CN117218786B - Fire intelligent monitoring and early warning system and method based on Internet of things - Google Patents
Fire intelligent monitoring and early warning system and method based on Internet of things Download PDFInfo
- Publication number
- CN117218786B CN117218786B CN202311276735.2A CN202311276735A CN117218786B CN 117218786 B CN117218786 B CN 117218786B CN 202311276735 A CN202311276735 A CN 202311276735A CN 117218786 B CN117218786 B CN 117218786B
- Authority
- CN
- China
- Prior art keywords
- fire
- monitoring
- early warning
- alarm prompt
- fire monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 310
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000008859 change Effects 0.000 claims abstract description 47
- 230000005856 abnormality Effects 0.000 claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 230000007246 mechanism Effects 0.000 claims abstract description 13
- 238000009960 carding Methods 0.000 claims abstract description 10
- 238000011835 investigation Methods 0.000 claims abstract description 8
- 238000007726 management method Methods 0.000 claims description 55
- 238000012545 processing Methods 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 17
- 238000013523 data management Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000013070 change management Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Fire Alarms (AREA)
Abstract
The invention relates to the technical field of fire intelligent supervision, in particular to a fire intelligent monitoring and early warning system and method based on the Internet of things, comprising the steps of building a fire monitoring and early warning platform of a target area, building an alarm mechanism of the fire monitoring and early warning platform, collecting all historical alarm prompt records sent by the fire monitoring and early warning platform to a management terminal, evaluating influence characteristic values and classifying events of fire alarm events corresponding to the historical alarm prompt records, and carrying out information carding on monitoring data change trend curves of fire monitoring sensors in the fire alarm events; performing abnormality analysis of alarm prompts on each history alarm prompt record in each history alarm prompt record set, and performing abnormality marking on related fire monitoring sensors; and performing performance evaluation on each fire monitoring sensor, and sending prompt feedback to a manager by the fire monitoring sensors needing performance investigation.
Description
Technical Field
The invention relates to the technical field of intelligent fire monitoring and early warning, in particular to an intelligent fire monitoring and early warning system and method based on the Internet of things.
Background
The intelligent fire control is a new fire control management mode for realizing the intellectualization, informatization and scientification of fire prevention and control by utilizing new generation information technology means such as the Internet of things, cloud computing and big data. In recent years, along with the acceleration of the urban process, the increase of high-rise buildings, the aggravation of traffic jams and other problems, the fire risk is increased, and the importance of intelligent fire protection is increasingly prominent;
The fire monitoring and early warning platform combines various sensors, monitoring equipment and intelligent algorithms according to the characteristics and development rules of the fire, and an intelligent system for real-time monitoring, early warning and emergency treatment of the fire is realized.
Disclosure of Invention
The invention aims to provide an intelligent fire monitoring and early warning system and method based on the Internet of things, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a fire intelligent monitoring and early warning method based on the Internet of things comprises the following steps:
Step S100: building a fire monitoring and early warning platform of a target area, wherein the fire monitoring and early warning platform comprises a plurality of fire monitoring sensors, an alarm mechanism of the fire monitoring and early warning platform is built, and the alarm mechanism comprises that when monitoring data transmitted by the plurality of fire monitoring sensors show a data distribution rule when fire danger can be initiated at a certain moment, the fire monitoring and early warning platform sends an alarm prompt to a management terminal, and a fire early warning event is judged to occur in the current target area;
Step S200: collecting all historical alarm prompt records sent by a fire monitoring and early warning platform to a management terminal, combing fire processing data in each historical alarm prompt record, and carrying out evaluation and event classification of influence characteristic values on fire early warning events corresponding to each historical alarm prompt record according to the fire processing data to obtain a plurality of historical alarm prompt record sets; wherein, one history alarm prompt record set corresponds to one type of fire early warning event;
Step S300: respectively constructing a monitoring data change trend curve for each fire monitoring sensor in each history alarm prompt record set, and carrying out information carding on the monitoring data change trend curve of each fire monitoring sensor in each fire early warning event;
Step S400: based on the change trend curve information of the monitoring data of each fire monitoring sensor in each fire early warning event, carrying out abnormal analysis of alarm prompts on each history alarm prompt record in each history alarm prompt record set, and carrying out abnormal marking on the related fire monitoring sensors involved in the abnormal analysis process;
Step S500: based on the abnormal mark information distribution condition of each fire monitoring sensor, performance evaluation is carried out on each fire monitoring sensor, and prompt feedback is sent to management personnel by the fire monitoring sensors needing performance investigation.
Further, step S200 includes:
step S201: acquiring a time stamp T r of an alarm prompt sent by a fire monitoring and early warning platform to a management terminal in each historical alarm prompt record, and acquiring a time stamp T s of release of the corresponding alarm prompt, wherein the duration time T=t s-tr of a fire early warning event corresponding to each historical alarm prompt record;
Step S202: acquiring the total number N of fire extinguishing people involved in fire extinguishment in each history alarm prompt record and the total number M of used fire extinguishing devices, respectively acquiring the consumption of the corresponding fire extinguishing agents of M fire extinguishing devices in the fire extinguishment event, normalizing the consumption and accumulating to obtain the total consumption Q in the fire extinguishment event;
the normalization is performed because the types and kinds of fire extinguishing agents are various, so that when the consumption is measured, the consumption of various fire extinguishing agents needs to be quantized into the same evaluation standard;
Step S203: calculating the influence characteristic value beta=T×N×M×Q of the fire early warning event corresponding to each history alarm prompt record respectively; setting a deviation threshold, and judging fire early-warning events corresponding to the two historical alarm prompt records as one type of fire early-warning event when the influence characteristic values of the fire early-warning events corresponding to the two historical alarm prompt records meet the condition that the deviation between the influence characteristic values is smaller than the deviation threshold; fire events of the same category are those that affect the proximity of characteristic values.
