CN116845863A - Terminal power grid abnormal equipment access alarm method and device based on space-time track - Google Patents
Terminal power grid abnormal equipment access alarm method and device based on space-time track Download PDFInfo
- Publication number
- CN116845863A CN116845863A CN202310710877.9A CN202310710877A CN116845863A CN 116845863 A CN116845863 A CN 116845863A CN 202310710877 A CN202310710877 A CN 202310710877A CN 116845863 A CN116845863 A CN 116845863A
- Authority
- CN
- China
- Prior art keywords
- track
- time
- space
- point
- data
- 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.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000004140 cleaning Methods 0.000 claims abstract description 7
- 230000011218 segmentation Effects 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 3
- 238000005070 sampling Methods 0.000 claims description 74
- 239000013598 vector Substances 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 5
- 230000001502 supplementing effect Effects 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000007405 data analysis Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
Landscapes
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The method utilizes the device to collect real-time voltage and current data in the power utilization line of the terminal power grid, and the time-space track information is obtained after cleaning and preprocessing. And carrying out segmentation and feature extraction on the space-time track, then carrying out track clustering and recognition by using a DBSCAN algorithm, and establishing a feature information base. By comparing the line characteristics with the characteristic information base, the difference between different tracks is analyzed, so that an abnormal track or an unknown track is detected, whether abnormal equipment is accessed is judged, and then an alarm is given. The method has higher accuracy and practicability, meanwhile, the calculation force requirement on hardware is low, each functional module can be integrated on one terminal, and the cost of deploying the cloud system on the server is saved.
Description
Technical Field
The application belongs to the technical field of electric automation, relates to equipment management of a terminal power grid, and particularly relates to a terminal power grid abnormal equipment access alarming method and device based on space-time track.
Background
The intelligent and automatic level of the current power system is continuously improved, and the scale of the current power system is also larger and larger. The number and variety of various power devices in the power system are also increasing, including various substations, distribution stations, transmission lines, etc., so that the monitoring and management of the power system is more complicated. The end grid has become the last line of defense in the power system. Abnormal equipment access may cause faults and accidents of the power system, such as overload, short circuit, ground fault, etc., which have serious influence on normal operation of the power equipment and safety and stability of the power system. Therefore, how to accurately identify abnormal equipment access conditions in the terminal power grid in time becomes an important problem in operation management of the power system.
The intelligent ammeter is adopted to collect electricity consumption of the terminal power grid, and is a mature technology. The collected electricity consumption data can be used for analyzing abnormal electricity consumption behaviors of the terminal power grid, so that abnormal equipment can be identified. However, the identification result of this method is always lagged, i.e. the alarm notification cannot be made at the first time the abnormal device is connected to the end grid. There are also some methods for identifying abnormal equipment based on machine learning, for example, a random forest algorithm is used to collect current characteristics of a large number of electric devices in advance, and alarm notification is performed on abnormal equipment access of a terminal power grid by integrating a plurality of decision trees. However, machine learning algorithms require that a large amount of device data be acquired in advance for model training, and are computationally expensive, with obvious drawbacks.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides a method and a device for alarming access of abnormal equipment of a terminal power grid based on a space-time track algorithm.
The method for alarming access of the abnormal equipment of the tail end power grid based on the space-time trajectory algorithm comprises the following steps:
step 1, data preparation
And collecting ID, position and current and voltage data with time stamps of lines in the terminal power grid, and carrying out normalization processing after data cleaning.
Step 2, calculating space-time track characteristics
The processed line data is used as a space-time track, wherein the time stamp is information of a time dimension and reflects the running change of equipment in the line, the position is information of a space dimension and reflects the geographic position of the equipment in the line, and the current and the voltage are used as the running track and describe the state change of the running equipment in the time dimension and the space dimension. Analyzing and modeling the space-time track, extracting feature vectors, and specifically, the method comprises the following steps:
s2.1 track segmentation
And dividing the space-time track into a plurality of sections according to the same time interval to finish track segmentation.
s2.2 feature extraction
And respectively extracting track length, track direction and speed change rate for the space-time track after s2.1 segmentation.
The track Length is obtained by calculating the cumulative difference or curve Length of the current data over time sequence:
wherein t is i Represents the ith sampling time point, I i Representing the device current corresponding to the ith sampling time point, N is oneThe number of sampling time points in the segment track, abs () represents the absolute value.
And estimating the track direction according to the change trend of the current data, wherein positive and negative values of continuous current data slopes in the defined segmented track are respectively the track positive direction and the track negative direction.
