CN113516820B - Fire early warning method and fire early warning system - Google Patents
Fire early warning method and fire early warning system Download PDFInfo
- Publication number
- CN113516820B CN113516820B CN202110776539.6A CN202110776539A CN113516820B CN 113516820 B CN113516820 B CN 113516820B CN 202110776539 A CN202110776539 A CN 202110776539A CN 113516820 B CN113516820 B CN 113516820B
- Authority
- CN
- China
- Prior art keywords
- fire
- early warning
- data
- result
- preliminary
- 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
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000011156 evaluation Methods 0.000 claims description 27
- 230000015654 memory Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 description 6
- 239000000779 smoke Substances 0.000 description 6
- 101100281682 Danio rerio fsta gene Proteins 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 101100273916 Schizosaccharomyces pombe (strain 972 / ATCC 24843) wip1 gene Proteins 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
Abstract
The invention discloses a fire early warning method and a fire early warning system, wherein the method comprises the following steps: acquiring real-time data acquired by a fire detector in a monitored target area; outputting a preliminary early warning result of the monitored target area according to the similarity degree of real-time data acquired by the fire detector and stored historical fire data; and outputting a final early warning result based on the condition that the same type of early warning results continuously appear in the preliminary early warning results. The technical scheme provided by the invention overcomes the problems of low accuracy and high time delay of the traditional fire alarm method.
Description
Technical Field
The invention relates to the field of fire safety, in particular to a fire early warning method and a fire early warning system.
Background
The fire disaster is one of the most destructive accidents, if the fire disaster is not found in time, immeasurable damage can be caused to public property safety and personal safety, so that the damage caused by the fire disaster can be avoided to the maximum extent by early warning in time. Fire early warning is usually monitored by means of fire detectors such as smoke sensors and temperature sensors, while the traditional fire early warning technology sets a fixed alarm threshold value for the fire detectors such as smoke sensors and temperature sensors, and a signal acquired by any single sensor exceeds the alarm threshold value, a fire alarm signal is triggered to start an automatic fire-fighting system, and the situation of fire misinformation can be generated in the mode at a high probability. In order to avoid the failure or false alarm of a single sensor, the prior art provides that after a plurality of alarm signals need to be triggered cumulatively, an automatic fire-fighting system is started. However, the above techniques all adopt a mode of setting a fixed alarm threshold value for monitoring, and due to different arrangement positions and detection sensitivities of different detectors, when the alarm triggering condition is met, a fire is likely to be formed due to the existence of time delay, so that the gold time for identifying and extinguishing the fire is missed, a disaster is often caused, and property and personnel loss is caused.
Disclosure of Invention
In view of this, the embodiment of the present invention provides a fire early warning method and an early warning system, so as to reduce the time delay of the conventional fire early warning system.
According to a first aspect, the present invention provides a fire early warning method, including:
acquiring real-time data acquired by a fire detector in a monitored target area;
outputting a preliminary early warning result of the monitored target area according to the similarity degree of the real-time data collected by the fire detector and the stored historical fire data;
and monitoring whether a result of fire occurrence occurs in the process of continuously outputting the preliminary early warning result, judging whether the number of times of fire occurrence which continuously occurs from the next moment reaches a preset early warning number when the fire occurrence occurs, and generating a final early warning result according to the judgment result.
Optionally, the historical fire data includes fire scene data of different levels, and fire labels for marking whether fire occurs in the fire scene data of each level.
Optionally, the real-time data includes the current time collected by the fire detector and the detection data of a preset number of times before the current time.
Optionally, outputting a preliminary warning result of the monitored target region according to a similarity degree between real-time data collected by the fire detector and stored historical fire data, including:
respectively determining the similarity degree of the real-time data and the fire scene data of each grade in the historical fire data;
and sequentially screening a preset number of fire scene data according to the arrangement sequence of the similarity degrees from large to small, obtaining fire labels corresponding to the fire scene data, and obtaining a preliminary early warning result of the monitored target area according to the early warning results corresponding to the same fire labels at most.
