CN110115819A - Fire water monitor orientation early warning and extinguishing method, storage medium and fire water monitor based on artificial intelligence - Google Patents
Fire water monitor orientation early warning and extinguishing method, storage medium and fire water monitor based on artificial intelligence Download PDFInfo
- Publication number
- CN110115819A CN110115819A CN201910401519.3A CN201910401519A CN110115819A CN 110115819 A CN110115819 A CN 110115819A CN 201910401519 A CN201910401519 A CN 201910401519A CN 110115819 A CN110115819 A CN 110115819A
- Authority
- CN
- China
- Prior art keywords
- fire water
- water monitor
- processor
- sent
- flame
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C31/00—Delivery of fire-extinguishing material
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C37/00—Control of fire-fighting equipment
- A62C37/36—Control of fire-fighting equipment an actuating signal being generated by a sensor separate from an outlet device
- A62C37/38—Control of fire-fighting equipment an actuating signal being generated by a sensor separate from an outlet device by both sensor and actuator, e.g. valve, being in the danger zone
- A62C37/40—Control of fire-fighting equipment an actuating signal being generated by a sensor separate from an outlet device by both sensor and actuator, e.g. valve, being in the danger zone with electric connection between sensor and actuator
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Fire-Extinguishing By Fire Departments, And Fire-Extinguishing Equipment And Control Thereof (AREA)
Abstract
The invention discloses based on artificial intelligence fire water monitor orientation early warning and extinguishing method, storage medium and fire water monitor, method include: acquisition sensor data, when sensing that flame then generates first level angle rotation control signal and be sent to first motor;It controls camera to open, obtain at camera through the image data of the corresponding position after first motor rotation control;By the convolutional neural networks model after image data input training, the flame grade in image data is exported;Judge flame grade: when flame grade is cigarette or small fire, generating pre-warning signal and be sent to communication module;When flame grade is moderate heat or more, generates the second level angle rotation control signal and be sent to first motor and generate the second motor that vertical angles rotation control signal is sent to control outlet pipe rotation angle.Method of the invention solves the problems, such as that erroneous judgement and water spray effect are undesirable, and storage device and fire water monitor also solve the problems, such as corresponding.
Description
Technical field
The present invention relates to fire-fighting domains, more particularly to based on artificial intelligence fire water monitor orientation early warning and extinguishing method,
Storage medium and fire water monitor.
Background technique
" fire-fighting " is to remove a hidden danger, and prevents calamity, that is, prevents and solve people to meet in life, work, learning process
Artificial and natural, accidental disaster the general name arrived.
Existing automatic sprinkler system is by components and pipelines, water facilities group such as sprinkler tip, alarm valve groups
At, and the automatic fire extinguishing system that can be sprayed water in the case of fire.By wet alarm valve group, closed nozzle, water flow indicator, control
The composition such as valve, end water testing device, pipeline and water facilities.Pressure water is full of in the pipeline of system, once fire occurs, spray
It sprays water immediately after head movement.
However existing automatic sprinkler system can't put out a fire according to the actual conditions for generating fire, especially work as pumping
When the smog that cigarette generates is located at around detection device, it is easy to cause erroneous judgement to spray water;And existing automatic water jetting
Fire extinguishing system can not carry out concentration sprinkling to fire area.
Therefore fire water monitor orientation early warning and extinguishing method, storage medium and fire water monitor based on artificial intelligence are provided,
To solve erroneous judgement and the undesirable situation of water spray effect, belong to this field urgent problem to be solved.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide the fire water monitors based on artificial intelligence to orient early warning
And extinguishing method, storage medium and fire water monitor, solve the problems, such as that the prior art is easy erroneous judgement.
The purpose of the present invention is achieved through the following technical solutions:
The first aspect of the present invention provides the fire water monitor orientation early warning and extinguishing method based on artificial intelligence, based on disappearing
The processor of anti-water cannon, the described method comprises the following steps:
Sensor data is obtained, when sensing that flame then generates first level angle rotation control signal and be sent to first
Motor;
It controls camera to open, obtain at camera through the picture number of the corresponding position after first motor rotation control
According to;
By the convolutional neural networks model after the input training of described image data, the flame etc. in described image data is exported
Grade;
Judge flame grade: when flame grade is cigarette or small fire, generating pre-warning signal and be sent to communication module;Work as fire
When flame grade is moderate heat or more, generates the second level angle rotation control signal and be sent to first motor and generate vertical angle
Degree rotation control signal is sent to the second motor of control outlet pipe rotation angle, generates water spray open signal later and controls to corresponding
Device processed.
