CN109686036B - Fire monitoring method and device and edge computing device - Google Patents
Fire monitoring method and device and edge computing device Download PDFInfo
- Publication number
- CN109686036B CN109686036B CN201910019256.XA CN201910019256A CN109686036B CN 109686036 B CN109686036 B CN 109686036B CN 201910019256 A CN201910019256 A CN 201910019256A CN 109686036 B CN109686036 B CN 109686036B
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- data
- fire
- environmental monitoring
- 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.)
- Active
Links
Images
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 invention is suitable for the technical field of fire monitoring, and provides a fire monitoring method, a fire monitoring device and an edge calculating device, wherein the method comprises the following steps: the method comprises the steps of obtaining more than two groups of environment monitoring data, preprocessing the environment monitoring data according to a time sequence of the environment monitoring data, obtaining preprocessed environment monitoring data, inputting the preprocessed environment monitoring data into a pre-training machine learning model, obtaining a decision result output by the pre-training machine learning model, and sending corresponding warning information to a user terminal according to the decision result. The invention utilizes the edge computing device to operate the machine learning model to perform data fusion on the environmental monitoring data so as to calculate the fire hazard degree, thereby realizing real-time, objective, safe and reliable fire hazard risk assessment. Meanwhile, corresponding warning information is sent according to the state of the fire, so that a real and reliable decision basis is provided for fire-fighting rescue personnel, and the efficiency of fire-fighting rescue actions is improved.
Description
Technical Field
The invention belongs to the technical field of fire monitoring, and particularly relates to a fire monitoring method and device and an edge computing device.
Background
The existing fire monitoring system can only provide simple warning signals, for example, the most common fire alarm can only give out the same alarm sound no matter how the danger degree of the fire is, so that a director of fire fighting and rescue actions cannot know the real danger degree of the fire, and no way is available for arranging evacuation personnel and fire fighting according to the simple warning information, so that the efficiency of the fire fighting and rescue actions is influenced. Moreover, if the fire hazard degree needs to be evaluated, related personnel are often required to judge the fire condition on the fire scene, the judgment result is high in subjectivity, and the life safety of the personnel can be threatened.
On the other hand, some intelligent fire alarm systems often rely on the internet of things and cloud computing technology, upload environment monitoring data collected by a sensor to a cloud for processing, then transmit a processing result to a user terminal through the internet and a mobile network, so that a large delay exists in the data transmission process, the cloud processing also can meet the conditions of network congestion and queuing, and the real-time requirements of the fire-fighting rescue scene for data processing and transmission in a very diverse manner are difficult to meet.
Disclosure of Invention
In view of this, embodiments of the present invention provide a fire monitoring method and apparatus, and an edge calculating apparatus, so as to solve the problems in the prior art that a warning signal is too simple, real-time performance is poor, and it is difficult to provide an objective fire risk level.
A first aspect of an embodiment of the present invention provides a fire monitoring method, including:
acquiring more than two groups of environment monitoring data;
preprocessing the environmental monitoring data according to the time sequence of the environmental monitoring data to obtain preprocessed environmental monitoring data;
inputting the preprocessed environmental monitoring data into a pre-training machine learning model to obtain a decision result output by the pre-training machine learning model;
and sending corresponding warning information to the user terminal according to the decision result.
Optionally, before inputting the preprocessed environmental monitoring data into a pre-training machine learning model and obtaining a decision result output by the pre-training machine learning model, the method includes:
acquiring environmental monitoring data of a historical fire incident, and establishing sample data according to the environmental monitoring data of the historical fire incident;
adding a label to the sample data and using the sample data as a training sample;
and training a machine learning model according to the training samples to obtain the pre-training machine learning model.
Optionally, adding a label to the sample data as a training sample, including:
and adding a label to the sample data by using a fuzzy comprehensive evaluation method to obtain a training sample.
Optionally, before sending the corresponding warning information to the user terminal according to the decision result, the method includes:
and establishing a corresponding relation between the decision result and the warning information.
Optionally, the preprocessing the environmental monitoring data according to the time sequence of the environmental monitoring data to obtain the preprocessed environmental monitoring data includes:
deleting error data in the environment monitoring data to obtain updated environment monitoring data; wherein the error data comprises environmental monitoring data exceeding a first preset data threshold and/or environmental monitoring data below a second preset data threshold;
and obtaining the change rate of the updated environment monitoring data changing according to the time sequence, and obtaining the preprocessed environment monitoring data.
Optionally, the machine learning model includes a decision tree model and/or a BP neural network model.
A second aspect of an embodiment of the present invention provides a fire monitoring apparatus, including:
the first acquisition module is used for acquiring more than two groups of environment monitoring data;
the preprocessing module is used for preprocessing the environmental monitoring data according to the time sequence of the environmental monitoring data to obtain preprocessed environmental monitoring data;
the input module is used for inputting the preprocessed environmental monitoring data into a pre-training machine learning model to obtain a decision result output by the pre-training machine learning model;
and the sending module is used for sending the corresponding warning information to the user terminal according to the decision result.
A third aspect of an embodiment of the present invention provides an edge calculation apparatus, including: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method as described above when executing the computer program.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as described above.
On one hand, the embodiment of the invention utilizes the edge computing device to operate the machine learning model to perform data fusion on the environment monitoring data so as to calculate the fire hazard degree, thereby realizing real-time, objective, safe and reliable fire hazard risk assessment. On the other hand, the embodiment of the invention sends the corresponding warning information according to the state of the fire, thereby providing a real and reliable decision basis for fire-fighting rescue personnel and improving the efficiency of fire-fighting rescue actions.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a fire monitoring method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a fire monitoring method according to a second embodiment of the present invention;
FIG. 3 is a schematic flow chart of a fire monitoring method according to a third embodiment of the present invention;
FIG. 4 is a schematic flow chart of a fire monitoring method according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a fire monitoring apparatus according to a fifth embodiment of the present invention;
fig. 6 is a schematic diagram of an edge computing device according to a sixth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "comprises" and "comprising," and any variations thereof, in the description and claims of this invention and the above-described drawings are intended to cover non-exclusive inclusions. For example, a process, method, or system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. Furthermore, the terms "first," "second," and "third," etc. are used to distinguish between different objects and are not used to describe a particular order.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Example one
As shown in fig. 1, the present embodiment provides a fire monitoring method, which can be applied to terminal devices such as mobile phones, PCs, tablet computers, etc., or edge computing devices specifically designed for fire monitoring. The fire monitoring method provided by the embodiment comprises the following steps:
s101, acquiring more than two groups of environment monitoring data;
in specific application, two or more groups of environment monitoring data are obtained; the environment monitoring data refers to environment parameters acquired by a sensor; sensors include, but are not limited to, temperature sensors, smoke sensors, oxygen concentration detection sensors, carbon monoxide sensors; each set of environmental monitoring data includes, but is not limited to, temperature, oxygen concentration, carbon monoxide concentration, smoke concentration. It should be noted that the environmental monitoring data may be sorted according to the time when the environmental monitoring data is obtained (i.e., the environmental monitoring data is sorted according to the time sequence), and similarly, a time tag may be added to the environmental monitoring data according to the time sequence.
In one embodiment, the method may be performed by an edge computing device comprising a preprocessing module, a decision module, an alarm module, and a communication module.
In one embodiment, step S101 may be performed by a communication module, and the communication module is communicatively connected to the sensor, the user terminal (or the cloud).
S102, preprocessing the environment monitoring data according to the time sequence of the environment monitoring data, and acquiring the preprocessed environment monitoring data.
