CN111359132A - Intelligent fire-fighting alarm method and system based on artificial intelligence - Google Patents
Intelligent fire-fighting alarm method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN111359132A CN111359132A CN202010237674.9A CN202010237674A CN111359132A CN 111359132 A CN111359132 A CN 111359132A CN 202010237674 A CN202010237674 A CN 202010237674A CN 111359132 A CN111359132 A CN 111359132A
- Authority
- CN
- China
- Prior art keywords
- fire
- fighting
- strategy
- sensor
- determination
- 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.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C37/00—Control of fire-fighting equipment
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
Abstract
The embodiment of the application provides an intelligent fire-fighting alarm method and system based on artificial intelligence. The method comprises the following steps: under the condition that any sensor finds that fire exists in a building, a fire determination sensor set is calculated through the sensors, an assistance determination signal is sent to each sensor in the fire determination sensor set, and meanwhile the assistance determination signal is sent to a fire control center; each sensor in the fire determination sensor set determines the position and type in the signal according to assistance; the fire control center guides the fire scene site characteristics in the assistance determination signal and the fire verification signal into the first deep learning network to obtain the fire determination probability, and guides the fire scene site characteristics in the assistance determination signal and the fire verification signal into the second deep learning network to obtain an escape strategy and a fire protection strategy; and sending the escape strategy to a building broadcasting system, and sending the fire-fighting strategy to a fire-fighting decision department. This application is through the efficiency that has improved the fire control alarm.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to an intelligent fire-fighting alarm method and system based on artificial intelligence.
Background
In the present case of fire fighting, the alarm is generally given in two ways: one mode is a telephone alarm mode of on-site witness personnel, which may have false alarm and misrepresentation conditions, and firefighters cannot master the on-site fire condition according to the description of witness personnel; another way is by sensing through an internet of things device installed in the fire scene, which also cannot give an alarm accurately, for example, if someone smokes in a room, a smoke sensor will give an alarm. After the two modes are used for alarming, fire-fighting personnel are required to analyze the fire cause and the fire intensity, and decision-making is required to be carried out on the configuration of the fire-fighting personnel, the scheduling of fire-fighting equipment and the research and judgment of the fire-fighting steps, so that a large amount of time is occupied, the optimal time for extinguishing the fire is delayed, and even personal injury is possibly caused to the fire-fighting personnel.
Disclosure of Invention
In view of this, the present application aims to provide an intelligent fire alarm method and system based on artificial intelligence, so as to improve fire alarm efficiency, and solve the technical problems that in the existing fire alarm process, the alarm accuracy is not high, the intelligence level is low, and thus the fire alarm efficiency is affected.
Based on the above purpose, the application provides an intelligent fire-fighting alarm method based on artificial intelligence, including:
sensing whether a fire occurs in a building or not through multiple types of sensors in the building, calculating a fire determination sensor set through the sensors under the condition that any sensor finds that the fire exists in the building, sending an assistance determination signal to each sensor in the fire determination sensor set, and sending the assistance determination signal to a fire control center; the assistance determination signal comprises the position and the type of the fire;
each sensor in the fire determination sensor set determines fire characteristics and obtains a fire verification signal according to the position and the type in the assistance determination signal, and sends the fire verification signal to the fire control center;
the fire control center guides the fire scene site characteristics in the assistance determination signal and the fire verification signal into a first deep learning network to obtain a fire determination probability, and guides the fire scene site characteristics in the assistance determination signal and the fire verification signal into a second deep learning network to obtain an escape strategy and a fire control strategy under the condition that the fire determination probability exceeds a preset alarm probability;
and sending the escape strategy to a building broadcasting system, guiding personnel in the building to escape, and sending the fire-fighting strategy to a fire-fighting decision department, wherein the fire-fighting strategy comprises the steps of fire fighter configuration, fire-fighting resource scheduling and fire scene operation.
In some embodiments, the method further comprises:
the fire fighting control center sends a fire condition acquisition instruction to a specified sensor, and the specified sensor returns the specified fire condition to the fire fighting control center after acquiring the specified fire condition according to the fire condition acquisition instruction;
and leading the specified fire into the second deep learning network, and updating the escape strategy and the fire-fighting strategy.