Further, the method further include:
Judge that flame changes: when the pace of change of flame is more than threshold value, generating the second level angle rotation control signal
It is sent to first motor and generates the second motor that vertical angles rotation control signal is sent to control outlet pipe rotation angle,
Water spray open signal is generated later to corresponding control device.
Further, the convolutional neural networks model after the training after the training of higher level's terminal by communication module by being sent out
It send.
Further, the training includes:
Training sample is input to convolutional neural networks model to be trained, the convolutional neural networks mould after being trained
Type;And the convolutional neural networks model after training is tested using the test sample, test obtains described after the completion
Convolutional neural networks model after training;
The convolutional neural networks include: input layer, the first convolutional layer, the first pond layer, the second convolutional layer, the second pond
Layer, full articulamentum and output layer.
Further, the method also includes:
Described image data are uploaded to higher level's terminal by timing, for the training sample and test sample to be added;
The renewal time of convolutional neural networks model after the current training of judgement, prompt information is generated if overruning simultaneously
It is sent to higher level's terminal;
Convolutional neural networks model after obtaining the training updated.
Further, the method also includes initialization steps:
After powering on, timing generates icmp request command and superior terminal is sent;
After receiving icmp response command, stop generating icmp request command;
Convolutional neural networks model after receiving the training that higher level's terminal is sent for the first time.
The second aspect of the present invention provides a kind of storage medium, is stored thereon with computer instruction, the computer instruction
The step of fire water monitor based on artificial intelligence orients early warning and extinguishing method is executed when operation.
The third aspect of the present invention provides a kind of fire water monitor, including memory and processor, stores on the memory
There is the computer instruction that can be run on the processor, the processor executes the base when running the computer instruction
In the step of fire water monitor of artificial intelligence orients early warning and extinguishing method.
Further, the fire water monitor further include:
Shell, the memory and processor are located at the enclosure interior;
Fixed bracket, one end connect the shell, and the other end is installed on outside;
Inductor is connected to the processor, and is set to the housing bottom, for incuding surrounding flame;
Camera is connected to the processor, and the housing sidewall is set to, for obtaining image data;
Water inlet pipe passes through the shell and is arranged;
Outlet pipe passes through the shell and is arranged, connect with the water inlet pipe;
First motor is connect with the shell and processor respectively, for receiving the first level angle of processor transmission
It controls the shell after rotation control signal and the second level angle rotation control signal to be rotated, to realize control camera shooting
Head and outlet pipe rotate horizontally;
Second motor is connect with the outlet pipe and processor respectively, for receiving the vertical angles rotation of processor transmission
It controls the outlet pipe after turning control signal and rotates vertically;
Control device is connect with processor, is set to inside outlet pipe or water inlet pipe, for receiving the life of processor transmission
At unlatching outlet pipe or water inlet pipe after water spray open signal;
Communication module is connect with processor, is sent data for superior terminal or is received the number that higher level's terminal is sent
According to, and send pre-warning signal.
Further, the fire water monitor further include:
Device for detecting water pressure is connect with processor, is set to inside outlet pipe or water inlet pipe, for detecting real-time hydraulic pressure simultaneously
It is sent to processor.
The beneficial effects of the present invention are:
(1) method of the invention is using inductor induction, camera acquisition, convolutional neural networks judgement and flame grade
The mode of classification judgement and processing solves the problems, such as that erroneous judgement and water spray effect are undesirable.Storage device and fire water of the invention
Big gun also solves the problems, such as corresponding.
(2) in a preferred embodiment of method of the invention, under the action of considering flammable object, the variation of flame is to refer to
Several levels increase, therefore during progress flame puts out judgement, not only judge flame grade, it is also considered that the variation of flame itself
Speed.
(3) in a preferred embodiment of method of the invention, the convolutional neural networks model after training is by under higher level
It is sent to fire water monitor, the convolutional neural networks model for being stored in processor when production can be used always to avoid fire water monitor,
So that the problem of data judgement inaccuracy.