In specific application, the environmental monitoring data are preprocessed according to the time sequence of obtaining the environmental monitoring data, and the preprocessed environmental monitoring data are obtained; the preprocessing comprises processing methods such as deleting error data in the environment monitoring data, performing discretization processing on the environment monitoring data and the like. The rate of change of each environmental parameter, such as the rate of temperature rise, the rate of temperature fall, the rate of smoke concentration rise, the rate of smoke concentration fall, etc., may also be calculated from the time series of environmental monitoring data. When using the BP neural network model as a machine learning model, the preprocessing further includes normalizing the data.
In one embodiment, step S102 may be performed by a preprocessing module,
s103, inputting the preprocessed environmental monitoring data into a pre-training machine learning model to obtain a decision result output by the pre-training machine learning model.
In specific application, the preprocessed environmental monitoring data is input into a pre-training machine learning model obtained through pre-training so as to obtain a decision result output by the pre-training machine learning model. The decision result can be judged according to the stage of the fire to acquire the fire state and acquire the corresponding danger degree of the fire stage; decision results include, but are not limited to, initial-primary-risk level of fire, fire expansion stage-intermediate-risk level, fierce-advanced-risk level, fire descent stage-intermediate-risk level, fire extinguishment stage-hidden-risk level. In one embodiment, step S103 may be performed by a decision module.
And S104, sending corresponding warning information to the user terminal according to the decision result.
In specific application, corresponding warning information is sent to the user terminal according to the decision result so as to remind the user to execute a corresponding fire coping method according to the warning information. In this embodiment, the corresponding alarm information can be sent to the fire center or the terminal device of the monitoring personnel according to the decision result, so as to inform the fire fighter or the monitoring personnel to perform corresponding operations such as fire extinguishing, personnel evacuation and the like according to the alarm information. In one embodiment, the alarm module may generate corresponding warning information according to the decision result, and the communication module sends the warning information to the user terminal (or cloud).
In the embodiment, the machine learning model is used for carrying out data fusion on the environmental monitoring data so as to calculate the danger degree of the fire, thereby realizing real-time, objective, safe and reliable fire hazard risk assessment; meanwhile, corresponding warning information is sent according to the state of the fire, so that a real and reliable decision basis is provided for fire-fighting rescue personnel, and the efficiency of fire-fighting rescue actions is improved.
Example two
As shown in fig. 2, this embodiment is a further description of the method steps in the first embodiment. In this embodiment, before step S103, the method further includes:
s201, obtaining environmental monitoring data of a historical fire incident, and establishing sample data according to the environmental monitoring data of the historical fire incident.
In specific application, environment monitoring data measured by environment sensors (such as a temperature sensor, a smoke sensor, a carbon monoxide sensor and the like) in a truly occurring historical fire incident and a time series of the environment monitoring data can be obtained from a database of a fire protection information system, the change rate (rising rate and falling rate) of each environment parameter (such as temperature, smoke concentration and the like) can be calculated according to the time series of the environment monitoring data, and the environment monitoring data and the change rate data can be normalized, so that sample data can be established. The standard fire experiment can also be carried out in a monitored place, a preset number of environmental monitoring data are obtained through an environmental sensor of an experiment site, and sample data are established according to the environmental monitoring data of the standard fire experiment.
And S202, adding a label to the sample data and using the sample data as a training sample.
In specific application, a label is added to sample data (namely, a label of a fire stage is added to the sample data according to the development process of a historical fire incident), and the sample data added with the label is used as a training sample to pre-train a machine learning model. For example, if a set of sample data is environmental monitoring data at a fire expansion stage of a historical fire event, a fire expansion tag is added to the sample data to generate a corresponding training sample. The labels may be manually assigned to corresponding sample data based on the environmental monitoring data and the rate of change of the environmental parameters. In some embodiments, the sample data may be tagged using fuzzy comprehensive evaluation to obtain training samples. Specifically, the environmental parameters and the change rates of the environmental parameters may be used as evaluation indexes, a comment set (e.g., { low risk degree, medium risk degree, high risk degree … }) is established according to the fire risk degree classification, and a weight vector of the evaluation indexes is constructed by an expert experience method or an analytic hierarchy process. And then constructing a membership function of each evaluation index for each fire hazard degree rating. And when fire hazard degree labels are added to a group of samples, obtaining a fuzzy comprehensive evaluation matrix according to the membership function of each index and the numerical value of the evaluation index. And selecting a proper fuzzy operator to carry out fuzzy matrix synthesis on the weight vector and the evaluation matrix. And then judging the corresponding fire hazard degree classification by utilizing a maximum membership principle according to the synthetic result. The fire risk level is then graded as a label for the sample. And sequentially adding labels to all samples in the sample data to obtain training samples for training the machine learning model. And adding a label to the sample data by using a fuzzy comprehensive evaluation method to obtain a training sample, so that a machine learning model can learn expert experience, and the fire evaluation precision is improved.
