fire-fighting equipment state parameter initial values according to the fire-fighting equipment state parameters;
setting an environment parameter standard value and a fire fighting equipment state parameter standard value;
and adjusting the initial value of the environmental parameter to the standard value of the environmental parameter to obtain an adjusted value of the environmental parameter, and adjusting the initial value of the state parameter of the fire-fighting facility to the standard value of the state parameter of the fire-fighting facility to obtain an adjusted value of the state parameter of the fire-fighting facility.
4. A method for monitoring and forewarning of building fires as claimed in claim 3, wherein: the method for analyzing the simulation result to obtain the fire disaster factor table corresponding to various buildings comprises the following steps:
when the environmental parameter adjustment value is smaller than the environmental parameter standard value and the fire fighting equipment state parameter adjustment value is equal to the fire fighting equipment state parameter standard value, recording the current environmental parameter adjustment value as a first low-risk environmental parameter early warning value, and recording the current fire fighting equipment state parameter adjustment value as a first low-risk environmental parameter early warning value;
when the environmental parameter adjustment value is equal to the environmental parameter standard value and the fire fighting equipment state parameter adjustment value is smaller than the fire fighting equipment state parameter standard value, recording the current environmental parameter adjustment value as a second low-risk environmental parameter early warning value, and recording the current fire fighting equipment state parameter adjustment value as a second low-risk environmental parameter early warning value;
when the environment parameter adjustment value is larger than the environment parameter standard value and the fire fighting equipment state parameter adjustment value is larger than the fire fighting equipment state parameter standard value, recording the current environment parameter adjustment value as a high risk environment parameter early warning value, and recording the current fire fighting equipment state parameter adjustment value as a high risk environment parameter early warning value;
obtaining a low risk environmental parameter early warning range according to the first low risk environmental parameter early warning value and the second low risk environmental parameter early warning value;
obtaining a low-risk fire-fighting facility state early warning range according to the first fire-fighting facility state parameter early warning value and the second fire-fighting facility state parameter early warning value;
and integrating the low-risk environmental parameter early warning range, the low-risk fire-fighting facility state early warning range, the high-risk environmental parameter early warning value and the high-risk environmental parameter early warning value into a fire disaster factor table.
5. A method for monitoring and forewarning of building fires as claimed in claim 4, wherein: the method for collecting historical image data of various buildings and constructing a building scene recognition model comprises the following steps:
building a building scene recognition sample data set according to the historical image data;
selecting a set number of building scene identification samples from the building scene identification sample data set;
inputting the building scene identification sample into the convolutional neural network to calculate building general features;
converting the building general characteristics into building characteristics through a full-link neural network;
determining model building characteristics through the minimized error of the building scene identification sample;
and constructing a building scene recognition model according to the building characteristics and the model building characteristics.
6. A method for monitoring and forewarning of building fires as claimed in claim 5, wherein: the acquiring of the image data of the target building and the inputting of the image data into the building scene recognition model for recognition to obtain the corresponding building category comprises the following steps:
inputting the image data into the building scene recognition model to obtain a building feature vector of a target building;
and comparing the building feature vector with the building feature vector distance of each type of building in the building scene recognition model, and if the building feature vector distance is smaller than a threshold value, determining that the building is the same building, otherwise, determining that the building is different.
7. A method for monitoring and forewarning of a building fire according to claim 6, wherein: the step of determining the corresponding fire disaster factor table according to the building types comprises the following steps:
determining the type of a target building according to the recognition result of the building scene recognition model;
and selecting a corresponding fire disaster causing factor table according to the type of the target building, and acquiring a low-risk environmental parameter early warning range, a low-risk fire-fighting facility state early warning range, a high-risk environmental parameter early warning value and a high-risk environmental parameter early warning value corresponding to the target building.
8. A method for monitoring and forewarning of building fires as claimed in claim 7, wherein: the real-time monitoring of the site parameters in the target building includes:
determining the type of a target building according to the recognition result of the building scene recognition model;
acquiring corresponding building structure data and building attribute data according to the type of the target building, and setting a real-time monitoring point in the target building according to the building structure data and the building attribute data;
and acquiring corresponding field parameters through the real-time monitoring points, wherein the field parameters comprise actual values of environmental parameters and actual values of state parameters of the fire-fighting equipment.