(4) in a preferred embodiment of method of the invention, the image data with flame is uploaded to by fire water monitor
Higher level's terminal, higher level's terminal are further trained, and since the data that fire water monitor uploads are actual flame data, and are led to
Test data and training data might not be corresponding with practical scene in normal situation, therefore can make subsequent obtained convolution
Neural network model is more in line with this environment, and further increases recognition accuracy;
Fire water monitor can voluntarily judge to be currently stored in inside processor after the training of (or in external memory) simultaneously
Convolutional neural networks model renewal time, prompt information is generated if overruning and sends supreme grade terminal, i.e. fire-fighting
Water cannon can be further ensured that as the renewal time of the convolutional neural networks model after newest training.
The step is combined with previous advantage, it can the convolutional neural networks after guaranteeing the training inside fire water monitor
Model is the high model of accuracy rate.
(5) it in a preferred embodiment of method of the invention, using the network test function of ping order, not only realizes
The network connection of fire water monitor and higher level's terminal detects, and also sends address to higher level terminal to realize that higher level terminal will instruct
Convolutional neural networks model after white silk is sent to the function of corresponding fire water monitor.
Detailed description of the invention
Fig. 1 is the flow chart of an example embodiments of the invention;
Fig. 2 is the connection block diagram of an example embodiments of the invention.
Specific embodiment
Technical solution of the present invention is clearly and completely described with reference to the accompanying drawing, it is clear that described embodiment
It is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that belong to "center", "upper", "lower", "left", "right", "vertical",
The direction of the instructions such as "horizontal", "inner", "outside" or positional relationship be based on direction or positional relationship described in attached drawing, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, belong to " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can
To be mechanical connection, it is also possible to be electrically connected;It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
It is only to be not intended to be limiting the application merely for for the purpose of describing particular embodiments in term used in this application.
It is also intended in the application and the "an" of singular used in the attached claims, " described " and "the" including majority
Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps
It may be combined containing one or more associated any or all of project listed.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from
In the case where the application range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination ".
As long as in addition, the non-structure each other of technical characteristic involved in invention described below different embodiments
It can be combined with each other at conflict.
Existing automatic sprinkler system can't put out a fire according to the actual conditions for generating fire, especially produce when smoking
When raw smog is located at around detection device, it is easy to cause erroneous judgement to spray water;And existing automatic sprinkling fire-extinguishing
System can not carry out concentration sprinkling to fire area.
In view of this, the application be intended to provide provide based on artificial intelligence fire water monitor orientation early warning and extinguishing method,
Storage medium and fire water monitor, for solving erroneous judgement and the undesirable situation of water spray effect.
Early warning is oriented referring to the fire water monitor based on artificial intelligence that Fig. 1, Fig. 1 are one exemplary embodiments of the application and is gone out
The method of ignition method, this method are applied to the processor based on fire water monitor, and the method can comprise the following steps that
S1: obtaining sensor data, when sensing that flame then generates first level angle rotation control signal and be sent to
First motor.
Wherein, inductor is preferably disposed on fire water monitor, i.e., is wholely set with fire water monitor.Inductor can be infrared
Induction, is also possible to ultraviolet induction.
And the range of observation of inductor depends on installation site, such as the fire water monitor can be set among room,
To the inductor of 360 degree of observations of selection, it also can choose and be installed on house corner, thus the inductor of 90 degree of observations of selection.
It might have flame because inductor is only capable of sensing and exist, but be inaccurate, therefore needed later using taking the photograph
As head is further confirmed that, angle is generated to induction signal according to the position of inductor sensing at this time.
S2: control camera is opened, and is obtained at camera through the figure of the corresponding position after first motor rotation control
As data.
Later after the completion of rotation, first motor can be to signal after the completion of a rotation, the camera shooting of processor control at this time
Head is opened, and camera takes pictures to corresponding position.
S3: by the convolutional neural networks model after the input training of described image data, the fire in described image data is exported
Flame grade.
After the completion of taking pictures, processor obtains image data, later the convolutional Neural net after the training inside input processor
Network model, the model can export the flame grade in the image data.
Wherein, flame grade is artificially defined, is classified according to flame size.
S4: judge flame grade: when flame grade is cigarette or small fire, generating pre-warning signal and be sent to communication module;
When flame grade is moderate heat or more, generates the second level angle rotation control signal and be sent to first motor and generate perpendicular
Squareness rotation control signal is sent to the second motor of control outlet pipe rotation angle, generates water spray open signal later to right
Answer control device.
It should be noted that the application use grading forewarning system and fire extinguishing, i.e., when the flame grade in inferior grade, not into
Row fire extinguishing, but generate pre-warning signal and notify corresponding personnel;And when flame grade high-grade in, then it is put out a fire (pre-
Alert signal, which also produces, to be notified).
