CN114999095B - Building electrical fire monitoring method and system based on time and space fusion - Google Patents
Building electrical fire monitoring method and system based on time and space fusion Download PDFInfo
- Publication number
- CN114999095B CN114999095B CN202210564672.XA CN202210564672A CN114999095B CN 114999095 B CN114999095 B CN 114999095B CN 202210564672 A CN202210564672 A CN 202210564672A CN 114999095 B CN114999095 B CN 114999095B
- Authority
- CN
- China
- Prior art keywords
- data
- suspicious
- arc
- arc data
- comparing
- 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 52
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000004927 fusion Effects 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 6
- 230000002123 temporal effect Effects 0.000 claims description 6
- 238000010891 electric arc Methods 0.000 abstract description 24
- 238000003745 diagnosis Methods 0.000 abstract description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012790 confirmation Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
Abstract
The application belongs to the technical field of fire monitoring, and provides a building electrical fire monitoring method and system based on time and space fusion, which comprises the steps of firstly comparing suspicious arc data with historical arc data closest to the suspicious arc data in acquisition time, wherein the historical arc data and the arcing data come from the same signal source; if the result of judging the electric arc or the history electric arc data closest to the time cannot be obtained by comparing with the history electric arc data closest to the time, the suspicious electric arc data is compared with the history electric arc data closest to the acquisition space, at the moment, the history electric arc data and the suspicious electric arc data come from signal sources in different adjacent space positions respectively, and identification and diagnosis are carried out on the suspicious electric arc data in longitudinal time and transverse space respectively, so that the real-time performance and accuracy of fire alarm are improved, the occurrence of false alarm and false alarm is reduced, and the accurate and rapid automatic fire alarm can be realized.
Description
Technical Field
The application belongs to the technical field of fire monitoring, and particularly relates to a building electrical fire monitoring method and system based on time and space fusion.
Background
The number of electrical fires has been increasing in recent years, accounting for more than 1/3 of the number of various fires, and more than half of large fires are caused by electrical causes. The building is a main life and workplace of people, and once an electric fire disaster occurs, equipment faults can be caused, normal operation of the equipment is affected, economic loss is caused, and personal safety is even endangered. The building electric fire alarm system has important significance for preventing electric fire, reducing the caused economic loss, improving the safety of buildings and the like. Arc feature extraction is decisive for the feasibility and effectiveness of the diagnostic results, but often the actual arc data is small.
The inventor finds that the electric fire disaster is an accidental event, even one fire disaster can not occur in the whole life cycle of the building, even if the fire disaster occurs, certain singleness and specificity exist in fire disaster data, and the generalization performance is poor. The real arc data is the basis for diagnosing the suspicious arc data, and the rarity of the real arc data seriously influences the subsequent diagnosis of the suspicious arc data, so that the occurrence rate of the false alarm missing report condition is high.
Disclosure of Invention
In order to solve the problems, the application provides a building electrical fire monitoring method and a system based on time and space fusion.
In order to achieve the above object, the present application is realized by the following technical scheme:
in a first aspect, the application provides a building electrical fire monitoring method based on time and space fusion, comprising the following steps:
acquiring line operation state data of building electricity;
determining suspicious arc data in the line running state data according to a threshold comparison method;
comparing the suspicious arc data with data in a preset database, judging whether the suspicious arc data is arc or not, if yes, carrying out fire alarm, otherwise, not giving an alarm;
when the suspicious arc data is compared with the data in the preset database, the suspicious arc data is compared with the historical arc data closest to the suspicious arc data in acquisition time, and the historical arc data and the arc data come from the same signal source; if the result of the arc determination or the historical arc data closest in time are not obtained by comparison with the historical arc data closest in time, the suspicious arc data is compared with the historical arc data closest in acquisition space, and the historical arc data and the arcing data come from signal sources in adjacent different spatial positions respectively.
Further, when determining suspicious arc data in the line operation state data according to a threshold comparison method: the threshold value comprises three cycle current effective value average values, current effective value slope, current harmonic distortion rate and zero-break time, meets the comparison requirement of line operation state data and any threshold value, and judges that the line operation state data is suspicious arc data.
Further, comparing the suspicious arc data with its closest historical arc data in acquisition time, comprising:
performing arithmetic average filtering and normalization processing on suspicious arc data;
performing data fitting on suspicious arc data subjected to arithmetic average filtering and normalization processing, and determining a load type;
acquiring a modal component actual value of the suspicious arc data after fitting;
and carrying out dynamic time warping operation on the actual value of the modal component and the actual value of the modal component of the historical arc data which is closest to the suspicious arc data in time in a preset database, calculating to obtain similarity, and judging the suspicious arc data as the arc after the similarity exceeds a preset threshold value.
Further, when the similarity obtained by comparing with the historical arc data closest in time does not meet the threshold condition, comparing the suspicious arc data with the historical arc data closest in acquisition space, including:
and comparing the actual modal component value of the suspicious arc data with the actual modal component value of the historical arc data of the signal source adjacent to the spatial position, and judging the suspicious arc data to be an arc when the similarity exceeds a preset threshold value.
Further, when comparing with adjacent signal sources, comparing with the adjacent line signal source of the upper stage, and then comparing with the adjacent line signal source of the same-level distribution layer or other line signal sources of different levels;
if the whole preset database is empty, comparing the theoretical values of modal components of the signal sources with different load types.
Further, the preset database is updated by using suspicious arc data which is judged to be the arc.
Further, the acquired line operational status data includes line operational status data, floor line operational status data, and building line operational status data in a room in the building.
In a second aspect, the present application also provides a building electrical fire monitoring system based on temporal and spatial fusion, comprising:
a data acquisition module configured to: acquiring line operation state data of building electricity;
a processing module configured to: determining suspicious arc data in the line running state data according to a threshold comparison method;
a monitor pretension module configured to: comparing the suspicious arc data with data in a preset database, judging whether the suspicious arc data is arc or not, if yes, carrying out fire alarm, otherwise, not giving an alarm;
when the suspicious arc data is compared with the data in the preset database, the suspicious arc data is compared with the historical arc data closest to the suspicious arc data in acquisition time, and the historical arc data and the arc data come from the same signal source; if the result of the arc determination or the historical arc data closest in time are not obtained by comparison with the historical arc data closest in time, the suspicious arc data is compared with the historical arc data closest in acquisition space, and the historical arc data and the arcing data come from signal sources in adjacent different spatial positions respectively.
In a third aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of the building electrical fire monitoring method of the first aspect based on temporal and spatial fusion.
In a fourth aspect, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the building electrical fire monitoring method based on temporal and spatial fusion according to the first aspect when the program is executed.
Compared with the prior art, the application has the beneficial effects that:
1. in the application, suspicious arc data is compared with the historical arc data closest to the suspicious arc data in acquisition time, and the historical arc data and the arc data come from the same signal source; if the result of judging the electric arc or the history electric arc data closest to the time cannot be obtained by comparing with the history electric arc data closest to the time, the suspicious electric arc data is compared with the history electric arc data closest to the acquired space, at the moment, the history electric arc data and the suspicious electric arc data come from signal sources in different adjacent space positions respectively, and identification and diagnosis are carried out on the suspicious electric arc data in longitudinal time and transverse space respectively, so that the real-time performance and accuracy of fire alarm are improved, the occurrence of false alarm and false alarm is reduced, and the accurate and rapid automatic fire alarm can be realized;
2. in the application, the preset database is updated by utilizing the suspicious arc data which is judged to be the arc, so that the timeliness of the preset database is ensured, and the accuracy of the monitoring result is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments and are incorporated in and constitute a part of this specification, illustrate and explain the embodiments and together with the description serve to explain the embodiments.
FIG. 1 is a flow chart of embodiment 1 of the present application;
fig. 2 is a system frame diagram of embodiment 1 of the present application.
The specific embodiment is as follows:
the application will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
Example 1:
the embodiment provides a building electrical fire monitoring method based on time and space fusion, which comprises the following steps:
acquiring line operation state data of building electricity;
determining suspicious arc data in the line running state data according to a threshold comparison method;
comparing the suspicious arc data with data in a preset database, judging whether the suspicious arc data is arc or not, if yes, carrying out fire alarm, otherwise, not giving an alarm; updating a preset database by using suspicious arc data which is judged to be arc;
when the suspicious arc data is compared with the data in the preset database, the suspicious arc data is compared with the historical arc data closest to the suspicious arc data in acquisition time, and the historical arc data and the arc data come from the same signal source; if the result of the arc determination or the historical arc data closest in time are not obtained by comparison with the historical arc data closest in time, the suspicious arc data is compared with the historical arc data closest in acquisition space, and the historical arc data and the arcing data come from signal sources in adjacent different spatial positions respectively.
When the circuit operation state data of the building electrical is obtained, the operation state of the tested circuit can be monitored in real time through an electric arc monitoring module, such as a sensor, and the specific type and the specific setting position of the sensor are set conventionally; it can be understood that the suspicious arc data is the line operation state data which accords with the comparison result after being compared by a threshold comparison method; the alarm form can be understood as all alarm forms such as on-site audible and visual alarm and remote communication alarm.
In this embodiment, when determining suspicious arc data in the line operation state data according to the threshold comparison method: the threshold value comprises three cycle current effective value average values, current effective value slope, current harmonic distortion rate and zero-break time, meets the comparison requirement of line operation state data and any threshold value, and judges that the line operation state data is suspicious arc data.
Comparing the suspicious arc data with data in a preset database, including:
performing arithmetic average filtering and normalization processing on suspicious arc data;
performing data fitting on suspicious arc data subjected to arithmetic average filtering and normalization processing, and determining a load type;
acquiring a modal component actual value of the suspicious arc data after fitting;
carrying out dynamic time warping operation on the actual value of the modal component and the actual value of the modal component of the historical arc data which is closest to the suspicious arc data in time in a preset database, calculating to obtain similarity, and judging the suspicious arc data as an arc after the similarity exceeds a preset threshold value;
when the similarity obtained by comparing the current historical arc data with the current historical arc data in time does not meet the threshold condition, comparing the actual modal component value of the suspicious arc data with the actual modal component value of the historical arc data of the signal source adjacent to the current spatial position, and judging that the current historical arc data is an arc when the similarity exceeds a preset threshold value; when comparing with adjacent signal sources, firstly comparing with the adjacent line signal source of the upper stage, and then comparing with the adjacent line signal source of the same-level distribution layer or other line signal sources of different levels; if the whole preset database is empty, comparing the theoretical values of modal components of the signal sources with different load types; the acquired line operational status data includes line operational status data, floor line operational status data, and building line operational status data in a room in the building.
When the method in the embodiment is implemented, the method can be implemented by means of an Internet of things building electrical fire monitoring system based on time and space data fusion, and as shown in fig. 2, the system mainly comprises a bottom arc monitoring module, an edge side gateway and a building electrical fire monitoring platform. The arc monitoring modules are deployed in three levels, namely a room arc monitoring module, a floor arc monitoring module and a building arc monitoring module. The building electrical fire monitoring platform has the functions of monitoring communication, identification and judgment, storage inquiry, alarm linkage and the like. The electric arc monitoring module monitors the running state of a detected line in real time, when suspicious electric arc data appear on the line, a communication reporting mechanism of the electric arc monitoring module of the line is triggered, the suspicious electric arc data are uploaded to the building electric fire monitoring platform through the edge side gateway, and the building electric fire monitoring platform further performs identification and diagnosis on the suspicious electric arc data from two aspects of transverse space and longitudinal time.
In the embodiment, when the suspicious arc data is determined, a multi-threshold determination method is adopted for determining the suspicious arc data appearing on the line; the first threshold value can be an average value of three effective values of the cyclic current, and when the average value is larger than the first threshold value, the current is suddenly changed, and the data at the moment is uploaded as suspicious data; the second threshold value can be the slope of the effective current value, and when the rising rate of the current is generally higher than that of the normal current, the change of the running state of the line is indicated, and the data need to be uploaded for further diagnosis; the third threshold value can be a current harmonic distortion rate, and the arc current waveform contains a large amount of higher harmonics, so that when the harmonic distortion rate is abnormal, the data is packaged and uploaded as suspicious data; the fourth threshold value can be zero-break time, the arc current is temporarily extinguished almost before each zero crossing point, and reburning is performed after the arc current passes through the zero crossing point, and the intermediate temporary extinction is zero-break time; when n consecutive points in the data are 0, the data is also determined to be suspicious if zero rest time possibly occurs. In summary, the concept of determining suspicious arc data is to identify the line different from the normal load current, and upload the line to the building electrical fire monitoring platform, so that the building electrical fire monitoring platform is required to be further identified.
The method comprises the steps of establishing a suspicious feature library and a preset database, wherein the suspicious feature library is established on the building electrical fire monitoring platform, and after suspicious data are uploaded to the building electrical fire monitoring platform, the suspicious feature library is stored immediately, that is to say, the suspicious feature library stores suspicious arc data triggered and reported by each arc monitoring module, and each piece of data has information such as module numbers, module positions, final judging results and the like. The establishment of suspicious feature library provides for accumulating arc suspicious data, and making intensive research and improvement algorithm.
The building electrical fire monitoring platform is also provided with a preset database which can be understood as a confirmation characteristic database. After the building electrical fire monitoring platform identifies and judges the suspicious arc data uploaded by a certain module, if the diagnosis result is arc, or after the diagnosis result is confirmed by a manual site, the suspicious arc data is stored in a confirmed feature database, and the suspicious arc data uploaded at the time is removed from the confirmed feature database. Stored in the validation feature database are historical arc data that has been algorithmically validated and manually validated as an arc in the field.
The logic flow based on the space-time fusion arc identification method is shown in fig. 1, suspicious arc data is uploaded to the building electrical fire monitoring platform, and after the suspicious arc data is stored in a suspicious feature library, the arc identification flow based on the space-time fusion is started, wherein the logic flow comprises the following specific steps:
step S1, carrying out arithmetic average filtering and normalization processing on suspicious arc data uploaded by a certain module, such as a bottom arc monitoring module;
step S2, carrying out data fitting through a Gaussian function, determining the load type, and generating two output results through fitting: linear or nonlinear load;
s3, obtaining actual values of modal components (Intrinsic Mode Function, IMF) by adopting a complementary set empirical mode decomposition (Empirical Mode Decomposition, EMD) method;
and S4, carrying out dynamic time warping (Dynamic Time Warping, DTW) operation on the actual modal component value of the suspicious arc data and the IMF value of the latest historical arc data in the time of the verification feature library, calculating the similarity of a DTW result, judging the reported suspicious arc data as an arc after the similarity exceeds a preset threshold value, and ending the recognition algorithm. And when the threshold condition is not met, continuously carrying out dynamic time warping comparison with the actual value of the obtained modal component of the next piece of historical arc data of the module. And when the threshold condition is not met or the historical arc data of the module does not exist in the feature library, performing calculation in the fifth step. The time longitudinal characteristics of the identification method are reflected by the time-by-time comparison of the historical arc data with the module; the present module in step S4 may be understood as a signal source when acquiring suspicious arc data, such as a line of building electrical, a distribution line.
And S5, carrying out dynamic time warping comparison on the actual value of the modal component of the suspicious arc data and the historical arc data of the spatial adjacent module, and judging that the electric arc exists when the similarity exceeds a preset threshold value.
The comparison sequence with the adjacent modules can be that the adjacent modules are compared with the upper stage of the distribution line, and then the adjacent lines with the same level (distribution level), other lines with different levels and even modules with different buildings. For example, in fig. 1, if the monitoring module of the room 1 of the first floor 1F reports suspicious arc data, the comparison sequence is: firstly, comparing the historical arc data with the first floor 1F floor monitoring module (the upper level of the distribution line of the room 1), and judging that the arc exists if the similarity exceeds a threshold value; if the similarity does not reach the threshold value, or the historical arc data of the first 1F floor monitoring module does not exist; comparing the historical arc data with the historical arc data of the adjacent line on the upper layer of the building monitoring module, judging to be arc if the similarity exceeds a threshold value, and judging that the historical arc data of the building monitoring module does not exist if the similarity does not reach the threshold value; the first layer is then compared with the historical arc data of the same-level adjacent lines of the 1F room 2 monitoring module, and similarly, the comparison of other lines of different levels (different buildings) is continued. If the whole confirmation database is empty, comparing the theoretical value of the modal component with theoretical values of modal components of different loads, wherein the theoretical value of the modal component is a numerical value obtained through an arc discharge experiment. The comparison with the historical arc data of the spatial adjacent module shows that the spatial transverse characteristic of the identification method is embodied.
And S6, after the recognition algorithm of the time longitudinal direction and the space transverse direction is carried out, if the conclusion that the suspicious arc data of the module is an arc is obtained, the platform sends out an alarm signal, relevant personnel carry out field processing, and whether the arc and the fire hazard exist on the field is explored. If the spot investigation is also arc, cutting off the power supply of the circuit, cutting off the hidden trouble of the electric fire, storing the suspicious arc data into a confirmation feature library to form historical arc data, and eliminating the suspicious arc data uploaded at the time from the suspicious feature library. If the algorithm judges that the suspicious arc data of the module is not arc or the arc is confirmed to be absent by a manual site, the suspicious arc data of the suspicious database is added with the information label of the final judging result. Information tags of the final determination result are classified into two types: the first type is data which is judged to be not arc through an identification algorithm; and the second type is data which is judged to be an arc through an identification algorithm but is not an arc through manual field confirmation. And storing the information labels of the final judging result into a suspicious feature library, and corresponding to the suspicious arc data, and accumulating the data for further improving and correcting the multi-threshold judging method and the arc identification of space-time fusion.
Example 2:
the embodiment provides a building electrical fire monitoring system based on time and space fusion, which comprises:
a data acquisition module configured to: acquiring line operation state data of building electricity;
a processing module configured to: determining suspicious arc data in the line running state data according to a threshold comparison method;
a monitor pretension module configured to: comparing the suspicious arc data with data in a preset database, judging whether the suspicious arc data is arc or not, if yes, carrying out fire alarm, otherwise, not giving an alarm;
when the suspicious arc data is compared with the data in the preset database, the suspicious arc data is compared with the historical arc data closest to the suspicious arc data in acquisition time, and the historical arc data and the arc data come from the same signal source; if the result of the arc determination or the historical arc data closest in time are not obtained by comparison with the historical arc data closest in time, the suspicious arc data is compared with the historical arc data closest in acquisition space, and the historical arc data and the arcing data come from signal sources in adjacent different spatial positions respectively.
The working method of the system is the same as that of the building electrical fire monitoring method based on time and space fusion in embodiment 1, and is not repeated here.
Example 3:
the present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the building electrical fire monitoring method based on temporal and spatial fusion of embodiment 1.
Example 4:
the present embodiment provides an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the building electrical fire monitoring method based on temporal and spatial fusion of embodiment 1 when the program is executed by the processor.
The above description is only a preferred embodiment of the present embodiment, and is not intended to limit the present embodiment, and various modifications and variations can be made to the present embodiment by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment should be included in the protection scope of the present embodiment.
Claims (6)
1. The building electrical fire monitoring method based on time and space fusion is characterized by comprising the following steps of:
acquiring line operation state data of building electricity;
determining suspicious arc data in the line running state data according to a threshold comparison method;
comparing the suspicious arc data with data in a preset database, judging whether the suspicious arc data is arc or not, if yes, carrying out fire alarm, otherwise, not giving an alarm;
when comparing the suspicious arc data with data in a preset database, comparing the suspicious arc data with the historical arc data closest to the suspicious arc data in acquisition time, wherein the historical arc data and the suspicious arc data come from the same signal source; if the result of the arc is not obtained or the historical arc data closest in time is not found by comparing with the historical arc data closest in time, comparing the suspicious arc data with the historical arc data closest in acquisition space, wherein the historical arc data and the suspicious arc data come from signal sources in adjacent different space positions respectively;
when suspicious arc data in the line operation state data is determined according to a threshold comparison method: the threshold value comprises three cycle current effective value average values, current effective value slope, current harmonic distortion rate and zero-break time, meets the comparison requirement of line operation state data and any threshold value, and judges that the line operation state data is suspicious arc data;
comparing the suspicious arc data with its closest historical arc data in acquisition time, comprising:
performing arithmetic average filtering and normalization processing on suspicious arc data;
performing data fitting on suspicious arc data subjected to arithmetic average filtering and normalization processing, and determining a load type;
acquiring a modal component actual value of the suspicious arc data after fitting;
carrying out dynamic time warping operation on the actual value of the modal component and the actual value of the modal component of the historical arc data which is closest to the suspicious arc data in time in a preset database, calculating to obtain similarity, and judging the suspicious arc data as an arc after the similarity exceeds a preset threshold value;
when the similarity obtained by comparing with the historical arc data which is the latest in time does not meet the threshold condition, comparing the suspicious arc data with the historical arc data which is the closest in acquisition space, wherein the method comprises the following steps:
comparing the actual modal component value of the suspicious arc data with the actual modal component value of the historical arc data of the signal source adjacent to the spatial position, and judging the suspicious arc data to be an arc when the similarity exceeds a preset threshold value;
when comparing with adjacent signal sources, firstly comparing with the adjacent line signal source of the upper stage, and then comparing with the adjacent line signal source of the same-level distribution layer or comparing with other line signal sources of different levels;
if the whole preset database is empty, comparing the theoretical values of modal components of the signal sources with different load types.
2. The method for building electrical fire monitoring based on temporal and spatial fusion according to claim 1, wherein the preset database is updated with suspicious arc data determined to be an arc.
3. The electrical fire monitoring method of buildings based on time and space fusion of claim 1, wherein the acquired line operational status data includes line operational status data, floor line operational status data and building line operational status data in rooms in the building.
4. Building electrical fire monitoring system based on time and space fusion, characterized by comprising:
a data acquisition module configured to: acquiring line operation state data of building electricity;
a processing module configured to: determining suspicious arc data in the line running state data according to a threshold comparison method;
a monitor pretension module configured to: comparing the suspicious arc data with data in a preset database, judging whether the suspicious arc data is arc or not, if yes, carrying out fire alarm, otherwise, not giving an alarm;
when comparing the suspicious arc data with data in a preset database, comparing the suspicious arc data with the historical arc data closest to the suspicious arc data in acquisition time, wherein the historical arc data and the suspicious arc data come from the same signal source; if the result of the arc is not obtained or the historical arc data closest in time is not found by comparing with the historical arc data closest in time, comparing the suspicious arc data with the historical arc data closest in acquisition space, wherein the historical arc data and the suspicious arc data come from signal sources in adjacent different space positions respectively;
when suspicious arc data in the line operation state data is determined according to a threshold comparison method: the threshold value comprises three cycle current effective value average values, current effective value slope, current harmonic distortion rate and zero-break time, meets the comparison requirement of line operation state data and any threshold value, and judges that the line operation state data is suspicious arc data;
comparing the suspicious arc data with its closest historical arc data in acquisition time, comprising:
performing arithmetic average filtering and normalization processing on suspicious arc data;
performing data fitting on suspicious arc data subjected to arithmetic average filtering and normalization processing, and determining a load type;
acquiring a modal component actual value of the suspicious arc data after fitting;
carrying out dynamic time warping operation on the actual value of the modal component and the actual value of the modal component of the historical arc data which is closest to the suspicious arc data in time in a preset database, calculating to obtain similarity, and judging the suspicious arc data as an arc after the similarity exceeds a preset threshold value;
when the similarity obtained by comparing with the historical arc data which is the latest in time does not meet the threshold condition, comparing the suspicious arc data with the historical arc data which is the closest in acquisition space, wherein the method comprises the following steps:
comparing the actual modal component value of the suspicious arc data with the actual modal component value of the historical arc data of the signal source adjacent to the spatial position, and judging the suspicious arc data to be an arc when the similarity exceeds a preset threshold value;
when comparing with adjacent signal sources, firstly comparing with the adjacent line signal source of the upper stage, and then comparing with the adjacent line signal source of the same-level distribution layer or comparing with other line signal sources of different levels;
if the whole preset database is empty, comparing the theoretical values of modal components of the signal sources with different load types.
5. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the steps of a time and space fusion based building electrical fire monitoring method according to any of claims 1-3.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the time and space fusion based building electrical fire monitoring method of any one of claims 1-3 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210564672.XA CN114999095B (en) | 2022-05-23 | 2022-05-23 | Building electrical fire monitoring method and system based on time and space fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210564672.XA CN114999095B (en) | 2022-05-23 | 2022-05-23 | Building electrical fire monitoring method and system based on time and space fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114999095A CN114999095A (en) | 2022-09-02 |
| CN114999095B true CN114999095B (en) | 2023-11-14 |
Family
ID=83026324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210564672.XA Active CN114999095B (en) | 2022-05-23 | 2022-05-23 | Building electrical fire monitoring method and system based on time and space fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114999095B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115775436A (en) * | 2022-11-02 | 2023-03-10 | 北京百瑞盛田环保科技发展有限公司 | Plain forest fire situation recognition processing method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009042581A1 (en) * | 2007-09-24 | 2009-04-02 | Edsa Micro Corporation | Real-time stability indexing for intelligent energy monitoring and management of electrical power network system |
| WO2009127068A1 (en) * | 2008-04-14 | 2009-10-22 | Corporation Nuvolt Inc. | Electrical anomaly detection method and system |
| CN105354614A (en) * | 2015-10-21 | 2016-02-24 | 国家电网公司 | Big data based power grid information operation and maintenance active early-warning method |
| CN106959404A (en) * | 2017-05-31 | 2017-07-18 | 山东钢铁股份有限公司 | A kind of method and system for searching power line short-circuit abort situation |
| CN109813956A (en) * | 2018-11-22 | 2019-05-28 | 常州天正工业发展股份有限公司 | A kind of system and method according to device data assessment safety |
| CN110647093A (en) * | 2019-11-13 | 2020-01-03 | 上海迈内能源科技有限公司 | Intelligent monitoring system and monitoring method for power system based on big data analysis |
| CN111458599A (en) * | 2020-04-16 | 2020-07-28 | 福州大学 | Series arc fault detection method based on one-dimensional convolutional neural network |
| CN212181599U (en) * | 2020-07-01 | 2020-12-18 | 安徽北斗易通信息技术有限公司 | Electric line fire early warning terminal |
| CN112466082A (en) * | 2020-11-12 | 2021-03-09 | 上海意静信息科技有限公司 | Artificial intelligence fire alarm grading early warning method based on time-space and linkage relation |
| CN113589105A (en) * | 2021-08-09 | 2021-11-02 | 山东建筑大学 | Building electrical fire series fault arc identification method and system based on Internet of things |
-
2022
- 2022-05-23 CN CN202210564672.XA patent/CN114999095B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009042581A1 (en) * | 2007-09-24 | 2009-04-02 | Edsa Micro Corporation | Real-time stability indexing for intelligent energy monitoring and management of electrical power network system |
| WO2009127068A1 (en) * | 2008-04-14 | 2009-10-22 | Corporation Nuvolt Inc. | Electrical anomaly detection method and system |
| CN105354614A (en) * | 2015-10-21 | 2016-02-24 | 国家电网公司 | Big data based power grid information operation and maintenance active early-warning method |
| CN106959404A (en) * | 2017-05-31 | 2017-07-18 | 山东钢铁股份有限公司 | A kind of method and system for searching power line short-circuit abort situation |
| CN109813956A (en) * | 2018-11-22 | 2019-05-28 | 常州天正工业发展股份有限公司 | A kind of system and method according to device data assessment safety |
| CN110647093A (en) * | 2019-11-13 | 2020-01-03 | 上海迈内能源科技有限公司 | Intelligent monitoring system and monitoring method for power system based on big data analysis |
| CN111458599A (en) * | 2020-04-16 | 2020-07-28 | 福州大学 | Series arc fault detection method based on one-dimensional convolutional neural network |
| CN212181599U (en) * | 2020-07-01 | 2020-12-18 | 安徽北斗易通信息技术有限公司 | Electric line fire early warning terminal |
| CN112466082A (en) * | 2020-11-12 | 2021-03-09 | 上海意静信息科技有限公司 | Artificial intelligence fire alarm grading early warning method based on time-space and linkage relation |
| CN113589105A (en) * | 2021-08-09 | 2021-11-02 | 山东建筑大学 | Building electrical fire series fault arc identification method and system based on Internet of things |
Non-Patent Citations (1)
| Title |
|---|
| 基于ＬａｂＷｉｎｄｏｗｓ／ＣＶＩ的故障电弧在线 检测系统的设计;杨 艺等;《河南理工大学学报》;第27卷(第1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114999095A (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111609883B (en) | Communication machine room protection monitoring management system based on big data | |
| CN109684179B (en) | Early warning method, device, equipment and storage medium for system fault | |
| US9292408B2 (en) | Automated detection of a system anomaly | |
| CN109639797A (en) | A kind of wisdom safety monitoring system | |
| US10573421B2 (en) | Plant operation system and plant operation method | |
| CN114999095B (en) | Building electrical fire monitoring method and system based on time and space fusion | |
| CN103227662B (en) | A kind of electric power communication device safety detection method based on mode control and system | |
| CN114049738B (en) | Building electrical fire identification method and system based on smoke, temperature and electrical quantity | |
| CN104285189A (en) | System and method for detecting electric power plant equipment overheating with real-time plural parallel detection and analysis parameters | |
| CN109448332A (en) | A kind of equipment alarm processing method and system based on Internet of Things wisdom Electrical Safety | |
| CN116756966A (en) | Power grid fault early warning method, system, terminal equipment and storage medium | |
| CN115656812A (en) | Motor real-time state multi-dimensional monitoring method and system | |
| CN111807181A (en) | Web elevator monitoring platform | |
| CN114994565A (en) | Electrical cabinet water and electricity leakage prevention alarm system | |
| CN117409526A (en) | Electrical fire extremely early warning and monitoring system and fire extinguishing method | |
| CN116149226B (en) | Switch cabinet remote control system based on data analysis | |
| CN116247820A (en) | Autonomous operation and maintenance management system | |
| CN111960207B (en) | Elevator running environment abnormity detection method and detection system based on multivariate analysis | |
| KR102128333B1 (en) | Remote electrical safety system and method with electrical spark monitoring | |
| CN113704066A (en) | Machine room equipment monitoring and management method, storage medium and system | |
| CN111404740A (en) | Fault analysis method and device, electronic equipment and computer readable storage medium | |
| CN110851329A (en) | Machine room state diagnosis system and method | |
| KR102246425B1 (en) | System and Method for Detcting Fire of in advance | |
| CN116071884B (en) | Electrical fire alarm monitoring method, system, equipment and medium | |
| Du et al. | Analyzing the effects of failure on fire equipment in building by FAST |
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 |