CN117825864A - Power distribution network line short-circuit capacity monitoring and diagnosing method and system - Google Patents
Power distribution network line short-circuit capacity monitoring and diagnosing method and system Download PDFInfo
- Publication number
- CN117825864A CN117825864A CN202311544257.9A CN202311544257A CN117825864A CN 117825864 A CN117825864 A CN 117825864A CN 202311544257 A CN202311544257 A CN 202311544257A CN 117825864 A CN117825864 A CN 117825864A
- Authority
- CN
- China
- Prior art keywords
- data
- distribution network
- power distribution
- network line
- line
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 282
- 238000012544 monitoring process Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003745 diagnosis Methods 0.000 claims abstract description 61
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000004044 response Effects 0.000 claims abstract description 13
- 230000033228 biological regulation Effects 0.000 claims abstract description 10
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 5
- 238000003064 k means clustering Methods 0.000 claims abstract description 5
- 238000001514 detection method Methods 0.000 claims description 24
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000011217 control strategy Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 230000004931 aggregating effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000000452 restraining effect Effects 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 238000002405 diagnostic procedure Methods 0.000 claims 1
- 238000011002 quantification Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The invention discloses a method and a system for monitoring and diagnosing the short-circuit capacity of a power distribution network line, which relate to the technical field of power systems and comprise the steps of collecting power distribution network line data and converting power distribution network information into line topology graph data; checking and normalizing the data, and calculating the correlation between the characteristic and the target variable based on the pearson correlation coefficient; and positioning and identifying the problem of the short-circuit capacity of the line, monitoring and early warning through the diagnosis result, and formulating a regulation strategy. According to the method, the abstract complex power grid data is structured, so that the operability and the analyzability of the data are enhanced; the correlation between the characteristics and the target variable is calculated based on the Pearson correlation coefficient, so that the quantification of the relation between the data characteristics is realized, and the accuracy of fault prediction is improved; by combining the K-means clustering and the analysis tool of the convolutional neural network, the positioning and the identification of the problem of the short-circuit capacity of the line are carried out, and the response speed and the accuracy of the fault processing of the power distribution network line are improved.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to a method and a system for monitoring and diagnosing the short-circuit capacity of a power distribution network line.
Background
In the field of safety and stability of operation of a power system, a power distribution network is used as an important link for connecting power production and consumption, the health state of the power distribution network is directly related to the reliability of the power system, along with the development of social economy and the continuous increase of power demand, the structure of the power distribution network is more and more complex, higher requirements are put forward on a monitoring and diagnosis technology of the short-circuit capacity of a power distribution network line, the prior art mainly ensures the safe operation of the power distribution network through traditional overload protection and short-circuit protection, but the problems of slow response time, insufficient accuracy, insufficient reliability and the like exist in the methods, and in addition, the accurate monitoring of the short-circuit capacity of the power distribution network line is very important for fault prevention and quick response, but the prior art cannot provide real-time monitoring and accurate diagnosis.
In recent years, development of a smart grid provides a new technical platform for monitoring the short-circuit capacity of a power distribution network line, real-time acquisition and dynamic monitoring of the power distribution network line data are realized by integrating advanced sensor technology, wireless communication technology and large data processing technology, however, even under the framework of the smart grid, the prior art still faces challenges in terms of data processing and fault diagnosis, on one hand, the power distribution network line data volume is huge and contains a large amount of noise, how to effectively extract useful information from the useful information and perform accurate feature recognition is a difficult problem, on the other hand, the prior monitoring diagnosis method often lacks deep analysis on the relevance of data, cannot fully utilize the inherent relation between the data, thereby affecting the accuracy and timeliness of fault recognition.
Disclosure of Invention
The present invention has been made in view of the above-described problems.
Therefore, the technical problems solved by the invention are as follows: the existing power distribution network data processing and fault diagnosis methods have the problems of low accuracy, slow response and low efficiency, and how to provide real-time power distribution network line monitoring and accurate diagnosis.
In order to solve the technical problems, the invention provides the following technical scheme: a method for monitoring and diagnosing the short-circuit capacity of a power distribution network line comprises the steps of collecting power distribution network line data and converting the power distribution network information into line topological graph data; checking and normalizing the data, and calculating the correlation between the characteristic and the target variable based on the pearson correlation coefficient; and positioning and identifying the problem of the short-circuit capacity of the line, monitoring and early warning through the diagnosis result, and formulating a regulation strategy.
As a preferable scheme of the power distribution network line short-circuit capacity monitoring and diagnosing method, the invention comprises the following steps: the method comprises the steps that collecting power distribution network line data comprises installing a current transformer, a voltage sensor and a temperature sensor at power distribution network line nodes, measuring the power distribution network line current data by the current transformer, measuring the power distribution network line voltage data by the voltage sensor, and measuring the power distribution network line temperature data by the temperature sensor.
As a preferable scheme of the power distribution network line short-circuit capacity monitoring and diagnosing method, the invention comprises the following steps: the method comprises the steps that power distribution network information is converted into line topology map data, a wireless sensor network is formed by wireless nodes of a current transformer, a voltage sensor and a temperature sensor, the power distribution network line topology map is obtained through the power distribution network information, the power distribution network information comprises line names, equipment models, installation positions and connection modes, connection points of power distribution network lines and equipment are used as nodes of the power distribution network line topology map, and the connection points are converted into line topology map data.
The conversion process uses OCR image conversion tool to convert the characters and symbols in the line topological graph into vector images, and uses wireless connection mode to connect the sensor equipment through the API interface of the data acquisition module.
As a preferable scheme of the power distribution network line short-circuit capacity monitoring and diagnosing method, the invention comprises the following steps: the checking and normalizing of the data includes checking for error values in the distribution network line current data, the distribution network line voltage data, the distribution network line temperature data, and the line topology map data based on a created list of temporary data centers.
When the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data are checked, if the data exceed the measuring range of the sensor, the data are abnormal, and if the data do not exceed the measuring range of the sensor, the data are normal.
When checking the circuit topology map data, if the circuit topology map data has error and inconsistent information, correcting the circuit topology map data, filling missing values through prepared data items, and if the circuit topology map data has no error and inconsistent information, restraining the circuit current data of the power distribution network, the circuit voltage data of the power distribution network, the circuit temperature data of the power distribution network and the circuit topology map data through minimum-maximum normalization, and mapping the circuit current data, the circuit voltage data of the power distribution network, the circuit temperature data of the power distribution network and the circuit topology map data to the same scale, wherein the steps are as follows:
wherein Z represents normalized power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topology map data, and x represents original power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topology map data, and x min Representing raw distribution network line current data, distribution network line voltage data, and distributionMinimum value of network line temperature data and line topology map data, x max And representing the maximum value of original power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topological graph data.
As a preferable scheme of the power distribution network line short-circuit capacity monitoring and diagnosing method, the invention comprises the following steps: calculating the correlation between the characteristics and the target variable comprises projecting the power distribution network line current data, the power distribution network line voltage data, the power distribution network line temperature data and the line topological graph data into a low-dimensional space based on linear discriminant analysis, aggregating samples of the same class, separating samples of different classes, performing characteristic selection based on the correlation between the characteristics and the target variable, calculating the statistical correlation between the characteristics and the target variable through pearson correlation coefficients, and selecting the characteristic r with the highest correlation with the target variable, wherein the characteristic r is expressed as:
wherein,and->Data means representing different distribution network line current data, distribution network line voltage data, distribution network line temperature data and line topology map data, X i 、Y i The i-th observations representing X and Y, X, Y represent data variables for two different power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data, and line topology map data.
As a preferable scheme of the power distribution network line short-circuit capacity monitoring and diagnosing method, the invention comprises the following steps: the positioning and identifying of the line short-circuit capacity problem comprises dividing samples in a data set into different clusters through a K-means clustering iterative algorithm, wherein each cluster represents a potential short-circuit capacity problem; dividing the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data into clustered cluster numbers K respectively, calculating the intra-cluster square sum under different cluster numbers K, drawing a line graph of the intra-cluster square sum and the cluster numbers K, selecting the cluster numbers K at the inflection points as final clustered cluster numbers through inflection points with obviously slowed down falling speeds of the intra-cluster square sum on the line graph, and calculating the intra-cluster square sum under different cluster numbers K to be expressed as:
wherein SSE represents the intra-cluster square sum under different cluster number K values, d (i) represents the distance between cluster number data of partition clusters and cluster centers, n represents the number of cluster numbers K of different clusters, K samples are randomly selected from power distribution network line current data, power distribution network line voltage data and power distribution network line temperature data and serve as initial cluster centers, the distance between each sample and each cluster center is calculated and distributed into the cluster closest to the cluster, for each cluster, the average value of the samples is calculated and serves as a new cluster center, repeated distribution and updating operation meets stop conditions, the conditions comprise that the maximum iteration number is reached and the change of the cluster center is smaller than a threshold value, and each sample is distributed into one cluster for obtaining a final clustering result; inputting line topological graph data and dividing the line topological graph data into grid cells with fixed sizes, wherein each grid cell is responsible for predicting the category and the position of a target object, and characteristic extraction is carried out on the line topological graph data by using a convolutional neural network; the method comprises the steps of capturing low-level and high-level characteristics in an image through a convolution layer, wherein the low-level and high-level characteristics comprise topological graph edges, textures and shapes, carrying out downsampling through a pooling layer, repeating the processes of rolling and downsampling, converting a characteristic graph into a vector form by a full-connection layer and mapping the vector form to a space of a target class, decoding full-connection layer output, obtaining position and class prediction of a target object in the topological graph, predicting the class and the position of the target object in each grid unit, predicting one or more bounding boxes in each grid unit, screening the bounding boxes according to the predicted confidence level, selecting the best bounding box for the overlapped bounding boxes by using a non-maximum suppression algorithm, sorting all the detecting boxes according to the confidence level from high to low, selecting the detecting box with the highest confidence level, adding the detecting box with the highest confidence level into a final detecting result list, and calculating the overlapping degree of the selected detecting boxes, wherein the overlapping degree of the selected detecting boxes is expressed as follows:
Wherein IoU represents the overlapping degree of the detection frames, intersection represents the area of the Intersection region of the two detection frames, and Union represents the area of the Union region of the two detection frames; discarding the detection frame when the overlapping degree is greater than 0.5; when the overlapping degree is less than or equal to 0.5, adding the detection frames into a final detection result list, repeatedly calculating the overlapping degree, traversing all the detection frames, returning to the final detection result list, outputting the category, the position and the confidence of the detected target object, and positioning and identifying the target object in the image; and obtaining a distribution network data diagnosis result by using dimension reduction mapping of a three-dimensional coordinate system of the line topological graph data through a cluster of the final clustering results of the distribution network line current data, the distribution network line voltage data and the distribution network line temperature data.