At this point, what is controlled is the horizontal direction angle and vertical direction angle of outlet pipe.
In addition, the control device can be solenoid valve.
Therefore, using this kind of mode, the case where both having can solve erroneous judgement, is (by convolutional neural networks model to image data
Judgement, and flame grade is judged) and the case where water spray effect undesirable (position rotating outlet pipe).
More preferably, in one exemplary embodiment, the method further include:
S4 ': judge that flame changes: when the pace of change of flame is more than threshold value, generating the rotation control of the second level angle
Signal is sent to first motor and generation vertical angles rotation control signal is sent to the second of control outlet pipe rotation angle
Motor generates water spray open signal to corresponding control device later.
The judgment step is existed simultaneously with above-mentioned step S4, i.e., not only judges flame grade, it is also considered that flame itself
Pace of change.
Such as in the several image datas in front and back, if its pace of change of flame is higher than setting value, even if the flame
Grade is small fire, also can execute extinguishing operations to it.
Since under the action of flammable object, the variation of flame is exponential growth, therefore the step considers the point, right
The state that flame is put out is further limited.
More preferably, in one exemplary embodiment, the convolutional neural networks model after the training is instructed by higher level's terminal
It is sent after white silk by communication module.
That is, the convolutional neural networks model after the training is to be issued to fire water monitor by higher level.Using this kind
Mode, can be to avoid fire water monitor always using the convolutional neural networks model for being stored in processor when production, so that data
Judgement inaccuracy.
More preferably, based in the above exemplary embodiments, in one exemplary embodiment, the training includes:
Training sample is input to convolutional neural networks model to be trained, the convolutional neural networks mould after being trained
Type;And the convolutional neural networks model after training is tested using the test sample, test obtains described after the completion
Convolutional neural networks model after training;
The convolutional neural networks include: input layer, the first convolutional layer, the first pond layer, the second convolutional layer, the second pond
Layer, full articulamentum and output layer.
Wherein, which is applied in higher level's terminal, and this step is only to be defined to it.
Wherein, higher level's terminal can be dfs server.
More preferably, it is based in the above exemplary embodiments, in one exemplary embodiment, the method also includes:
Described image data are uploaded to higher level's terminal by timing, for the training sample and test sample to be added;
The renewal time of convolutional neural networks model after the current training of judgement, prompt information is generated if overruning simultaneously
It is sent to higher level's terminal;
Convolutional neural networks model after obtaining the training updated.
It should be noted that there are two advantages for step tool:
Image data with flame is uploaded to higher level's terminal for fire water monitor by one, and higher level's terminal is further instructed
Practice, since the data that fire water monitor uploads are actual flame data, and test data and training data be simultaneously under normal conditions
It is not necessarily corresponding with practical scene, therefore the step can make subsequent obtained convolutional neural networks model be more in line with this
Environment, and further increase recognition accuracy.
Secondly can voluntarily judge the training for being currently stored in (or in external memory) inside processor for fire water monitor
The renewal time of convolutional neural networks model afterwards generates prompt information if overruning and sends supreme grade terminal, i.e., should
Step meeting fire water monitor can be further ensured that as the renewal time of the convolutional neural networks model after newest training.The step with
A upper advantage is combined, it can the convolutional neural networks model after guaranteeing the training inside fire water monitor is that accuracy rate is high
Model.
Wherein, renewal time can be for for 24 hours.
More preferably, in one exemplary embodiment, the method also includes initialization steps:
After powering on, timing generates icmp request command and superior terminal is sent;
After receiving icmp response command, stop generating icmp request command;
Convolutional neural networks model after receiving the training that higher level's terminal is sent for the first time.
Due to the application use convolutional neural networks model, in order to realize fire water monitor connection network initialization and
The acquisition of convolutional neural networks model, after fire water monitor powers on, timing generates icmp request command and superior terminal is sent:
(1) if network is not connected, icmp request command can be generated at regular intervals and superior terminal is sent;(2) if net
Network is feasible, and higher level's terminal can receive icmp request command and generate icmp the corresponding command to fire water monitor, and fire water monitor receives
Stop generating icmp request command after arriving, and is connected to higher level's terminal.
Due to including the mailing address of fire water monitor itself in icmp request command, higher level's terminal is according to the communication at this time
Convolutional neural networks model after training is sent to corresponding fire water monitor by address.