The rate of change of speed Deltav is obtained by calculating the rate of change of the current data over a continuous time:
△v＝abs(I i -I i-1 )/(t i -t i-1 )
s2.3 feature fusion
And combining the track length, track direction and speed change rate of the segmented track into a three-dimensional feature vector to complete feature fusion.
Step 3, classifying sampling points
Cluster analysis is carried out on the three-dimensional feature vectors after fusion by using a DBSCAN algorithm so as to identify the running states of the equipment corresponding to different time nodes, and the method comprises the following specific steps:
s3.1, determining a neighborhood radius Eps of each sampling point and a minimum sample number Min_samples of a DBSCAN algorithm in the three-dimensional feature vector, wherein the specific method comprises the following steps:
converting the current and voltage data of the sampling points into plane coordinates, sequentially calculating the distances between the current sampling point and other sampling points, sequencing from small to large according to the distances, fitting into a smooth distance curve, and taking the distance value corresponding to the slope abrupt change position in the distance curve as the neighborhood radius Eps value of the current sampling point.
Counting the number P of sampling points in each sampling point neighborhood radius i The minimum sample number min_samples is calculated:
preferably, the distance between the sampling points is calculated using the Euclidean distance formula:
wherein d ij Represents the distance, x, between the ith and jth sampling points i 、x j Respectively converting the voltage plane coordinates, y after two sampling points i 、y j And the current plane coordinates after conversion of the two sampling points are respectively.
S3.2, clustering according to the number of sampling points in the neighborhood radius, and determining a clustering center, wherein the specific steps are as follows:
s3.2.1 according to the number P of other sampling points in the neighborhood radius of each sampling point i Determining the type of the sampling point:
(1) when P i And marking the current sampling point as a core point when the sampling point is not less than Min_samples.
(2) When P i And when Min_samples are less than, and the current sampling point is in the neighborhood radius of a certain core point, marking the current sampling point as a boundary point.
(3) When P i And when the sampling point is not in the neighborhood radius of any core point and is less than Min_samples, marking the sampling point as a noise point.
And s3.3.2, removing noise points, taking the core points as clustering center points, and classifying the rest sampling points in the neighborhood radius into the same cluster according to density-accessibility (density-accessibility).
And s3.3, sequentially calculating the distance between the clustering center points, and merging the two clustering clusters with the clustering center point distance smaller than the set threshold value.
s3.4, repeating s3.3 until the distances among all the cluster center points are larger than a set threshold value. The sampling points in the same cluster are labeled the same. And storing the three-dimensional feature vector and the label of the clustering center in a database.
Step 4, judging abnormal equipment access
And calculating space-time track features aiming at the acquired equipment data, inputting a DBSCAN algorithm for classification, comparing the three-dimensional feature vector of the clustering center with the stored three-dimensional feature vector, and judging the clustering label. If an abnormal tag or an unknown tag occurs, a warning is triggered.
Step 5, abnormality repair
When the trigger alarm condition is reached, the line ID, the line position and the label type are pushed to related personnel, and the related personnel perform field maintenance. And for the abnormal label, directly powering off and removing the equipment. And (3) performing on-site rechecking on the unknown label, if the equipment belongs to normal equipment, directly supplementing the characteristic vector and the corresponding label into the database, and if the equipment belongs to abnormal equipment, supplementing the characteristic vector and the corresponding label into the database after power failure and removal.
Preferably, the alarm information is sent to related personnel in a mode of short message, mail, telephone and app push.
The terminal power grid abnormal equipment access alarming device based on the space-time track comprises a sensor module, a controller module, a data analyzer module and an alarm module. The input interface of the sensor module is connected with the tail end power grid line and is used for collecting real-time current and voltage data of the line and transmitting the collected data to the controller module through the output interface. The controller module is used for inputting the data into the data analyzer module after cleaning and normalizing the received data. The data analyzer module analyzes through a clustering algorithm, judges the state of electric equipment in the line, stores the judging result in a database, and returns to the controller module. The controller module recognizes the judging result, and controls the alarm module to give an alarm when abnormal equipment or unknown equipment appears in the line.
Preferably, the sensor module includes a current transformer and a voltage transformer.
Preferably, the alarm module comprises an acousto-optic alarm module and an alarm communication module. The audible and visual alarm module sends out an alarm signal in one or more modes of sounding through a buzzer and flashing through an LED lamp. The alarm communication module sends alarm information to related personnel in one or more modes of short message, mail, telephone and app push.
Preferably, the alarm information includes a line ID, a line location, and a state of the electric device.
The application has the following beneficial effects:
1. the characteristics of the terminal power grid data in the time dimension and the space dimension are mined, the operation condition of the power system is understood, abnormal equipment is detected and the management and operation of the power network are optimized based on space-time track characteristic analysis, the characteristics of the space-time track data are fully utilized, abnormal electric equipment in the terminal power grid is timely found, the misjudgment and omission detection conditions are reduced, a new thought and method are provided for power grid safety management, and the method has higher applicability and flexibility.
2. By monitoring parameters such as voltage, current, temperature and power of a line in a power system and adopting a DBSCAN algorithm to perform track clustering analysis, abnormal conditions and noise in a terminal power grid and the problem of nonstandard distribution of equipment can be adapted, the clustering quantity is determined in a self-adaptive mode, noise and abnormal points of track data are effectively processed, and recognition accuracy and recognition efficiency are improved. In addition, the system gives an alarm fast, so that related personnel can find out abnormal equipment access of the power utilization line fast, and the system contributes to power utilization safety of enterprises.
3. The alarm method does not need to collect a large amount of operation characteristic data of electric equipment in advance, does not need to carry out long-time network training, has lower calculation power requirement on the data analysis module, ensures that all functional hardware can be integrated on one terminal, does not need to arrange a cloud system by an additional server, saves cost and also ensures data privacy.
Drawings
FIG. 1 is a schematic block diagram of an access alarm device for an end grid anomaly device based on a space-time trajectory
FIG. 2 is a flow chart of an end grid anomaly device access alarm based on a space-time trajectory;
FIG. 3 is a plot of end grid line current and voltage scatter collected in an embodiment
FIG. 4 is a flowchart of a sample point classification method according to an embodiment;
FIG. 5 is a plot of sample point distance plotted in an example;
fig. 6 is a sample point cluster analysis result in the embodiment.
Detailed Description
The application is further explained below with reference to the drawings;
as shown in FIG. 1, the terminal power grid abnormal equipment access alarm device based on space-time track comprises a sensor module, a controller module, a data analyzer module and an alarm module. The input interface of the sensor module is connected with the tail end power grid line, real-time current and voltage data of the line are respectively collected through the current transformer and the voltage transformer, and the data with the time stamp are transmitted to the controller module through the output interface. The controller module is used for cleaning and normalizing the received data through the data cleaning module and inputting the cleaned and normalized data into the data analyzer module. The data analyzer module comprises a data analysis module and a data modeling module, wherein the data analysis module clusters and analyzes input data through a clustering algorithm, the data modeling module marks each piece of data according to a clustering analysis result, and after data features and marks are stored, the analysis result is returned to the controller module. The alarm signal control module of the controller module identifies the analysis result returned by the data analyzer module, and if the analysis result indicates that abnormal equipment or unknown equipment exists in the line, signals are sent to the alarm module to control the alarm module to send an alarm. The alarm module comprises an audible and visual alarm module and an alarm communication module. The audible and visual alarm module sends out an alarm signal in one or more modes of sounding through a buzzer and flashing through an LED lamp. The alarm communication module sends the line ID, the line position and the state of the electric equipment to related personnel in one or more modes of short message, mail, telephone and app push.
The method for carrying out access alarm on abnormal equipment of the terminal power grid by using the device is shown in fig. 2, and comprises the following specific steps:
step 1, data preparation
And acquiring ID, position and current and voltage data with time stamps of the lines in the terminal power grid according to the frequency of one second, and carrying out normalization processing after removing abnormal values and missing values.
Step 2, calculating space-time track characteristics
The processed line data is used as a space-time track and is divided according to the time length of one hour. And then extracting the characteristics of the segmented track in three dimensions of track length, track direction and speed change rate to obtain the three-dimensional characteristic vector corresponding to each segmented track.
Step 3, classifying sampling points
The sample point data of the segmented track shown in fig. 3 is classified. It can be seen from the figure that a large amount of voltage and current data is distributed mainly at 5 positions and has the same characteristics. The analysis can thus be performed using a clustering algorithm. The embodiment selects a DBSCAN algorithm to identify the device operating states corresponding to different time nodes. The DBSCAN algorithm is a density-based clustering algorithm that automatically identifies and groups data points that are adjacent in density. The core idea is to characterize the density of data points by defining a neighborhood with radius length of Eps, and determine core points and non-core points by density reachability, thereby realizing cluster analysis. The specific process is shown in fig. 4:
s3.1, initializing parameters: and traversing each sampling point, calculating the neighborhood radius Eps of each sampling point, and determining the minimum sample number Min_samples according to the sampling point data in the neighborhood radius of each sampling point.
Whether the DBSCAN algorithm clustering result is reasonable depends on the selection of the neighborhood radius Eps to a great extent. Too large a neighborhood radius Eps may result in too many noise points being incorporated into a cluster, or sampling points with dissimilar features being incorporated into the same cluster. When the neighborhood radius Eps is too small, the sampling points with similar characteristics are divided into a plurality of different clustering clusters, so that the clustering result is meaningless. Therefore, reasonable Eps is the key to success or failure of clustering. According to the application, the distances between the current sampling point and other sampling points in the segmented track are sequentially calculated through a Euclidean distance calculation formula, a smooth distance curve is drawn after sorting from small to large, as shown in fig. 5, and a distance value corresponding to a slope abrupt change point in the distance curve is selected as a neighborhood radius Eps value of the current sampling point. In this embodiment, if the slope of a point is greater than the sum of the slopes of the first three consecutive sampling points, the point is a slope abrupt point. And finally, calculating to obtain the minimum sample number Min_samples according to the number of sampling points in the neighborhood radius of each sampling point.
s3.2, neighbor detection: and dividing the sampling points into core points, boundary points or noise points according to the number of the sampling points in the neighborhood radius of the sampling points.
s3.3, expanding the neighborhood: for all core points, the neighborhood is expanded based on all data points in its neighborhood and labeled as the same class.
(a) Noise points are removed and all core points are marked as unprocessed.
(b) Each unprocessed core point is traversed in turn.
(c) For the current core point P, a set G is established, all sampling points in the neighborhood radius of the core point P are added into the set G, and the set G is marked as processed.
(d) If the unprocessed core points exist in the set G, adding all sampling points in the neighborhood radius of the core points into the set G, and marking the sampling points as unprocessed.
(e) Repeating the step (d) until no unprocessed core points exist in the set G, and storing the set G.
(f) Returning to step (b) until all core points are marked as processed.
s3.4, outputting the set G stored in s3.3, as a clustering result, as shown in fig. 6, successfully dividing the data into 5 clusters, namely 5 equipment or equipment group features, and storing three-dimensional feature vectors and labels of clustering centers of the 5 clusters.
Step 4, judging abnormal equipment access
And calculating space-time track features aiming at the acquired equipment data, inputting a DBSCAN algorithm for classification, comparing the three-dimensional feature vector of the clustering center with the stored three-dimensional feature vector, and judging the clustering label. If an abnormal tag or an unknown tag occurs, a warning is triggered.
Step 5, abnormality repair
When the trigger alarm condition is reached, the line ID, the line position and the label type are pushed to related personnel, and the related personnel perform field maintenance. And for the abnormal label, directly powering off and removing the equipment. And (3) performing on-site rechecking on the unknown label, if the equipment belongs to normal equipment, directly supplementing the characteristic vector and the corresponding label into the database, and if the equipment belongs to abnormal equipment, supplementing the characteristic vector and the corresponding label into the database after power failure and removal.
Claims (10)
1. The method and the device for alarming access of the abnormal equipment of the terminal power grid based on the space-time track are characterized in that: the method specifically comprises the following steps:
step 1, collecting ID, position and current and voltage data with time stamps of a line in a terminal power grid, and carrying out normalization processing after data cleaning;
step 2, taking the processed line data as a space-time track, calculating track length, track direction and speed change rate in a segmented mode, and then combining the track length, the track direction and the speed change rate into a three-dimensional feature vector serving as segmented track features;
step 3, performing cluster analysis on the sampling point data in the segmented track by using a DBSCAN algorithm to identify the running states of the equipment corresponding to different time nodes, and storing the labels of the cluster centers and the corresponding three-dimensional feature vectors in a database;
step 4, calculating space-time track characteristics aiming at the acquired equipment data, inputting a DBSCAN algorithm for classification, comparing the three-dimensional characteristic vector of the clustering center with the three-dimensional characteristic vector stored in the database, and judging a clustering label; if abnormal labels or unknown labels appear, triggering a warning;
step 5, when the triggering alarm condition is reached, pushing the line ID, the line position and the label type to related personnel, and carrying out field maintenance by the related personnel; for the abnormal label, directly powering off and removing the equipment; checking the unknown label on site, and supplementing the characteristic vector and the corresponding label to a database if the equipment belongs to normal equipment; if the device belongs to abnormal equipment, after power failure and removal, the characteristic vector and the corresponding label are supplemented into a database.
2. The method and device for alarming access of abnormal equipment of terminal power grid based on space-time track as set forth in claim 1, wherein the method is characterized in that: the space-time track is subjected to sectional analysis and modeling, and feature vectors are extracted, wherein the specific steps are as follows:
s2.1 track segmentation
Dividing the space-time track into a plurality of sections according to the same time interval to finish track segmentation;
s2.2 feature extraction
Respectively extracting track length, track direction and speed change rate for the space-time track after s2.1 segmentation;
the track Length is obtained by calculating the cumulative difference or curve Length of the current data over time sequence:
wherein t is i Represents the ith sampling time point, I i Representing the device current corresponding to the ith sampling time point, N is the number of sampling time points in a segmented track, and abs () represents the absolute value;
the track direction estimates the track direction according to the change trend of the current data, and positive and negative values of continuous current data slopes in the segmented track are defined as the track positive direction and the track negative direction respectively;
the rate of change of speed Deltav is obtained by calculating the rate of change of the current data over a continuous time:
△v＝abs(I i -I i-1 )/(t i -t i-1 )
s2.3 feature fusion
And combining the track length, track direction and speed change rate of the segmented track into a three-dimensional feature vector to complete feature fusion.
3. The method and device for alarming access of abnormal equipment of terminal power grid based on space-time track as set forth in claim 1, wherein the method is characterized in that: in step 1, line data in the end grid is collected at a frequency of once a second; in step 2, the spatio-temporal trajectory is segmented at one hour intervals.
4. The method and device for alarming access of abnormal equipment of terminal power grid based on space-time track as set forth in claim 1, wherein the method is characterized in that: the clustering method for sampling the segmented tracks in the step 3 is as follows:
s3.1, converting current and voltage data of a sampling point into plane coordinates, sequentially calculating the distance between the current sampling point and other sampling points, sequencing the distances from small to large, fitting a smooth distance curve, and taking a distance value corresponding to a slope abrupt change position in the distance curve as a neighborhood radius Eps value of the current sampling point;
counting the number P of sampling points in each sampling point neighborhood radius i The minimum sample number min_samples is calculated:
s3.2, taking the point with the number of sampling points in the neighborhood radius not less than Min_samples as the center point of the sub-cluster, and classifying the sampling points in the neighborhood radius into the sub-cluster where the sampling points are located;
s3.3, sequentially calculating the distances between the central points of the sub-clusters, and combining two sub-clusters with the central point distances smaller than a set threshold value into a new sub-cluster;
s3.4, repeating s3.3 until the distances among all the sub-cluster center points are larger than a set threshold value; the labels of sampling points in the same cluster are the same; and storing the three-dimensional feature vector and the label of the clustering center in a database.
5. The method and the device for alarming access of the abnormal equipment of the terminal power grid based on the space-time track as claimed in claim 4 are characterized in that: the distance between the sampling points is calculated using the Euclidean distance formula:
wherein d ij Represents the distance, x, between the ith and jth sampling points i 、x j Respectively converting the voltage plane coordinates, y after two sampling points i 、y j And the current plane coordinates after conversion of the two sampling points are respectively.
6. The method and the device for alarming access of the abnormal equipment of the terminal power grid based on the space-time track as claimed in claim 4 are characterized in that: and defining a point with a slope larger than the sum of slopes of the first three continuous sampling points as a slope abrupt change point in the distance curve.
7. The method and the device for alarming access of the abnormal equipment of the terminal power grid based on the space-time track as claimed in claim 4 are characterized in that: in step s3.2, according to the number P of other sampling points within each sampling point neighborhood radius i Determining the type of the sampling point:
(1) when P i When the sampling points are not less than Min_samples, marking the current sampling point as a core point;
(2) when P i When Min_samples are less than, and the current sampling point is in the neighborhood radius of a certain core point, marking the current sampling point as a boundary point;
(3) when P i When Min_samples are less than, and the sampling point is not in the neighborhood radius of any core point, marking as a noise point;
the core points are used as the central points of the sub-clusters of the clusters, and the boundary points are directly removed and do not participate in the clustering.
8. Terminal electric wire netting abnormal equipment access alarm device based on space-time track, its characterized in that: the device is used for realizing the terminal power grid abnormal equipment access alarming method according to any one of claims 1 to 7, and comprises a sensor module, a controller module, a data analyzer module and an alarm module; the input interface of the sensor module is connected with the tail end power grid line and is used for collecting real-time current and voltage data of the line and transmitting the collected data to the controller module through the output interface; the controller module is used for inputting the data into the data analyzer module after cleaning and normalizing the received data; the data analyzer module analyzes through a clustering algorithm, judges the state of electric equipment in the line, stores a judging result in a database, and returns to the controller module; the controller module recognizes the judging result, and controls the alarm module to give an alarm when abnormal equipment or unknown equipment appears in the line.
9. The method and device for alarming access of abnormal equipment of terminal power grid based on space-time track as set forth in claim 8, wherein the method is characterized in that: the sensor module comprises a current transformer and a voltage transformer.
10. The method and device for alarming access of abnormal equipment of terminal power grid based on space-time track as set forth in claim 8, wherein the method is characterized in that: the alarm module comprises an audible and visual alarm module and an alarm communication module; the audible and visual alarm module sends out an alarm signal in one or more modes of sounding by the buzzer and flashing by the LED lamp; the alarm communication module sends alarm information to related personnel in one or more modes of short message, mail, telephone and app push.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310710877.9A CN116845863A (en) | 2023-06-15 | 2023-06-15 | Terminal power grid abnormal equipment access alarm method and device based on space-time track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310710877.9A CN116845863A (en) | 2023-06-15 | 2023-06-15 | Terminal power grid abnormal equipment access alarm method and device based on space-time track |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116845863A true CN116845863A (en) | 2023-10-03 |
Family
ID=88164516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310710877.9A Pending CN116845863A (en) | 2023-06-15 | 2023-06-15 | Terminal power grid abnormal equipment access alarm method and device based on space-time track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116845863A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117540225A (en) * | 2024-01-09 | 2024-02-09 | 成都电科星拓科技有限公司 | Distributed ups system consistency assessment system and method based on DBSCAN clustering |
-
2023
- 2023-06-15 CN CN202310710877.9A patent/CN116845863A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117540225A (en) * | 2024-01-09 | 2024-02-09 | 成都电科星拓科技有限公司 | Distributed ups system consistency assessment system and method based on DBSCAN clustering |
| CN117540225B (en) * | 2024-01-09 | 2024-04-12 | 成都电科星拓科技有限公司 | Distributed ups system consistency assessment system and method based on DBSCAN clustering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104091070B (en) | Rail transit fault diagnosis method and system based on time series analysis | |
| CN107528832B (en) | Baseline construction and unknown abnormal behavior detection method for system logs | |
| CN106888205B (en) | Non-invasive PLC anomaly detection method based on power consumption analysis | |
| CN111507376B (en) | Single-index anomaly detection method based on fusion of multiple non-supervision methods | |
| CN103812577A (en) | Method for automatically identifying and learning abnormal radio signal type | |
| CN110738255A (en) | device state monitoring method based on clustering algorithm | |
| CN109491339B (en) | Big data-based substation equipment running state early warning system | |
| CN109711664B (en) | Power transmission and transformation equipment health assessment system based on big data | |
| CN116845863A (en) | Terminal power grid abnormal equipment access alarm method and device based on space-time track | |
| CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN114371353A (en) | Power equipment abnormity monitoring method and system based on voiceprint recognition | |
| CN116205265A (en) | Power grid fault diagnosis method and device based on deep neural network | |
| CN112734977A (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN116089218A (en) | Dynamic baseline alarm method and system based on Kubernetes historical data and trend analysis | |
| CN115311585A (en) | A discernment detecting system for electric wire netting overhead line foreign matter | |
| CN110690699A (en) | Transformer substation intelligent detection system based on ubiquitous power Internet of things | |
| CN112232235B (en) | Intelligent factory remote monitoring method and system based on 5G sum algorithm | |
| CN116302809A (en) | Edge end data analysis and calculation device | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| CN114429240A (en) | Method and device for monitoring running state of highway equipment | |
| CN117347791B (en) | Power grid fault online identification system and method based on big data | |
| CN117610971B (en) | Highway electromechanical system health index evaluation method | |
| CN117554737B (en) | Health condition detection method and system of vehicle-mounted charger | |
| CN116702045A (en) | Power supply room safety monitoring method and device based on multi-sensor data |
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 |