S203, training a machine learning model according to the training samples, and obtaining the pre-training machine learning model.
In specific application, a machine learning model is trained according to sample data, and a pre-training machine learning model is obtained. When the sample data is input into the pre-training machine learning model, the pre-training machine learning model can output a decision result (namely a fire stage and a corresponding danger degree) corresponding to the sample data.
In one embodiment, the machine learning model includes, but is not limited to, a decision tree model and/or a BP neural network model.
In one embodiment, the step S202 includes:
adding a corresponding label according to the development stage of the fire in the sample data to obtain a training sample; wherein the development stage of the fire comprises the initial stage of the fire, the fire expansion stage, the fire fierce stage, the fire descending stage and the fire extinguishing stage.
In one embodiment, the step S202 further includes:
and adding a label to the sample data by using a fuzzy comprehensive evaluation method to obtain a training sample.
In specific application, a fuzzy comprehensive evaluation method is used for adding labels to the sample data to obtain training samples, so that a machine learning model can learn expert experience, and the fire evaluation precision is improved.
According to the method and the device for pre-training the machine learning model, the sample data is processed, and the machine learning model is pre-trained according to the processed sample data, so that the precision of the model is improved, and a foundation is laid for providing accurate warning information.
EXAMPLE III
As shown in fig. 3, this embodiment is a further description of the method steps in the first embodiment. In this embodiment, before step S104, the method further includes:
s301, establishing a corresponding relation between the decision result and the warning information.
In a specific application, a corresponding relation between a decision result and the warning information is established. For example, if the decision result is a fierce stage, i.e., a high-level risk degree, the corresponding warning information is that the fire is fierce when the fire is present, and the fire site should be evacuated immediately.
In the embodiment, the corresponding relation between the decision result and the warning information is established, so that the corresponding warning information can be sent when the decision result is obtained, the user is reminded to execute a corresponding measure corresponding to the warning information, and the safety of the user is ensured.
Example four
As shown in fig. 4, this embodiment is a further description of the method steps in the first embodiment. In this embodiment, step S102 includes:
s1021, deleting error data in the environment monitoring data, and acquiring updated environment monitoring data; wherein the error data comprises environmental monitoring data exceeding a first preset data threshold and/or environmental monitoring data below a second preset data threshold.
In specific application, error data in the environmental monitoring data is deleted, and updated environmental monitoring data is obtained; wherein the error data comprises environmental monitoring data exceeding a first preset data threshold and/or environmental monitoring data below a second preset data threshold. The first preset data threshold and the second preset data threshold can be specifically set according to actual conditions. For example, a second preset data threshold for temperature is set to-40 ℃, and temperature values below the second preset data threshold are deleted. (i.e., temperatures below the second predetermined data threshold are less likely to cause a fire or it is determined that the temperature sensor may fail, resulting in erroneous temperature data being acquired).
And S1022, acquiring the change rate of the updated environment monitoring data changing according to the time sequence, and acquiring the preprocessed environment monitoring data.