Optionally, the method includes that a plurality of fire detectors are included in a monitored target area, and the preliminary warning result of the monitored target area is output according to the similarity between the real-time data collected by the fire detectors and the stored historical fire data, and further includes:
and dividing the preliminary early warning results based on the preliminary early warning results of the fire detectors, and taking more than half of the preliminary early warning results as the preliminary early warning results of the monitored target area.
Optionally, monitoring whether a result of fire occurrence occurs in a process of continuously outputting the preliminary early warning result, when the fire occurrence occurs, determining whether the number of times of fire occurrence that occurs continuously from a next moment reaches a preset early warning number, and generating a final early warning result according to a determination result, including:
when a fire disaster occurs in the continuously monitored preliminary early warning result, acquiring an early warning result of a subsequent continuous moment by taking the early warning moment when the fire disaster occurs as a reference;
when the early warning result of the fire hazard continuously appears from the next moment and the appearing times of the early warning result reach the preset early warning times, generating the final early warning result of the fire hazard;
and when the early warning result of the fire is continuously generated from the next moment, but the occurrence frequency of the early warning result does not reach the preset early warning frequency when the continuous occurrence process of the early warning result is finished, or the early warning result of the fire is not generated from the next moment, generating a final early warning result of the non-fire and returning to the step of monitoring whether the result of the fire is generated in the process of continuously outputting the primary early warning result.
Optionally, the method further comprises:
obtaining an evaluation index of the fire early warning method by using the final early warning result;
and generating an evaluation result according to the evaluation index.
Optionally, the evaluation index includes at least: accuracy of fire onset time and false fire alarm rate.
According to a second aspect, embodiments of the present invention provide a fire early warning system, the system including:
the data acquisition module is used for acquiring real-time data acquired by a fire detector in a monitored target area;
the preliminary early warning module is used for outputting a preliminary early warning result of the monitored target area according to the similarity degree of the real-time data acquired by the fire detector and the stored historical fire data;
and the final early warning module is used for outputting a final early warning result based on the condition that the same type of early warning results continuously appear in the initial early warning results.
Optionally, the system further comprises:
and the calibration module is used for acquiring the evaluation index of the fire early warning method by using the final early warning result and generating an evaluation result according to the evaluation index.
According to a third aspect, an embodiment of the present invention provides an electronic device, including:
a memory and a processor, the memory and the processor being communicatively coupled to each other, the memory having stored therein computer instructions, and the processor performing the method of the first aspect, or any one of the optional embodiments of the first aspect, by executing the computer instructions.
The technical scheme of the invention has the following advantages:
the embodiment of the invention provides a fire early warning method and a fire early warning system. The method specifically comprises the following steps: the method comprises the steps of obtaining real-time data of the current time and a plurality of previous times of a fire, and carrying out similarity analysis on the real-time data and prestored historical data representing different fire grades, so that whether a fire happens in a target area or not is obtained according to labels corresponding to a plurality of historical data with the highest similarity. By combining historical data, wrong conclusions caused by data mutation are avoided, the robustness of the whole system is improved, slight changes before fire disaster occur are reflected in advance by combining the historical data, early warning can be given out when the fire disaster is in a weak fire disaster grade, the time delay of fire early warning is reduced, and the fire early warning accuracy is improved. And then, selecting the early warning results which account for more than half of the detectors through a voting mechanism, and comprehensively analyzing the early warning results which are continuously predicted for multiple times to further reduce the false alarm rate. The fire early warning system evaluation part is added according to the fire early warning evaluation index, problems in the system are adjusted in time, and the reliability of the system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic diagram illustrating steps of a fire warning method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for fire early warning according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a fire warning system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 technical features mentioned in the different embodiments of the invention described below can be combined with each other as long as they do not conflict with each other.
Referring to fig. 1 and 2, a fire early warning method according to an embodiment of the present invention includes the following steps:
step S101: and acquiring real-time data acquired by a fire detector in the monitored target area, wherein the real-time data comprises the current moment acquired by the fire detector and detection data of a preset number of moments before the current moment.
