CN109686036A - A kind of fire monitoring method, device and edge calculations device - Google Patents
A kind of fire monitoring method, device and edge calculations device Download PDFInfo
- Publication number
- CN109686036A CN109686036A CN201910019256.XA CN201910019256A CN109686036A CN 109686036 A CN109686036 A CN 109686036A CN 201910019256 A CN201910019256 A CN 201910019256A CN 109686036 A CN109686036 A CN 109686036A
- Authority
- CN
- China
- Prior art keywords
- environmental monitoring
- monitoring data
- fire
- data
- machine learning
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
Abstract
The present invention is suitable for fire hazard monitoring technical field, provide a kind of fire monitoring method, device and edge calculations device, wherein, method includes: to obtain environmental monitoring data more than two, the environmental monitoring data is pre-processed according to the time series of the environmental monitoring data, obtain pretreated environmental monitoring data, the pretreated environmental monitoring data is inputted into pre-training machine learning model, the result of decision for obtaining the pre-training machine learning model output sends corresponding information warning to user terminal according to the result of decision.The present invention, which carries out data fusion to environmental monitoring data using edge calculations device operation machine learning model, realizes real-time, objective, safe and reliable Fire danger assessment to calculate the degree of danger of fire.Corresponding information warning is sent according to the state of fire simultaneously and improves the efficiency of fire fighting and rescue action to provide true and reliable decision-making foundation for fire fighting and rescue personnel.
Description
Technical field
The invention belongs to fire hazard monitoring technical field more particularly to a kind of fire monitoring methods, device and edge calculations dress
It sets.
Background technique
Existing fire monitoring system can only often provide simple alarm signal, for example, the most common fire-alarm no matter
How is the degree of danger of fire, can only issue the same alarm bell sound, therefore the cammander of fire fighting and rescue action is difficult to understand fire
The real hazard degree of calamity, the arrangement that evacuation personnel and fire extinguishing are made according to these simple information warnings of having no idea influence
The efficiency of action of fighting calamities and providing relief.Also, if necessary to assessment fire hazard degree, related personnel is generally required in scene of fire
Fire behavior is judged, judging result subjectivity is stronger, and may threaten safely to human life.
On the other hand, some intelligent fire alarm systems tend to rely on Internet of Things and cloud computing technology, and sensor is adopted
The environmental monitoring data of collection is uploaded to cloud and is handled, and processing result is then transmitted to use by internet and mobile network
Family terminal can have the case where larger delay, cloud processing may also can encounter network congestion, be lined up in data transmission procedure,
It is difficult to meet fast changing fire fighting and rescue scene to the requirement of real-time of data processing and transmission.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of fire monitoring method, device and edge calculations device, to solve
Alarm signal is too simple in the prior art, real-time is poor, is difficult to the problem of providing objective fire hazard rating.
The first aspect of the embodiment of the present invention provides a kind of fire monitoring method, comprising:
Obtain environmental monitoring data more than two；
The environmental monitoring data is pre-processed according to the time series of the environmental monitoring data, obtains pretreatment
Environmental monitoring data afterwards；
The pretreated environmental monitoring data is inputted into pre-training machine learning model, obtains the pre-training machine
The result of decision of learning model output；
Corresponding information warning is sent to user terminal according to the result of decision.
Optionally, the pretreated environmental monitoring data is inputted into pre-training machine learning model, obtained described pre-
Before the result of decision of training machine learning model output, comprising:
The environmental monitoring data for obtaining history event of fire is established according to the environmental monitoring data of the history event of fire
Sample data；
Label is added for the sample data and as training sample；
According to the training sample training machine learning model, the pre-training machine learning model is obtained.
Optionally, label is added as training sample for the sample data, comprising:
It is that the sample data adds label to obtain training sample using Field Using Fuzzy Comprehensive Assessment.
Optionally, before according to the corresponding information warning to user terminal of result of decision transmission, comprising:
Establish the corresponding relationship between the result of decision and the information warning.
Optionally, the environmental monitoring data is pre-processed according to the time series of the environmental monitoring data, is obtained
Take pretreated environmental monitoring data, comprising:
The error information in the environmental monitoring data is deleted, updated environmental monitoring data is obtained；Wherein, the mistake
Difference data includes the environmental monitoring data more than the first preset data threshold value and/or the environment prison lower than the second preset data threshold value
Measured data；
Updated environmental monitoring data is obtained according to the rate of change of time series variation, is obtained described pretreated
Environmental monitoring data.
Optionally, the machine learning model includes decision-tree model and/or BP neural network model.
The second aspect of the embodiment of the present invention provides a kind of fire-disaster monitoring device, comprising:
First obtains module, for obtaining environmental monitoring data more than two；
Preprocessing module carries out the environmental monitoring data for the time series according to the environmental monitoring data pre-
Processing, obtains pretreated environmental monitoring data；
Input module is obtained for the pretreated environmental monitoring data to be inputted pre-training machine learning model
The result of decision of the pre-training machine learning model output；
Sending module, for sending corresponding information warning to user terminal according to the result of decision.