In some embodiments, the method further comprises:
the fire control center sends a cooperative fire alarm to a plurality of fire departments around the building, and each fire department returns the condition of the fire resource;
and importing a third deep learning network according to the fire fighting resource condition returned by each fire fighting department in the plurality of fire fighting departments, generating a collaborative fire fighting strategy, and distributing the collaborative fire fighting strategy to each fire fighting department.
In some embodiments, calculating a fire determination sensor set by the sensors includes:
calculating the sensors inside the buildings in the fire situation determination sensor set according to the positions and types of the fire situations;
and calculating the sensors outside the building in the fire determination sensor set according to the positions and types of the fires.
In some embodiments, each sensor in the set of fire determination sensors determines a fire signature and derives a fire verification signal based on the location and type in the assistance determination signal, including:
the fire condition verification signal comprises a fire condition degree and a fire source type;
the visual sensor determines position information in the signal through the assistance, collects the fire from different angles and identifies the fire degree;
and the chemical sensor puts a substance sampling robot into the position in the assistant determination signal, and the sampling robot is close to a fire point to sample the characteristics of the fire source and identify the type of the fire source.
In some embodiments, the activation function of the intermediate hidden layer neuron of the second deep learning network adopts a ReLU function, and the loss function adopts a cross entropy loss function, and the formula is as follows:
wherein x(i)In order to be able to output the desired output,
is the actual output;
and the optimization function adopts a random gradient descent method, and iterative training is carried out until the second deep learning network enters a steady state.
In some embodiments, the fire policy is sent to a fire decision department, the fire policy includes fire fighter configuration, fire resource scheduling, and fire scene operations, including:
solving a scheduling strategy for scheduling the fire fighters and the fire fighting resources required in the fire fighting strategy according to the states of the fire fighters and the fire fighting resources around the building;
and sending the scheduling strategy to the corresponding fire fighters and fire fighting resources.
Based on above-mentioned purpose, this application has still provided an wisdom fire control alarm system based on artificial intelligence, includes:
the fire detection system comprises a sensing module, a fire detection module and a fire control module, wherein the sensing module is used for sensing whether a fire occurs in a building through various types of sensors in the building, under the condition that any sensor finds that the fire exists in the building, a fire determination sensor set is calculated through the sensors, an assistance determination signal is sent to each sensor in the fire determination sensor set, and meanwhile, the assistance determination signal is sent to a fire control center; the assistance determination signal comprises the position and the type of the fire;
the verification module is used for determining the fire characteristics and obtaining a fire verification signal according to the position and the type in the assistance determination signal by each sensor in the fire determination sensor set, and sending the fire verification signal to the fire control center;
the fire control center is used for guiding fire scene site characteristics in the assistance determination signal and the fire verification signal into a first deep learning network to obtain a fire determination probability, and guiding the fire scene site characteristics in the assistance determination signal and the fire verification signal into a second deep learning network to obtain an escape strategy and a fire control strategy under the condition that the fire determination probability exceeds a preset alarm probability;
and the scheduling module is used for sending the escape strategy to a building broadcasting system, guiding personnel in the building to escape, and sending the fire-fighting strategy to a fire-fighting decision department, wherein the fire-fighting strategy comprises the steps of fire-fighting personnel configuration, fire-fighting resource scheduling and fire scene operation.
In some embodiments, the system further comprises:
the acquisition module is used for sending a fire condition acquisition instruction to a specified sensor by the fire control center, and returning the specified fire condition to the fire control center after the specified sensor acquires the specified fire condition according to the fire condition acquisition instruction;
and the updating module is used for guiding the specified fire into the second deep learning network and updating the escape strategy and the fire-fighting strategy.
In some embodiments, the system further comprises:
the coordination module is used for sending coordination fire-fighting alarms to a plurality of fire-fighting departments around the building by the fire-fighting control center, and each fire-fighting department returns the condition of the fire-fighting resource;
and the distribution module is used for importing a third deep learning network according to the fire fighting resource condition returned by each fire fighting department in the plurality of fire fighting departments, generating a collaborative fire fighting strategy and distributing the collaborative fire fighting strategy to each fire fighting department.