Further, step S300 includes:
Step S301: when the fire monitoring and early warning platform sends out alarm prompts to the management terminal, the transmitted monitoring data are displayed on each fire monitoring sensor to obtain an alarm data set of fire early warning events corresponding to any history alarm prompt record; the fire monitoring and early warning platform is arranged in any history alarm prompt record, and the corresponding time stamp is T when the fire monitoring and early warning platform sends an alarm prompt to the management terminal;
Step S302: the method comprises the steps that in any historical alarm prompt record, the monitoring data transmitted by an ith fire monitoring sensor at the time of T is a i, the monitoring data transmitted and displayed by the ith fire monitoring sensor before the time of T are traversed, the number n of unit monitoring data is set, if continuous n monitoring data exist before the time of T, the condition that the condition is met between the continuous n monitoring data is met
A 1-ai|>|a2-ai|>...>|an-ai |, judging that an early warning trend data structure is formed among n continuous monitoring data, wherein a 1、a2、...、an respectively represents 1 st, 2 nd, n-th monitoring data in the n continuous monitoring data, and a corresponding time stamp T 1、t2、...、tn of a 1、a2、...、an meets T 1<t2<...<tn < T; judging that the time stamp t 1 corresponding to the a 1 is a trend starting point of the ith fire monitoring sensor; wherein, n continuous monitoring data refer to n continuous monitoring data with data change, i.e. t 1、t2、...、tn may not be continuous;
Step S303: capturing all pre-warning trend data structures existing in all monitoring data transmitted by the ith fire monitoring sensor before a time stamp T, and extracting trend starting points of all pre-warning trend data structures; collecting all monitoring data between time intervals [ T ', T ] according to monitoring data a i ' corresponding to the minimum trend starting point T ' in the trend starting point, fitting and generating a monitoring data change trend curve presented in the process that the ith fire monitoring sensor displays the transmitted monitoring data a i ' when the monitored data is converted into T and displays the transmitted monitoring data a i when the monitored data is converted from T ', and acquiring the slope of the monitoring data change trend curve of the ith fire monitoring sensor;
Step S304: and in each history alarm prompt record set, acquiring the slope of the monitoring data change trend curve presented by each fire monitoring sensor in each history alarm prompt record, and respectively calculating to obtain the average slope of the monitoring data change trend curve of each fire monitoring sensor in each history alarm prompt record set.
Further, step S400 includes:
Step S401: in each history alarm prompting record set, sequencing each fire monitoring sensor according to the average slope of the change trend curve of the monitoring data of each fire monitoring sensor from large to small to obtain a fire monitoring sensor sequence Y, setting the number M of units, and collecting the first M fire monitoring sensors sequentially selected from the fire monitoring sensor sequence Y to obtain a characteristic sensor set of fire early warning events corresponding to each history alarm prompting record set;
The method is equivalent to capturing a fire monitoring sensor sensitive to the change of the monitoring data in various fire early warning events, and the larger the average slope of the change trend curve of the monitoring data is, the more obvious the change of the monitoring data displayed and transmitted on the fire monitoring sensor is;
Step S402: setting the characteristic sensor set corresponding to the h historical alarm prompting record set U h as Q (h), capturing and collecting all fire monitoring sensors with the slope of a change trend curve presented in the A by corresponding monitoring data for any one historical alarm prompting record A in U h which is smaller than the average slope in a fire early-warning event corresponding to U h to obtain a set W, and extracting the set W' =Q (h) U W;
the method is equivalent to a process of capturing and extracting the sensor which presents abnormal data change in the characteristic sensor;
Step S403: if the average influence characteristic value of the fire disaster early-warning event corresponding to the g-th historical alarm prompt record set U g,Ug is alpha (g), the average influence characteristic value of the fire disaster early-warning event corresponding to U h is alpha (h), the characteristic sensor set of U g is Q (g), and alpha (g) is < alpha (h), Capturing two types of fire early-warning events with the characteristic value data differences, wherein the severity of the fire early-warning event corresponding to U g is smaller than that of the fire early-warning event corresponding to U h, and the characteristic sensor sets presented by the two types of fire early-warning events are overlapped when the fire early-warning events are prompted, so that the process of verifying event relevance between the fire early-warning event corresponding to U g and the fire early-warning event corresponding to U h is realized, and when any one historical alarm prompt record A in U h meets the condition of card [ W' UQ (g) ]/card [ Q (g) ] > delta; performing anomaly marking on all fire monitoring sensors in the set W'; wherein δ is a threshold, and card [ W '. Cndot.Q (g) ] represents the number of elements contained in the set W'. Cndot.Q (g), and card [ Q (g) ] represents the number of elements contained in the set Q (g);
(card [ W'. AndU.Q (g) ]/card [ Q (g) ] calculates that all feature sensors with abnormal data change in the history alarm prompt record A in U h have the larger overlapping ratio with the feature sensor set of Ug, which means that the possibility of alarm prompt delay caused by sensor sensitivity reduction is higher in the history alarm prompt record A, and the occurrence of the fire alarm event corresponding to the history alarm prompt record A is inferred due to the event correlation presented between the fire alarm event corresponding to U g and the fire alarm event corresponding to U h.