The third aspect of the embodiment of the present invention provides a kind of edge calculations device, comprising: memory, processor and deposits
The computer program that can be run in the memory and on the processor is stored up, the processor executes the computer journey
It realizes when sequence such as the step of the above method.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, realizes when the computer program is executed by processor such as the step of the above method.
On the one hand, the embodiment of the present invention carries out environmental monitoring data using edge calculations device operation machine learning model
Data fusion realizes real-time, objective, safe and reliable Fire danger assessment to calculate the degree of danger of fire.It is another
Aspect, the embodiment of the present invention sends corresponding information warning according to the state of fire, to provide really for fire fighting and rescue personnel
Reliable decision-making foundation improves the efficiency of fire fighting and rescue action.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the flow diagram for the fire monitoring method that the embodiment of the present invention one provides；
Fig. 2 is the flow diagram of fire monitoring method provided by Embodiment 2 of the present invention；
Fig. 3 is the flow diagram for the fire monitoring method that the embodiment of the present invention three provides；
Fig. 4 is the flow diagram for the fire monitoring method that the embodiment of the present invention four provides；
Fig. 5 is the structural schematic diagram for the fire-disaster monitoring device that the embodiment of the present invention five provides；
Fig. 6 is the schematic diagram for the edge calculations device that the embodiment of the present invention six provides.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical solution in the embodiment of the present invention are explicitly described, it is clear that described embodiment is the present invention one
The embodiment divided, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, should fall within the scope of the present invention.
Description and claims of this specification and term " includes " and their any deformations in above-mentioned attached drawing, meaning
Figure, which is to cover, non-exclusive includes.Such as process, method or system comprising a series of steps or units, product or equipment do not have
It is defined in listed step or unit, but optionally further comprising the step of not listing or unit, or optionally also wrap
Include the other step or units intrinsic for these process, methods, product or equipment.In addition, term " first ", " second " and
" third " etc. is for distinguishing different objects, not for description particular order.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Embodiment one
As shown in Figure 1, this method can be applied to such as mobile phone, PC, plate the present embodiment provides a kind of fire monitoring method
The terminal devices such as computer, or the edge calculations device exclusively for fire hazard monitoring design.Fire hazard monitoring side provided by the present embodiment
Method, comprising:
S101, environmental monitoring data more than two is obtained；
In a particular application, two groups or more environmental monitoring data is obtained；Wherein, environmental monitoring data refers to logical
Cross the environmental parameter of sensor acquisition；Sensor includes but is not limited to temperature sensor, smoke sensor device, oxygen concentration detection biography
Sensor, carbon monoxide transducer；Every group of environmental monitoring data includes but is not limited to temperature, oxygen concentration, carbonomonoxide concentration, cigarette
Mistiness degree.It should be noted that (i.e. root can be ranked up to environmental monitoring data according to the time for getting environmental monitoring data
Environmental monitoring data is arranged according to time series), likewise, can be that environmental monitoring data adds the time according to time series
Label.
In one embodiment, this method can be executed by edge calculations device, and edge calculations device includes pretreatment mould
Block, decision-making module, alarm module, communication module.
In one embodiment, step S101 can be executed by communication module, communication module and sensor, user terminal
(or cloud) communication connection.
S102, the environmental monitoring data is pre-processed according to the time series of the environmental monitoring data, is obtained
Pretreated environmental monitoring data.
In a particular application, environmental monitoring data is pre-processed according to the time series for obtaining environmental monitoring data,
Obtain pretreated environmental monitoring data；Wherein, pretreatment includes the error information deleted in environmental monitoring data, to environment
Monitoring data carry out the processing methods such as sliding-model control.Each environment can also be calculated according to the time series of environmental monitoring data to join
Several rate of changes, such as temperature rate-of-rise, temperature fall off rate, smokescope climbing speed, smokescope fall off rate
Deng.When using BP neural network model as machine learning model, pretreatment further includes that data are normalized.
In one embodiment, step S102 can be executed by preprocessing module,
S103, the pretreated environmental monitoring data is inputted into pre-training machine learning model, obtains the pre- instruction
Practice the result of decision of machine learning model output.
In a particular application, pretreated environmental monitoring data is inputted to the pre-training engineering obtained by pre-training
Model is practised, to obtain the result of decision of pre-training machine learning model output.Wherein, the result of decision can be according to the stage to fire
Judged to obtain intensity of a fire state, and obtains the corresponding degree of danger of fire stage；The result of decision includes but is not limited to fire
Initial stage-primary degree of danger, the intensity of a fire expand under stage-intermediate degree of danger, the intensity of a fire violent stage-advanced degree of danger, the intensity of a fire
Depression of order section-middle rank degree of danger, fire extinguish the stage-and hide degree of danger.In one embodiment, step S103 can be by certainly
Plan module executes.