This application is through adopting artifical intelligent mode at the scene of a fire, characteristics such as the fire source type, the scene of a fire degree of discernment and check-up scene of a fire, intelligent decision-making formula fire alarm such as automatic generation fire control resource allocation, personnel's dispatch, fire control strategy provides accurate information for developing of fire control work to win the valuable time of fire control rescue, improved the efficiency of fire control rescue.
Drawings
In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.
Fig. 1 shows a flowchart of an intelligent fire alarm method based on artificial intelligence according to an embodiment of the present invention.
Fig. 2 illustrates a flowchart of an intelligent fire alarm method based on artificial intelligence according to an embodiment of the present invention.
Fig. 3 shows a flowchart of an intelligent fire alarm method based on artificial intelligence according to an embodiment of the present invention.
Fig. 4 shows a block diagram of an intelligent fire alarm system based on artificial intelligence according to an embodiment of the present invention.
Fig. 5 shows a block diagram of an intelligent fire alarm system based on artificial intelligence according to an embodiment of the present invention.
Fig. 6 shows a block diagram of an intelligent fire alarm system based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows a flowchart of an intelligent fire alarm method based on artificial intelligence according to an embodiment of the present invention. As shown in fig. 1, the intelligent fire alarm method based on artificial intelligence includes:
step S11, sensing whether a fire occurs in a building through multiple types of sensors in the building, calculating a fire determination sensor set through the sensors under the condition that any sensor finds that the fire exists in the building, sending an assistance determination signal to each sensor in the fire determination sensor set, and sending the assistance determination signal to a fire control center; the assistance determination signal includes the location and type of the fire.
Specifically, the position of the fire includes the position and angle of the ignition point, the distance from the acquisition target, and the like; the type of fire includes the form of the fire point (e.g., solid, liquid, gaseous, etc.), the type of combustible material in the vicinity of the fire point, the size of the fire space, etc.
In one embodiment, a set of fire determination sensors is computed by the sensors, comprising:
calculating the sensors inside the buildings in the fire situation determination sensor set according to the positions and types of the fire situations;
and calculating the sensors outside the building in the fire determination sensor set according to the positions and types of the fires.
Specifically, the determination of whether a fire has occurred in a building can generally be performed from two points, one from the inside of the building and the other from the outside of the building. For example, the identification can be performed by the temperature of a fire scene, the form of flames, the generation of smoke, and the like inside a building, and the identification can be performed by the scene of smoke, the color of flames, and the like outside the building.
And S12, determining fire characteristics and obtaining a fire verification signal according to the position and the type in the assistance determination signal by each sensor in the fire determination sensor set, and sending the fire verification signal to the fire control center.
Specifically, when any one of the sensors finds a fire, all the sensors in the sensor set can be immediately notified to confirm the fire detected by the found fire sensor, so that the accuracy of fire alarm is improved.
In one embodiment, each sensor in the set of fire determination sensors determines a fire signature and derives a fire verification signal based on the location and type in the assistance determination signal, including:
the fire condition verification signal comprises a fire condition degree and a fire source type;
the visual sensor determines position information in the signal through the assistance, collects the fire from different angles and identifies the fire degree;
and the chemical sensor puts a substance sampling robot into the position in the assistant determination signal, and the sampling robot is close to a fire point to sample the characteristics of the fire source and identify the type of the fire source.
Specifically, the visual sensor mainly identifies the degree of fire by collecting visual characteristics of a fire scene, such as the combustion range of flame, the concentration degree of smoke and the like; the chemical sensor can judge the fire cause by identifying the characteristics of chemical substances near the fire point, and provides a decision basis for the designation of a fire extinguishing strategy.
And step S13, the fire control center introduces fire scene site characteristics in the assistance determination signal and the fire verification signal into a first deep learning network to obtain a fire determination probability, and introduces fire scene site characteristics in the assistance determination signal and the fire verification signal into a second deep learning network to obtain an escape strategy and a fire protection strategy under the condition that the fire determination probability exceeds a preset alarm probability.
In one embodiment, the activation function of the intermediate hidden layer neuron of the second deep learning network adopts a ReLU function, and the loss function adopts a cross entropy loss function, and the formula is as follows:
wherein x(i)In order to be able to output the desired output,
is the actual output;
and the optimization function adopts a random gradient descent method, and iterative training is carried out until the second deep learning network enters a steady state.
In the second deep learning network, by adopting the above cross entropy loss function, the accuracy of deep learning can be improved.
In one embodiment, the fire policy is sent to a fire decision department, and the fire policy includes fire fighter configuration, fire resource scheduling, and fire scene operation steps, including:
solving a scheduling strategy for scheduling the fire fighters and the fire fighting resources required in the fire fighting strategy according to the states of the fire fighters and the fire fighting resources around the building;
and sending the scheduling strategy to the corresponding fire fighters and fire fighting resources.
And S14, sending the escape strategy to a building broadcasting system, guiding personnel in the building to escape, and sending the fire-fighting strategy to a fire-fighting decision department, wherein the fire-fighting strategy comprises the steps of fire-fighting personnel configuration, fire-fighting resource scheduling and fire scene operation.
Fig. 2 illustrates a flowchart of an intelligent fire alarm method based on artificial intelligence according to an embodiment of the present invention. As shown in fig. 2, the intelligent fire alarm method based on artificial intelligence further includes:
and S15, the fire control center sends a fire collecting instruction to a specified sensor, and the specified sensor returns the specified fire to the fire control center after collecting the specified fire according to the fire collecting instruction.
And step S16, introducing the specified fire into the second deep learning network, and updating the escape strategy and the fire-fighting strategy.
Specifically, when a fire alarm is generated, two types of strategies need to be obtained through analysis of the on-site fire, on one hand, the two types of strategies are fire-fighting strategies facing fire departments, such as materials needing to be dispatched facing a specific fire, equipped professionals, specific steps for fire extinguishment and the like; on the other hand, the life-saving strategy is directed to people who live in the fire scene, for example, which path is selected to rapidly escape from the scene, which preparation needs to be performed in advance for a specific fire situation in the escape process, and the like.
Fig. 3 shows a flowchart of an intelligent fire alarm method based on artificial intelligence according to an embodiment of the present invention. As shown in fig. 3, the intelligent fire alarm method based on artificial intelligence further includes:
step S17, the fire control center sends a coordinated fire alarm to a plurality of fire departments around the building, and each fire department returns the situation of the fire resource.
And step S18, importing a third deep learning network according to the fire fighting resource condition returned by each fire fighting department in the plurality of fire fighting departments, generating a collaborative fire fighting strategy, and distributing the collaborative fire fighting strategy to each fire fighting department.
For example, there may be a situation that the fire department near the fire place has limited hands and short supplies, and at this time, it is necessary to schedule multiple fire departments near the fire place to cooperatively perform fire rescue, and fire alarms need to be sent to these departments at the same time. Therefore, personnel and material allocation, cooperation strategies and the like required to be provided by each fire department are calculated through the third deep learning network.
Fig. 4 shows a block diagram of an intelligent fire alarm system based on artificial intelligence according to an embodiment of the present invention. As shown in fig. 4, the intelligent fire alarm system based on artificial intelligence includes:
the fire detection system comprises a sensing module 41, a fire detection module and a fire control module, wherein the sensing module is used for sensing whether a fire occurs in a building through various types of sensors in the building, calculating a fire determination sensor set through the sensors under the condition that any sensor finds that the fire exists in the building, sending an assistance determination signal to each sensor in the fire determination sensor set, and sending the assistance determination signal to a fire control center; the assistance determination signal comprises the position and the type of the fire;
the verification module 42 is used for determining the fire characteristics and obtaining a fire verification signal according to the position and the type in the assistance determination signal by each sensor in the fire determination sensor set, and sending the fire verification signal to the fire control center;
the strategy module 43 is configured to, by the fire control center, import the fire scene site features in the assistance determination signal and the fire verification signal into a first deep learning network to obtain a fire determination probability, and import the fire scene site features in the assistance determination signal and the fire verification signal into a second deep learning network to obtain an escape strategy and a fire protection strategy when the fire determination probability exceeds a preset alarm probability;
and the scheduling module 44 is configured to send the escape strategy to a building broadcasting system, guide personnel in the building to escape, and send the fire-fighting strategy to a fire-fighting decision-making department, where the fire-fighting strategy includes fire-fighting personnel configuration, fire-fighting resource scheduling, and fire scene operation steps.