That is, the step utilizes the network test function of ping order, not only realizes fire water monitor and higher level is whole
The network connection at end detects, and also sends address to higher level terminal to realize higher level's terminal by the convolutional neural networks after training
Model is sent to the function of corresponding fire water monitor.
Another exemplary embodiment of the invention provides a kind of storage medium, is stored thereon with computer instruction, the meter
The step of fire water monitor based on artificial intelligence orients early warning and extinguishing method is executed when the instruction operation of calculation machine.Wherein,
With the method related content herein without repeating.
Another exemplary embodiment of the invention provides a kind of fire water monitor, including memory and processor, described
The computer instruction that can be run on the processor is stored on memory, when the processor runs the computer instruction
Execute the step of fire water monitor based on artificial intelligence orients early warning and extinguishing method.Wherein, related to the method
Content is herein without repeating.
More preferably, Fig. 2 is the connection block diagram of the fire water monitor of one exemplary embodiment of the application, further include:
Shell, the memory and processor are located at the enclosure interior;
Fixed bracket, one end connect the shell, and the other end is installed on outside;
Inductor is connected to the processor, and is set to the housing bottom, for incuding surrounding flame;
Camera is connected to the processor, and the housing sidewall is set to, for obtaining image data;
Water inlet pipe passes through the shell and is arranged;
Outlet pipe passes through the shell and is arranged, connect with the water inlet pipe;
First motor is connect with the shell and processor respectively, for receiving the first level angle of processor transmission
It controls the shell after rotation control signal and the second level angle rotation control signal to be rotated, to realize control camera shooting
Head and outlet pipe rotate horizontally;
Second motor is connect with the outlet pipe and processor respectively, for receiving the vertical angles rotation of processor transmission
It controls the outlet pipe after turning control signal and rotates vertically;
Control device is connect with processor, is set to inside outlet pipe or water inlet pipe, for receiving the life of processor transmission
At unlatching outlet pipe or water inlet pipe after water spray open signal;
Communication module is connect with processor, is sent data for superior terminal or is received the number that higher level's terminal is sent
According to, and send pre-warning signal.
Wherein, communication module can be wireless communication module or wire communication module, be configured according to the actual situation,
Such as wire communication module can be used the case where office building etc. facilitates wiring, and be inconvenient to be routed in construction operation environment etc.
The case where can use wireless communication module.
More preferably, in one exemplary embodiment, the fire water monitor further include:
Device for detecting water pressure is connect with processor, is set to inside outlet pipe or water inlet pipe, for detecting real-time hydraulic pressure simultaneously
It is sent to processor.
The device for detecting water pressure is for detecting real-time hydraulic pressure.
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments, right
For those of ordinary skill in the art, can also make on the basis of the above description other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And thus amplify out it is obvious variation or
It changes still within the protection scope of the invention.
Claims (10)
1. fire water monitor orientation early warning and extinguishing method, the processor based on fire water monitor, feature based on artificial intelligence exist
In: it the described method comprises the following steps:
Obtain sensor data, when sense flame then generate first level angle rotation control signal and be sent to first electricity
Machine;
It controls camera to open, obtain at camera through the image data of the corresponding position after first motor rotation control;
By the convolutional neural networks model after the input training of described image data, the flame grade in described image data is exported;
Judge flame grade: when flame grade is cigarette or small fire, generating pre-warning signal and be sent to communication module;When flame etc.
When grade is moderate heat or more, generates the second level angle rotation control signal and be sent to first motor and generate vertical angles rotation
Turn the second motor that control signal is sent to control outlet pipe rotation angle, generates water spray open signal later to corresponding control dress
It sets.
2. the fire water monitor orientation early warning and extinguishing method according to claim 1 based on artificial intelligence, it is characterised in that:
The method further include:
Judge that flame changes: when the pace of change of flame is more than threshold value, generating the second level angle rotation control signal and send
The second motor of control outlet pipe rotation angle is sent to first motor and generation vertical angles rotation control signal, later
Water spray open signal is generated to corresponding control device.
3. the fire water monitor orientation early warning and extinguishing method according to claim 1 based on artificial intelligence, it is characterised in that:
Convolutional neural networks model after the training after the training of higher level's terminal by communication module by being sent.