Specifically, in order to improve the accuracy of the traditional fire early warning technology, the real-time data acquired by the fire detector is different from that of the traditional technology, the real-time data not only comprise the sensor data of the fire detector at the current moment but also comprise the sensor data of a plurality of previous moments, and the condition of fire generation is analyzed from the change trend angle of the data, so that the fluctuation degree of the fire is timely monitored when the temperature, the smoke and the like start to change, and the condition of fire occurrence is discovered as soon as possible. Furthermore, the method can avoid instantaneous disturbance at the current moment or detector fault outputting error data so as to draw an error conclusion on one hand, and can increase the robustness of the prediction system on the other hand. In the embodiment of the invention, the sampling interval is 1 second, and the acquired data is a group of data consisting of the data at the current moment and the data in the last 20 seconds. The fire detector includes but is not limited to temperature-sensing detector and smoke detector, and the detector also includes photosensitive detector, infrared detector and ultraviolet detector.
Step S102: and outputting a preliminary early warning result of the monitored target area according to the similarity degree of the real-time data collected by the fire detector and the stored historical fire data.
In particular, in order to further improve the accuracy of fire early warning so that a fire can be detected at an early stage of occurrence, it is required to improve attention to environmental changes at the early stage of occurrence of the fire. Therefore, historical fire data are trained and stored in the detection equipment, so that the detected real-time data and the historical data are compared conveniently, the historical data with the highest similarity to the real-time data are found, and then the current fire situation is predicted according to the known fire occurrence situation corresponding to the historical data.
The historical fire data comprises fire scene data of different levels and fire labels for marking whether fire occurs in the fire scene data of each level. The historical fire data is composed of scene data of a preset fire class. For example, a large amount of historical fire data is composed of scene data of 20 different fire levels, the scene data of each level corresponds to the size of a fire, the level can correspond to the increasing condition of the fire by the increasing sequence, and the fire is larger when the level is larger. Each scene data is detector data reflecting a period of time to reflect changes in the surrounding environment. In the embodiment of the invention, according to the size of fire, each grade of data is marked with a label for judging whether fire occurs, and in order to more accurately find early fire, for the condition that the temperature or smoke change is extremely small and can be ignored, the corresponding historical data label is that no fire occurs; other data labels of each grade with fire suspicion are fire occurrence. And then carrying out similarity analysis according to the real-time data and the 20 scene data with different grades to obtain a similarity value representing the similarity degree of the real-time data and each scene data. And sequentially screening out a preset number of fire scene data according to the arrangement sequence of the similarity values from large to small, and obtaining the corresponding fire labels. For example, the scene data are ranked from top to bottom according to the similarity degree as levels 5, 6, 7, 8, 4, 3, 9, 2, 1, 10, and 11, and the most similar 3 groups of data are selected as the scene data corresponding to the levels 5, 6, and 7. And then obtaining fire labels corresponding to the selected data, and obtaining a preliminary early warning result according to the result corresponding to the most fire labels. For example, the fire labels corresponding to the scene data of the classes 5, 6, and 7 are no fire, and fire. And if the fire label corresponding to the most fire labels is the fire, judging that the preliminary early warning result is the fire. The method not only can discover the fire condition early according to the environmental change trend, but also reduces the false alarm rate of the fire.
Then, in order to further improve the reliability of the method provided by the embodiment of the present invention, the monitored target area includes a plurality of fire detectors, the division is performed based on the preliminary early warning results of the fire detectors, and more than half of the preliminary early warning results are used as the preliminary early warning results of the monitored target area. Specifically, for example, 10 fire detectors are previously installed in a target area, and monitoring is performed by the above method, wherein 7 fire detectors have a fire occurrence result and 3 fire detectors have no fire occurrence result, and then the target area takes the fire occurrence as a preliminary warning result.