9. A method for monitoring and forewarning of a building fire as claimed in claim 8, wherein: the method for performing comparative analysis according to the field parameters and the fire disaster causing factor table corresponding to the target building, and performing fire monitoring and pre-disaster warning according to the analysis result comprises the following steps:
comparing the actual values of the environmental parameters and the actual values of the fire fighting equipment state parameters with the corresponding environmental parameters and the fire fighting equipment state parameters in the fire disaster causing factor table respectively;
when the actual value of the environmental parameter is within the low-risk environmental parameter early warning range and the actual value of the fire fighting equipment state parameter is within the low-risk fire fighting equipment state early warning range, marking the real-time monitoring point as a suspected fire point;
when the actual value of the environmental parameter exceeds the high-risk environmental parameter early warning value and the actual value of the fire fighting equipment state parameter is within the low-risk fire fighting equipment state early warning range, or the actual value of the environmental parameter is within the low-risk environmental parameter early warning range and the actual value of the fire fighting equipment state parameter exceeds the high-risk fire fighting equipment state early warning value, the real-time monitoring point sends out alarm information and gives out the position information of the real-time monitoring point;
and when the actual value of the environmental parameter exceeds the early warning value of the high-risk environmental parameter and the actual value of the state parameter of the fire fighting equipment exceeds the early warning value of the state of the high-risk fire fighting equipment, the real-time monitoring point sends out alarm information and sends alarm information to nearby rescue units.
10. A monitoring and early warning system for building fires, characterized in that: the method comprises the following steps:
the parameter simulation module is used for simulating the environment parameters and the fire-fighting equipment state parameters corresponding to various buildings and analyzing the simulation results to obtain fire disaster factor tables corresponding to various buildings;
the building scene recognition model construction module is used for collecting historical image data of various buildings and constructing a building scene recognition model;
the building type identification module is used for acquiring image data of a target building and inputting the image data into the building scene identification model for identification to obtain a corresponding building type;
the fire disaster causing factor table selecting module is used for determining a corresponding fire disaster causing factor table according to the building category;
the field monitoring module is used for monitoring field parameters in the target building in real time;
and the analysis scheduling module is used for carrying out comparison analysis according to the field parameters and the fire disaster causing factor table corresponding to the target building, and carrying out fire monitoring and emergency treatment according to the analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211019258.7A CN115394036A (en) | 2022-08-24 | 2022-08-24 | Monitoring and early warning method and system for building fire |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211019258.7A CN115394036A (en) | 2022-08-24 | 2022-08-24 | Monitoring and early warning method and system for building fire |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115394036A true CN115394036A (en) | 2022-11-25 |
Family
ID=84120082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211019258.7A Pending CN115394036A (en) | 2022-08-24 | 2022-08-24 | Monitoring and early warning method and system for building fire |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115394036A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116189367A (en) * | 2022-12-09 | 2023-05-30 | 嘉应学院 | Building fire alarm system based on Internet of things |
| CN116469565A (en) * | 2023-03-29 | 2023-07-21 | 中国人民解放军总医院 | Aviation medical emergency rescue self-adaptive simulation scene control method, system and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU117684U1 (en) * | 2011-10-31 | 2012-06-27 | Сергей Иванович Бурдюгов | ADAPTIVE FIRE ALARM SYSTEM |
| CN107146357A (en) * | 2017-07-14 | 2017-09-08 | 重庆和航科技股份有限公司 | Fire based on Internet of Things in advance, thing neutralize retroactive method and monitoring system afterwards |
| CN110309727A (en) * | 2019-06-11 | 2019-10-08 | 四川隧唐科技股份有限公司 | A kind of foundation of Building recognition model, Building recognition method and apparatus |
| CN110363949A (en) * | 2019-07-25 | 2019-10-22 | 湖北烽火平安智能消防科技有限公司 | A kind of fire alarm system and method based on Internet of Things |
| CN110969796A (en) * | 2019-12-06 | 2020-04-07 | 无锡圣敏传感科技股份有限公司 | Fire alarm method and fire detector |