Further, step S500 includes:
Step S501: setting the number of accumulated marked anomalies of a certain fire monitoring sensor as R, and setting the total number of history alarm prompt record sets as F; capturing a history alarm prompt record set corresponding to each abnormal mark of a certain fire monitoring sensor, and accumulating the history alarm prompt record set number G related in total in R abnormal marks;
Step S502: and calculating the performance characteristic value O=R× (G/F) of a certain fire monitoring sensor, and when the performance characteristic value of the certain fire monitoring sensor is larger than a threshold value, judging that the certain fire monitoring sensor is the fire monitoring sensor needing performance checking, and sending prompt feedback to a manager.
In order to better realize the method, the intelligent fire monitoring and early warning system is also provided, and comprises a fire monitoring and early warning management module, a fire early warning event data management module, a monitoring data trend change management module, a sensor abnormality mark management module and a sensor performance evaluation management module;
The fire monitoring and early warning management module is used for building a fire monitoring and early warning platform of a target area, the fire monitoring and early warning platform comprises a plurality of fire monitoring sensors, an alarm mechanism of the fire monitoring and early warning platform is built, and the alarm mechanism comprises that when monitoring data transmitted by the plurality of fire monitoring sensors show a data distribution rule when fire danger can be initiated at a certain moment, the fire monitoring and early warning platform sends an alarm prompt to the management terminal, and a fire early warning event occurs in the current target area is judged;
The fire early-warning event data management module is used for collecting all the historical alarm prompt records sent by the fire monitoring early-warning platform to the management terminal, combing fire processing data in each historical alarm prompt record, and carrying out evaluation and event classification of influence characteristic values on fire early-warning events corresponding to each historical alarm prompt record according to the fire processing data to obtain a plurality of historical alarm prompt record sets; wherein, one history alarm prompt record set corresponds to one type of fire early warning event;
The monitoring data trend change management module is used for respectively constructing monitoring data change trend curves for the fire monitoring sensors in each history alarm prompt record set and carrying out information carding on the monitoring data change trend curves of the fire monitoring sensors in each fire early warning event;
The sensor abnormality mark management module is used for carrying out abnormality analysis of alarm prompts on each history alarm prompt record in each history alarm prompt record set based on the change trend curve information of the monitoring data of each fire monitoring sensor in each fire early warning event and carrying out abnormality mark on the related fire monitoring sensor involved in the abnormality analysis process;
The sensor performance evaluation management module is used for performing performance evaluation on each fire monitoring sensor based on the abnormal mark information distribution condition of each fire monitoring sensor, and sending prompt feedback to management personnel from the fire monitoring sensors needing performance investigation.
Further, the fire early-warning event data management module comprises an influence characteristic value calculation unit and a fire early-warning event classification management unit;
The influence characteristic value calculation unit is used for collecting all the history alarm prompt records sent by the fire monitoring and early warning platform to the management terminal, carding fire processing data in each history alarm prompt record, and evaluating the influence characteristic value of the fire early warning event corresponding to each history alarm prompt record according to the fire processing data;
The fire early warning event classifying management unit is used for receiving the data in the influence characteristic value calculation unit, classifying all the historical alarm prompt records and obtaining a plurality of historical alarm prompt record sets; one of the history alarm prompt record sets corresponds to one type of fire early warning event.
Further, the sensor abnormality mark management module comprises a trend abnormality analysis unit and an abnormality mark processing unit;
The trend anomaly analysis unit is used for carrying out anomaly analysis of alarm prompts on each historical alarm prompt record in each historical alarm prompt record set based on the change trend curve information of the monitoring data of each fire monitoring sensor in each fire early warning event;
The abnormality mark processing unit is used for performing abnormality mark on related fire monitoring sensors involved in the abnormality analysis process.
Compared with the prior art, the application has the following beneficial effects: according to the fire alarm system, the fire processing data presented in each historical alarm prompt record are evaluated, the influence degree value of the fire early-warning event corresponding to each historical alarm prompt record is measured, and classification and division processing of all the historical alarm prompt records is realized; according to the application, trend analysis of monitoring data is developed for each fire early-warning event in the history alarm prompt record sets corresponding to each degree level obtained after division, the history alarm prompt record which possibly has alarm prompt delay is captured based on the change trend of the monitoring data displayed by the sensor transmission in each history alarm prompt record set, and abnormal analysis is developed in the related sensor, so that performance monitoring of the fire monitoring sensor is realized, alarm timeliness and accuracy of a fire monitoring early-warning platform are improved, and efficient supervision of the fire monitoring sensor in the fire monitoring early-warning platform is realized.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow diagram of an intelligent fire monitoring and early warning method based on the Internet of things;
Fig. 2 is a schematic structural diagram of an intelligent fire monitoring and early warning system based on the internet of things.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions: a fire intelligent monitoring and early warning method based on the Internet of things comprises the following steps:
Step S100: building a fire monitoring and early warning platform of a target area, wherein the fire monitoring and early warning platform comprises a plurality of fire monitoring sensors, an alarm mechanism of the fire monitoring and early warning platform is built, and the alarm mechanism comprises that when monitoring data transmitted by the plurality of fire monitoring sensors show a data distribution rule when fire danger can be initiated at a certain moment, the fire monitoring and early warning platform sends an alarm prompt to a management terminal, and a fire early warning event is judged to occur in the current target area; for example, the presentation form of the alarm prompt can adopt an audible and visual alarm, so that a manager can be reminded obviously;
Step S200: collecting all historical alarm prompt records sent by a fire monitoring and early warning platform to a management terminal, combing fire processing data in each historical alarm prompt record, and carrying out evaluation and event classification of influence characteristic values on fire early warning events corresponding to each historical alarm prompt record according to the fire processing data to obtain a plurality of historical alarm prompt record sets; wherein, one history alarm prompt record set corresponds to one type of fire early warning event;
wherein, step S200 includes:
step S201: acquiring a time stamp T r of an alarm prompt sent by a fire monitoring and early warning platform to a management terminal in each historical alarm prompt record, and acquiring a time stamp T s of release of the corresponding alarm prompt, wherein the duration time T=t s-tr of a fire early warning event corresponding to each historical alarm prompt record;
Step S202: acquiring the total number N of fire extinguishing people involved in fire extinguishment in each history alarm prompt record and the total number M of used fire extinguishing devices, respectively acquiring the consumption of the corresponding fire extinguishing agents of M fire extinguishing devices in the fire extinguishment event, normalizing the consumption and accumulating to obtain the total consumption Q in the fire extinguishment event;
Step S203: calculating the influence characteristic value beta=T×N×M×Q of the fire early warning event corresponding to each history alarm prompt record respectively; setting a deviation threshold, and judging that fire early-warning events corresponding to the two historical alarm prompt records are one type of fire early-warning event when the influence characteristic values of the fire early-warning events corresponding to the two historical alarm prompt records meet the condition that the deviation between the influence characteristic values is smaller than the deviation threshold.