The embodiment of the invention adopts DWT (Dynamic Time Warping) algorithm to carry out similarity analysis, supposing that the system has p fire detectors in total, the sampling interval is 1s, and the data set of the multiple detectors is X ═ X { (X) 1 ,…x j ,…x p }，x j ＝{x j (i) I ═ 1, … T } represents the data for the jth detector at period T, j ∈ {1, …, p }. For p fire detectors, there are N sets of sample data for different scenes (no fire and different stages of fire), namely: x train ＝{X 1 ,…X n ,…X N And Y train ＝{Y 1 ,…Y n ,…Y N In which X is n ＝{x n1 ,…x nj ,…x np Denotes the nth set of sample data, Y n And e {0,1} represents the fire state corresponding to the nth group of training sample data, 0 represents no fire, 1 represents fire, and N belongs to {1, …, N }.
The embodiment of the invention will be based on the newly acquired data X of each detector new ＝{x new1 ,…x newj ,…x newp }，x newj ＝{x newj (i) E R, i is t-w …, t-1, t (w represents the number of data before the moment in the new state analysis), and the Y corresponding to the prediction is adopted by combining the sample data new And e, the fire state of {0,1}, and calculating a path with the minimum regular cost of the data of the new acquisition mode and the historical training sample data by using the following formula.
Wherein smaller paths represent higher similarity. And then, based on a proximity algorithm, a method for determining a preliminary early warning result according to the fire label is provided.
Step S103: and outputting a final early warning result based on the condition that the same type of early warning results continuously appear in the preliminary early warning results. Monitoring whether a result of fire occurrence occurs in the process of continuously outputting the preliminary early warning result, and when the fire occurrence occurs in the continuously monitored preliminary early warning result, acquiring an early warning result at a subsequent continuous time by taking the early warning time of the fire occurrence as a reference; when the early warning result of the fire hazard continuously appears from the next moment and the appearing times of the early warning result reach the preset early warning times, generating the final early warning result of the fire hazard; and when the early warning result of the fire is continuously generated from the next moment, but the occurrence frequency of the early warning result does not reach the preset early warning frequency when the continuous occurrence process of the early warning result is finished, or the early warning result of the fire is not generated from the next moment, generating a final early warning result of the non-fire and returning to the step of monitoring whether the result of the fire is generated in the process of continuously outputting the primary early warning result.
Specifically, the early warning method provided by the embodiment of the invention is further optimized. And in the process of continuously outputting the preliminary early warning result, continuously recording the result, and counting the maximum continuous times of fire early warning which is judged to occur. Namely, when the 'fire occurrence' occurs in the continuously monitored preliminary early warning result, acquiring the early warning result of the subsequent continuous time by taking the early warning time of the 'fire occurrence' as a reference; in the first case: when the early warning result of 'fire occurrence' continuously appears from the next moment and the occurrence frequency reaches the preset early warning frequency, generating and broadcasting the final early warning result of 'fire occurrence'; in the second case: when the early warning result of 'fire occurrence' continuously appears from the next moment, but the occurrence frequency of the early warning result does not reach the preset early warning frequency when the continuous occurrence process is finished, the early warning result is judged to be 'no fire occurrence'; in the third case: if the early warning result of the occurrence of a fire does not occur from the next time, it is determined that "no fire has occurred". And generating a final early warning result of 'no fire' in the second situation and the third situation, returning to the initial monitoring process step, and continuously monitoring whether the early warning result of 'fire' appears in the process of continuously outputting the initial early warning result.
For example, the number k of fire alarms is preset to be 3, in the process of monitoring fire early warning, once a "fire occurrence" alarm occurs, the system highly pays attention to the subsequent alarm result, if the "fire occurrence" alarm also occurs from the next moment and continuously occurs, and the occurrence number reaches 3 times or more than 3 times continuously, the fire occurrence is the final early warning result. If the alarm of 'no fire occurrence' is output at the next moment, or the continuous output of the alarm of 'fire occurrence' is interrupted only twice, the system outputs the final early warning result of 'no fire occurrence', returns to the monitoring step of the step S103, restarts to monitor the preliminary early warning result, and enters the next round of evaluation. Through the processing of the steps, the false alarm rate of the early warning method is further reduced.