4. the fire water monitor orientation early warning and extinguishing method according to claim 3 based on artificial intelligence, it is characterised in that:
The training includes:
Training sample is input to convolutional neural networks model to be trained, the convolutional neural networks model after being trained;And
The convolutional neural networks model after training is tested using the test sample, after the training is obtained after the completion of test
Convolutional neural networks model;
The convolutional neural networks include: input layer, the first convolutional layer, the first pond layer, the second convolutional layer, the second pond layer,
Full articulamentum and output layer.
5. the fire water monitor orientation early warning and extinguishing method according to claim 4 based on artificial intelligence, it is characterised in that:
The method also includes:
Described image data are uploaded to higher level's terminal by timing, for the training sample and test sample to be added;
The renewal time of convolutional neural networks model after the current training of judgement, prompt information is generated if overruning and is sent
To higher level's terminal;
Convolutional neural networks model after obtaining the training updated.
6. the fire water monitor orientation early warning and extinguishing method according to claim 1 based on artificial intelligence, it is characterised in that:
The method also includes initialization steps:
After powering on, timing generates icmp request command and superior terminal is sent;
After receiving icmp response command, stop generating icmp request command;
Convolutional neural networks model after receiving the training that higher level's terminal is sent for the first time.
7. a kind of storage medium, is stored thereon with computer instruction, it is characterised in that: the right of execution when computer instruction is run
Benefit require any one of 1~6 described in fire water monitor orientation early warning based on artificial intelligence and the step of extinguishing method.
8. a kind of fire water monitor, including memory and processor, it is stored with and can runs on the processor on the memory
Computer instruction, which is characterized in that perform claim requires any in 1~6 when the processor runs the computer instruction
The step of fire water monitor based on artificial intelligence described in orients early warning and extinguishing method.
9. fire water monitor according to claim 8, it is characterised in that: the fire water monitor further include:
Shell, the memory and processor are located at the enclosure interior;
Fixed bracket, one end connect the shell, and the other end is installed on outside;
Inductor is connected to the processor, and is set to the housing bottom, for incuding surrounding flame;
Camera is connected to the processor, and the housing sidewall is set to, for obtaining image data;
Water inlet pipe passes through the shell and is arranged;
Outlet pipe passes through the shell and is arranged, connect with the water inlet pipe;
First motor is connect with the shell and processor respectively, for receiving the first level angle rotation of processor transmission
Control the shell after control signal and the second level angle rotation control signal and rotated, thus realize control camera and
Outlet pipe rotates horizontally;
Second motor is connect with the outlet pipe and processor respectively, for receiving the vertical angles rotation control of processor transmission
The outlet pipe is controlled after signal processed to rotate vertically;
Control device is connect with processor, is set to inside outlet pipe or water inlet pipe, for receiving the generation spray of processor transmission
Outlet pipe or water inlet pipe are opened after water open signal;
Communication module is connect with processor, is sent data for superior terminal or is received the data that higher level's terminal is sent, with
And send pre-warning signal.
10. fire water monitor according to claim 9, it is characterised in that: the fire water monitor further include:
Device for detecting water pressure is connect with processor, is set to inside outlet pipe or water inlet pipe, for detecting real-time hydraulic pressure and sending
To processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910401519.3A CN110115819A (en) | 2019-05-14 | 2019-05-14 | Fire water monitor orientation early warning and extinguishing method, storage medium and fire water monitor based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910401519.3A CN110115819A (en) | 2019-05-14 | 2019-05-14 | Fire water monitor orientation early warning and extinguishing method, storage medium and fire water monitor based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110115819A true CN110115819A (en) | 2019-08-13 |
Family
ID=67522403