Step S300: respectively constructing a monitoring data change trend curve for each fire monitoring sensor in each history alarm prompt record set, and carrying out information carding on the monitoring data change trend curve of each fire monitoring sensor in each fire early warning event;
Wherein, step S300 includes:
Step S301: when the fire monitoring and early warning platform sends out alarm prompts to the management terminal, the transmitted monitoring data are displayed on each fire monitoring sensor to obtain an alarm data set of fire early warning events corresponding to any history alarm prompt record; the fire monitoring and early warning platform is arranged in any history alarm prompt record, and the corresponding time stamp is T when the fire monitoring and early warning platform sends an alarm prompt to the management terminal;
Step S302: the method comprises the steps that in any historical alarm prompt record, the monitoring data transmitted by an ith fire monitoring sensor at the time of T is a i, the monitoring data transmitted and displayed by the ith fire monitoring sensor before the time of T are traversed, the number n of unit monitoring data is set, if continuous n monitoring data exist before the time of T, the condition that the condition is met between the continuous n monitoring data is met
A 1-ai|>|a2-ai|>...>|an-ai |, judging that an early warning trend data structure is formed among n continuous monitoring data, wherein a 1、a2、...、an respectively represents 1 st, 2 nd, n-th monitoring data in the n continuous monitoring data, and a corresponding time stamp T 1、t2、...、tn of a 1、a2、...、an meets T 1<t2<...<tn < T; judging that the time stamp t 1 corresponding to the a 1 is a trend starting point of the ith fire monitoring sensor;
Generally, when the temperature displayed by the temperature sensing constant temperature sensor in the fire monitoring and early warning platform is set at about 57 ℃, an alarm signal is sent; for example, n=6, t=19:00, and when the temperature-sensitive constant temperature sensor is traversed by transmitting the displayed monitoring data before 19:00, the continuous 6 monitoring data are captured at 36 ℃, 39 ℃, 43 ℃, 46 ℃, 52 ℃, 55 ℃; the time points corresponding to 36 ℃, 39 ℃, 43 ℃, 46 ℃, 52 ℃ and 55 ℃ are 16:35, 16:43, 16:46, 16:50, 16:52 and 16:57 respectively;
because the temperature of the alloy meets the requirements of |36-57 ℃ | > 39-57 ℃ | > 43-57 ℃ | > 46-57 ℃ | > 52 DEG C
-57 ℃ | > 55 ℃ -57 ℃ |, So that an early warning trend data structure is formed between the continuous 6 monitoring data; the time stamp 16:35 corresponding to 36 ℃ is a trend starting point of the temperature sensing constant temperature sensor in the early warning trend data structure;
Step S303: capturing all pre-warning trend data structures existing in all monitoring data transmitted by the ith fire monitoring sensor before a time stamp T, and extracting trend starting points of all pre-warning trend data structures; collecting all monitoring data between time intervals [ T ', T ] according to monitoring data a i ' corresponding to the minimum trend starting point T ' in the trend starting point, fitting and generating a monitoring data change trend curve presented in the process that the ith fire monitoring sensor displays the transmitted monitoring data a i ' when the monitored data is converted into T and displays the transmitted monitoring data a i when the monitored data is converted from T ', and acquiring the slope of the monitoring data change trend curve of the ith fire monitoring sensor;
step S304: in each history alarm prompting record set, acquiring the slope of the monitoring data change trend curve presented by each fire monitoring sensor in each history alarm prompting record, and respectively calculating to obtain the average slope of the monitoring data change trend curve of each fire monitoring sensor in each history alarm prompting record set;
Step S400: based on the change trend curve information of the monitoring data of each fire monitoring sensor in each fire early warning event, carrying out abnormal analysis of alarm prompts on each history alarm prompt record in each history alarm prompt record set, and carrying out abnormal marking on the related fire monitoring sensors involved in the abnormal analysis process;
wherein, step S400 includes:
Step S401: in each history alarm prompting record set, sequencing each fire monitoring sensor according to the average slope of the change trend curve of the monitoring data of each fire monitoring sensor from large to small to obtain a fire monitoring sensor sequence Y, setting the number M of units, and collecting the first M fire monitoring sensors sequentially selected from the fire monitoring sensor sequence Y to obtain a characteristic sensor set of fire early warning events corresponding to each history alarm prompting record set;
Step S402: setting the characteristic sensor set corresponding to the h historical alarm prompting record set U h as Q (h), capturing and collecting all fire monitoring sensors with the slope of a change trend curve presented in the A by corresponding monitoring data for any one historical alarm prompting record A in U h which is smaller than the average slope in a fire early-warning event corresponding to U h to obtain a set W, and extracting the set W' =Q (h) U W;
Step S403: if the average influence characteristic value of the fire disaster early-warning event corresponding to the g-th historical alarm prompt record set U g,Ug is alpha (g), the average influence characteristic value of the fire disaster early-warning event corresponding to U h is alpha (h), the characteristic sensor set of U g is Q (g), and alpha (g) is < alpha (h), When any one history alarm prompt record A in U h meets the requirements of card [ W'. U.Q (g) ]/card [ Q (g) ] > delta; performing anomaly marking on all fire monitoring sensors in the set W'; where δ is a threshold, and card [ W '. Cndot.Q (g) ] represents the number of elements contained in set W'. Cndot.Q (g), and card [ Q (g) ] represents the number of elements contained in set Q (g).