Fig. 5 shows a block diagram of an intelligent fire alarm system based on artificial intelligence according to an embodiment of the present invention. As shown in fig. 5, the intelligent fire alarm system based on artificial intelligence further includes:
the acquisition module 45 is used for sending a fire condition acquisition instruction to a specified sensor by the fire control center, and returning the specified fire condition to the fire control center after the specified sensor acquires the specified fire condition according to the fire condition acquisition instruction;
and the updating module 46 is used for guiding the specified fire into the second deep learning network and updating the escape strategy and the fire fighting strategy.
Fig. 6 shows a block diagram of an intelligent fire alarm system based on artificial intelligence according to an embodiment of the present invention. As shown in fig. 6, the intelligent fire alarm system based on artificial intelligence further includes:
a coordination module 47, configured to send a coordination fire alarm to multiple fire departments around the building by the fire control center, where each fire department returns its fire resource status;
and the distribution module 48 is configured to import the third deep learning network according to the fire-fighting resource condition returned by each of the multiple fire-fighting departments, generate a collaborative fire-fighting strategy, and distribute the collaborative fire-fighting strategy to each of the fire-fighting departments.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. An intelligent fire-fighting alarm method based on artificial intelligence is characterized by comprising the following steps:
sensing whether a fire occurs in a building or not through multiple types of sensors in the building, calculating a fire determination sensor set through the sensors under the condition that any sensor finds that the fire exists in the building, sending an assistance determination signal to each sensor in the fire determination sensor set, and sending the assistance determination signal to a fire control center; the assistance determination signal comprises the position and the type of the fire;
each sensor in the fire determination sensor set determines fire characteristics and obtains a fire verification signal according to the position and the type in the assistance determination signal, and sends the fire verification signal to the fire control center;
the fire control center guides the fire scene site characteristics in the assistance determination signal and the fire verification signal into a first deep learning network to obtain a fire determination probability, and guides the fire scene site characteristics in the assistance determination signal and the fire verification signal into a second deep learning network to obtain an escape strategy and a fire control strategy under the condition that the fire determination probability exceeds a preset alarm probability;
and sending the escape strategy to a building broadcasting system, guiding personnel in the building to escape, and sending the fire-fighting strategy to a fire-fighting decision department, wherein the fire-fighting strategy comprises the steps of fire fighter configuration, fire-fighting resource scheduling and fire scene operation.
2. The method of claim 1, further comprising:
the fire fighting control center sends a fire condition acquisition instruction to a specified sensor, and the specified sensor returns the specified fire condition to the fire fighting control center after acquiring the specified fire condition according to the fire condition acquisition instruction;
and leading the specified fire into the second deep learning network, and updating the escape strategy and the fire-fighting strategy.
3. The method of claim 1, further comprising:
the fire control center sends a cooperative fire alarm to a plurality of fire departments around the building, and each fire department returns the condition of the fire resource;
and importing a third deep learning network according to the fire fighting resource condition returned by each fire fighting department in the plurality of fire fighting departments, generating a collaborative fire fighting strategy, and distributing the collaborative fire fighting strategy to each fire fighting department.
4. The method of claim 1, wherein computing a fire determination sensor set from the sensors comprises:
calculating the sensors inside the buildings in the fire situation determination sensor set according to the positions and types of the fire situations;
and calculating the sensors outside the building in the fire determination sensor set according to the positions and types of the fires.
5. The method of claim 1, wherein each sensor of the set of fire determination sensors determines a fire signature and derives a fire verification signal based on a location and a type in the assistance determination signal, comprising:
the fire condition verification signal comprises a fire condition degree and a fire source type;
the visual sensor determines position information in the signal through the assistance, collects the fire from different angles and identifies the fire degree;
and the chemical sensor puts a substance sampling robot into the position in the assistant determination signal, and the sampling robot is close to a fire point to sample the characteristics of the fire source and identify the type of the fire source.
6. The method of claim 1, wherein the activation function of the second deep learning network intermediate hidden layer neuron adopts a ReLU function, and the loss function adopts a cross entropy loss function, and the formula is as follows:
wherein x(i)In order to be able to output the desired output,
is the actual output;
and the optimization function adopts a random gradient descent method, and iterative training is carried out until the second deep learning network enters a steady state.