| CN111035872A (en) * | 2020-01-02 | 2020-04-21 | 中车青岛四方车辆研究所有限公司 | Battery box fire prevention and control system and method |
| CN112466082A (en) * | 2020-11-12 | 2021-03-09 | 上海意静信息科技有限公司 | Artificial intelligence fire alarm grading early warning method based on time-space and linkage relation |
| CN112801457A (en) * | 2020-12-31 | 2021-05-14 | 杭州拓深科技有限公司 | Fire-fighting linkage method and system based on regional fire risk assessment |
| CN113920670A (en) * | 2021-09-14 | 2022-01-11 | 烟台艾睿光电科技有限公司 | Fire safety monitoring method, device and system, fire monitoring equipment and medium |
| CN114748818A (en) * | 2022-05-18 | 2022-07-15 | 安徽鑫思诚科技有限公司 | Battery box intelligence fire extinguishing systems |
-
2022
- 2022-08-24 CN CN202211019258.7A patent/CN115394036A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU117684U1 (en) * | 2011-10-31 | 2012-06-27 | Сергей Иванович Бурдюгов | ADAPTIVE FIRE ALARM SYSTEM |
| CN107146357A (en) * | 2017-07-14 | 2017-09-08 | 重庆和航科技股份有限公司 | Fire based on Internet of Things in advance, thing neutralize retroactive method and monitoring system afterwards |
| CN110309727A (en) * | 2019-06-11 | 2019-10-08 | 四川隧唐科技股份有限公司 | A kind of foundation of Building recognition model, Building recognition method and apparatus |
| CN110363949A (en) * | 2019-07-25 | 2019-10-22 | 湖北烽火平安智能消防科技有限公司 | A kind of fire alarm system and method based on Internet of Things |
| CN110969796A (en) * | 2019-12-06 | 2020-04-07 | 无锡圣敏传感科技股份有限公司 | Fire alarm method and fire detector |
| CN111035872A (en) * | 2020-01-02 | 2020-04-21 | 中车青岛四方车辆研究所有限公司 | Battery box fire prevention and control system and method |
| CN112466082A (en) * | 2020-11-12 | 2021-03-09 | 上海意静信息科技有限公司 | Artificial intelligence fire alarm grading early warning method based on time-space and linkage relation |
| CN112801457A (en) * | 2020-12-31 | 2021-05-14 | 杭州拓深科技有限公司 | Fire-fighting linkage method and system based on regional fire risk assessment |
| CN113920670A (en) * | 2021-09-14 | 2022-01-11 | 烟台艾睿光电科技有限公司 | Fire safety monitoring method, device and system, fire monitoring equipment and medium |
| CN114748818A (en) * | 2022-05-18 | 2022-07-15 | 安徽鑫思诚科技有限公司 | Battery box intelligence fire extinguishing systems |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116189367A (en) * | 2022-12-09 | 2023-05-30 | 嘉应学院 | Building fire alarm system based on Internet of things |
| CN116189367B (en) * | 2022-12-09 | 2023-09-26 | 嘉应学院 | Building fire alarm system based on Internet of things |
| CN116469565A (en) * | 2023-03-29 | 2023-07-21 | 中国人民解放军总医院 | Aviation medical emergency rescue self-adaptive simulation scene control method, system and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115394036A (en) | Monitoring and early warning method and system for building fire | |
| CN110555617B (en) | Real-time dynamic quantitative assessment method for building fire risk based on Internet of things | |
| CN111311085A (en) | Dynamic risk assessment method and device for building fire based on Internet of things monitoring | |
| CN111754715B (en) | Fire-fighting emergency response method, device and system | |
| CN113936239A (en) | Intelligent fire fighting condition identification method and system based on neural network algorithm | |
| CN105976116B (en) | Fire safety dynamic evaluation method and system based on Internet of things | |
| 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 | |
| CN115035674A (en) | Intelligent fire-fighting monitoring and early-warning management system for smart building | |
| CN112488576A (en) | Fire-fighting risk assessment method, system, computer equipment and readable storage medium | |
| CN112800910A (en) | Communication machine room maintenance operation efficiency evaluation method and system | |
| CN116611562A (en) | Intelligent park fire early warning management system and method based on Internet of things | |
| CN114997754B (en) | Emergency plan analysis method and device based on cloud model and entropy weight method | |
| KR20220071880A (en) | Digital twin disaster management system customized for underground public areas | |
| CN116645775A (en) | Cloud platform fire alarm information response system | |
| CN115550609A (en) | Building Internet of things monitoring system capable of realizing automatic adaptation | |
| CN115660922A (en) | Intelligent safety and fire integrated early warning management system based on Internet of things | |
| CN116966468A (en) | Intelligent fire-fighting equipment supervision system | |
| CN117854221A (en) | Fire intelligent automatic alarm system for mail wheels | |
| CN110288789A (en) | A kind of building electric fire fighting alarm device and its control method | |
| CN111359132B (en) | Intelligent fire-fighting alarm method and system based on artificial intelligence | |
| Zhang et al. | Analysis and research on fire safety of university dormitory based on Bayesian network | |
| CN112863105A (en) | Fire-fighting early warning system based on fire-fighting relevance | |
| CN117151478A (en) | Chemical enterprise risk early warning method and system based on convolutional neural network | |
| CN118091054B (en) | Dangerous gas on-line monitoring system and method |
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 |