Step S500: based on the abnormal mark information distribution condition of each fire monitoring sensor, performing performance evaluation on each fire monitoring sensor, and sending prompt feedback to a manager by the fire monitoring sensor needing performance investigation;
Wherein, step S500 includes:
Step S501: setting the number of accumulated marked anomalies of a certain fire monitoring sensor as R, and setting the total number of history alarm prompt record sets as F; capturing a history alarm prompt record set corresponding to each abnormal mark of a certain fire monitoring sensor, and accumulating the history alarm prompt record set number G related in total in R abnormal marks;
Step S502: and calculating the performance characteristic value O=R× (G/F) of a certain fire monitoring sensor, and when the performance characteristic value of the certain fire monitoring sensor is larger than a threshold value, judging that the certain fire monitoring sensor is the fire monitoring sensor needing performance checking, and sending prompt feedback to a manager.
In order to better realize the method, the intelligent fire monitoring and early warning system is also provided, and comprises a fire monitoring and early warning management module, a fire early warning event data management module, a monitoring data trend change management module, a sensor abnormality mark management module and a sensor performance evaluation management module;
The fire monitoring and early warning management module is used for building a fire monitoring and early warning platform of a target area, the fire monitoring and early warning platform comprises a plurality of fire monitoring sensors, an alarm mechanism of the fire monitoring and early warning platform is built, and the alarm mechanism comprises that when monitoring data transmitted by the plurality of fire monitoring sensors show a data distribution rule when fire danger can be initiated at a certain moment, the fire monitoring and early warning platform sends an alarm prompt to the management terminal, and a fire early warning event occurs in the current target area is judged;
The fire early-warning event data management module is used for collecting all the historical alarm prompt records sent by the fire monitoring early-warning platform to the management terminal, combing fire processing data in each historical alarm prompt record, and carrying out evaluation and event classification of influence characteristic values on fire early-warning events corresponding to each historical alarm prompt record according to the fire processing data to obtain a plurality of historical alarm prompt record sets; wherein, one history alarm prompt record set corresponds to one type of fire early warning event;
the fire early-warning event data management module comprises an influence characteristic value calculation unit and a fire early-warning event classification management unit;
The influence characteristic value calculation unit is used for collecting all the history alarm prompt records sent by the fire monitoring and early warning platform to the management terminal, carding fire processing data in each history alarm prompt record, and evaluating the influence characteristic value of the fire early warning event corresponding to each history alarm prompt record according to the fire processing data;
The fire early warning event classifying management unit is used for receiving the data in the influence characteristic value calculation unit, classifying all the historical alarm prompt records and obtaining a plurality of historical alarm prompt record sets; wherein, one history alarm prompt record set corresponds to one type of fire early warning event;
The monitoring data trend change management module is used for respectively constructing monitoring data change trend curves for the fire monitoring sensors in each history alarm prompt record set and carrying out information carding on the monitoring data change trend curves of the fire monitoring sensors in each fire early warning event;
The sensor abnormality mark management module is used for carrying out abnormality analysis of alarm prompts on each history alarm prompt record in each history alarm prompt record set based on the change trend curve information of the monitoring data of each fire monitoring sensor in each fire early warning event and carrying out abnormality mark on the related fire monitoring sensor involved in the abnormality analysis process;
the sensor abnormality mark management module comprises a trend abnormality analysis unit and an abnormality mark processing unit;
The trend anomaly analysis unit is used for carrying out anomaly analysis of alarm prompts on each historical alarm prompt record in each historical alarm prompt record set based on the change trend curve information of the monitoring data of each fire monitoring sensor in each fire early warning event;
The abnormality mark processing unit is used for performing abnormality mark on related fire monitoring sensors involved in the abnormality analysis process;
The sensor performance evaluation management module is used for performing performance evaluation on each fire monitoring sensor based on the abnormal mark information distribution condition of each fire monitoring sensor, and sending prompt feedback to management personnel from the fire monitoring sensors needing performance investigation.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. The intelligent fire monitoring and early warning method based on the Internet of things is characterized by comprising the following steps of:
Step S100: building a fire monitoring and early warning platform of a target area, wherein the fire monitoring and early warning platform comprises a plurality of fire monitoring sensors, and an alarm mechanism of the fire monitoring and early warning platform is built, wherein the alarm mechanism comprises that when monitoring data transmitted by the fire monitoring sensors show a data distribution rule when fire danger can be initiated at a certain moment, the fire monitoring and early warning platform sends an alarm prompt to a management terminal to judge that a fire early warning event occurs in the current target area;
Step S200: collecting all historical alarm prompt records sent by a fire monitoring and early warning platform to a management terminal, combing fire processing data in each historical alarm prompt record, and carrying out evaluation and event classification of influence characteristic values on fire early warning events corresponding to each historical alarm prompt record according to the fire processing data to obtain a plurality of historical alarm prompt record sets; wherein, one history alarm prompt record set corresponds to one type of fire early warning event;
Step S300: respectively constructing a monitoring data change trend curve for each fire monitoring sensor in each history alarm prompt record set, and carrying out information carding on the monitoring data change trend curve of each fire monitoring sensor in each fire early warning event;
Step S400: based on the change trend curve information of the monitoring data of each fire monitoring sensor in each fire early warning event, carrying out abnormal analysis of alarm prompts on each history alarm prompt record in each history alarm prompt record set, and carrying out abnormal marking on the related fire monitoring sensors involved in the abnormal analysis process;
Step S500: based on the abnormal mark information distribution condition of each fire monitoring sensor, performing performance evaluation on each fire monitoring sensor, and sending prompt feedback to a manager by the fire monitoring sensor needing performance investigation;
The step S200 includes:
Step S201: acquiring a time stamp T r of an alarm prompt sent by a fire monitoring and early warning platform to a management terminal in each historical alarm prompt record, and acquiring a time stamp T s of release of the corresponding alarm prompt, wherein the duration time T=t s-tr of a fire early warning event corresponding to each historical alarm prompt record;
Step S202: acquiring the total number N of fire extinguishing devices involved in fire extinguishment in the fire early-warning event corresponding to each historical alarm prompt record, and respectively acquiring the consumption of corresponding fire extinguishing agents of M fire extinguishing devices in the fire early-warning event, and accumulating the consumption after normalizing the consumption to obtain the total consumption Q in the fire early-warning event;
Step S203: calculating the influence characteristic value beta=T×N×M×Q of the fire early warning event corresponding to each history alarm prompt record respectively; setting a deviation threshold, and judging fire early-warning events corresponding to two historical alarm prompt records as one type of fire early-warning event when the influence characteristic values of the fire early-warning events corresponding to the two historical alarm prompt records meet the condition that the deviation between the influence characteristic values is smaller than the deviation threshold;
The step S300 includes:
step S301: when the fire monitoring and early warning platform sends out alarm prompts to the management terminal, the transmitted monitoring data are displayed on each fire monitoring sensor to obtain an alarm data set of fire early warning events corresponding to the arbitrary history alarm prompt records; the fire monitoring and early warning platform is arranged in any history alarm prompt record, and the corresponding time stamp is T when the fire monitoring and early warning platform sends an alarm prompt to the management terminal;
Step S302: the method comprises the steps that in any history alarm prompt record, monitored data transmitted by an ith fire monitoring sensor at the time of T are a i, the monitored data transmitted and displayed by the ith fire monitoring sensor before the time of T are traversed, the number n of unit monitored data is set, if continuous n monitored data exist before the time of T, and |a 1-ai|>|a2-ai|>...>|an-ai | is met among the continuous n monitored data, an early warning trend data structure is judged to be formed among the continuous n monitored data, wherein a 1、a2、...、an respectively represents the 1 st, the 2 nd, the third and the n monitored data in the continuous n monitored data, and a timestamp T 1、t2、...、tn corresponding to a 1、a2、...、an meets T 1<t2<...<tn < T; judging that the time stamp t 1 corresponding to the a 1 is a trend starting point of the ith fire monitoring sensor;
Step S303: capturing all pre-warning trend data structures existing in all monitoring data transmitted by the ith fire monitoring sensor before a time stamp T, and extracting trend starting points of all pre-warning trend data structures; collecting all monitoring data between time intervals [ T ', T ] according to monitoring data a i ' corresponding to the minimum trend starting point T ' in the trend starting point, fitting and generating a monitoring data change trend curve presented in the process that the ith fire monitoring sensor displays the transmitted monitoring data a i ' when the monitored data is converted into T and displays the transmitted monitoring data a i when the monitored data is converted from T ', and acquiring the slope of the monitoring data change trend curve of the ith fire monitoring sensor;
Step S304: and in each history alarm prompt record set, acquiring the slope of the monitoring data change trend curve presented by each fire monitoring sensor in each history alarm prompt record, and respectively calculating to obtain the average slope of the monitoring data change trend curve of each fire monitoring sensor in each history alarm prompt record set.
2. The fire intelligent monitoring and early warning method based on the internet of things according to claim 1, wherein the step S400 includes:
Step S401: in each history alarm prompting record set, sequencing each fire monitoring sensor according to the average slope of the change trend curve of the monitoring data of each fire monitoring sensor from large to small to obtain a fire monitoring sensor sequence Y, setting the number M of units, and collecting the first M fire monitoring sensors sequentially selected from the fire monitoring sensor sequence Y to obtain a characteristic sensor set of fire early warning events corresponding to each history alarm prompting record set;
Step S402: setting the characteristic sensor set corresponding to the h historical alarm prompting record set U h as Q (h), capturing and collecting all fire monitoring sensors with the slope of a change trend curve presented in the A by corresponding monitoring data for any one historical alarm prompting record A in U h which is smaller than the average slope in a fire early-warning event corresponding to U h to obtain a set W, and extracting the set W' =Q (h) U W;
Step S403: if the average influence characteristic value of the fire disaster early-warning event corresponding to the g-th historical alarm prompt record set U g,Ug is alpha (g), the average influence characteristic value of the fire disaster early-warning event corresponding to U h is alpha (h), the characteristic sensor set of U g is Q (g), and alpha (g) is < alpha (h), When any one history alarm prompt record A in U h meets the requirements of card [ W'. U.Q (g) ]/card [ Q (g) ] > delta; performing anomaly marking on all fire monitoring sensors in the set W'; where δ is a threshold, and card [ W '. Cndot.Q (g) ] represents the number of elements contained in set W'. Cndot.Q (g), and card [ Q (g) ] represents the number of elements contained in set Q (g).
3. The fire intelligent monitoring and early warning method based on the internet of things according to claim 2, wherein the step S500 includes:
Step S501: setting the number of accumulated marked anomalies of a certain fire monitoring sensor as R, and setting the total number of history alarm prompt record sets as F; capturing a history alarm prompt record set corresponding to each abnormal mark of the certain fire monitoring sensor, and accumulating the number G of the history alarm prompt record sets which are related in total in R abnormal marks;
step S502: and calculating the performance characteristic value O=R× (G/F) of the certain fire monitoring sensor, and when the performance characteristic value of the certain fire monitoring sensor is larger than a threshold value, judging that the certain fire monitoring sensor is the fire monitoring sensor needing performance investigation, and sending prompt feedback to a manager.
4. The fire disaster intelligent monitoring and early warning system for executing the fire disaster intelligent monitoring and early warning method based on the Internet of things according to any one of claims 1 to 3 is characterized in that the system comprises a fire disaster monitoring and early warning management module, a fire disaster early warning event data management module, a monitoring data trend change management module, a sensor abnormality mark management module and a sensor performance evaluation management module;
The fire monitoring and early warning management module is used for building a fire monitoring and early warning platform of a target area, the fire monitoring and early warning platform comprises a plurality of fire monitoring sensors, an alarm mechanism of the fire monitoring and early warning platform is built, and the alarm mechanism comprises the steps that when monitoring data transmitted by the plurality of fire monitoring sensors show a data distribution rule when fire danger can be caused at a certain moment, the fire monitoring and early warning platform sends an alarm prompt to a management terminal, and a fire early warning event is judged to occur in the current target area;
The fire early-warning event data management module is used for collecting all the historical alarm prompt records sent by the fire monitoring early-warning platform to the management terminal, combing fire processing data in each historical alarm prompt record, and carrying out evaluation and event classification of influence characteristic values on fire early-warning events corresponding to each historical alarm prompt record according to the fire processing data to obtain a plurality of historical alarm prompt record sets; wherein, one history alarm prompt record set corresponds to one type of fire early warning event;
The monitoring data trend change management module is used for respectively constructing monitoring data change trend curves for the fire monitoring sensors in each history alarm prompt record set and carrying out information carding on the monitoring data change trend curves of the fire monitoring sensors in each fire early warning event;
The sensor abnormality mark management module is used for carrying out abnormality analysis of alarm prompts on each history alarm prompt record in each history alarm prompt record set based on the change trend curve information of the monitoring data of each fire monitoring sensor in each fire early warning event and carrying out abnormality mark on the related fire monitoring sensor involved in the abnormality analysis process;
The sensor performance evaluation management module is used for evaluating the performance of each fire monitoring sensor based on the abnormal mark information distribution condition of each fire monitoring sensor, and sending prompt feedback to management personnel from the fire monitoring sensors needing performance investigation.
5. The fire intelligent monitoring and early warning system according to claim 4, wherein the fire early warning event data management module comprises an influence characteristic value calculation unit and a fire early warning event classification management unit;
The influence characteristic value calculation unit is used for collecting all the history alarm prompt records sent by the fire monitoring and early warning platform to the management terminal, carding fire processing data in each history alarm prompt record, and evaluating the influence characteristic value of the fire early warning event corresponding to each history alarm prompt record according to the fire processing data;
The fire early warning event classifying and managing unit is used for receiving the data in the influence characteristic value calculating unit, classifying all the historical alarm prompt records and obtaining a plurality of historical alarm prompt record sets; one of the history alarm prompt record sets corresponds to one type of fire early warning event.
6. The intelligent fire monitoring and early warning system according to claim 4, wherein the sensor abnormality mark management module comprises a trend abnormality analysis unit and an abnormality mark processing unit;
The trend anomaly analysis unit is used for carrying out anomaly analysis of alarm prompts on each history alarm prompt record in each history alarm prompt record set based on the monitoring data change trend curve information of each fire monitoring sensor in each fire early warning event;
The abnormality mark processing unit is used for performing abnormality mark on related fire monitoring sensors involved in the abnormality analysis process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311276735.2A CN117218786B (en) | 2023-10-06 | 2023-10-06 | Fire intelligent monitoring and early warning system and method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311276735.2A CN117218786B (en) | 2023-10-06 | 2023-10-06 | Fire intelligent monitoring and early warning system and method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117218786A CN117218786A (en) | 2023-12-12 |
| CN117218786B true CN117218786B (en) | 2024-05-24 |
Family
ID=89035219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311276735.2A Active CN117218786B (en) | 2023-10-06 | 2023-10-06 | Fire intelligent monitoring and early warning system and method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117218786B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117994105B (en) * | 2023-12-15 | 2024-07-02 | 中广(舟山)有线信息网络有限公司 | Digital-based intelligent city operation management system and method |
| CN118245880B (en) * | 2024-04-01 | 2024-09-20 | 中建安装集团有限公司 | Building safety early warning method and system based on data analysis |
| CN118280090B (en) * | 2024-05-31 | 2024-08-23 | 深圳科建鸿兴建设工程有限公司 | Fire emergency monitoring alarm management system and method based on artificial intelligence |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210047491A (en) * | 2019-10-22 | 2021-04-30 | 전남대학교산학협력단 | Determining the risk of fire situation system by analyzing fire record information on the fire situation and method thereof |
| CN113516374A (en) * | 2021-06-18 | 2021-10-19 | 云南电网有限责任公司保山供电局 | Indoor fire extinguishing system of electronic equipment and unmanned on duty place |
| DE202021106450U1 (en) * | 2021-11-26 | 2022-02-09 | Biswaranjan Acharya | Automatic intelligent switching enables IoT-based fire alarm system |
| CN114202907A (en) * | 2021-11-24 | 2022-03-18 | 华中科技大学 | Fire alarm real-time classification method and system |
| CN116205498A (en) * | 2023-05-04 | 2023-06-02 | 深圳市洪恩智能消防有限公司 | Fire potential occurrence assessment and early warning method, system and medium based on Internet of things |
| CN116611562A (en) * | 2023-05-23 | 2023-08-18 | 浙江之科智元科技有限公司 | Intelligent park fire early warning management system and method based on Internet of things |
| CN116740883A (en) * | 2023-06-21 | 2023-09-12 | 株洲市旷几信息技术有限公司 | Security monitoring alarm system based on cloud computing |
-
2023
- 2023-10-06 CN CN202311276735.2A patent/CN117218786B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210047491A (en) * | 2019-10-22 | 2021-04-30 | 전남대학교산학협력단 | Determining the risk of fire situation system by analyzing fire record information on the fire situation and method thereof |
| CN113516374A (en) * | 2021-06-18 | 2021-10-19 | 云南电网有限责任公司保山供电局 | Indoor fire extinguishing system of electronic equipment and unmanned on duty place |
| CN114202907A (en) * | 2021-11-24 | 2022-03-18 | 华中科技大学 | Fire alarm real-time classification method and system |
| DE202021106450U1 (en) * | 2021-11-26 | 2022-02-09 | Biswaranjan Acharya | Automatic intelligent switching enables IoT-based fire alarm system |
| CN116205498A (en) * | 2023-05-04 | 2023-06-02 | 深圳市洪恩智能消防有限公司 | Fire potential occurrence assessment and early warning method, system and medium based on Internet of things |
| CN116611562A (en) * | 2023-05-23 | 2023-08-18 | 浙江之科智元科技有限公司 | Intelligent park fire early warning management system and method based on Internet of things |
| CN116740883A (en) * | 2023-06-21 | 2023-09-12 | 株洲市旷几信息技术有限公司 | Security monitoring alarm system based on cloud computing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117218786A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117218786B (en) | Fire intelligent monitoring and early warning system and method based on Internet of things | |
| US20220262221A1 (en) | Fire detection system | |
| CN111754715B (en) | Fire-fighting emergency response method, device and system | |
| CN112765257B (en) | Method for designing environment acquisition system based on time sequence predicted temperature | |
| CN116105802B (en) | Underground facility safety monitoring and early warning method based on Internet of things | |
| CN113053063A (en) | Mobile terminal-based disaster online disposal flow implementation method | |
| CN117392815A (en) | Alarm method and system for secondary water supply based on Internet of things | |
| CN117094852B (en) | Energy monitoring system and method for industrial and commercial energy storage | |
| CN117579789A (en) | School monitoring system based on big data acquisition | |
| JP6832890B2 (en) | Monitoring equipment, monitoring methods, and computer programs | |
| CN116054416A (en) | Intelligent monitoring operation and maintenance management system based on Internet of things | |
| CN112348419B (en) | Internet of things processing system and method | |
| CN114742375A (en) | Construction site construction safety air management method based on intelligent construction site system | |
| CN118494510B (en) | Active safe driving auxiliary integrated machine cloud management platform | |
| CN118134269B (en) | Land power generation safety intelligent supervision system based on data analysis | |
| Sohn et al. | Damage diagnosis using statistical process control | |
| JP2020167552A (en) | Facility monitoring device and facility monitoring method | |
| CN115548481B (en) | Fault diagnosis method, energy storage system and computer equipment | |
| CN116434478B (en) | Intelligent early warning response method, device and system for geological disasters | |
| CN117893010A (en) | Intelligent construction site safety risk evaluation method based on self-adaptive weighted fusion | |
| CN118503794A (en) | Transformer substation equipment abnormality detection system and method based on multi-mode data | |
| CN115511339A (en) | Intelligent information processing system and method based on big data | |
| CN117852747A (en) | Urban data processing method and system based on cloud computing | |
| KR20230071565A (en) | System for disaster observation monitoring and method thereof | |
| CN118462318A (en) | Mine water disaster monitoring and early warning and disaster spreading simulation 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 |