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910401519.3A Pending CN110115819A (en) | 2019-05-14 | 2019-05-14 | Fire water monitor orientation early warning and extinguishing method, storage medium and fire water monitor based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110115819A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111686392A (en) * | 2020-06-23 | 2020-09-22 | 海南科技职业大学 | Artificial intelligence fire extinguishing system is surveyed to full scene of vision condition |
CN112947147A (en) * | 2021-01-27 | 2021-06-11 | 上海大学 | Fire-fighting robot based on multi-sensor and cloud platform algorithm |
CN114558267A (en) * | 2022-03-03 | 2022-05-31 | 上海应用技术大学 | Industrial scene fire prevention and control system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103337123A (en) * | 2013-06-17 | 2013-10-02 | 西安石油大学 | System and method for oil field united station fire disaster pre-warning system based on video images |
CN104299351A (en) * | 2014-10-22 | 2015-01-21 | 常州大学 | Intelligent early warning and fire extinguishing robot |
CN105879284A (en) * | 2016-06-06 | 2016-08-24 | 合肥市嘉升电子科技有限公司 | Fire water monitor control system comprising multiple sensors and control method |
CN106530569A (en) * | 2016-10-17 | 2017-03-22 | 北京小米移动软件有限公司 | Method and device for fire monitoring |
JP2018101416A (en) * | 2016-12-21 | 2018-06-28 | ホーチキ株式会社 | Fire monitoring system |
CN109376747A (en) * | 2018-12-11 | 2019-02-22 | 北京工业大学 | A kind of video flame detecting method based on double-current convolutional neural networks |
-
2019
- 2019-05-14 CN CN201910401519.3A patent/CN110115819A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103337123A (en) * | 2013-06-17 | 2013-10-02 | 西安石油大学 | System and method for oil field united station fire disaster pre-warning system based on video images |
CN104299351A (en) * | 2014-10-22 | 2015-01-21 | 常州大学 | Intelligent early warning and fire extinguishing robot |
CN105879284A (en) * | 2016-06-06 | 2016-08-24 | 合肥市嘉升电子科技有限公司 | Fire water monitor control system comprising multiple sensors and control method |
CN106530569A (en) * | 2016-10-17 | 2017-03-22 | 北京小米移动软件有限公司 | Method and device for fire monitoring |
JP2018101416A (en) * | 2016-12-21 | 2018-06-28 | ホーチキ株式会社 | Fire monitoring system |
CN109376747A (en) * | 2018-12-11 | 2019-02-22 | 北京工业大学 | A kind of video flame detecting method based on double-current convolutional neural networks |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111686392A (en) * | 2020-06-23 | 2020-09-22 | 海南科技职业大学 | Artificial intelligence fire extinguishing system is surveyed to full scene of vision condition |
CN112947147A (en) * | 2021-01-27 | 2021-06-11 | 上海大学 | Fire-fighting robot based on multi-sensor and cloud platform algorithm |
CN114558267A (en) * | 2022-03-03 | 2022-05-31 | 上海应用技术大学 | Industrial scene fire prevention and control system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110115819A (en) | Fire water monitor orientation early warning and extinguishing method, storage medium and fire water monitor based on artificial intelligence | |
US20220128428A1 (en) | Consumable gas leak detection | |
CN110102002A (en) | The early warning of fire-fighting robot based on artificial intelligence and fire extinguishing system and method | |
CN215427107U (en) | Building fire control coordinated control device | |
CN206892701U (en) | A kind of cable tunnel monitoring system | |
CN110197567A (en) | A kind of inspection well cover monitoring system | |
US20230211194A1 (en) | Community outdoor fire defense | |
CN109324582A (en) | Intelligent sound Classroom System | |
CN206837312U (en) | A kind of artificial intelligence type end water testing device and system | |
CN213876977U (en) | Internet-of-things city intelligent building security monitoring system | |
CN208975053U (en) | A kind of fire-fighting fire extinguishing dual system | |
CN210612762U (en) | Intelligent fire extinguisher, intelligent fire extinguishing vehicle and remote fire extinguishing system | |
CN208985001U (en) | Urban Underground pipe gallery ACU control cabinet control system | |
CN214485411U (en) | Household indoor fire-fighting system | |
ES2822475T3 (en) | Water or other fluid management system and procedure | |
CN104208839B (en) | A kind of fire-blocking belt forming apparatus | |
CN210302138U (en) | High-rise fire extinguishing self-rescue system | |
CN111420334B (en) | Internet-based household intelligent mobile fire-fighting measurement and control system and use method | |
CN113577622B (en) | Spraying fire extinguishing system and method based on multi-fire probe linkage detection | |
CN202942579U (en) | Testing apparatus for evaluating total-flooding fire extinguishing performance | |
CN209859005U (en) | Intelligent acquisition unit for secondary water supply pump room | |
CN210992756U (en) | Intelligent automatic fire catching device | |
CN202236993U (en) | Intelligent automatic scanning and positioning fire-extinguishing apparatus | |
CN208911332U (en) | Diesel engine scavenging air box extinguishing device and system | |
CN107045320A (en) | A kind of water system massaging device of fire-fighting Internet of Things |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190813 |
|
RJ01 | Rejection of invention patent application after publication |