S104, corresponding information warning is sent to user terminal according to the result of decision.
In a particular application, corresponding information warning is sent to user terminal according to the result of decision, with remind user according to
Information warning executes corresponding fire countermeasure.In the present embodiment, corresponding warning message can be sent according to the result of decision
To fire-fighting center or the terminal device of monitoring personnel, to notify that fire fighter or monitoring personnel are corresponding according to warning message progress
The operation such as fire extinguishing, evacuating personnel.In one embodiment, alarm module can generate corresponding information warning according to the result of decision,
Information warning is sent to the user terminal (or cloud) by communication module.
The present embodiment carries out data fusion to environmental monitoring data using machine learning model, to calculate the dangerous journey of fire
Degree, realizes real-time, objective, safe and reliable Fire danger assessment；Meanwhile corresponding police is sent according to the state of fire
Show information, to provide true and reliable decision-making foundation for fire fighting and rescue personnel, improves the efficiency of fire fighting and rescue action.
Embodiment two
As shown in Fig. 2, the present embodiment is the further explanation to the method and step in embodiment one.In the present embodiment,
Before step S103, further includes:
S201, the environmental monitoring data for obtaining history event of fire, according to the environmental monitoring number of the history event of fire
According to establishing sample data.
In a particular application, the history event of fire really occurred can be obtained from the database of Fire-fighting Information System
In the environmental monitoring data that is measured by environmental sensor (such as temperature sensor, smoke sensor device, carbon monoxide transducer etc.),
And the time series of environmental monitoring data, and according to the time series of environmental monitoring data calculate each environmental parameter (such as temperature,
Smokescope etc.) rate of change (climbing speed and fall off rate), can also be to environmental monitoring data and rate of change data
It is normalized, to establish sample data.The experiment of standard fire can also be carried out in monitored place, pass through experimental field
Environmental sensor obtains the environmental monitoring data of predetermined number, establishes sample number according to the environmental monitoring data that standard fire is tested
According to.
S202, label is added for the sample data and as training sample.
In a particular application, label is added (i.e. according to the development process of history event of fire to sample number for sample data
According to the label of addition fire stage), and the sample data after label will be added as training sample, with to machine learning model into
Row pre-training.For example, adding if certain group sample data is that the intensity of a fire of certain history event of fire expands the environmental monitoring data in stage
The widened label of flame enrichment gesture is to sample data, to generate corresponding training sample.It can manually be supervised according to the environment of environmental parameter
Measured data and rate of change to specify label for corresponding sample data.In some embodiments, it can use fuzzy synthesis to comment
Valence method is that the sample data adds label to obtain training sample.It specifically, can be by environmental parameter and environmental parameter
Rate of change establishes Comment gathers (such as { low degree of danger, moderate risk as evaluation index, according to fire hazard grading
Degree, high-risk degree ... }), the weight vectors of evaluation index are constructed by method of expertise or analytic hierarchy process (AHP).Then structure
Build the subordinating degree function that each evaluation index grades for each fire hazard degree.Fire hazard degree label is added for one group of sample
When, fuzzy overall evaluation matrix is obtained according to the numerical value of the subordinating degree function of each index and evaluation index.It chooses suitable fuzzy
Operator carries out fuzzy matrix composition to weight vectors and evaluations matrix.Then sentenced according to composite result using maximum membership grade principle
Break corresponding fire hazard grading.Then using the fire hazard grading as the label of sample.Successively to sample number
All samples in add label, to obtain the training sample for being used for training machine learning model.Utilize fuzzy overall evaluation
Method is that the sample data adds label acquisition training sample, and machine learning model can be made to learn expertise, improve fire behavior
The precision of assessment.
S203, according to the training sample training machine learning model, obtain the pre-training machine learning model.
In a particular application, according to sample data training machine learning model, pre-training machine learning model is obtained.With reality
When sample data now being inputted pre-training machine learning model, pre-training machine learning model is exportable corresponding with sample data
The result of decision (i.e. fire stage and corresponding degree of danger).
In one embodiment, machine learning model includes but is not limited to decision-tree model and/or BP neural network model.
In one embodiment, the step S202, comprising:
Corresponding label is added according to the developing stage of fire in the sample data, to obtain training sample；Wherein, institute
The developing stage for stating fire includes Initial Stage of Fire, intensity of a fire expansion stage, the intensity of a fire violent stage, intensity of a fire decline stage, fire extinguishing
Stage.
In one embodiment, the step S202, further includes:
It is that the sample data adds label to obtain training sample using Field Using Fuzzy Comprehensive Assessment.
It in a particular application, is that the sample data adds label acquisition training sample using Field Using Fuzzy Comprehensive Assessment, it can
So that machine learning model learns expertise, the precision of fire behavior assessment is improved.
The present embodiment by handling sample data, and according to treated sample data to machine learning model into
Row pre-training improves the precision of model, lays a good foundation to provide accurately information warning.