In a specific application, the change rate of the updated environment monitoring data changing according to the time sequence is obtained, (the updated environment monitoring data can be discretized according to the change rate of the updated environment monitoring data), and the preprocessed environment monitoring data is obtained. For example, according to the time sequence, the change rate of the temperature data acquired from the first time to the second time is acquired, and the change rate of the temperature data acquired from the second time to the third time is acquired. The change rate may be a ratio of the temperature data acquired at the later time to the temperature data acquired at the previous time. The temperature obtained at 10:00 was 23 ℃, 10: 30 is obtained at a temperature of 25 ℃ and 11:00 is obtained at a temperature of 30 ℃, then 10: 00-10: the temperature change rate of 30 was 25/23, 10: the temperature change rate of 30-11:00 was 30/25.
In one embodiment, step S103 includes:
and S1031, inputting the preprocessed environmental monitoring data into a pre-training machine learning model.
In specific application, the preprocessed environmental monitoring data are input into the pre-training machine learning model, so that the pre-training machine learning model processes the preprocessed environmental monitoring data to obtain a corresponding decision result.
S1032, performing data fusion on the preprocessed environmental monitoring data through the pre-training machine learning model, and outputting the decision result.
In specific application, the preprocessed environmental monitoring data is subjected to data fusion through a pre-training machine learning model, and a decision result is output.
According to the embodiment, the environmental monitoring data are preprocessed to obtain effective and accurate environmental monitoring data, so that the accuracy of a decision result is improved, and the efficiency of fire prevention and control is further improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
EXAMPLE five
As shown in fig. 5, the present embodiment provides a fire monitoring apparatus 100 for performing the method steps of the first embodiment. The fire monitoring apparatus 100 according to the present embodiment includes:
the first acquisition module 101 is used for acquiring more than two groups of environment monitoring data;
the preprocessing module 102 is configured to preprocess the environmental monitoring data according to the time sequence of the environmental monitoring data, and acquire preprocessed environmental monitoring data;
an input module 103, configured to input the preprocessed environmental monitoring data into a pre-training machine learning model, and obtain a decision result output by the pre-training machine learning model;
and a sending module 104, configured to send corresponding warning information to the user terminal according to the decision result.
In one embodiment, the apparatus 100 further comprises:
the second obtaining module 201 is configured to obtain environmental monitoring data of a historical fire event, and establish sample data according to the environmental monitoring data of the historical fire event;
a label module 202, configured to add a label to the sample data and use the sample data as a training sample;
a third obtaining module 203, configured to train a machine learning model according to the training sample, and obtain the pre-training machine learning model.
In one embodiment, the tag module 202 includes:
and the label unit is used for adding a label to the sample data by utilizing a fuzzy comprehensive evaluation method to obtain a training sample.
In one embodiment, the apparatus 100 further comprises:
and the establishing module is used for establishing the corresponding relation between the decision result and the warning information.
In one embodiment, the pre-processing module 102 includes:
the deleting unit is used for deleting error data in the environment monitoring data and acquiring updated environment monitoring data; wherein the error data comprises environmental monitoring data exceeding a first preset data threshold and/or environmental monitoring data below a second preset data threshold;
and the discretization unit is used for acquiring the change rate of the updated environment monitoring data changing according to the time sequence and acquiring the preprocessed environment monitoring data.
In one embodiment, the machine learning model includes a decision tree model and/or a BP neural network model.
In the embodiment, the machine learning model is used for carrying out data fusion on the environmental monitoring data so as to calculate the danger degree of the fire, thereby realizing real-time, objective, safe and reliable fire hazard risk assessment; meanwhile, corresponding warning information is sent according to the state of the fire, so that a real and reliable decision basis is provided for fire-fighting rescue personnel, and the efficiency of fire-fighting rescue actions is improved.
EXAMPLE six
Fig. 6 is a schematic diagram of an edge calculating apparatus provided in this embodiment. As shown in fig. 6, the edge calculation device 6 of this embodiment includes: a processor 60, a memory 61 and a computer program 62, such as a fire monitoring program, stored in the memory 61 and operable on the processor 60. The processor 60, when executing the computer program 62, implements the steps in the various fire monitoring method embodiments described above, such as steps S101-S104 shown in fig. 1. Alternatively, the processor 60, when executing the computer program 62, implements the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the modules 101 to 104 shown in fig. 5.