As a preferable scheme of the power distribution network line short-circuit capacity monitoring and diagnosing method, the invention comprises the following steps: the monitoring and early warning and the regulation strategy making through the diagnosis result comprise the steps of acquiring a real-time power distribution network data diagnosis result through timing polling, periodically sending a request to a line diagnosis module by using a monitoring alarm module according to a set polling time interval when the timing polling is performed, waiting for the response of the diagnosis module, and judging according to the diagnosis result by using the monitoring alarm module when the response is received; presetting judgment alarm conditions, wherein the judgment alarm conditions comprise a power distribution network line current data safety value of 30mA/s, a power distribution network line voltage data safety value of 36V and a power distribution network line temperature data safety value of 40-60 ℃; triggering an alarm when the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data in the power distribution network data diagnosis result exceed the set safety limit values, and setting the times and time of continuous abnormality occurrence; triggering an alarm when the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data continuously appear abnormal and reach set times and time in the power distribution network data diagnosis results, acquiring a power distribution network line diagnosis position through line topology map data mapped by the power distribution network data diagnosis results when alarm judgment conditions are met, sending alarm information by a monitoring alarm module through sound, alarm lamps and mail modes, recording alarm events through a cloud data center, and transmitting the alarm events to a line control module, wherein the alarm event content comprises alarm time, alarm content and alarm level; receiving an indication of a line diagnosis module and a monitoring alarm module through wireless communication, wherein the indication comprises a power distribution network data diagnosis result and alarm information, analyzing and reading the power distribution network data diagnosis result and the alarm information, and analyzing and reading the power distribution network data diagnosis result and comparing safety limit values; and (3) formulating a corresponding control strategy based on the analysis result and the interpretation and executing the control strategy, wherein the control strategy comprises cutting off a fault line, adjusting power supply, starting standby equipment and scheduling maintenance personnel, monitoring feedback information comprises monitoring a line state, power supply condition and equipment working state, and controlling and updating a system state comprises updating the line state, the equipment state and an alarm state.
The invention also aims to provide a monitoring and diagnosing system for the short-circuit capacity of the power distribution network, which can solve the problems of slow response in the current power distribution network data processing and fault diagnosis by performing monitoring and early warning and formulating a regulation and control strategy through the diagnosis result by performing positioning and identification on the problem of the short-circuit capacity of the power distribution network.
As a preferable scheme of the power distribution network line short-circuit capacity monitoring and diagnosing system, the invention comprises the following steps: comprising
A computer device comprising a memory storing a computer program and a processor executing the computer program is a step of implementing a method for monitoring and diagnosing the short circuit capacity of a power distribution network line.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method for monitoring and diagnosing a short circuit capacity of a distribution network line.
The invention has the beneficial effects that: according to the power distribution network line short-circuit capacity monitoring and diagnosing method, the power distribution network information is converted into the line topological graph data, the abstract complex power grid data are structured, and the operability and the analyzability of the data are enhanced; the data is subjected to verification and normalization processing, and the correlation between the characteristics and the target variable is calculated based on the Pearson correlation coefficient, so that the quantification of the relation between the characteristics of the data is realized, and the accuracy of fault prediction is improved; by combining K-means clustering and analysis tools of a convolutional neural network, the method and the device for determining the short-circuit capacity of the power distribution network have the advantages that the positioning and the identification of the short-circuit capacity problem of the power distribution network are carried out, the response speed and the processing accuracy of the power distribution network line fault processing are improved, and better effects are achieved in the aspects of reliability, accuracy and efficiency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an overall flowchart of a method for monitoring and diagnosing short-circuit capacity of a power distribution network according to a first embodiment of the present invention.
Fig. 2 is an overall flowchart of a power distribution network line short-circuit capacity monitoring and diagnosing system according to a third embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Referring to fig. 1, for one embodiment of the present invention, there is provided a method for monitoring and diagnosing a short-circuit capacity of a power distribution network, including:
s1: and acquiring power distribution network line data, and converting the power distribution network information into line topological graph data.
Further, collecting the power distribution network line data includes installing a current transformer, a voltage sensor and a temperature sensor at the power distribution network line node, measuring the power distribution network line current data by the current transformer, measuring the power distribution network line voltage data by the voltage sensor, and measuring the power distribution network line temperature data by the temperature sensor.
It should be noted that, converting the power distribution network information into line topology map data includes forming a wireless sensor network through wireless nodes of a current transformer, a voltage sensor and a temperature sensor, obtaining a power distribution network line topology map through the power distribution network information, wherein the power distribution network information includes a line name, a device model, an installation position and a connection mode, and using connection points of a power distribution network line and a device as nodes of the power distribution network line topology map and converting the connection points into line topology map data; the conversion process uses OCR image conversion tool to convert the characters and symbols in the line topological graph into vector images, and uses wireless connection mode to connect the sensor equipment through the API interface of the data acquisition module.
It should also be noted that, through the highly integrated monitoring means, the key data of the distribution network line are collected in real time, including three basic electrical parameters of current, voltage and temperature, through the current transformer installed at the node of the distribution network, voltage sensor and temperature sensor realize, these sensors form wireless sensor network, provide the basis for the real-time monitoring and data analysis of the distribution network, current transformer measures the electric current through the wire, voltage sensor monitors the potential difference, and temperature sensor then records the thermal state of the wire, these are the key index of evaluating the health condition of the distribution network, the collection process is not only stopped at the data collection level, but also includes the ability to convert these real-time data into line topological graph data, this conversion is realized through the API interface of OCR image conversion tool and data collection module, the traditional line topological graph is digitized, thereby facilitate data processing and analysis, this conversion process has promoted the readability and the maneuverability of data, make the monitoring and analysis of the line state more efficient and accurate, furthermore, through the application of the wireless connection mode, the invention has not only improved the flexibility of sensor network deployment and the transmission efficiency, and the data conversion efficiency of the data, and the data conversion efficiency and the data reliability and the reliability of the power distribution network are obviously improved in the aspects of the power network and the power management and the reliability of the system are improved, and the reliability of the data management and the reliability are improved.
S2: and (3) checking and normalizing the data, and calculating the correlation between the characteristic and the target variable based on the Pearson correlation coefficient.
Further, the checking and normalizing of the data includes checking for error values in the distribution network line current data, the distribution network line voltage data, the distribution network line temperature data, and the line topology map data based on the created list of temporary data centers.
When the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data are checked, if the data exceed the measuring range of the sensor, the data are abnormal, and if the data do not exceed the measuring range of the sensor, the data are normal.
When checking the circuit topology map data, if the circuit topology map data has error and inconsistent information, correcting the circuit topology map data, filling missing values through prepared data items, and if the circuit topology map data has no error and inconsistent information, restraining the circuit current data of the power distribution network, the circuit voltage data of the power distribution network, the circuit temperature data of the power distribution network and the circuit topology map data through minimum-maximum normalization, and mapping the circuit current data, the circuit voltage data of the power distribution network, the circuit temperature data of the power distribution network and the circuit topology map data to the same scale, wherein the steps are as follows:
wherein Z represents normalized power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topology map data, and x represents original power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topology map data, and x min Representing the minimum value of original power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topological graph data, x max And representing the maximum value of original power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topological graph data.
It should be noted that calculating the correlation of the feature and the target variable includes projecting the power distribution network line current data, the power distribution network line voltage data, the power distribution network line temperature data, and the line topology map data into a low-dimensional space based on the linear discriminant analysis, aggregating the samples of the same class, separating the samples of different classes, performing feature selection based on the correlation of the feature and the target variable, calculating the statistical correlation of the feature and the target variable by pearson correlation coefficient, and selecting the feature r having the highest correlation with the target variable, expressed as:
wherein,and->Data means representing different distribution network line current data, distribution network line voltage data, distribution network line temperature data and line topology map data, X i 、Y i The i-th observations representing X and Y, X, Y represent two different power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data, and line topology Data variables of the flutter map data.
It should also be noted that, by means of the list created by the temporary data center, the system checks the current, voltage and temperature data of the distribution network lines, as well as the line topology map data, to identify and correct outliers or errors, and during the data check process, if any data is found to be outside the measurement range of the sensor, it is determined that it is abnormal and marked as requiring further analysis, for the line topology map data, the system ensures the integrity and accuracy of the data by correcting the error and inconsistent information, or by filling the missing values with preliminary data items, and then, by means of a min-max normalization process, converts all critical data to a uniform scale for subsequent analysis, the conversion is critical to the comparison and analysis of data because it eliminates the influence of data dimension, allows different types of data to be compared and processed under the same standard, further, the data is projected to a low-dimensional space by utilizing Linear Discriminant Analysis (LDA), the degree of aggregation of samples of the same class is enhanced, and samples of different classes are dispersed, which is helpful for subsequent fault diagnosis and feature selection, and features with highest correlation with target variables are selected by calculating pearson correlation coefficients.
S3: and positioning and identifying the problem of the short-circuit capacity of the line, monitoring and early warning through the diagnosis result, and formulating a regulation strategy.
Furthermore, the positioning and identifying of the line short-circuit capacity problem comprises dividing the samples in the data set into different clusters through a K-means clustering iterative algorithm, wherein each cluster represents a potential short-circuit capacity problem; dividing the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data into clustered cluster numbers K respectively, calculating the intra-cluster square sum under different cluster numbers K, drawing a line graph of the intra-cluster square sum and the cluster numbers K, selecting the cluster numbers K at the inflection points as final clustered cluster numbers through inflection points with obviously slowed down falling speeds of the intra-cluster square sum on the line graph, and calculating the intra-cluster square sum under different cluster numbers K to be expressed as:
wherein SSE represents the intra-cluster square sum under different cluster number K values, d (i) represents the distance between cluster number data of partition clusters and cluster centers, n represents the number of cluster numbers K of different clusters, K samples are randomly selected from power distribution network line current data, power distribution network line voltage data and power distribution network line temperature data and serve as initial cluster centers, the distance between each sample and each cluster center is calculated and distributed into the cluster closest to the cluster, for each cluster, the average value of the samples is calculated and serves as a new cluster center, repeated distribution and updating operation meets stop conditions, the conditions comprise that the maximum iteration number is reached and the change of the cluster center is smaller than a threshold value, and each sample is distributed into one cluster for obtaining a final clustering result; inputting line topological graph data and dividing the line topological graph data into grid cells with fixed sizes, wherein each grid cell is responsible for predicting the category and the position of a target object, and characteristic extraction is carried out on the line topological graph data by using a convolutional neural network; the method comprises the steps of capturing low-level and high-level characteristics in an image through a convolution layer, wherein the low-level and high-level characteristics comprise topological graph edges, textures and shapes, carrying out downsampling through a pooling layer, repeating the processes of rolling and downsampling, converting a characteristic graph into a vector form by a full-connection layer and mapping the vector form to a space of a target class, decoding full-connection layer output, obtaining position and class prediction of a target object in the topological graph, predicting the class and the position of the target object in each grid unit, predicting one or more bounding boxes in each grid unit, screening the bounding boxes according to the predicted confidence level, selecting the best bounding box for the overlapped bounding boxes by using a non-maximum suppression algorithm, sorting all the detecting boxes according to the confidence level from high to low, selecting the detecting box with the highest confidence level, adding the detecting box with the highest confidence level into a final detecting result list, and calculating the overlapping degree of the selected detecting boxes, wherein the overlapping degree of the selected detecting boxes is expressed as follows:
Wherein IoU represents the overlapping degree of the detection frames, intersection represents the area of the Intersection region of the two detection frames, and Union represents the area of the Union region of the two detection frames; discarding the detection frame when the overlapping degree is greater than 0.5; when the overlapping degree is less than or equal to 0.5, adding the detection frames into a final detection result list, repeatedly calculating the overlapping degree, traversing all the detection frames, returning to the final detection result list, outputting the category, the position and the confidence of the detected target object, and positioning and identifying the target object in the image; and obtaining a distribution network data diagnosis result by using dimension reduction mapping of a three-dimensional coordinate system of the line topological graph data through a cluster of the final clustering results of the distribution network line current data, the distribution network line voltage data and the distribution network line temperature data.
The method comprises the steps of carrying out monitoring and early warning through a diagnosis result and formulating a regulation strategy, wherein the step of obtaining a real-time power distribution network data diagnosis result through timing polling is carried out, a monitoring alarm module is used for periodically sending a request to a line diagnosis module according to a set polling time interval during the timing polling, waiting for the response of the diagnosis module, and judging according to the diagnosis result when the response is received; the method comprises the steps of presetting judgment alarm conditions, wherein the judgment alarm conditions comprise that the safety value of the power distribution network line current data is 30mA/s, the safety value of the power distribution network line voltage data is 36V, and the safety value of the power distribution network line temperature data is 40-60 ℃.
When the distribution network line current data, the distribution network line voltage data and the distribution network line temperature data in the distribution network data diagnosis result exceed the set safety limit values, triggering an alarm, and setting the times and time of continuous abnormality occurrence.
When the distribution network line current data, the distribution network line voltage data and the distribution network line temperature data in the distribution network data diagnosis result continuously appear abnormally to reach the set times and time, triggering an alarm, and when the judgment alarm condition is met, acquiring the distribution network line diagnosis position through the line topology map data mapped by the distribution network data diagnosis result, sending alarm information by the monitoring alarm module in a sound, alarm lamp and mail mode, recording an alarm event by the cloud data center, and transmitting the alarm event to the line control module, wherein the alarm event content comprises alarm time, alarm content and alarm level.
And receiving the indication of the line diagnosis module and the monitoring alarm module through wireless communication, wherein the indication comprises a power distribution network data diagnosis result and alarm information, analyzing and reading, and analyzing and reading comprises analysis of the diagnosis result and comparison of safety limit values.
And (3) formulating a corresponding control strategy based on the analysis result and the interpretation and executing the control strategy, wherein the control strategy comprises cutting off a fault line, adjusting power supply, starting standby equipment and scheduling maintenance personnel, monitoring feedback information comprises monitoring a line state, power supply condition and equipment working state, and controlling and updating a system state comprises updating the line state, the equipment state and an alarm state.
It should be further noted that, in the power system management, the real-time monitoring and fault early warning mechanism is crucial to ensure the reliability and safety of the power distribution network, the monitoring alarm module is utilized to perform timing polling to obtain the diagnosis result of the power distribution network data, the polling mechanism ensures the real-time performance of the data, the monitoring is effectively performed through the preset safety threshold value, namely 30mA/s, the voltage is 36V, and the temperature is 40 ℃ to 60 ℃, when the diagnosis result shows that the data exceeds the safety values, the monitoring system triggers the alarm, and further warns according to the occurrence times and the duration of continuous abnormal data, and the system has the advantages that the system can intervene in the early stage of the problem, prevent the small fault from becoming a big problem, and through the mapping with the line topology map data, the system not only can accurately position the fault position, but also can rapidly inform maintainers through various communication means, including sound, alarm lamps and mail warning, in addition, the integration of the cloud data center can record and transmit key alarm event information to the line control module for further analysis and response, the existing monitoring technology and novel communication means are integrated, and the efficiency of fault processing of the power distribution network is improved.
Example 2
In order to verify the beneficial effects of the invention, the invention provides a monitoring and diagnosing method for the short-circuit capacity of the power distribution network line, and scientific demonstration is carried out through economic benefit calculation and simulation experiments.
Firstly, four distribution lines are selected for experiments, each line is provided with a current transformer, a voltage sensor and a temperature sensor, the sensors transmit data to a temporary data center in real time, current, voltage and temperature data of each line are recorded and compared with set safety thresholds in the data center to identify possible abnormalities, for example, the current value 37mA of the line 2 exceeds a safety value of 30mA and is identified as a potential problem, and the temperature value 61 ℃ exceeds a set range for the line 4, an alarm is triggered, so that the practical application of the invention and the potential of the invention in real-time monitoring and diagnosis are successfully demonstrated through the process.
Referring to table 1, record analysis was performed on experimental data.
Table 1 table of experimental data records
The running states of the line 1 and the line 3 can be seen to be normal, the current, the voltage and the temperature data are all in a safe range, the current of the line 2 and the voltage and the temperature of the line 4 exceed safe thresholds, and a diagnosis result shows that the line 2 has potential problems, and the line 4 detects the problems, so that the invention can effectively monitor the line data of the power distribution network in real time and discover potential safety hazards in time.
Example 3
Referring to fig. 2, in one embodiment of the present invention, a system for monitoring and diagnosing short-circuit capacity of a power distribution network is provided, which includes a data acquisition module, a data check calculation module, and a problem processing module.
The data acquisition module is used for acquiring power distribution network line data and converting the power distribution network information into line topological graph data; the data checking and calculating module is used for checking and normalizing the data, and calculating the correlation between the characteristic and the target variable based on the Pearson correlation coefficient; the problem processing module is used for positioning and identifying the problem of the short-circuit capacity of the line, monitoring and early warning the problem and making a regulation strategy according to the diagnosis result.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like. It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. The utility model provides a distribution network line short circuit capacity monitoring diagnosis method which is characterized by comprising the following steps:
acquiring power distribution network line data, and converting power distribution network information into line topological graph data;
checking and normalizing the data, and calculating the correlation between the characteristic and the target variable based on the pearson correlation coefficient;
and positioning and identifying the problem of the short-circuit capacity of the line, monitoring and early warning through the diagnosis result, and formulating a regulation strategy.
2. The power distribution network line short-circuit capacity monitoring and diagnosing method according to claim 1, wherein: the method comprises the steps that collecting power distribution network line data comprises installing a current transformer, a voltage sensor and a temperature sensor at power distribution network line nodes, measuring the power distribution network line current data by the current transformer, measuring the power distribution network line voltage data by the voltage sensor, and measuring the power distribution network line temperature data by the temperature sensor.
3. The power distribution network line short-circuit capacity monitoring and diagnosing method according to claim 2, wherein: the method comprises the steps that distribution network information is converted into line topology map data, wherein a wireless sensor network is formed by wireless nodes of a current transformer, a voltage sensor and a temperature sensor, the distribution network line topology map is obtained through the distribution network information, the distribution network information comprises a line name, a device model, an installation position and a connection mode, connection points of a distribution network line and devices are used as nodes of the distribution network line topology map, and the connection points are converted into line topology map data;
The conversion process uses OCR image conversion tool to convert the characters and symbols in the line topological graph into vector images, and uses wireless connection mode to connect the sensor equipment through the API interface of the data acquisition module.
4. A method of monitoring and diagnosing short-circuit capacity of a power distribution network as set forth in claim 3, wherein: checking and normalizing the data comprises checking error values in the power distribution network line current data, the power distribution network line voltage data, the power distribution network line temperature data and the line topology map data based on a creation list of a temporary data center;
when checking the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data, if the data exceeds the measuring range of the sensor, the data is abnormal, and if the data does not exceed the measuring range of the sensor, the data is normal;
when checking the circuit topology map data, if the circuit topology map data has error and inconsistent information, correcting the circuit topology map data, filling missing values through prepared data items, and if the circuit topology map data has no error and inconsistent information, restraining the circuit current data of the power distribution network, the circuit voltage data of the power distribution network, the circuit temperature data of the power distribution network and the circuit topology map data through minimum-maximum normalization, and mapping the circuit current data, the circuit voltage data of the power distribution network, the circuit temperature data of the power distribution network and the circuit topology map data to the same scale, wherein the steps are as follows:
Wherein Z represents normalized power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topology map data, and x represents original power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topology map data, and x min Representing the minimum value of original power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topological graph data, x max And representing the maximum value of original power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data and line topological graph data.
5. The power distribution network line short-circuit capacity monitoring and diagnosing method according to claim 4, wherein: calculating the correlation between the characteristics and the target variable comprises projecting the power distribution network line current data, the power distribution network line voltage data, the power distribution network line temperature data and the line topological graph data into a low-dimensional space based on linear discriminant analysis, aggregating samples of the same class, separating samples of different classes, performing characteristic selection based on the correlation between the characteristics and the target variable, calculating the statistical correlation between the characteristics and the target variable through pearson correlation coefficients, and selecting the characteristic r with the highest correlation with the target variable, wherein the characteristic r is expressed as:
Wherein,and->Data means representing different distribution network line current data, distribution network line voltage data, distribution network line temperature data and line topology map data, X i 、Y i The i-th observations representing X and Y, X, Y represent data variables for two different power distribution network line current data, power distribution network line voltage data, power distribution network line temperature data, and line topology map data.
6. The power distribution network line short-circuit capacity monitoring and diagnosing method according to claim 5, wherein: the positioning and identifying of the line short-circuit capacity problem comprises dividing samples in a data set into different clusters through a K-means clustering iterative algorithm, wherein each cluster represents a potential short-circuit capacity problem;
dividing the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data into clustered cluster numbers K respectively, calculating the intra-cluster square sum under different cluster numbers K, drawing a line graph of the intra-cluster square sum and the cluster numbers K, selecting the cluster numbers K at the inflection points as final clustered cluster numbers through inflection points with obviously slowed down falling speeds of the intra-cluster square sum on the line graph, and calculating the intra-cluster square sum under different cluster numbers K to be expressed as:
Wherein SSE represents the intra-cluster square sum under different cluster number K values, d (i) represents the distance between cluster number data of partition clusters and cluster centers, n represents the number of cluster numbers K of different clusters, K samples are randomly selected from power distribution network line current data, power distribution network line voltage data and power distribution network line temperature data and serve as initial cluster centers, the distance between each sample and each cluster center is calculated and distributed into the cluster closest to the cluster, for each cluster, the average value of the samples is calculated and serves as a new cluster center, repeated distribution and updating operation meets stop conditions, the conditions comprise that the maximum iteration number is reached and the change of the cluster center is smaller than a threshold value, and each sample is distributed into one cluster for obtaining a final clustering result;
inputting line topological graph data and dividing the line topological graph data into grid cells with fixed sizes, wherein each grid cell is responsible for predicting the category and the position of a target object, and characteristic extraction is carried out on the line topological graph data by using a convolutional neural network;
the method comprises the steps of capturing low-level and high-level characteristics in an image through a convolution layer, wherein the low-level and high-level characteristics comprise topological graph edges, textures and shapes, carrying out downsampling through a pooling layer, repeating the processes of rolling and downsampling, converting a characteristic graph into a vector form by a full-connection layer and mapping the vector form to a space of a target class, decoding full-connection layer output, obtaining position and class prediction of a target object in the topological graph, predicting the class and the position of the target object in each grid unit, predicting one or more bounding boxes in each grid unit, screening the bounding boxes according to the predicted confidence level, selecting the best bounding box for the overlapped bounding boxes by using a non-maximum suppression algorithm, sorting all the detecting boxes according to the confidence level from high to low, selecting the detecting box with the highest confidence level, adding the detecting box with the highest confidence level into a final detecting result list, and calculating the overlapping degree of the selected detecting boxes, wherein the overlapping degree of the selected detecting boxes is expressed as follows:
Wherein IoU represents the overlapping degree of the detection frames, intersection represents the area of the Intersection region of the two detection frames, and Union represents the area of the Union region of the two detection frames;
discarding the detection frame when the overlapping degree is greater than 0.5;
when the overlapping degree is less than or equal to 0.5, adding the detection frames into a final detection result list, repeatedly calculating the overlapping degree, traversing all the detection frames, returning to the final detection result list, outputting the category, the position and the confidence of the detected target object, and positioning and identifying the target object in the image;
and obtaining a distribution network data diagnosis result by using dimension reduction mapping of a three-dimensional coordinate system of the line topological graph data through a cluster of the final clustering results of the distribution network line current data, the distribution network line voltage data and the distribution network line temperature data.
7. The power distribution network line short-circuit capacity monitoring and diagnosing method according to claim 6, wherein: the monitoring and early warning and the regulation strategy making through the diagnosis result comprise the steps of acquiring a real-time power distribution network data diagnosis result through timing polling, periodically sending a request to a line diagnosis module by using a monitoring alarm module according to a set polling time interval when the timing polling is performed, waiting for the response of the diagnosis module, and judging according to the diagnosis result by using the monitoring alarm module when the response is received;
Presetting judgment alarm conditions, wherein the judgment alarm conditions comprise a power distribution network line current data safety value of 30mA/s, a power distribution network line voltage data safety value of 36V and a power distribution network line temperature data safety value of 40-60 ℃;
triggering an alarm when the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data in the power distribution network data diagnosis result exceed the set safety limit values, and setting the times and time of continuous abnormality occurrence;
triggering an alarm when the power distribution network line current data, the power distribution network line voltage data and the power distribution network line temperature data continuously appear abnormal and reach set times and time in the power distribution network data diagnosis results, acquiring a power distribution network line diagnosis position through line topology map data mapped by the power distribution network data diagnosis results when alarm judgment conditions are met, sending alarm information by a monitoring alarm module through sound, alarm lamps and mail modes, recording alarm events through a cloud data center, and transmitting the alarm events to a line control module, wherein the alarm event content comprises alarm time, alarm content and alarm level;
receiving an indication of a line diagnosis module and a monitoring alarm module through wireless communication, wherein the indication comprises a power distribution network data diagnosis result and alarm information, analyzing and reading the power distribution network data diagnosis result and the alarm information, and analyzing and reading the power distribution network data diagnosis result and comparing safety limit values;
And (3) formulating a corresponding control strategy based on the analysis result and the interpretation and executing the control strategy, wherein the control strategy comprises cutting off a fault line, adjusting power supply, starting standby equipment and scheduling maintenance personnel, monitoring feedback information comprises monitoring a line state, power supply condition and equipment working state, and controlling and updating a system state comprises updating the line state, the equipment state and an alarm state.
8. A system employing the power distribution network line short-circuit capacity monitoring and diagnosing method according to any one of claims 1 to 7, characterized in that: the system comprises a data acquisition module, a data checking and calculating module and a problem processing module;
the data acquisition module is used for acquiring power distribution network line data and converting power distribution network information into line topological graph data;
the data checking and calculating module is used for checking and normalizing the data, and calculating the correlation between the characteristic and the target variable based on the pearson correlation coefficient;
the problem processing module is used for positioning and identifying the problem of the short-circuit capacity of the line, monitoring and early warning the line through the diagnosis result and formulating a regulation strategy.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the power distribution network line short circuit capacity monitoring diagnostic method of any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the power distribution network line short circuit capacity monitoring and diagnosing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311544257.9A CN117825864A (en) | 2023-11-20 | 2023-11-20 | Power distribution network line short-circuit capacity monitoring and diagnosing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311544257.9A CN117825864A (en) | 2023-11-20 | 2023-11-20 | Power distribution network line short-circuit capacity monitoring and diagnosing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117825864A true CN117825864A (en) | 2024-04-05 |
Family
ID=90521785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311544257.9A Pending CN117825864A (en) | 2023-11-20 | 2023-11-20 | Power distribution network line short-circuit capacity monitoring and diagnosing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117825864A (en) |
-
2023
- 2023-11-20 CN CN202311544257.9A patent/CN117825864A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461555B (en) | Production line quality monitoring method, device and system | |
| CN112766342A (en) | Abnormity detection method for electrical equipment | |
| CN111878320B (en) | Monitoring method and system of wind generating set and computer readable storage medium | |
| CN111209934B (en) | Fan fault pre-alarm method and system | |
| CN113163353B (en) | Intelligent health service system of power supply vehicle and data transmission method thereof | |
| CN116148679A (en) | Battery health state prediction method and related device | |
| CN116066343A (en) | Intelligent early warning method and system for fault model of oil delivery pump unit | |
| CN113203954A (en) | Battery fault diagnosis method based on time-frequency image processing | |
| CN113526282A (en) | Method, device, medium and equipment for diagnosing medium and long-term aging faults of elevator | |
| CN115617784A (en) | Data processing system and processing method for informationized power distribution | |
| CN116108402A (en) | Method, equipment and storage medium based on electric power multi-source heterogeneous data fusion analysis | |
| CN117349711B (en) | Electronic tag data processing method and system for railway locomotive parts | |
| CN113487223B (en) | Risk assessment method and system based on information fusion | |
| CN114610553A (en) | Intelligent equipment detection system and detection method thereof | |
| CN117331790A (en) | Machine room fault detection method and device for data center | |
| CN114492636B (en) | Transformer winding state signal acquisition system | |
| CN117825864A (en) | Power distribution network line short-circuit capacity monitoring and diagnosing method and system | |
| CN111314110A (en) | Fault early warning method for distributed system | |
| CN116956089A (en) | Training method and detection method for temperature anomaly detection model of electrical equipment | |
| CN114429240A (en) | Method and device for monitoring running state of highway equipment | |
| CN114233581A (en) | Intelligent patrol alarm system for fan engine room | |
| CN116993319B (en) | Remote equipment health monitoring method and device based on Internet of things | |
| CN117040137B (en) | Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data | |
| CN117171176B (en) | Electricity consumption big data self-upgrading supervision platform based on artificial intelligence | |
| CN117649015A (en) | Power grid time sequence data quality assessment method, system, equipment and storage medium |
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 |