Embodiment three
As shown in figure 3, the present embodiment is the further explanation to the method and step in embodiment one.In the present embodiment,
Before step S104, further includes:
S301, corresponding relationship between the result of decision and the information warning is established.
In a particular application, the corresponding relationship between the result of decision and the information warning is established.For example, if the result of decision
For the intensity of a fire violent stage-advanced degree of danger, then corresponding information warning is that the intensity of a fire is violent instantly, and it is existing please to withdraw fire immediately
?.
The present embodiment is getting the result of decision by establishing the corresponding relationship between the result of decision and information warning, realization
When can issue corresponding information warning, to remind user to execute corresponding with information warning reply means, ensure that the peace of user
Entirely.
Example IV
As shown in figure 4, the present embodiment is the further explanation to the method and step in embodiment one.In the present embodiment,
Step S102, comprising:
Error information in S1021, the deletion environmental monitoring data, obtains updated environmental monitoring data；Wherein,
The error information includes more than the environmental monitoring data of the first preset data threshold value and/or lower than the second preset data threshold value
Environmental monitoring data.
In a particular application, the error information in environmental monitoring data is deleted, updated environmental monitoring data is obtained；Its
In, error information includes more than the environmental monitoring data of the first preset data threshold value and/or lower than the second preset data threshold value
Environmental monitoring data.Wherein, the first preset data threshold value and the second preset data threshold value can specifically be set according to the actual situation
It is fixed.For example, the second preset data threshold value of temperature is set as -40 DEG C, the temperature number for being lower than the second preset data threshold value is deleted
Value.(a possibility that occurring lower than fire at a temperature of this second preset data threshold value is very small or judges temperature sensor
It is likely to occur failure, leads to the temperature data for getting mistake).
S1022, updated environmental monitoring data is obtained according to the rate of change of time series variation, obtain the pre- place
Environmental monitoring data after reason.
In a particular application, updated environmental monitoring data is obtained according to the changed rate of change of time series,
(environmental monitoring data that can be updated according to the rate of change discretization of updated environmental monitoring data), obtains pretreated
Environmental monitoring data.For example, obtaining the temperature that the temperature data obtained at the first time is got to the second time according to time series
The change rate of degree evidence, the change rate for the temperature data that the temperature data that the second time of acquisition obtains to third time is got.
Wherein, change rate can be the ratio of the temperature data for the temperature data and the acquisition of previous time that latter time obtains.10:00 is obtained
The temperature got is 23 DEG C, and the temperature that 10:30 is got is 25 DEG C, and the temperature that 11:00 is got is 30 DEG C, then 10:00-10:
The rate of temperature change that 30 rate of temperature change is 25/23,10:30-11:00 is 30/25.
In one embodiment, step S103, comprising:
S1031, the pretreated environmental monitoring data is inputted into pre-training machine learning model.
In a particular application, pretreated environmental monitoring data is inputted into pre-training machine learning model, so that pre- instruction
Practice machine learning model to handle pretreated environmental monitoring data, obtains the corresponding result of decision.
S1032, data are carried out to the pretreated environmental monitoring data by the pre-training machine learning model
Fusion, exports the result of decision.
In a particular application, data are carried out to pretreated environmental monitoring data by pre-training machine learning model to melt
It closes, exports the result of decision.
The present embodiment, to obtain effective, accurate environmental monitoring data, is mentioned by pre-processing to environmental monitoring data
The high accuracy of the result of decision simultaneously further improves the efficiency that fire is prevented and treated.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment five
As shown in figure 5, the present embodiment provides a kind of fire-disaster monitoring device 100, for executing the step of the method in embodiment one
Suddenly.Fire-disaster monitoring device 100 provided in this embodiment, comprising:
First obtains module 101, for obtaining environmental monitoring data more than two；
Preprocessing module 102, for according to the time series of the environmental monitoring data to the environmental monitoring data into
Row pretreatment, obtains pretreated environmental monitoring data；
Input module 103 is obtained for the pretreated environmental monitoring data to be inputted pre-training machine learning model
Obtain the result of decision of the pre-training machine learning model output；
Sending module 104, for sending corresponding information warning to user terminal according to the result of decision.
In one embodiment, described device 100, further includes:
Second obtains module 201, for obtaining the environmental monitoring data of history event of fire, according to the history fire thing
The environmental monitoring data of part establishes sample data；
Label model 202, for adding label for the sample data and as training sample；
Third obtains module 203, for obtaining the pre-training machine according to the training sample training machine learning model
Device learning model.
In one embodiment, the label model 202, comprising:
Tag unit, for being that the sample data adds label to obtain training sample using Field Using Fuzzy Comprehensive Assessment.
In one embodiment, described device 100, further includes:
Module is established, the corresponding relationship for establishing between the result of decision and the information warning.
In one embodiment, preprocessing module 102, comprising:
It deletes unit and obtains updated environmental monitoring number for deleting the error information in the environmental monitoring data
According to；Wherein, the error information includes more than the environmental monitoring data of the first preset data threshold value and/or lower than the second present count
According to the environmental monitoring data of threshold value；
Discretization unit is obtained for obtaining updated environmental monitoring data according to the rate of change of time series variation
Take the pretreated environmental monitoring data.
In one embodiment, the machine learning model includes decision-tree model and/or BP neural network model.
The present embodiment carries out data fusion to environmental monitoring data using machine learning model, to calculate the dangerous journey of fire
Degree, realizes real-time, objective, safe and reliable Fire danger assessment；Meanwhile corresponding police is sent according to the state of fire
Show information, to provide true and reliable decision-making foundation for fire fighting and rescue personnel, improves the efficiency of fire fighting and rescue action.
Embodiment six
Fig. 6 is the schematic diagram of edge calculations device provided in this embodiment.As shown in fig. 6, the edge calculations of the embodiment
Device 6 includes: processor 60, memory 61 and is stored in the memory 61 and can run on the processor 60
Computer program 62, such as fire hazard monitoring program.The processor 60 is realized above-mentioned each when executing the computer program 62
Step in fire monitoring method embodiment, such as step S101 to S104 shown in FIG. 1.Alternatively, the processor 60 executes
The function of each module/unit in above-mentioned each Installation practice, such as module 101 shown in Fig. 5 are realized when the computer program 62
To 104 function.
Illustratively, the computer program 62 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 61, and are executed by the processor 60, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 62 in the edge calculations device 6 is described.For example, the computer program 62 can be with
It is divided into the first acquisition module, preprocessing module, input module and sending module, each module concrete function is as follows:
First obtains module, for obtaining environmental monitoring data more than two；
Preprocessing module carries out the environmental monitoring data for the time series according to the environmental monitoring data pre-
Processing, obtains pretreated environmental monitoring data；
Input module is obtained for the pretreated environmental monitoring data to be inputted pre-training machine learning model
The result of decision of the pre-training machine learning model output；
Sending module, for sending corresponding information warning to user terminal according to the result of decision.
The edge calculations device 6 can be the calculating such as desktop PC, notebook, palm PC and Edge Server
Equipment.The edge calculations device may include, but be not limited only to, processor 60, memory 61.Those skilled in the art can manage
Solution, Fig. 6 is only the example of edge calculations device 6, does not constitute the restriction to edge computing device 6, may include than diagram
More or fewer components perhaps combine certain components or different components, such as the edge calculations device can also wrap
Include input-output equipment, network access equipment, bus etc..
Alleged processor 60 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 61 can be the internal storage unit of the edge calculations device 6, such as edge calculations device 6
Hard disk or memory.The memory 61 is also possible to the External memory equipment of the edge calculations device 6, such as the edge meter
Calculate the plug-in type hard disk being equipped on device 6, intelligent memory card (Smart Media Card, SMC), safe digital card (Secure
Digital, SD), flash card (Flash Card) etc..Further, the memory 61 can also both include the edge meter
The internal storage unit for calculating device 6 also includes External memory equipment.The memory 61 for store the computer program with
And other programs and data needed for the edge calculations device.The memory 61 can be also used for temporarily storing defeated
Out or the data that will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/edge calculations device and method,
It may be implemented in other ways.For example, device described above/edge calculations Installation practice is only schematic
, for example, the division of the module or unit, only a kind of logical function partition, can there is other draw in actual implementation
The mode of dividing, such as multiple units or components can be combined or can be integrated into another system, or some features can be ignored,
Or it does not execute.Another point, shown or discussed mutual coupling or direct-coupling or communication connection can be by one
The INDIRECT COUPLING or communication connection of a little interfaces, device or unit can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of fire monitoring method characterized by comprising
Obtain environmental monitoring data more than two；
The environmental monitoring data is pre-processed according to the time series of the environmental monitoring data, is obtained pretreated
Environmental monitoring data；
The pretreated environmental monitoring data is inputted into pre-training machine learning model, obtains the pre-training machine learning
The result of decision of model output；
Corresponding information warning is sent to user terminal according to the result of decision.
2. fire monitoring method as described in claim 1, which is characterized in that the pretreated environmental monitoring data is defeated
Enter pre-training machine learning model, before the result of decision for obtaining the pre-training machine learning model output, further includes:
The environmental monitoring data for obtaining history event of fire, establishes sample according to the environmental monitoring data of the history event of fire
Data；
Label is added for the sample data and as training sample；
According to the training sample training machine learning model, the pre-training machine learning model is obtained.
3. fire monitoring method as claimed in claim 2, which is characterized in that add label as training for the sample data
Sample, comprising:
It is that the sample data adds label to obtain training sample using Field Using Fuzzy Comprehensive Assessment.
4. fire monitoring method as described in claim 1, which is characterized in that send corresponding warning according to the result of decision
Before information to user terminal, further includes:
Establish the corresponding relationship between the result of decision and the information warning.
5. fire monitoring method as described in claim 1, which is characterized in that according to the time series of the environmental monitoring data
The environmental monitoring data is pre-processed, pretreated environmental monitoring data is obtained, comprising:
The error information in the environmental monitoring data is deleted, updated environmental monitoring data is obtained；Wherein, the margin of error
According to including the environmental monitoring data more than the first preset data threshold value and/or the environmental monitoring number lower than the second preset data threshold value
According to；
Updated environmental monitoring data is obtained according to the rate of change of time series variation, obtains the pretreated environment
Monitoring data.
6. fire monitoring method as described in claim 1, which is characterized in that the machine learning model includes decision-tree model
And/or BP neural network model.
7. a kind of fire-disaster monitoring device characterized by comprising
First obtains module, for obtaining environmental monitoring data more than two；
Preprocessing module, for being located in advance according to the time series of the environmental monitoring data to the environmental monitoring data
Reason, obtains pretreated environmental monitoring data；
Input module, for will the pretreated environmental monitoring data input pre-training machine learning model, described in acquisition
The result of decision of pre-training machine learning model output；
Sending module, for sending corresponding information warning to user terminal according to the result of decision.
8. fire-disaster monitoring device as claimed in claim 7, which is characterized in that further include:
Second obtains module, for obtaining the environmental monitoring data of history event of fire, according to the ring of the history event of fire
Border monitoring data establish sample data；
Label model, for adding label for the sample data and as training sample；
Third obtains module, for obtaining the pre-training machine learning according to the training sample training machine learning model
Model.
9. a kind of edge calculations device, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, which is characterized in that the processor realizes such as claim 1 when executing the computer program
The step of to any one of 6 the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 6 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910019256.XA CN109686036B (en) | 2019-01-09 | 2019-01-09 | Fire monitoring method and device and edge computing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910019256.XA CN109686036B (en) | 2019-01-09 | 2019-01-09 | Fire monitoring method and device and edge computing device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109686036A true CN109686036A (en) | 2019-04-26 |
| CN109686036B CN109686036B (en) | 2020-12-22 |
Family
ID=66192136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910019256.XA Active CN109686036B (en) | 2019-01-09 | 2019-01-09 | Fire monitoring method and device and edge computing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109686036B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110220554A (en) * | 2019-06-05 | 2019-09-10 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN110278416A (en) * | 2019-07-12 | 2019-09-24 | 山东智洋电气股份有限公司 | Power transmission line intelligent prison based on artificial intelligence claps device |
| CN110322656A (en) * | 2019-06-28 | 2019-10-11 | 三一重机有限公司 | Digger engine cabin fire automatic alarm device and excavator |
| CN110459031A (en) * | 2019-08-06 | 2019-11-15 | 福建工程学院 | A kind of anti-disaster method of fire-fighting, system and storage medium having warning function |
| CN110475223A (en) * | 2019-07-01 | 2019-11-19 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of method for safety monitoring, device and terminal device |
| CN110930626A (en) * | 2019-11-25 | 2020-03-27 | 西安和光明宸科技有限公司 | Fire early warning system |
| CN111031107A (en) * | 2019-11-29 | 2020-04-17 | 武汉智菱物联科技有限公司 | Geological disaster monitoring system and method based on low-power-consumption communication network |
| CN111079855A (en) * | 2019-12-27 | 2020-04-28 | 三一重能有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting console |
| CN111238446A (en) * | 2020-01-15 | 2020-06-05 | 湖北民族大学 | Communication tower inclination monitoring system |
| CN111275270A (en) * | 2020-03-09 | 2020-06-12 | 南京中电科能技术有限公司 | Method for predicting regional electrical fire risk based on edge calculation and neural network |
| CN111753900A (en) * | 2020-06-23 | 2020-10-09 | 中南林业科技大学 | Forest fire monitoring method |
| CN111784994A (en) * | 2020-07-14 | 2020-10-16 | 中国民航大学 | Fire detection method and device |
| CN112016886A (en) * | 2020-08-17 | 2020-12-01 | 北京双洲科技有限公司 | Mobile terminal safety office management and control method, device and system |
| CN112666851A (en) * | 2019-10-15 | 2021-04-16 | 许桂林 | Projector with environment monitoring function and personal health data generation method |
| CN113125675A (en) * | 2021-04-19 | 2021-07-16 | 北京物资学院 | Storage yard coal spontaneous combustion early warning device and early warning method of edge computing framework |
| CN113743015A (en) * | 2021-09-07 | 2021-12-03 | 同济大学 | Fire scene data acquisition method, medium and electronic device |
| CN114627607A (en) * | 2022-01-30 | 2022-06-14 | 江苏蓝图消防装备有限公司 | Fire-fighting comprehensive information retrieval system based on industrial sensor network |
| CN114758470A (en) * | 2022-06-16 | 2022-07-15 | 张家港金典软件有限公司 | Fire early warning method and system based on fire engineering |
| CN114949665A (en) * | 2022-05-20 | 2022-08-30 | 国能包头能源有限责任公司 | Spontaneous combustion prevention processing method and device for coal yard and computer readable storage medium |
| CN115100838A (en) * | 2022-05-31 | 2022-09-23 | 杭州鸿泉物联网技术股份有限公司 | Vehicle fire early warning method, device, equipment, medium and computer program product |
| CN116542442A (en) * | 2023-04-03 | 2023-08-04 | 中国消防救援学院 | Unmanned aerial vehicle-based fire-fighting auxiliary dispatching management method and system |
| CN117592789A (en) * | 2024-01-18 | 2024-02-23 | 山东金桥保安器材有限公司 | Power grid environment fire risk assessment method and equipment based on time sequence analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101581940A (en) * | 2009-06-05 | 2009-11-18 | 西安电子科技大学 | Tunnel event detection method based on integrated learning time sequence prediction |
| CN102013148A (en) * | 2010-10-28 | 2011-04-13 | 中国科学技术大学 | Multi-information fusion fire hazard detection method |
| CN105806400A (en) * | 2016-02-29 | 2016-07-27 | 北斗导航位置服务（北京）有限公司 | Intelligent method and system for monitoring hydrant's safety state |
| CN108230637A (en) * | 2017-12-29 | 2018-06-29 | 深圳市泛海三江科技发展有限公司 | A kind of fire alarm method and system |
| CN108447210A (en) * | 2018-03-22 | 2018-08-24 | 河南科技大学 | A kind of multiple spot push intelligent repository fire alarm system and its alarm method |
| CN108985192A (en) * | 2018-06-29 | 2018-12-11 | 东南大学 | A kind of video smoke recognition methods based on multitask depth convolutional neural networks |
-
2019
- 2019-01-09 CN CN201910019256.XA patent/CN109686036B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101581940A (en) * | 2009-06-05 | 2009-11-18 | 西安电子科技大学 | Tunnel event detection method based on integrated learning time sequence prediction |
| CN102013148A (en) * | 2010-10-28 | 2011-04-13 | 中国科学技术大学 | Multi-information fusion fire hazard detection method |
| CN105806400A (en) * | 2016-02-29 | 2016-07-27 | 北斗导航位置服务（北京）有限公司 | Intelligent method and system for monitoring hydrant's safety state |
| CN108230637A (en) * | 2017-12-29 | 2018-06-29 | 深圳市泛海三江科技发展有限公司 | A kind of fire alarm method and system |
| CN108447210A (en) * | 2018-03-22 | 2018-08-24 | 河南科技大学 | A kind of multiple spot push intelligent repository fire alarm system and its alarm method |
| CN108985192A (en) * | 2018-06-29 | 2018-12-11 | 东南大学 | A kind of video smoke recognition methods based on multitask depth convolutional neural networks |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110220554A (en) * | 2019-06-05 | 2019-09-10 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN110322656A (en) * | 2019-06-28 | 2019-10-11 | 三一重机有限公司 | Digger engine cabin fire automatic alarm device and excavator |
| CN110475223A (en) * | 2019-07-01 | 2019-11-19 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of method for safety monitoring, device and terminal device |
| CN110278416A (en) * | 2019-07-12 | 2019-09-24 | 山东智洋电气股份有限公司 | Power transmission line intelligent prison based on artificial intelligence claps device |
| CN110459031A (en) * | 2019-08-06 | 2019-11-15 | 福建工程学院 | A kind of anti-disaster method of fire-fighting, system and storage medium having warning function |
| CN112666851A (en) * | 2019-10-15 | 2021-04-16 | 许桂林 | Projector with environment monitoring function and personal health data generation method |
| CN110930626A (en) * | 2019-11-25 | 2020-03-27 | 西安和光明宸科技有限公司 | Fire early warning system |
| CN111031107A (en) * | 2019-11-29 | 2020-04-17 | 武汉智菱物联科技有限公司 | Geological disaster monitoring system and method based on low-power-consumption communication network |
| CN111031107B (en) * | 2019-11-29 | 2022-08-05 | 武汉智菱物联科技有限公司 | Geological disaster monitoring system and method based on low-power-consumption communication network |
| CN111079855A (en) * | 2019-12-27 | 2020-04-28 | 三一重能有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting console |
| CN111079855B (en) * | 2019-12-27 | 2023-08-11 | 三一重能股份有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting control console |
| CN111238446A (en) * | 2020-01-15 | 2020-06-05 | 湖北民族大学 | Communication tower inclination monitoring system |
| CN111275270A (en) * | 2020-03-09 | 2020-06-12 | 南京中电科能技术有限公司 | Method for predicting regional electrical fire risk based on edge calculation and neural network |
| CN111753900A (en) * | 2020-06-23 | 2020-10-09 | 中南林业科技大学 | Forest fire monitoring method |
| CN111753900B (en) * | 2020-06-23 | 2023-04-07 | 中南林业科技大学 | Forest fire monitoring method |
| CN111784994A (en) * | 2020-07-14 | 2020-10-16 | 中国民航大学 | Fire detection method and device |
| CN111784994B (en) * | 2020-07-14 | 2021-11-30 | 中国民航大学 | Fire detection method and device |
| CN112016886A (en) * | 2020-08-17 | 2020-12-01 | 北京双洲科技有限公司 | Mobile terminal safety office management and control method, device and system |
| CN113125675A (en) * | 2021-04-19 | 2021-07-16 | 北京物资学院 | Storage yard coal spontaneous combustion early warning device and early warning method of edge computing framework |
| CN113743015A (en) * | 2021-09-07 | 2021-12-03 | 同济大学 | Fire scene data acquisition method, medium and electronic device |
| CN113743015B (en) * | 2021-09-07 | 2024-03-29 | 同济大学 | Fire scene data acquisition method, medium and electronic equipment |
| CN114627607B (en) * | 2022-01-30 | 2022-11-29 | 江苏蓝图消防装备有限公司 | Fire-fighting comprehensive information retrieval system based on industrial sensor network |
| CN114627607A (en) * | 2022-01-30 | 2022-06-14 | 江苏蓝图消防装备有限公司 | Fire-fighting comprehensive information retrieval system based on industrial sensor network |
| CN114949665A (en) * | 2022-05-20 | 2022-08-30 | 国能包头能源有限责任公司 | Spontaneous combustion prevention processing method and device for coal yard and computer readable storage medium |
| CN115100838A (en) * | 2022-05-31 | 2022-09-23 | 杭州鸿泉物联网技术股份有限公司 | Vehicle fire early warning method, device, equipment, medium and computer program product |
| CN114758470A (en) * | 2022-06-16 | 2022-07-15 | 张家港金典软件有限公司 | Fire early warning method and system based on fire engineering |
| CN116542442A (en) * | 2023-04-03 | 2023-08-04 | 中国消防救援学院 | Unmanned aerial vehicle-based fire-fighting auxiliary dispatching management method and system |
| CN117592789A (en) * | 2024-01-18 | 2024-02-23 | 山东金桥保安器材有限公司 | Power grid environment fire risk assessment method and equipment based on time sequence analysis |
| CN117592789B (en) * | 2024-01-18 | 2024-04-16 | 山东金桥保安器材有限公司 | Power grid environment fire risk assessment method and equipment based on time sequence analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109686036B (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109686036A (en) | A kind of fire monitoring method, device and edge calculations device | |
| US11615695B2 (en) | Coverage agent for computer-aided dispatch systems | |
| WO2020259421A1 (en) | Method and apparatus for monitoring service system | |
| CN109978005A (en) | A kind of fire alarm method, device, storage medium and terminal device | |
| CN109460664A (en) | Risk analysis method, device, Electronic Design and computer-readable medium | |
| JP6355683B2 (en) | Risk early warning method, apparatus, storage medium, and computer program | |
| CN106844138A (en) | O＆M warning system and method | |
| CN109242361A (en) | A kind of fire-fighting methods of risk assessment, device and terminal device | |
| Park et al. | Technological opportunities discovery for safety through topic modeling and opinion mining in the fourth industrial revolution: The case of artificial intelligence | |
| CN108877172B (en) | A kind of false alarm analysis method, device and terminal device | |
| CN109669837A (en) | Equipment state method for early warning, system, computer installation and readable storage medium storing program for executing | |
| KR102087959B1 (en) | Artificial intelligence operations system of telecommunication network, and operating method thereof | |
| CN110730164B (en) | Safety early warning method, related equipment and computer readable storage medium | |
| CN107861856A (en) | The processing method and computer-readable storage medium of warning information in cloud data system | |
| CN112446511A (en) | Fault handling method, device, medium and equipment | |
| US11620341B1 (en) | Industrial virtual assistant platform with robotic process automation for knowledge and insights management | |
| Skvortsova et al. | A hybrid intelligent system for risk assessment based on unstructured data | |
| Sindiramutty et al. | Modern Smart Cities and Open Research Challenges and Issues of Explainable Artificial Intelligence | |
| CN109035666A (en) | A kind of fire-smoke detection method, apparatus and terminal device | |
| Shao et al. | Hybrid artificial neural networks modeling for faults identification of a stochastic multivariate process | |
| Sula | Secriskai: a machine learning-based tool for cybersecurity risk assessment | |
| CN114168967A (en) | Industrial control system security situation prediction method and system | |
| CN113361855A (en) | Short, medium and long-term risk warning method and device | |
| CN112579402A (en) | Method and device for positioning faults of application system | |
| Ragsdale et al. | A study on trust in alarms in a nuclear power plant microworld simulation |
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 |