Illustratively, the computer program 62 may be partitioned into one or more modules/units that are stored in the memory 61 and executed by the processor 60 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions that describe the execution of the computer program 62 in the edge computing device 6. For example, the computer program 62 may be divided into a first acquiring module, a preprocessing module, an input module, and a sending module, and each module has the following specific functions:
the first acquisition module is used for acquiring more than two groups of environment monitoring data;
the preprocessing module is used for preprocessing the environmental monitoring data according to the time sequence of the environmental monitoring data to obtain preprocessed environmental monitoring data;
the input module is used for inputting the preprocessed environmental monitoring data into a pre-training machine learning model to obtain a decision result output by the pre-training machine learning model;
and the sending module is used for sending the corresponding warning information to the user terminal according to the decision result.
The edge computing device 6 may be a computing device such as a desktop computer, a notebook, a palm top computer, and an edge server. The edge computing device may include, but is not limited to, a processor 60, a memory 61. Those skilled in the art will appreciate that fig. 6 is merely an example of an edge computing device 6, and does not constitute a limitation of the edge computing device 6, and may include more or fewer components than shown, or some components in combination, or different components, e.g., the edge computing device may also include input output devices, network access devices, buses, etc.
The Processor 60 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 61 may be an internal storage unit of the edge computing device 6, such as a hard disk or a memory of the edge computing device 6. The memory 61 may also be an external storage device of the edge computing device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital Card (SD), a Flash memory Card (Flash Card), and the like, provided on the edge computing device 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the edge computing apparatus 6. The memory 61 is used to store the computer program and other programs and data required by the edge computing means. The memory 61 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/edge computing apparatus and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/edge computing apparatus are merely illustrative, and for example, the division of the modules or units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (5)
1. A fire monitoring method, comprising:
acquiring more than two groups of environment monitoring data;
preprocessing the environmental monitoring data according to the time sequence of the environmental monitoring data to obtain preprocessed environmental monitoring data; the preprocessing comprises deleting error data in the environment monitoring data and acquiring updated environment monitoring data; the error data comprises environmental monitoring data exceeding a first preset data threshold and/or environmental monitoring data below a second preset data threshold; obtaining the change rate of the updated environment monitoring data changing according to the time sequence, and obtaining the preprocessed environment monitoring data;
acquiring environmental monitoring data of a historical fire incident, and establishing sample data according to the environmental monitoring data of the historical fire incident;
adding a label to the sample data by using a fuzzy comprehensive evaluation method and using the sample data as a training sample;
training a machine learning model according to the training samples to obtain a pre-training machine learning model
Inputting the preprocessed environmental monitoring data into a pre-training machine learning model to obtain a decision result output by the pre-training machine learning model;
sending corresponding warning information to the user terminal according to the decision result;
before sending the corresponding warning information to the user terminal according to the decision result, the method further includes:
and establishing a corresponding relation between the decision result and the warning information.
2. A fire monitoring method as claimed in claim 1 in which the machine learning model comprises a decision tree model and/or a BP neural network model.
3. A fire monitoring device, comprising:
the first acquisition module is used for acquiring more than two groups of environment monitoring data;
the preprocessing module is used for preprocessing the environmental monitoring data according to the time sequence of the environmental monitoring data to obtain preprocessed environmental monitoring data; the preprocessing comprises deleting error data in the environment monitoring data and acquiring updated environment monitoring data; the error data comprises environmental monitoring data exceeding a first preset data threshold and/or environmental monitoring data below a second preset data threshold; obtaining the change rate of the updated environment monitoring data changing according to the time sequence, and obtaining the preprocessed environment monitoring data;
the second acquisition module is used for acquiring the environmental monitoring data of the historical fire incident and establishing sample data according to the environmental monitoring data of the historical fire incident;
the label module is used for adding a label to the sample data by utilizing a fuzzy comprehensive evaluation method and using the sample data as a training sample;
the third acquisition module is used for training a machine learning model according to the training samples and acquiring a pre-training machine learning model;
the input module is used for inputting the preprocessed environmental monitoring data into a pre-training machine learning model to obtain a decision result output by the pre-training machine learning model;
and the sending module is used for establishing the corresponding relation between the decision result and the warning information and sending the corresponding warning information to the user terminal according to the decision result.
4. An edge computing device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the method according to any of claims 1 to 2 are implemented when the computer program is executed by the processor.
5. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 2.
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 CN109686036A (en) | 2019-04-26 |
| CN109686036B true 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) |
Families Citing this family (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 |
| 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 |
| 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 |
| 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 |
| CN111238446B (en) * | 2020-01-15 | 2021-09-28 | 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 |
| CN111753900B (en) * | 2020-06-23 | 2023-04-07 | 中南林业科技大学 | Forest fire monitoring method |
| 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 |
| 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 |
| 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 |
| CN114758470B (en) * | 2022-06-16 | 2022-10-21 | 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 |
| 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 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101581940B (en) * | 2009-06-05 | 2011-04-27 | 西安电子科技大学 | Tunnel event detection method based on integrated learning time sequence prediction |
| CN102013148B (en) * | 2010-10-28 | 2012-06-27 | 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 |
| CN108230637B (en) * | 2017-12-29 | 2020-11-17 | 深圳市泛海三江科技发展有限公司 | Fire-fighting fire alarm method and system |
| CN108447210B (en) * | 2018-03-22 | 2020-04-03 | 河南科技大学 | Multi-point pushing intelligent warehouse fire alarm system and alarm method thereof |
| 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
Also Published As
| Publication number | Publication date |
|---|---|
| CN109686036A (en) | 2019-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109686036B (en) | Fire monitoring method and device and edge computing device | |
| CN108199795B (en) | A kind of monitoring method and device of equipment state | |
| JP6355683B2 (en) | Risk early warning method, apparatus, storage medium, and computer program | |
| CN112306808B (en) | Performance monitoring and evaluating method and device, computer equipment and readable storage medium | |
| CN115640915B (en) | Intelligent gas pipe network compressor safety management method and Internet of things system | |
| Vallmuur et al. | Harnessing information from injury narratives in the ‘big data’era: understanding and applying machine learning for injury surveillance | |
| CN107368975A (en) | Data checking method, system, storage medium and electronic equipment | |
| CN113592019A (en) | Fault detection method, device, equipment and medium based on multi-model fusion | |
| CN117151478B (en) | Chemical enterprise risk early warning method and system based on convolutional neural network | |
| CN115357470B (en) | Information generation method and device, electronic equipment and computer readable medium | |
| CN115222303B (en) | Industry risk data analysis method and system based on big data and storage medium | |
| CN116307674A (en) | Security supervision method, device, system, equipment, medium and product | |
| CN108877172A (en) | A kind of false alarm analysis method, device and terminal device | |
| Zamri et al. | A fuzzy TOPSIS with Z-numbers approach for evaluation on accident at the construction site | |
| CN111931047A (en) | Artificial intelligence-based black product account detection method and related device | |
| CN118261429B (en) | Engineering management method and system for construction safety | |
| CN110930176B (en) | Prediction method, prediction device, electronic equipment and storage medium | |
| CN115131706A (en) | Power operation violation datamation intelligent image recognition system and method | |
| CN109842682B (en) | Distributed environment safety learning and early warning method based on Internet of things | |
| CN117993643A (en) | Integral prevention and control method for human risk of electric power operation based on track prediction | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN114580979B (en) | High-temperature disaster prevention index detection method, device, equipment, storage medium and product | |
| CN114239849A (en) | Weather disaster prediction and model training method, device, equipment and storage medium | |
| CN115565329A (en) | Building site fire safety management system based on thing networking | |
| CN114238062A (en) | Board card burning device performance analysis method, device, equipment and readable storage medium |
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 |