7. The method of claim 1, wherein the fire policy is sent to a fire decision department, the fire policy including fire fighter configuration, fire resource scheduling, and fire scene operations steps, comprising:
solving a scheduling strategy for scheduling the fire fighters and the fire fighting resources required in the fire fighting strategy according to the states of the fire fighters and the fire fighting resources around the building;
and sending the scheduling strategy to the corresponding fire fighters and fire fighting resources.
8. The utility model provides an wisdom fire control alarm system based on artificial intelligence which characterized in that includes:
the fire detection system comprises a sensing module, a fire detection module and a fire control module, wherein the sensing module is used for sensing whether a fire occurs in a building through various types of sensors in the building, under the condition that any sensor finds that the fire exists in the building, a fire determination sensor set is calculated through the sensors, an assistance determination signal is sent to each sensor in the fire determination sensor set, and meanwhile, the assistance determination signal is sent to a fire control center; the assistance determination signal comprises the position and the type of the fire;
the verification module is used for determining the fire characteristics and obtaining a fire verification signal according to the position and the type in the assistance determination signal by each sensor in the fire determination sensor set, and sending the fire verification signal to the fire control center;
the fire control center is used for guiding fire scene site characteristics in the assistance determination signal and the fire verification signal into a first deep learning network to obtain a fire determination probability, and guiding the fire scene site characteristics in the assistance determination signal and the fire verification signal into a second deep learning network to obtain an escape strategy and a fire control strategy under the condition that the fire determination probability exceeds a preset alarm probability;
and the scheduling module is used for sending the escape strategy to a building broadcasting system, guiding personnel in the building to escape, and sending the fire-fighting strategy to a fire-fighting decision department, wherein the fire-fighting strategy comprises the steps of fire-fighting personnel configuration, fire-fighting resource scheduling and fire scene operation.
9. The system of claim 8, further comprising:
the acquisition module is used for sending a fire condition acquisition instruction to a specified sensor by the fire control center, and returning the specified fire condition to the fire control center after the specified sensor acquires the specified fire condition according to the fire condition acquisition instruction;
and the updating module is used for guiding the specified fire into the second deep learning network and updating the escape strategy and the fire-fighting strategy.
10. The system of claim 8, further comprising:
the coordination module is used for sending coordination fire-fighting alarms to a plurality of fire-fighting departments around the building by the fire-fighting control center, and each fire-fighting department returns the condition of the fire-fighting resource;
and the distribution module is used for importing a third deep learning network according to the fire fighting resource condition returned by each fire fighting department in the plurality of fire fighting departments, generating a collaborative fire fighting strategy and distributing the collaborative fire fighting strategy to each fire fighting department.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010237674.9A CN111359132B (en) | 2020-03-30 | 2020-03-30 | Intelligent fire-fighting alarm method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010237674.9A CN111359132B (en) | 2020-03-30 | 2020-03-30 | Intelligent fire-fighting alarm method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111359132A true CN111359132A (en) | 2020-07-03 |
| CN111359132B CN111359132B (en) | 2021-07-30 |
Family
ID=71198969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010237674.9A Active CN111359132B (en) | 2020-03-30 | 2020-03-30 | Intelligent fire-fighting alarm method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111359132B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383624A (en) * | 2020-11-13 | 2021-02-19 | 杭州海康消防科技有限公司 | Fire extinguishing system based on thing networking |
| CN112699745A (en) * | 2020-12-16 | 2021-04-23 | 安徽建筑大学 | Method for positioning trapped people on fire scene |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2305760B (en) * | 1995-09-29 | 1997-12-03 | Pittway Corp | Apparatus and method for discrimination of fire types |
| CN103394171A (en) * | 2013-08-02 | 2013-11-20 | 重庆大学 | Large high-rise building indoor fire urgent evacuation indication escape method and system |
| CN106934980A (en) * | 2017-05-10 | 2017-07-07 | 南京三宝弘正视觉科技有限公司 | Method for safety monitoring and alarm method |
| CN109416864A (en) * | 2016-07-12 | 2019-03-01 | 德国美力有限两合公司 | For determining the system and method for fire condition verifiedly and for this traveling tool and central location |
| CN109887221A (en) * | 2019-03-13 | 2019-06-14 | 杭州图析同创科技有限公司 | A kind of fire disaster intelligently detection system and its control method |
| CN110046837A (en) * | 2019-05-20 | 2019-07-23 | 北京唐芯物联网科技有限公司 | A kind of fire management system based on artificial intelligence |
| CN110223209A (en) * | 2019-05-06 | 2019-09-10 | 特斯联（北京）科技有限公司 | A kind of community management method and device surpassing brain based on city |
-
2020
- 2020-03-30 CN CN202010237674.9A patent/CN111359132B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2305760B (en) * | 1995-09-29 | 1997-12-03 | Pittway Corp | Apparatus and method for discrimination of fire types |
| CN103394171A (en) * | 2013-08-02 | 2013-11-20 | 重庆大学 | Large high-rise building indoor fire urgent evacuation indication escape method and system |
| CN109416864A (en) * | 2016-07-12 | 2019-03-01 | 德国美力有限两合公司 | For determining the system and method for fire condition verifiedly and for this traveling tool and central location |
| CN106934980A (en) * | 2017-05-10 | 2017-07-07 | 南京三宝弘正视觉科技有限公司 | Method for safety monitoring and alarm method |
| CN109887221A (en) * | 2019-03-13 | 2019-06-14 | 杭州图析同创科技有限公司 | A kind of fire disaster intelligently detection system and its control method |
| CN110223209A (en) * | 2019-05-06 | 2019-09-10 | 特斯联（北京）科技有限公司 | A kind of community management method and device surpassing brain based on city |
| CN110046837A (en) * | 2019-05-20 | 2019-07-23 | 北京唐芯物联网科技有限公司 | A kind of fire management system based on artificial intelligence |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383624A (en) * | 2020-11-13 | 2021-02-19 | 杭州海康消防科技有限公司 | Fire extinguishing system based on thing networking |
| CN112699745A (en) * | 2020-12-16 | 2021-04-23 | 安徽建筑大学 | Method for positioning trapped people on fire scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111359132B (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108648402A (en) | intelligent fire alarm method, terminal and storage medium | |
| KR102124067B1 (en) | SYSTEM FOR PREDICTING SMOKE SPREADING AND EVACUATION ROUTE USING INTERNET OF THING (IoT) SENSORS, AMD METHOD FOR THE SAME | |
| CN111359132B (en) | Intelligent fire-fighting alarm method and system based on artificial intelligence | |
| CN109819043A (en) | 3 D intelligent emergency fire control platform system and its operating method | |
| Cisek et al. | Evacuation route assessment model for optimization of evacuation in buildings with active dynamic signage system | |
| CN112044006A (en) | Monitoring fire-fighting system for building | |
| CN101162545A (en) | Tall building fire light-temperature composite intelligent monitoring prediction device | |
| US9852620B1 (en) | System and method for detecting sound and performing an action on the detected sound | |
| CN113936239A (en) | Intelligent fire fighting condition identification method and system based on neural network algorithm | |
| CN113034833B (en) | Artificial intelligence information management system based on multisensor fuses | |
| CN113378968A (en) | Building fire classification method and device based on K-means clustering | |
| CN105938648A (en) | Household safety integrated management system and method | |
| CN111178828A (en) | Method and system for building fire safety early warning | |
| Ouache et al. | Performance investigation of fire protection and intervention strategies: Artificial neural network-based assessment framework | |
| CN114724349A (en) | Gridding fire safety early warning method, system and storage medium based on P2P network | |
| CN110796822B (en) | Method for prejudging fire point direction based on improved smoke alarm | |
| CN111412014A (en) | Danger detection and emergency evacuation method and device | |
| CN113763664B (en) | Intelligent building fire control system | |
| JiJi et al. | Multivariate statistical process control for continuous monitoring of networked early warning fire detection (EWFD) systems | |
| CN201117044Y (en) | High-rise building fire forecast device based on light and temperature composite intelligent monitoring | |
| CN115394036A (en) | Monitoring and early warning method and system for building fire | |
| CN114792465A (en) | Fire safety monitoring system based on regional alarm model | |
| CN111539634A (en) | Fire rescue aid decision scheme generation method | |
| CN111160780A (en) | Dispatching robot and dispatching method | |
| CN111614938A (en) | Risk identification method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |