CN118247940B - Electrical fire early warning system and method based on Internet of things - Google Patents
Electrical fire early warning system and method based on Internet of things Download PDFInfo
- Publication number
- CN118247940B CN118247940B CN202410667598.3A CN202410667598A CN118247940B CN 118247940 B CN118247940 B CN 118247940B CN 202410667598 A CN202410667598 A CN 202410667598A CN 118247940 B CN118247940 B CN 118247940B
- Authority
- CN
- China
- Prior art keywords
- historical
- line
- sub
- auxiliary
- confirmation mark
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012790 confirmation Methods 0.000 claims abstract description 122
- 230000006698 induction Effects 0.000 claims abstract description 61
- 238000012546 transfer Methods 0.000 claims abstract description 46
- 238000013058 risk prediction model Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims description 17
- 239000000428 dust Substances 0.000 claims description 13
- 238000009825 accumulation Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Alarm Systems (AREA)
Abstract
The application discloses an electric fire early warning system and method based on the Internet of things, relating to the technical field of fire early warning, the method comprises the steps of obtaining and dividing a plurality of sections of a historical target line, a historical first auxiliary line and a historical second auxiliary line according to respective damage conditions, comparing and analyzing the obtained historical target induction mark sub-line set and the historical induction mark auxiliary sub-line set, predicting fire risk transfer values, when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under parallel and non-parallel conditions, respectively comparing and analyzing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, establishing a fire risk prediction model according to the obtained first and second condition factor sets of the history, and carrying out prediction and early warning on the sub-line with the impending fire risk by combining the obtained risk transfer value prediction result set. The electric fire early warning system and method based on the Internet of things provided by the application have the advantages that the fire early warning work efficiency is improved.
Description
Technical Field
The application relates to the technical field of fire early warning, in particular to an electric fire early warning system and method based on the Internet of things.
Background
The electric fire disaster is a fire disaster caused by taking electric energy as a fire source, is easy to develop into a serious fire accident, has electric shock and explosion risks during the extinguishing, and has larger hazard compared with other fire disasters.
The current electric fire monitoring system has simple functions, is mainly limited to single data acquisition, and lacks the capability of intelligent prediction analysis of big data. And when alarm data is required to be manually arranged, the data analysis can be performed only after manual screening and arrangement, and intelligent grabbing and processing of terminal data cannot be realized. The efficiency and the accuracy of the electric fire early warning system are lower.
Disclosure of Invention
In order to overcome the defects in the prior art, the application provides an electric fire early warning system and method based on the Internet of things.
In a first aspect, the application provides an electrical fire early warning method based on the internet of things, which comprises the following steps:
Acquiring a historical target line, acquiring a historical first auxiliary line and a historical second auxiliary line according to the historical target line, and dividing a plurality of sections of the historical target line, the historical first auxiliary line and the historical second auxiliary line according to the respective damage conditions to obtain a historical target confirmation mark sub-line set, a historical target induction mark sub-line set, a historical confirmation mark auxiliary sub-line set and a historical induction mark auxiliary sub-line set;
Comparing and analyzing the historical target induction mark sub-line set and the historical induction mark auxiliary sub-line set, and outputting a risk transfer value prediction result set;
When the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in parallel conditions, comparing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical first condition factor set;
When the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition, comparing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical second condition factor set;
and building a fire risk prediction model according to the historical first condition factor set and the historical second condition factor set, and combining a risk transfer value prediction result set to predict and early warn a sub-line with the impending fire risk and output a fire early warning notification result.
Preferably, obtaining a damage distribution condition of a historical target line, and dividing a plurality of sections of the historical target line according to the damage distribution condition to obtain a plurality of historical target sub-line sets;
Acquiring a history first auxiliary line and a history second auxiliary line adjacent to a history target line, and dividing a plurality of sections of the history first auxiliary line and the history second auxiliary line according to the damage condition of the history first auxiliary line and the history second auxiliary line to obtain a history first sub auxiliary line set and a history second sub auxiliary line set;
Determining marks of the easy-to-fail sub-line and the sub-line to be induced by the historical target sub-line sets according to the damaged areas, and outputting a historical target confirmation mark sub-line set and a historical target induction mark sub-line set;
And respectively determining marks and sets of the easy-to-fail sub-circuit and the sub-circuit to be induced by the historical first sub-auxiliary circuit set and the historical second sub-auxiliary circuit set according to the respective damage areas, and outputting a historical confirmation mark auxiliary sub-circuit set and a historical induction mark auxiliary sub-circuit set.
Preferably, the total damage area data set on each sub-line in the historical target induced mark sub-line set is counted;
Comparing the corresponding overlapping areas of the damaged blocks of the sub-lines in the historical induction mark auxiliary sub-line set and the historical target induction mark sub-line set, and outputting a first damaged overlapping area data set;
Calculating the occupation ratio of the first damage overlapping area data set and the total damage area data set to obtain a historical occupation ratio data set;
When the ratio data set stores a value larger than a preset ratio threshold, calculating a difference value exceeding the preset ratio threshold, and outputting a historical excess difference value data set;
Acquiring all fault information of a first history of a history induction mark auxiliary sub-line set, and formulating temperature and humidity data sets with different values;
establishing a fire risk transfer value prediction model according to the first historical all fault information, the temperature and humidity data set, the historical target induction mark sub-line set and the historical excess difference data set;
And acquiring first current all fault information, a current target induction mark sub-line set and a current excess difference value data set, inputting the first current all fault information, the current target induction mark sub-line set, the temperature and humidity data set and the current excess difference value data set into a fire risk transfer value prediction model for testing, and outputting a risk transfer value prediction result set.
Preferably, when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in a parallel condition, counting the corresponding damaged block comparison overlapping area of each sub-line in the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, and outputting a second damaged overlapping area data set;
Acquiring dust accumulation degree values of corresponding breakage positions of the second breakage overlapping area data set according to the second breakage overlapping area data set;
Counting the corresponding overlapping section length of each sub-line in the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, and outputting an overlapping section length data set;
acquiring second historical all fault information of the auxiliary sub-line set marked by the historical confirmation;
The second damage overlapping area data set, the dust accumulation degree value, the overlapping section length data set, the second historical all fault information, the temperature and humidity data set, the risk transfer value prediction result set and the historical target confirmation mark sub-line set are combined to form a historical first condition factor set.
Preferably, when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition, counting the distance between the historical target confirmation mark sub-line set and each corresponding sub-line in the historical confirmation mark auxiliary sub-line set, and outputting a correlation distance data set;
the second damage overlapping area data set, the dust accumulation degree value, the overlapping section length data set, the second history all fault information, the temperature and humidity data set, the history target confirmation mark sub-line set, the risk transfer value prediction result set and the correlation distance data set are combined into a history second condition factor set.
Preferably, a fire risk prediction model is established according to the historical first condition factor set and the historical second condition factor set;
Acquiring a current first condition factor set and a current second condition factor set, inputting the current first condition factor set and the current second condition factor set into a fire risk prediction model for testing, and outputting a fire risk prediction result;
And carrying out early warning notification on the sub-line position sections of the fire risk in the historical target confirmation mark sub-line set according to the fire risk prediction result, and outputting a fire early warning notification result.
In a second aspect, an electrical fire early warning system based on internet of things, comprising:
The line segmentation processing unit is used for acquiring a historical target line, acquiring a historical first auxiliary line and a historical second auxiliary line according to the historical target line, and respectively segmenting a plurality of sections of the historical target line, the historical first auxiliary line and the historical second auxiliary line according to the respective damage conditions to obtain a historical target confirmation mark sub-line set, a historical target induction mark sub-line set, a historical confirmation mark auxiliary sub-line set and a historical induction mark auxiliary sub-line set;
The risk transfer value prediction unit is used for comparing and analyzing the historical target induction mark sub-line set and the historical induction mark auxiliary sub-line set, establishing a fire risk transfer value prediction model, predicting a fire risk transfer value of a fire risk transferred from a historical induction mark auxiliary sub-line set sub-line to a historical target induction mark sub-line set sub-line, and outputting a risk transfer value prediction result set;
The first condition analysis unit is used for comparing and analyzing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical first condition factor set when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in a parallel condition;
The second condition analysis unit is used for comparing and analyzing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical second condition factor set when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition;
And the fire early warning notification unit is used for establishing a fire risk prediction model according to the historical first condition factor set and the historical second condition factor set, predicting and early warning is carried out on the sub-line with the current impending fire risk by combining the risk transfer value prediction result set, and a fire early warning notification result is output.
Compared with the prior art, the invention has the following characteristics and beneficial effects:
The method comprises the steps of dividing a plurality of sub-line sections according to damage distribution conditions on a historical target line, wherein damage of an outer insulating layer of the line can directly cause occurrence of line fire risks, and besides fire risks caused by factors of the historical target line, the fire risks of the historical target line are induced by mutual influence among other lines can not be ignored, so that two adjacent lines around the historical target line are subjected to identical division processing, and according to information comparison analysis among the sub-lines after division processing of the three lines, a plurality of characteristic influence factors are counted, namely a part section with serious damage and a part with normal damage degree, which are determined on one line, are obviously caused to a series of faults under the influence of other two lines, and the part with normal damage degree can generate fire fault induction possibility of risk transfer under the influence of relevance of the serious damage parts on the other two lines, and therefore, the part with normal damage degree needs to be subjected to prediction analysis of fire risk transfer values, so that accuracy and reliability of fire risk monitoring work of the whole line are improved, and early warning of fire risk fault information can be researched in time, and the information can be developed in a scientific and regular.
Drawings
Fig. 1 is a block diagram of steps of an electrical fire early warning method based on the internet of things, which is mainly embodied in the embodiment.
Fig. 2 is a block diagram of an electrical fire early warning system based on the internet of things, which is mainly embodied in the embodiment.
Detailed Description
The invention is described in further detail below in connection with the following examples.
Referring to fig. 1, an electrical fire early warning system and method based on internet of things, the method includes the following steps:
S1, acquiring a historical target line, acquiring a historical first auxiliary line and a historical second auxiliary line according to the historical target line, and dividing a plurality of sections of the historical target line, the historical first auxiliary line and the historical second auxiliary line according to the damage condition of each section to obtain a historical target confirmation mark sub-line set, a historical target induction mark sub-line set, a historical confirmation mark auxiliary sub-line set and a historical induction mark auxiliary sub-line set.
S2, comparing and analyzing the historical target induction mark sub-line set and the historical induction mark auxiliary sub-line set, and outputting a risk transfer value prediction result set.
S3, when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in parallel conditions, comparing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical first condition factor set.
S4, when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in a non-parallel condition, comparing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical second condition factor set.
S5, a fire risk prediction model is established according to the historical first condition factor set and the historical second condition factor set, prediction and early warning are carried out on the sub-line with the impending fire risk at present by combining the risk transfer value prediction result set, and a fire early warning notification result is output.
Specifically, the method includes the steps that firstly, the historical target line and two adjacent auxiliary lines around the historical target line are divided according to the damage distribution conditions of the auxiliary lines, so that comparison analysis is conducted on the three divided sub line sections under different conditions, a plurality of characteristic influence factors are counted respectively, the fire risk prediction analysis of the target line is facilitated, namely, a fire risk transfer value prediction model is built, the fire risk is transferred to the fire risk transfer value of the historical target induction mark sub line set sub line by the historical induction mark sub line set sub line through the auxiliary line sub line, the potential fire risk caused by induction among other relevance influence factors is considered, accuracy of a fire risk prediction result is improved, in order to improve analysis comprehensiveness of fire risk prediction work of the lines, distinguishing processing is conducted under different conditions, namely, the situation that the lines are parallel to each other, the distance between the lines does not need to be considered, the situation that the lines are far or far and near is needed to be considered if the distance between the lines is not parallel, the situation that the lines are far and far is needed to be considered, the situation that the fire risk is directly influenced by the line is not parallel to be considered, the situation that the fire risk is predicted, the fire risk is predicted is directly influenced by the line, the situation of the fire risk prediction factor is not parallel to be the line, the situation is obtained, the fire risk prediction factor is comprehensively is predicted, the fire risk prediction factor is obtained, and the fire risk prediction factor is obtained is timely, and the fire risk is predicted is under the condition is different.
The specific step S1 comprises the following substeps:
Obtaining damage distribution conditions of the historical target line, and dividing a plurality of sections of the historical target line according to the damage distribution conditions to obtain a plurality of historical target sub-line sets.
And acquiring a first historical auxiliary line and a second historical auxiliary line which are adjacent to the historical target line, and dividing the first historical auxiliary line and the second historical auxiliary line into a first historical auxiliary line set and a second historical auxiliary line set according to the damage condition of the first auxiliary line and the second auxiliary line respectively.
And determining marks of the easy-to-fail sub-line and the sub-line to be induced by the historical target sub-line sets according to the damaged areas, and outputting the historical target confirmation mark sub-line sets and the historical target induction mark sub-line sets.
And determining marks and sets of the easy-to-fail sub-line and the sub-line to be induced by the first historical sub-auxiliary line set and the second historical sub-auxiliary line set according to the damage areas respectively, and outputting a historical confirmation mark auxiliary sub-line set and a historical induction mark auxiliary sub-line set.
Specifically, if the distribution of the damage (i.e. the degree of the damage pothole of the outermost insulating layer on the line and the position of the covered line, if the positions are above, below, left and right of the line, and if the positions are below, the positions are required to be separately analyzed), the historical target sub-line sets (if the historical target line is 10 meters, the historical target line sets are divided according to the distribution of the damage, and if the result is 1 meter, 0.5 meter, 1.2 meter and other non-equal sections are obtained, the sub-line sections here include damaged portions with high concentration and damaged portions with low concentration), a first auxiliary line and a second auxiliary line (if the lines around the target line are all arranged horizontally and horizontally, then one line on the left and right adjacent to the target line is the first auxiliary line and the second auxiliary line), a first sub-auxiliary line set and a second sub-auxiliary line set (the same explanation as the plurality of target sub-line sets is omitted here), and a target identification mark sub-line set (i.e. the sub-line of the broken part section with high broken density in the divided sub-line set); A, B, C, D, E sub-lines) and a history-target-induced flag sub-line set (i.e., sub-lines in a broken portion section of the divided sub-lines having a low broken density: a, b, c, d, e sub-lines, if the same is true), a history-confirmed-flag sub-line set (i.e., F, G, H, I, J sub-lines, if the same is true) and a history-induced-flag sub-line set (i.e., similar is true, if f, g, h, i, j sub-lines).
The specific step S2 comprises the following substeps:
The statistical historical objective induces a total damage area dataset on each sub-line in the marked sub-line set.
And comparing the corresponding overlapping areas of the damaged blocks of the sub-lines in the historical induction mark auxiliary sub-line set and the sub-lines in the historical target induction mark sub-line set, and outputting a first damaged overlapping area data set.
And calculating the occupation ratio of the first damage superposition area data set and the total damage area data set to obtain a historical occupation ratio data set.
When the value larger than the preset ratio threshold is stored in the ratio data set, calculating the difference value exceeding the preset ratio threshold, and outputting a historical excess difference value data set.
And acquiring all fault information of a first history of the auxiliary sub-line set of the history induction mark, and formulating temperature and humidity data sets with different values.
And establishing a fire risk transfer value prediction model according to the first historical all fault information, the temperature and humidity data set, the historical target induction mark sub-line set and the historical excess difference data set.
And acquiring first current all fault information, a current target induction mark sub-line set and a current excess difference value data set, inputting the first current all fault information, the current target induction mark sub-line set, the temperature and humidity data set and the current excess difference value data set into a fire risk transfer value prediction model for testing, and outputting a risk transfer value prediction result set.
Specifically, for example, the total damage coverage area of each line of the five section sub-lines (a, b, c, d, e, taking the a sub-line as an example, if it is 30 square centimeters), the first damage overlapping area data set (the damage positions of the a sub-line and the f sub-line in the history-inducing mark sub-line on the opposite side are the a sub-line: the first block, the second block, the fourth block and the fifth block are overlapped, the first block, the second block and the fifth block are overlapped, the damage coverage areas in the three blocks are counted, if the damage coverage areas are 20 square centimeters, the first damage overlapping area data are counted, a historical occupation ratio data set (namely 2/3), a preset ratio threshold value (if the damage coverage areas are 3/5), a historical excess difference data set (namely 1/15) is counted, all fault information of the first history (namely f, g, h, i, j) is recorded on all faults of the five-section sub-line in the history period, such as short circuit, spark fire, electric leakage fire and the like), temperature and humidity data sets (different values are set according to the temperature and humidity conditions of the environment, such as 38 ℃ and 60%rh and 39 ℃ and 50%rh), a fire risk transfer value prediction model is established (namely a set of a function algorithm is obtained through mechanical learning according to a plurality of influence factors, such as a multiple function algorithm equation, a transfer value prediction set (such as a multiple function equation is obtained once when the first fault information is obtained as x, the current fault information is obtained in the first fault information of x) If the current target induction mark sub-line set is y, the temperature and humidity data set is z, and the current excess difference data set is o, the risk transfer value prediction result set is y: dependent variables) when only the factors of the target line are considered, the historical target induces and marks the sub-lines in the sub-line set without fire risk, but when the correlation influence and interference of other peripheral lines are caused, the fire risk is indirectly transferred to the target line due to the higher temperature or lower humidity influence emitted by the damaged part of the peripheral lines, so that the unexpected fire risk occurs in the hidden sub-lines.
The specific step S3 comprises the following substeps:
And when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in a parallel condition, counting the corresponding damaged block comparison overlapping area of each sub-line in the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, and outputting a second damaged overlapping area data set.
And acquiring dust accumulation degree values of corresponding breakage positions of the second breakage overlapping area data set according to the second breakage overlapping area data set.
And counting the corresponding overlapping section length of each sub-line in the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, and outputting an overlapping section length data set.
And acquiring second historical all fault information of the auxiliary sub-line set marked by the historical confirmation.
The second damage overlapping area data set, the dust accumulation degree value, the overlapping section length data set, the second historical all fault information, the temperature and humidity data set, the risk transfer value prediction result set and the historical target confirmation mark sub-line set are combined into a historical first condition factor set.
Specifically, if the lines are parallel to each other, the distance between the lines is not required to be considered, if the lines are not parallel, the influence of the near-far or the far-near between the lines is required to be considered, and the numerical variation of the temperature and humidity is directly influenced by the factor, the second damage overlapping area data set (which is explained in the same way as the first damage overlapping area data set described above, and is not described here), the dust accumulation level value (for example, the second damage overlapping area data corresponding to the a and a sub-lines is 25 square centimeters, the thickness of the retained dust can be estimated according to the characteristic information such as the damage coverage area and the damage depth, that is, if the dust accumulation level value is 15%), the overlapping section length data set (for example, the a sub-line and the a sub-line have a certain position difference, that is not completely overlapped in the position section), so the length of the sub-line at the same position section is counted, if the a sub-line length is 1 meter, the a sub-line length is 0.8 meter, and if the overlapping length is 0.5 meter, and all the second fault information is not described here, all the fault information is not interpreted in the same way.
The specific step S4 includes the following substeps:
And when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition, counting the distance between the historical target confirmation mark sub-line set and each corresponding sub-line in the historical confirmation mark auxiliary sub-line set, and outputting a correlation distance data set.
The second damage overlapping area data set, the dust accumulation degree value, the overlapping section length data set, the second history all fault information, the temperature and humidity data set, the history target confirmation mark sub-circuit set, the risk transfer value prediction result set and the correlation distance data set are combined into a history second condition factor set.
Specifically, if two lines are in a non-parallel state, the influence of temperature and humidity and the fire risk transfer value will decrease to a certain extent due to the fact that the distance between the two lines is further, and conversely, the distance influence factor is not negligible, and is a critical influence factor, the distance data set is associated (if one end of the a sub-line is named as an A1 end, the other end is named as an A2 end, if analysis processing is performed from the A1 end to the A2 end, and one end of the a sub-line is named as an A1 end, the other end is named as an A2 end, the same analysis processing is performed from the A1 end to the A2 end, if the distance between the a sub-line and the a sub-line gradually increases, the distance value of each corresponding breakage overlapping position is counted, for example, the distance value is sequentially 5 cm, 10 cm, 15 cm, and the like, that is the associated distance data.
The specific step S5 comprises the following substeps:
and establishing a fire risk prediction model according to the historical first condition factor set and the historical second condition factor set.
And acquiring a current first condition factor set and a current second condition factor set, inputting the current first condition factor set and the current second condition factor set into a fire risk prediction model for testing, and outputting a fire risk prediction result.
And carrying out early warning notification on the sub-line position sections of the fire risk in the historical target confirmation mark sub-line set according to the fire risk prediction result, and outputting a fire early warning notification result.
Specifically, if a fire risk prediction model is built (the explanation is the same as that of the above-mentioned fire risk transfer value prediction model, which is not described here), and the fire risk prediction result (if the A, C, E sub-line of the A, B, C, D, E sub-line set of the historical target confirmation mark sub-line is predicted to be the fire risk fault section point, the type of the fire risk fault, such as spark fire risk, is predicted, and the predicted fire risk verification level is also different) according to the historical first condition factor set and the historical second condition factor set obtained by analyzing the multiple influence feature factors in the first case and the second case, all the predicted data information of the A, C, E fire risk sub-line is reserved and sent to the management terminal, and timely early warning notification treatment is performed, so that the following treatment personnel can perform effective and timely risk aiming treatment.
An electric fire early warning system based on the Internet of things comprises a line segmentation processing unit, a risk transfer value prediction unit, a first condition analysis unit, a second condition analysis unit and a fire early warning notification unit, and referring to fig. 2, a historical target line is obtained through the line segmentation processing unit, a historical first auxiliary line and a historical second auxiliary line are obtained according to the historical target line, and a plurality of sections of the historical target line, the historical first auxiliary line and the historical second auxiliary line are respectively segmented according to respective damage conditions to obtain a historical target confirmation mark sub-line set, a historical target induction mark sub-line set, a historical confirmation mark auxiliary sub-line set and a historical induction mark auxiliary sub-line set; comparing and analyzing the historical target induction mark sub-line set and the historical induction mark auxiliary sub-line set through a risk transfer value prediction unit, and outputting a risk transfer value prediction result set; when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in parallel conditions, comparing and analyzing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set by a first condition analysis unit to obtain a historical first condition factor set; when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition, comparing and analyzing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set by a second condition analysis unit to obtain a historical second condition factor set; and establishing a fire risk prediction model through a fire early warning notification unit according to the historical first condition factor set and the historical second condition factor set, and carrying out prediction early warning on the sub-line with the impending fire risk by combining the risk transfer value prediction result set to output a fire early warning notification result.
The above embodiments are not intended to limit the scope of the present application, so: all equivalent changes in structure, shape and principle of the application should be covered in the scope of protection of the application.
Claims (5)
1. The electric fire early warning method based on the Internet of things is characterized by comprising the following steps of:
Acquiring a historical target line, acquiring a historical first auxiliary line and a historical second auxiliary line according to the historical target line, and dividing a plurality of sections of the historical target line, the historical first auxiliary line and the historical second auxiliary line according to the respective damage conditions to obtain a historical target confirmation mark sub-line set, a historical target induction mark sub-line set, a historical confirmation mark auxiliary sub-line set and a historical induction mark auxiliary sub-line set;
Comparing and analyzing the historical target induction mark sub-line set and the historical induction mark auxiliary sub-line set, and outputting a risk transfer value prediction result set;
When the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in parallel conditions, comparing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical first condition factor set;
When the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in a parallel condition, counting the corresponding damage block comparison overlapping area of each sub-line in the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, and outputting a second damage overlapping area data set;
Acquiring dust accumulation degree values of corresponding breakage positions of the second breakage overlapping area data set according to the second breakage overlapping area data set;
Counting the corresponding overlapping section length of each sub-line in the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, and outputting an overlapping section length data set;
acquiring second historical all fault information of the auxiliary sub-line set marked by the historical confirmation;
The second damage overlapping area data set, the dust accumulation degree value, the overlapping section length data set, the second historical all fault information, the temperature and humidity data set, the risk transfer value prediction result set and the historical target confirmation mark sub-line set are combined into a historical first condition factor set;
When the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition, comparing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical second condition factor set;
When the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition, counting the corresponding damaged block comparison overlapping area of each sub-line in the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, and outputting a second damaged overlapping area data set;
Acquiring dust accumulation degree values of corresponding breakage positions of the second breakage overlapping area data set according to the second breakage overlapping area data set;
Counting the corresponding overlapping section length of each sub-line in the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set, and outputting an overlapping section length data set;
acquiring second historical all fault information of the auxiliary sub-line set marked by the historical confirmation;
When the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition, counting the distance between the historical target confirmation mark sub-line set and each corresponding sub-line in the historical confirmation mark auxiliary sub-line set, and outputting a correlation distance data set;
the second damage overlapping area data set, the dust accumulation degree value, the overlapping section length data set, the second history all fault information, the temperature and humidity data set, the history target confirmation mark sub-line set, the risk transfer value prediction result set and the correlation distance data set are combined into a history second condition factor set;
and building a fire risk prediction model according to the historical first condition factor set and the historical second condition factor set, and combining a risk transfer value prediction result set to predict and early warn a sub-line with the impending fire risk and output a fire early warning notification result.
2. The method for early warning an electrical fire based on the internet of things according to claim 1, wherein a historical target line is obtained, a historical first auxiliary line and a historical second auxiliary line are obtained according to the historical target line, and the historical target line, the historical first auxiliary line and the historical second auxiliary line are respectively segmented into a plurality of sections according to respective damage conditions, so as to obtain a historical target confirmation mark sub-line set, a historical target induction mark sub-line set, a historical confirmation mark auxiliary sub-line set and a historical induction mark auxiliary sub-line set, which specifically are:
Obtaining damage distribution conditions of a historical target line, and dividing a plurality of sections of the historical target line according to the damage distribution conditions to obtain a plurality of historical target sub-line sets;
Acquiring a history first auxiliary line and a history second auxiliary line adjacent to a history target line, and dividing a plurality of sections of the history first auxiliary line and the history second auxiliary line according to the damage condition of the history first auxiliary line and the history second auxiliary line to obtain a history first sub auxiliary line set and a history second sub auxiliary line set;
Determining marks of the easy-to-fail sub-line and the sub-line to be induced by the historical target sub-line sets according to the damaged areas, and outputting a historical target confirmation mark sub-line set and a historical target induction mark sub-line set;
And respectively determining marks and sets of the easy-to-fail sub-circuit and the sub-circuit to be induced by the historical first sub-auxiliary circuit set and the historical second sub-auxiliary circuit set according to the respective damage areas, and outputting a historical confirmation mark auxiliary sub-circuit set and a historical induction mark auxiliary sub-circuit set.
3. The method for early warning an electrical fire based on the internet of things according to claim 2, wherein the step of comparing the historical target induction mark sub-line set with the historical induction mark auxiliary sub-line set for analysis and outputting a risk transfer value prediction result set is specifically as follows:
Counting a total damage area data set on each sub-line in the historical target induced mark sub-line set;
Comparing the corresponding overlapping areas of the damaged blocks of the sub-lines in the historical induction mark auxiliary sub-line set and the historical target induction mark sub-line set, and outputting a first damaged overlapping area data set;
Calculating the occupation ratio of the first damage overlapping area data set and the total damage area data set to obtain a historical occupation ratio data set;
When the ratio data set stores a value larger than a preset ratio threshold, calculating a difference value exceeding the preset ratio threshold, and outputting a historical excess difference value data set;
Acquiring all fault information of a first history of a history induction mark auxiliary sub-line set, and formulating temperature and humidity data sets with different values;
establishing a fire risk transfer value prediction model according to the first historical all fault information, the temperature and humidity data set, the historical target induction mark sub-line set and the historical excess difference data set;
And acquiring first current all fault information, a current target induction mark sub-line set and a current excess difference value data set, inputting the first current all fault information, the current target induction mark sub-line set, the temperature and humidity data set and the current excess difference value data set into a fire risk transfer value prediction model for testing, and outputting a risk transfer value prediction result set.
4. The electrical fire early warning method based on the internet of things according to claim 1, wherein a fire risk prediction model is established according to the historical first condition factor set and the historical second condition factor set, and a risk transfer value prediction result set is combined to predict and early warn a sub-line where a fire risk is about to occur currently, and the step of outputting a fire early warning notification result is specifically as follows:
establishing a fire risk prediction model according to the historical first condition factor set and the historical second condition factor set;
Acquiring a current first condition factor set and a current second condition factor set, inputting the current first condition factor set and the current second condition factor set into a fire risk prediction model for testing, and outputting a fire risk prediction result;
And carrying out early warning notification on the sub-line position sections of the fire risk in the historical target confirmation mark sub-line set according to the fire risk prediction result, and outputting a fire early warning notification result.
5. An electrical fire early warning system based on the internet of things, which is characterized in that the system is used for realizing the electrical fire early warning method based on the internet of things according to any one of claims 1-4, and comprises the following steps:
The line segmentation processing unit is used for acquiring a historical target line, acquiring a historical first auxiliary line and a historical second auxiliary line according to the historical target line, and respectively segmenting a plurality of sections of the historical target line, the historical first auxiliary line and the historical second auxiliary line according to the respective damage conditions to obtain a historical target confirmation mark sub-line set, a historical target induction mark sub-line set, a historical confirmation mark auxiliary sub-line set and a historical induction mark auxiliary sub-line set;
The risk transfer value prediction unit is used for comparing and analyzing the historical target induction mark sub-line set and the historical induction mark auxiliary sub-line set and outputting a risk transfer value prediction result set;
The first condition analysis unit is used for comparing and analyzing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical first condition factor set when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are in a parallel condition;
The second condition analysis unit is used for comparing and analyzing the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set to obtain a historical second condition factor set when the historical target confirmation mark sub-line set and the historical confirmation mark auxiliary sub-line set are under a non-parallel condition;
And the fire early warning notification unit is used for establishing a fire risk prediction model according to the historical first condition factor set and the historical second condition factor set, predicting and early warning is carried out on the sub-line with the impending fire risk by combining the risk transfer value prediction result set, and a fire early warning notification result is output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410667598.3A CN118247940B (en) | 2024-05-28 | 2024-05-28 | Electrical fire early warning system and method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410667598.3A CN118247940B (en) | 2024-05-28 | 2024-05-28 | Electrical fire early warning system and method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118247940A CN118247940A (en) | 2024-06-25 |
| CN118247940B true CN118247940B (en) | 2024-08-20 |
Family
ID=91553706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410667598.3A Active CN118247940B (en) | 2024-05-28 | 2024-05-28 | Electrical fire early warning system and method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118247940B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145517A (en) * | 2020-01-03 | 2020-05-12 | 上海枫昱能源科技有限公司 | Artificial intelligence electric line fire risk real-time early warning method and system |
| CN115983093A (en) * | 2022-11-29 | 2023-04-18 | 国网新疆电力有限公司经济技术研究院 | Power transmission line tower footing geological disaster prediction method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2023089167A (en) * | 2021-12-06 | 2023-06-27 | ホーチキ株式会社 | disaster prevention system |
| CN117523808B (en) * | 2024-01-04 | 2024-04-09 | 珠海派诺科技股份有限公司 | Electrical fire early warning system and method capable of being monitored in real time based on Internet of things |
-
2024
- 2024-05-28 CN CN202410667598.3A patent/CN118247940B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145517A (en) * | 2020-01-03 | 2020-05-12 | 上海枫昱能源科技有限公司 | Artificial intelligence electric line fire risk real-time early warning method and system |
| CN115983093A (en) * | 2022-11-29 | 2023-04-18 | 国网新疆电力有限公司经济技术研究院 | Power transmission line tower footing geological disaster prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118247940A (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9823289B2 (en) | Automated digital earth fault system | |
| CN117993696B (en) | Unmanned aerial vehicle power inspection-based risk management system and method | |
| CN106908674A (en) | A kind of Transformer condition evaluation based on the prediction of multimode amount | |
| CN110514970B (en) | GIS partial discharge source positioning method, system and medium based on data driving | |
| CN115883779B (en) | Intelligent park information safety management system based on big data | |
| CN112016835A (en) | Power distribution network cable line monitoring method, computer equipment and storage medium | |
| CN117991708B (en) | Industrial automatic early warning system based on Internet of things | |
| CN112115618A (en) | Power equipment fault diagnosis method and system based on matrix chart and confidence | |
| CN109342882A (en) | Cable fault on-line monitoring method based on multi-source Eigenvalues analysis | |
| CN118011143A (en) | High-voltage cable fault monitoring method based on built-in wireless passive sensor | |
| CN114252749A (en) | Transformer partial discharge detection method and device based on multiple sensors | |
| CN113762604A (en) | Industrial Internet big data service system | |
| CN104865500B (en) | A kind of evaluation method of high-tension cable outer jacket differentiation insulation defect | |
| CN118247940B (en) | Electrical fire early warning system and method based on Internet of things | |
| CN114740306A (en) | Power grid informatization-based power distribution network line fault online monitoring and early warning management system | |
| CN118566787B (en) | Cable fault detection method and system based on data analysis | |
| CN117890827B (en) | Intelligent monitoring system for operation of insulated tubular bus based on visualization | |
| CN117458722B (en) | Data monitoring method and system based on electric power energy management system | |
| CN118393291A (en) | Cable state evaluation and early warning method and device | |
| CN115656683B (en) | Cable operation monitoring method, system, terminal equipment and storage medium | |
| CN118396215A (en) | Evaluation system of intelligent alarm of transformer substation monitoring system | |
| CN115409372B (en) | Risk assessment method and system based on data analysis | |
| CN116402349A (en) | Risk early warning method for cable trench pipe well | |
| CN110361630A (en) | A kind of cable fault data management and analysis method based on FMEA | |
| CN115684829A (en) | Power secondary circuit fault detection early warning method and system |
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 |