Specifically, in an embodiment, the fire early warning method further includes the following steps:
step S104: and obtaining an evaluation index of the fire early warning method by using the final early warning result.
Step S105: and generating an evaluation result according to the evaluation index.
Specifically, a calibration part is arranged for the early warning method, and the early warning strategy is flexibly adjusted, so that the reliability of the method is improved. The embodiment of the invention adopts but is not limited to two indexes of fire start time precision and fire alarm false alarm rate. Wherein, the precision of the fire start time is as follows:
FSTA＝|TFST-EFST|
FSTA＝|TFST-EFST|
TFST refers to the time when a real fire starts, and EFST refers to the time when a fire starts, namely the time when a fire alarm signal is sent out, which is predicted by a prediction algorithm, and the prediction process is not repeated in the invention.
Wherein, the false alarm rate of fire alarm is:
y (t) belongs to {0,1}, which represents the actual fire state at the time t, 0 represents no fire, and 1 represents fire;
indicating the predicted fire state at time t, 0 indicating no fire, and 1 indicating fire.
The embodiment of the invention adopts a dictionary-like optimized file, wherein the reason of the abnormal condition and the common solution are recorded. And aiming at the abnormal conditions of the two indexes, generating an evaluation result by inquiring the optimization file so as to formulate a corresponding optimization strategy. According to the description of the optimized archive, if the FSTA time is greater than the preset threshold (in the embodiment of the present invention, 60s is adopted, and the FSTA time can be adjusted according to the actual situation), the main reasons and solutions for causing the accuracy decrease are as follows: the sensitivity of the detector is low due to aging and the like, and the detector needs to be replaced; the number of detectors arranged in fire key areas is small, early-stage fire abnormal data cannot be timely obtained, and the arrangement number of the detectors needs to be increased; the detector common mode fault adopts detectors of different models to replace the existing detector; the sample training data is insufficient, the fire state data information of the whole period and the whole process is supplemented, the similarity recognition algorithm precision is reduced, and the dimension (detector number) parameters are adjusted to improve the algorithm precision. If the false alarm rate of the fire alarm is greater than the preset threshold (10% is adopted in the embodiment of the invention, the false alarm rate can be adjusted according to the actual situation), the main reasons and the solving methods caused by the false alarm rate of the fire alarm are as follows: temporary disturbance causes false alarms (personnel smoke, gas stove starting and the like), and effective measures should be taken for locking; the extreme environment temperature condition can be dynamically adjusted with the ambient environment temperature; when the detector fails, replacing the new detector; the precision of the similarity identification algorithm is reduced, and the dimension (detector number) parameters are adjusted to improve the precision of the algorithm. In addition, trend comparison is carried out on the same type of detectors, the fault condition of the detectors is dynamically detected in real time, for example, 3 same type of temperature detectors exist in one room, but the distances between the detectors and an ignition point are different, when a fire disaster occurs, the temperatures of the three temperature detectors all rise, but the closer the temperature rise is faster, the longer the distance reaction time is, the slow rise is shown, although the response times of the three temperature detectors are different, the temperatures all rise stably, false alarm is avoided when a single sensor fault occurs, alarm can be prompted after two temperature sensors are identified to be heated stably, and therefore the fault of the detectors is judged in real time. According to fire alarm performance evaluation indexes, early-stage data and experience accumulation are combined, system optimization improvement suggestions are given regularly, system prediction accuracy is improved, and false alarm rate is reduced.
By executing the steps, the fire early warning method provided by the embodiment of the invention comprises the following steps: the method comprises the steps of obtaining real-time data of the current time and a plurality of previous times of a fire, and carrying out similarity analysis on the real-time data and prestored historical data representing different fire grades, so that whether a fire happens in a target area or not is obtained according to labels corresponding to a plurality of historical data with the highest similarity. By combining historical data, wrong conclusions caused by data mutation are avoided, the robustness of the whole method is improved, slight changes before fire disaster occur are reflected in advance by combining the historical data, early warning can be given out when the fire disaster is in a weak fire disaster grade, the time delay of fire early warning is reduced, and the fire early warning accuracy is improved. And then, selecting the early warning results which account for more than half of the detectors through a voting mechanism, and comprehensively analyzing the early warning results which are continuously predicted for multiple times to further reduce the false alarm rate. A part for evaluating the fire early warning method according to the fire early warning evaluation index is added, problems in the method are adjusted in time, and the reliability of the method is improved.
As shown in fig. 3, the present embodiment also provides a fire early warning system, which can be applied to an electronic device, and includes:
and the data acquisition module 101 is used for acquiring real-time data acquired by the fire detector in the monitored target area. For details, refer to the related description of step S101 in the above method embodiment, and no further description is provided here.
And the preliminary early warning module 102 outputs a preliminary early warning result of the monitored target area according to the similarity degree of the real-time data collected by the fire detector and the stored historical fire data. For details, refer to the related description of step S102 in the above method embodiment, and no further description is provided here.
And the final early warning module 103 outputs a final early warning result based on the condition that the same type of early warning results continuously appear in the preliminary early warning results. For details, refer to the related description of step S103 in the above method embodiment, and no further description is provided here.
Specifically, in an embodiment, the system further includes:
and the calibration module 104 acquires the evaluation index of the fire early warning method by using the final early warning result, and generates an evaluation result according to the evaluation index. For details, refer to the related descriptions of steps S104 to S105 in the above method embodiments, and are not repeated herein.
The fire early warning system provided by the embodiment of the invention is used for executing the fire early warning method provided by the embodiment, the implementation manner and the principle of the fire early warning system are the same, and the detailed contents refer to the related description of the method embodiment and are not repeated.
Through the cooperative cooperation of the components, the fire early warning system provided by the embodiment of the invention. The method comprises the steps of obtaining real-time data of the current time and a plurality of previous times of a fire, and carrying out similarity analysis on the real-time data and prestored historical data representing different fire grades, so that whether a fire happens in a target area or not is obtained according to labels corresponding to a plurality of historical data with the highest similarity. By combining historical data, wrong conclusions caused by data mutation are avoided, the robustness of the whole system is improved, slight changes before fire disaster occur are reflected in advance by combining the historical data, early warning can be given out when the fire disaster is in a weak fire disaster grade, the time delay of fire early warning is reduced, and the fire early warning accuracy is improved. And then, selecting the early warning results which account for more than half of the detectors through a voting mechanism, and comprehensively analyzing the early warning results which are continuously predicted for multiple times to further reduce the false alarm rate. The fire early warning system evaluation part is added according to the fire early warning evaluation index, problems in the system are adjusted in time, and the reliability of the system is improved.
Fig. 4 shows an electronic device of an embodiment of the invention, the device comprising: the processor 901 and the memory 902 may be connected by a bus or other means, and fig. 4 illustrates an example of a connection by a bus.
The memory 902, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the methods in the above-described method embodiments. The processor 901 executes various functional applications and data processing of the processor by executing non-transitory software programs, instructions and modules stored in the memory 902, that is, implements the methods in the above-described method embodiments.
The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 901, and the like. Further, the memory 902 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 902 may optionally include memory located remotely from the processor 901, which may be connected to the processor 901 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more modules are stored in the memory 902, which when executed by the processor 901 performs the methods in the above-described method embodiments.
The specific details of the electronic device may be understood by referring to the corresponding related descriptions and effects in the above method embodiments, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, and the implemented program can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (9)
1. A fire early warning method, comprising:
acquiring real-time data acquired by a fire detector in a monitored target area;
acquiring pre-stored historical fire data, wherein the historical fire data comprises fire scene data of different levels and fire labels for marking whether fire occurs in the fire scene data of each level;
respectively determining the similarity degree of the real-time data and the fire scene data of each grade in the historical fire data;
sequentially screening out a preset number of fire scene data according to the arrangement sequence of the similarity degrees from large to small, obtaining fire labels corresponding to the fire scene data, and obtaining a preliminary early warning result of the monitored target area according to the early warning results corresponding to the same fire labels at most;
and outputting a final early warning result based on the condition that the same type of early warning results continuously appear in the preliminary early warning results.
2. The method of claim 1, wherein a plurality of fire detectors are included in the monitored target area, and the outputting of the preliminary warning result of the monitored target area according to the similarity between the real-time data collected by the fire detectors and the stored historical fire data further comprises:
and dividing the preliminary early warning results based on the preliminary early warning results of the fire detectors, and taking more than half of the preliminary early warning results as the preliminary early warning results of the monitored target area.
3. The method of claim 1, wherein outputting a final early warning result based on the continuous occurrence of the same type of early warning results in the preliminary early warning results comprises:
monitoring whether a result of fire occurrence occurs in the process of continuously outputting the preliminary early warning result, and when the fire occurrence occurs in the continuously monitored preliminary early warning result, acquiring an early warning result at a subsequent continuous time by taking the early warning time of the fire occurrence as a reference;
when the early warning result of the fire hazard continuously appears from the next moment and the appearing times of the early warning result reach the preset early warning times, generating the final early warning result of the fire hazard;
and when the early warning result of the fire is continuously generated from the next moment, but the occurrence frequency of the early warning result does not reach the preset early warning frequency when the continuous occurrence process of the early warning result is finished, or the early warning result of the fire is not generated from the next moment, generating a final early warning result of the non-fire and returning to the step of monitoring whether the result of the fire is generated in the process of continuously outputting the primary early warning result.
4. The method of claim 1, further comprising:
obtaining an evaluation index of the fire early warning method by using the final early warning result;
and generating an evaluation result according to the evaluation index.
5. The method of claim 4, wherein evaluating the metrics comprises at least: accuracy of fire onset time and false fire alarm rate.
6. The method of claim 1, wherein the real-time data includes detection data collected by the fire detector at a current time and a predetermined number of times before the current time.
7. A fire early warning system, the system comprising:
the data acquisition module is used for acquiring real-time data acquired by a fire detector in a monitored target area;
the early warning system comprises a preliminary early warning module, a data processing module and a data processing module, wherein the preliminary early warning module is used for acquiring pre-stored historical fire data, and the historical fire data comprises fire scene data of different levels and fire labels for marking whether fire occurs in the fire scene data of each level; respectively determining the similarity degree of the real-time data and the fire scene data of each grade in the historical fire data; sequentially screening out a preset number of fire scene data according to the arrangement sequence of the similarity degrees from large to small, obtaining fire labels corresponding to the fire scene data, and obtaining a preliminary early warning result of the monitored target area according to the early warning results corresponding to the same fire labels at most;
and the final early warning module is used for outputting a final early warning result based on the condition that the same type of early warning results continuously appear in the initial early warning results.
8. The system of claim 7, further comprising:
and the calibration module acquires an evaluation index by using the final early warning result and generates an evaluation result according to the evaluation index.
9. An electronic device, comprising:
a memory and a processor communicatively coupled to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110776539.6A CN113516820B (en) | 2021-07-09 | 2021-07-09 | Fire early warning method and fire early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110776539.6A CN113516820B (en) | 2021-07-09 | 2021-07-09 | Fire early warning method and fire early warning system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113516820A CN113516820A (en) | 2021-10-19 |
| CN113516820B true CN113516820B (en) | 2022-08-02 |
Family
ID=78066740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110776539.6A Active CN113516820B (en) | 2021-07-09 | 2021-07-09 | Fire early warning method and fire early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113516820B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114333214A (en) * | 2021-12-30 | 2022-04-12 | 国能创新油品销售有限公司 | Fire early warning method and device for oil storage tank, electronic equipment and medium |
| CN115083131A (en) * | 2022-05-18 | 2022-09-20 | 浙江台谊消防股份有限公司 | Fire alarm control system |
| CN115359615B (en) * | 2022-08-15 | 2023-08-04 | 北京飞讯数码科技有限公司 | Indoor fire alarm early warning method, system, device, equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0381898A (en) * | 1989-08-25 | 1991-04-08 | Nohmi Bosai Ltd | Accumulation type fire alarm device |
| JPH11353564A (en) * | 1998-06-04 | 1999-12-24 | Nohmi Bosai Ltd | Difference type fire alarm system |
| JP2001067557A (en) * | 1999-08-24 | 2001-03-16 | Matsushita Electric Works Ltd | Fire sensor and tester for fire sensor |
| CN209885073U (en) * | 2019-05-14 | 2020-01-03 | 安阳工学院 | Intelligence extinguishing device based on single chip microcomputer control |
| JP2020160779A (en) * | 2019-03-26 | 2020-10-01 | 能美防災株式会社 | Heat detector and fire determination method with the same |
| CN112614295A (en) * | 2020-12-14 | 2021-04-06 | 云南电网有限责任公司电力科学研究院 | Fire monitoring and early warning system based on intelligent sensing terminal |
-
2021
- 2021-07-09 CN CN202110776539.6A patent/CN113516820B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0381898A (en) * | 1989-08-25 | 1991-04-08 | Nohmi Bosai Ltd | Accumulation type fire alarm device |
| JPH11353564A (en) * | 1998-06-04 | 1999-12-24 | Nohmi Bosai Ltd | Difference type fire alarm system |
| JP2001067557A (en) * | 1999-08-24 | 2001-03-16 | Matsushita Electric Works Ltd | Fire sensor and tester for fire sensor |
| JP2020160779A (en) * | 2019-03-26 | 2020-10-01 | 能美防災株式会社 | Heat detector and fire determination method with the same |
| CN209885073U (en) * | 2019-05-14 | 2020-01-03 | 安阳工学院 | Intelligence extinguishing device based on single chip microcomputer control |
| CN112614295A (en) * | 2020-12-14 | 2021-04-06 | 云南电网有限责任公司电力科学研究院 | Fire monitoring and early warning system based on intelligent sensing terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113516820A (en) | 2021-10-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113516820B (en) | Fire early warning method and fire early warning system | |
| CN110113226B (en) | Method and device for detecting equipment abnormity | |
| US10719577B2 (en) | System analyzing device, system analyzing method and storage medium | |
| US20070239629A1 (en) | Cluster Trending Method for Abnormal Events Detection | |
| JP2006105142A (en) | Fault detection method for device and fault detection/separation system | |
| US10581665B2 (en) | Content-aware anomaly detection and diagnosis | |
| KR101893563B1 (en) | Black-box System and operating method thereof based on Internet Of Things | |
| JP2019522297A (en) | Method and system for finding precursor subsequences in time series | |
| CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN111986436B (en) | Comprehensive flame detection method based on ultraviolet and deep neural networks | |
| CN111400850A (en) | Equipment fault analysis method, device, equipment and storage medium | |
| KR20070015703A (en) | Apparatus and method for detecting fire using image processing | |
| KR101876185B1 (en) | Learning method on recent data considering external effect in early alarm system, and system using thereof | |
| US20160275407A1 (en) | Diagnostic device, estimation method, non-transitory computer readable medium, and diagnostic system | |
| CN209433517U (en) | It is a kind of based on more flame images and the fire identification warning device for combining criterion | |
| JP4886461B2 (en) | Abnormality monitoring device | |
| CN111314110B (en) | Fault early warning method for distributed system | |
| Rammohan et al. | Exploratory investigations for intelligent damage prognosis using hidden Markov models | |
| KR102250200B1 (en) | Gateway apparatus, and control method thereof | |
| US20150347213A1 (en) | Apparatus and method for system monitoring | |
| US10921167B1 (en) | Methods and apparatus for validating event scenarios using reference readings from sensors associated with predefined event scenarios | |
| KR101971553B1 (en) | Device management system and method based on Internet Of Things | |
| CN117373198B (en) | Parking lot alarm monitoring method, device and storage medium | |
| Al-Saleh et al. | Towards an Autonomous Radiation Early Warning System. | |
| JP7359009B2 (en) | Data analysis device, program and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |