CN112417763A - Defect diagnosis method, device and equipment for power transmission line and storage medium - Google Patents
Defect diagnosis method, device and equipment for power transmission line and storage medium Download PDFInfo
- Publication number
- CN112417763A CN112417763A CN202011342125.4A CN202011342125A CN112417763A CN 112417763 A CN112417763 A CN 112417763A CN 202011342125 A CN202011342125 A CN 202011342125A CN 112417763 A CN112417763 A CN 112417763A
- Authority
- CN
- China
- Prior art keywords
- characteristic data
- temperature
- transmission line
- power transmission
- defect
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 196
- 230000007547 defect Effects 0.000 title claims abstract description 160
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003745 diagnosis Methods 0.000 title claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 50
- 230000008569 process Effects 0.000 claims abstract description 14
- 230000007613 environmental effect Effects 0.000 claims description 37
- 230000002950 deficient Effects 0.000 claims description 15
- 238000003064 k means clustering Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000000926 separation method Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 239000004020 conductor Substances 0.000 description 24
- 238000010586 diagram Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a defect diagnosis method of a power transmission line, which comprises the steps of collecting temperature characteristic data, current-carrying characteristic data and environment characteristic data of the power transmission line to be detected; inputting the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data into a defect discriminator obtained by pre-training to determine whether the power transmission line to be detected has defects; the defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, current carrying characteristic data and the environment characteristic data of the power transmission line. The influence of factors in various aspects such as temperature, current and environment on the normal operation of the power transmission line is fully considered, the power transmission line is accurately estimated in advance, maintenance personnel can be reminded as soon as possible to process the power transmission line in time, and efficient operation management of the power transmission line is facilitated. The application also provides a defect diagnosis device, equipment and a computer readable storage medium of the power transmission line, and the beneficial effects are achieved.
Description
Technical Field
The invention relates to the technical field of power grid safety, in particular to a method, a device and equipment for diagnosing defects of a power transmission line and a computer readable storage medium.
Background
Under the background and market trend of national power grid construction of three types and two networks, the construction of the power internet of things opens up a new path for safer operation, more lean management, more accurate investment and better service of the power grid.
The transmission line is an important component of the power system, and whether the transmission line is used for normally and efficiently transmitting current energy is a problem that the normal operation of a power grid needs important attention. Therefore, in the power transmission operation process of the power transmission line, the temperature is one of the key factors for representing whether the power transmission line works normally, and the fire is easily caused by the overhigh temperature of the power transmission line, so that greater potential safety hazards are generated. At present, when the fault defect of the power transmission line is detected and identified in China, the temperature of the power transmission line is mainly detected, a corresponding temperature alarm threshold value is set according to experience, when the temperature exceeds the temperature alarm threshold value, the power transmission line is considered to have the fault defect, and an alarm is immediately given out so as to remind a worker to process the fault defect in time. The fault detection and alarm mode is often low in accuracy and not beneficial to maintenance and management of normal operation of the power transmission line.
Disclosure of Invention
The invention aims to provide a defect diagnosis method, a defect diagnosis device, equipment and a computer readable storage medium for a power transmission line, which can carry out pre-estimation diagnosis on the faults of the power transmission line before obvious fault defects occur to the power transmission line and are beneficial to maintenance of the power transmission line.
In order to solve the technical problem, the invention provides a method for diagnosing the defects of the power transmission line, which comprises the following steps:
collecting temperature characteristic data, current-carrying characteristic data and environment characteristic data of a power transmission line to be detected;
inputting the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data into a defect discriminator obtained by pre-training to determine whether the power transmission line to be detected has defects;
the defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, the current carrying characteristic data and the environment characteristic data of the power transmission line.
Optionally, the collecting the temperature characteristic data, the current-carrying characteristic data and the environmental characteristic data of the power transmission line to be measured includes:
collecting temperature data, current data and environment data of the power transmission line to be detected;
obtaining the temperature characteristic data at least comprising a high-load lead temperature daily average value, a high-load lead temperature daily standard deviation, a low-load lead temperature daily average value, a low-load lead temperature daily standard deviation, a lead temperature daily average value, a lead temperature daily standard deviation, a high-load lead standard exceeding temperature time daily median value, a high-load lead standard exceeding temperature time daily average value, a high-load lead standard exceeding temperature daily time length standard deviation, a low-load lead standard exceeding temperature time daily median value, a low-load lead standard exceeding temperature time daily average value and a low-load lead standard exceeding temperature daily time length standard deviation according to the temperature data;
obtaining the current-carrying characteristic data at least comprising the current of the wire according to the current data;
and obtaining the environmental characteristic data at least comprising the environmental wind speed, the sunshine intensity and the environmental temperature according to the environmental data.
Optionally, the process of pre-training the defect discriminator includes:
collecting historical temperature characteristic data, historical current-carrying characteristic data and historical environment characteristic data of a plurality of defective power transmission lines as sample data of a training sample set;
and establishing a clustering model, and adopting a K-means clustering algorithm to analyze and operate the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data of each sample point of the training sample set to determine the defect discriminator.
Optionally, creating a clustering model, performing an analysis operation on the historical temperature characteristic data, the historical current-carrying characteristic data, and the historical environmental characteristic data of each sample point of the training sample set by using a K-means clustering algorithm, and determining the defect discriminator includes:
analyzing and operating the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data corresponding to each sample point of the training sample set according to a K-means clustering algorithm, determining an optimal clustering number K and a clustering center point, and eliminating abnormal sample points;
and calculating the sum of the separation lengths from each effective sample point to the clustering center point after the abnormal sample points are removed from the training sample set, and determining a classification threshold value based on the incremental change of the separation lengths.
Optionally, after determining the defect discriminator, the method further includes:
randomly acquiring temperature characteristic data, current carrying characteristic data and environment characteristic data of a plurality of different power transmission lines as sample data in a test sample set;
inputting the sample data in the test sample set into the defect discriminator to obtain the defect discrimination result of each test sample set;
and judging whether the accuracy of the defect judgment result reaches a preset accuracy threshold, and if not, re-executing the process of pre-training the defect judger.
A defect diagnosis apparatus for an electric transmission line, comprising:
the data acquisition module is used for acquiring temperature characteristic data, current-carrying characteristic data and environment characteristic data of the power transmission line to be detected;
the defect judging module is used for inputting the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data into a defect discriminator obtained by pre-training to determine whether the power transmission line to be detected has defects; the defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, the current carrying characteristic data and the environment characteristic data of the power transmission line.
Optionally, the data acquisition module is configured to acquire temperature data, current data, and environmental data of the power transmission line to be detected; obtaining the temperature characteristic data at least comprising a high-load lead temperature daily average value, a high-load lead temperature daily standard deviation, a low-load lead temperature daily average value, a low-load lead temperature daily standard deviation, a lead temperature daily average value, a lead temperature daily standard deviation, a high-load lead standard exceeding temperature time daily median value, a high-load lead standard exceeding temperature time daily average value, a high-load lead standard exceeding temperature daily time length standard deviation, a low-load lead standard exceeding temperature time daily median value, a low-load lead standard exceeding temperature time daily average value and a low-load lead standard exceeding temperature daily time length standard deviation according to the temperature data; obtaining the flow characteristic data at least comprising a wire current from the current data; and obtaining the environmental characteristic data at least comprising the environmental wind speed, the sunshine intensity and the environmental temperature according to the environmental data.
Optionally, the system further comprises a model training module, configured to acquire historical temperature characteristic data, historical current-carrying characteristic data, and historical environment characteristic data of the plurality of defective power transmission lines, as sample data of a training sample set; and establishing a clustering model, and adopting a K-means clustering algorithm to analyze and operate the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data of each sample point of the training sample set to determine the defect discriminator.
A defect diagnosis apparatus of a power transmission line, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for diagnosing a defect of the power transmission line according to any one of the above items when the computer program is executed.
A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for diagnosing defects of an electric transmission line according to any one of the preceding claims.
The invention provides a defect diagnosis method of a power transmission line, which comprises the steps of collecting temperature characteristic data, current-carrying characteristic data and environment characteristic data of the power transmission line to be detected; inputting the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data into a defect discriminator obtained by pre-training to determine whether the power transmission line to be detected has defects; the defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, current carrying characteristic data and the environment characteristic data of the power transmission line.
When the defect of the power transmission line is diagnosed, the current-carrying characteristic data and the environmental characteristic data are fully considered on the basis of acquiring the temperature characteristic data by referring to the temperature of the power transmission line singly, namely, the influence of factors in various aspects such as temperature, current and environment on the normal operation of the power transmission line is fully considered in the method, the fault defect of the power transmission line is evaluated based on the characteristic changes in various aspects such as temperature, current and environment, the evaluation mode can play a role in estimating the defect of the power transmission line in advance to a certain extent, the defect fault of the power transmission line is not required to be found when the temperature of the power transmission line is overhigh, the further serious deterioration of the defect fault is avoided, and the method is favorable for reminding maintenance personnel to process in time; and the defect fault of the power transmission line is determined based on the characteristic change of each aspect, so that the accuracy of defect fault prediction and evaluation can be improved to a certain extent, and the efficient operation management of the power transmission line is facilitated.
The application also provides a defect diagnosis device, equipment and a computer readable storage medium of the power transmission line, and the beneficial effects are achieved.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for diagnosing a defect of a power transmission line according to an embodiment of the present application;
fig. 2 is a schematic diagram of a cluster analysis result provided in the embodiment of the present application;
fig. 3 is a distribution line graph of a cluster center provided in an embodiment of the present application;
FIG. 4 is a diagram illustrating relative incremental values from a sample point to a cluster center point in a training sample set according to an embodiment of the present disclosure;
fig. 5 is a block diagram of a defect diagnosis apparatus for a power transmission line according to an embodiment of the present invention.
Detailed Description
In the traditional method for diagnosing the defects of the power transmission line, the temperature value of the power transmission line is mainly acquired in real time, and when the temperature value of the power transmission line reaches a certain threshold value, the power transmission line is considered to be in an abnormal working state. However, for the power transmission line, the initial stage of the fault defect usually does not directly cause the temperature to be excessively high, but the power transmission line shows a certain characteristic in temperature change, and the power transmission line is also promoted to generate the defect due to the change of the ambient environment, the change of the current and the like. Therefore, the defect fault of the power transmission line is determined through the temperature threshold, and is usually reflected through temperature rise when the fault of the power transmission line is serious, so that the damage to the power transmission line is serious, the maintenance and the management of the power transmission line are not facilitated, and the service life of the power transmission line is also influenced. If the fault defect detection of the power transmission line is realized only by reducing the temperature threshold value, the inaccuracy of the defect detection is improved to a certain extent, so that the problem of frequent false alarm is caused, and the maintenance and management of the power transmission line are not facilitated.
Therefore, the technical scheme capable of evaluating and diagnosing potential defect faults of the power transmission line is provided.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, fig. 1 is a schematic flowchart of a defect diagnosis method for an electric transmission line provided in an embodiment of the present application, where the defect diagnosis method may include:
s11: and collecting temperature characteristic data, current-carrying characteristic data and environment characteristic data of the power transmission line to be measured.
The temperature characteristic data can be obtained by analyzing the temperature data of the power transmission conductor measured in real time by a temperature sensor on a tower pole strain clamp on the power transmission line. The temperature characteristic data may include a high-load wire temperature daily average value, a high-load wire temperature daily standard deviation, a low-load wire temperature daily average value, a low-load wire temperature daily standard deviation, a wire temperature daily average value, a wire temperature daily standard deviation, a high-load wire exceeding temperature time daily median value, a high-load wire exceeding temperature time daily average value, a high-load wire exceeding temperature daily time length standard deviation, a low-load wire exceeding temperature time daily median value, a low-load wire exceeding temperature time daily average value, a low-load wire exceeding temperature daily time length standard deviation, and the like.
For the power transmission line with the hidden danger of the defect fault, the temperature characteristic data of the power transmission line is different from the temperature characteristic data of the normal power transmission line, and based on the difference of the temperature characteristic data of the normal power transmission line and the power transmission line with the hidden danger of the defect fault, the power transmission line with the hidden danger of the defect fault can be predicted in advance when the defect fault of the power transmission line with the hidden danger of the defect fault is not obvious, so that the power transmission line can be maintained in time.
The current-carrying characteristic data mainly refers to but is not limited to the current of a wire on the power transmission line, and the current of the wire can be obtained based on the current data measured by a wire current sensor on the power transmission line. For a power transmission line, an excessive lead current is also one of the important reasons for causing a fault of the power transmission line and further causing an excessive temperature of the power transmission line. Therefore, the current-carrying characteristic data of the wire current also represents one of data of whether the transmission line has faults or not to a certain extent.
The environmental characteristic data in this embodiment at least includes an ambient wind speed, a solar radiation intensity, and an ambient temperature. Similar to the current-carrying characteristic data, when the wind speed is too high (the risk of scraping the section exists) in the environment, the sunlight is too strong (the temperature of the power transmission line is directly high), and the environment temperature is too high or too low (icing), the defect fault of the power transmission line can be caused. By collecting the environmental characteristic data in real time, whether the transmission line has the defect fault or not can be predicted to a certain extent.
Therefore, in the embodiment, when the fault of the power transmission line is predicted, the temperature characteristic data capable of reflecting the defect fault of the power transmission line, the current-carrying characteristic data capable of causing the defect fault of the power transmission line and the environmental characteristic data are referred to simultaneously, and whether the hidden danger of the potential defect fault exists in the power transmission line is analyzed, predicted and diagnosed together, so that the prediction and diagnosis of the fault of the power transmission line are more accurately realized, and the power transmission line is maintained and processed timely.
S12: and inputting the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data into a defect discriminator obtained by pre-training to determine whether the power transmission line to be detected has defects.
The defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, current carrying characteristic data and the environment characteristic data of the power transmission line.
In order to simplify the analysis process based on the temperature characteristic data, the current-carrying characteristic data and the environmental characteristic data, in this embodiment, a defect discriminator for the correspondence between the three different characteristic data and the transmission line with hidden defects is created in advance. The defect discriminator may be created based on computer learning training.
In an optional embodiment of the present application, the creation process of the defect discriminator may be as follows:
collecting historical temperature characteristic data, historical current-carrying characteristic data and historical environment characteristic data of a plurality of defective power transmission lines as sample data of a training sample set;
and (3) creating a clustering model, and adopting a K-means clustering algorithm to analyze and calculate the historical temperature characteristic data, the historical current carrying characteristic data and the historical environment characteristic data of each sample point of the training sample set to determine a defect discriminator.
The plurality of defective power transmission lines in this embodiment refer to power transmission lines in which a defective fault has occurred. The historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data of the defective power transmission line can be obtained by monitoring temperature data, lead current data and environment data of a large number of power transmission lines in real time, taking the power transmission line with the defective fault as the defective power transmission line once some power transmission lines have the defective fault, and performing characteristic analysis based on the temperature data, the lead current data and the environment data in a preset time period before the defective power transmission line generates the obvious defective fault so as to determine the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data of the defective power transmission line, which are equivalent to the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data in the embodiment.
After sample data in a sample set for computer training learning are obtained, analyzing and learning the sample set by adopting a K-means clustering algorithm to determine the characteristics of the temperature, current carrying and environment of the power transmission line with the defect fault. Analyzing and operating historical temperature characteristic data, historical current-carrying characteristic data and historical environment characteristic data corresponding to each sample point of the training sample set based on the K-means clustering algorithm, and determining an optimal clustering number K and a clustering center point; meanwhile, the distance between each sample point and each clustering center can be determined through the determined optimal clustering number K, and when a sample point which is too far away from the Euclidean geometric distance of the clustering center exists, the sample point is indicated to be an abnormal sample point, and the sample point can be removed, so that the accuracy of the defect discriminator determined based on sample point training is ensured.
As shown in fig. 2, fig. 2 is a schematic diagram of a distribution of clustering samples provided in the embodiment of the present application, and fig. 2 is a sample point distribution example for determining an optimal clustering number of 3 by performing clustering operation on a training set P.
And processing the abnormal points on the basis of the clustering result to obtain 126 effective sampling points. The main distribution is shown in table 1.
Table 1:
| categories | CLSTR1 | CLSTR2 | CLSTR3 | Total up to |
| Number of samples | 25 | 64 | 37 | 126 |
As shown in fig. 2, for each cluster, each dimension feature value corresponding to the cluster center point can be obtained.
As shown in fig. 3, the feature is used as the abscissa and the feature value is used as the ordinate, a line graph is drawn, and the distribution of the three cluster center points is checked. As can be seen from fig. 3, fig. 3 shows the difference change of 9 temperature characteristic data, such as the high-load lead temperature daily average value, the high-load lead temperature daily standard deviation, the low-load lead temperature daily standard deviation, the lead temperature daily average value, the lead temperature daily standard deviation, the high-load lead out-of-standard temperature time daily median number, the high-load lead out-of-standard temperature time daily average value, the high-load lead out-of-standard temperature daily time standard deviation, the low-load lead out-of-standard temperature time daily median number, the low-load lead out-of-standard temperature daily average value, and the low-load lead out-of-standard temperature daily time standard deviation, in the above three clusters.
It can be seen that, on 6 temperature characteristics of the daily average value of the temperature of the high-load lead, the daily standard deviation of the temperature of the high-load lead, the daily average value of the temperature of the low-load lead, the daily standard deviation of the temperature of the low-load lead, the daily average value of the temperature of the lead and the daily standard deviation of the temperature of the lead, the overall trends of the CLSTR1 (cluster 1) and the CLSTR2 (cluster 2) are relatively close, and the characteristic values corresponding to the CLSTR2 (cluster 2) are all lower than the characteristic values corresponding to the CLSTR1 (cluster 1); but CLSTR3 (cluster 3) and CLSTR1 (cluster 1) are opposite in trend overall.
Specifically, there are the following differences:
(1) for the conductors in CLSTR1, the following conclusions are drawn:
the temperature daily average index of the high-load conductor is normal, but the transmission conductor belongs to a line with a small proportion in a high-load period;
the mean value of the temperature of the low-load tower conductor is high, which indicates that the temperature of the transmission conductor is larger under the low-load condition;
the day-to-day average index of the temperature of the conductor has large change, which indicates that the overall index of the transmission conductor is abnormal.
This type of power transmission conductor is therefore a conductor with temperature anomalies characteristic of a power transmission line with a small typical high load period occupancy.
(2) For the conductors in CLSTR2, the following conclusions are drawn:
the daily average index of the temperature of the high-load conductor is the highest, which shows that the temperature of the transmission conductor seriously exceeds the standard under the condition of high load;
the temperature daily average index of the low-load conductor is higher, which shows that the temperature of the power transmission conductor is higher than that of the power transmission conductor under the condition of low load than that under the normal condition;
the conductor temperature daily average value index is also higher, which indicates that the overall index of the transmission conductor is higher.
It can be seen that the temperature of the wire is uniformly higher, so that the temperature characteristics of the power transmission line with serious defects are similar from the temperature characteristic point of view.
(3) For the conductors in CLSTR3, the following conclusions are drawn:
the daily average index of the temperature of the high-load conductor is higher, which shows that the temperature of the transmission conductor exceeds the standard under the high-load condition;
the temperature daily average index of the low-load conductor is normal, which shows that the temperature change of the transmission conductor is not large under the normal load condition;
the mean value index of the temperature of the lead is higher, which shows that the temperature characteristics of the transmission lead are similar to those of the transmission lead with common defects.
Therefore, from the viewpoint of temperature characteristics, the temperature characteristics are similar to those of a typical general-defect power transmission line conductor.
(4) In a general view:
the temperature of the wire in the CLSTR2 has the characteristic of the temperature of the typical serious defect wire;
the temperature of the wires in the CLSTR1 and the CLSTR3 is similar to the temperature characteristics of the wires of the transmission line with general defects.
After determining each cluster center point, further calculating the sum of the distances from each effective sample point x to the center point in the training set P, and sorting, and drawing a distance increment graph, as shown in fig. 4: in fig. 4, the x-axis represents the training sample number, and the y-axis represents the sum of the distances from the sample point to the center point. As can be seen from fig. 4:
when x is less than 117, the increasing speed of the spacing distance is more gradual;
when x >117, the increase rate of the separation distance is faster;
this yields: x 117 is the inflection point in the training sample set. Therefore, its corresponding bay length, i.e., y value, is set as the threshold for classification: TNR ═ y (x ═ 117) ═ 2.323337.
When the defect diagnosis is carried out on the power transmission line based on the classification threshold, the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data corresponding to the power transmission line can be substituted into the defect identifier, and the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data of the power transmission line are used as sample points to carry out category attribution judgment. And when the sum of the distances from the sample point corresponding to the power transmission line to the three clustering central points is greater than a threshold value, judging the power transmission line with the defect hidden danger, and otherwise, judging the power transmission line without the defect hidden danger.
Certainly, after the defect discriminator is obtained through training, the defect discriminator can be further verified, and a plurality of temperature characteristic data, current carrying characteristic data and environment characteristic data with and without defect faults can be randomly extracted to be used as sample data of the test sample set; inputting the test sample set into a defect discriminator to obtain the defect discrimination result of each verification sample; and judging whether the accuracy of the defect judgment result reaches a preset accuracy threshold, if the accuracy of the judgment result reaches a preset accuracy requirement, indicating that the defect recognizer can be put into application, and if the accuracy of the judgment result does not reach the preset accuracy requirement, re-executing the step of the process of pre-training the defect recognizer, and re-performing clustering operation to determine a more accurate defect recognizer.
In the following, the defect diagnosis apparatus for an electric transmission line according to an embodiment of the present invention is introduced, and the defect diagnosis apparatus for an electric transmission line described below and the defect diagnosis method for an electric transmission line described above may be referred to correspondingly.
Fig. 5 is a block diagram of a defect diagnosis apparatus for an electric transmission line according to an embodiment of the present invention, where the defect diagnosis apparatus for an electric transmission line in fig. 5 includes:
the data acquisition module 100 is used for acquiring temperature characteristic data, current-carrying characteristic data and environment characteristic data of the power transmission line to be detected;
a defect judging module 200, configured to input the temperature characteristic data, the current-carrying characteristic data, and the environment characteristic data into a defect discriminator obtained through pre-training, and determine whether a defect exists in the power transmission line to be detected; the defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, the current carrying characteristic data and the environment characteristic data of the power transmission line.
In an optional embodiment of the present application, the data acquisition module 100 is configured to acquire temperature data, current data, and environmental data of the power transmission line to be detected; obtaining the temperature characteristic data at least comprising a high-load lead temperature daily average value, a high-load lead temperature daily standard deviation, a low-load lead temperature daily average value, a low-load lead temperature daily standard deviation, a lead temperature daily average value, a lead temperature daily standard deviation, a high-load lead standard exceeding temperature time daily median value, a high-load lead standard exceeding temperature time daily average value, a high-load lead standard exceeding temperature daily time length standard deviation, a low-load lead standard exceeding temperature time daily median value, a low-load lead standard exceeding temperature time daily average value and a low-load lead standard exceeding temperature daily time length standard deviation according to the temperature data; obtaining the current-carrying characteristic data at least comprising the current of the wire according to the current data; and obtaining the environmental characteristic data at least comprising the environmental wind speed, the sunshine intensity and the environmental temperature according to the environmental data.
In an optional embodiment of the present application, the system further includes a model training module, configured to acquire historical temperature characteristic data, historical current-carrying characteristic data, and historical environment characteristic data of the plurality of defective power transmission lines, as sample data of a training sample set; and establishing a clustering model, and adopting a K-means clustering algorithm to analyze and operate the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data of each sample point of the training sample set to determine the defect discriminator.
In an optional embodiment of the present application, the model training module is specifically configured to perform analysis and operation on the historical temperature characteristic data, the historical current-carrying characteristic data, and the historical environmental characteristic data corresponding to each sample point of the training sample set according to a K-means clustering algorithm, determine an optimal clustering number K and a clustering center point, and reject abnormal sample points; and calculating the sum of the separation lengths from each effective sample point to the clustering center point after the abnormal sample points are removed from the training sample set, and determining a classification threshold value based on the incremental change of the sum of the separation lengths.
In an optional embodiment of the present application, the system further includes a test module, configured to randomly acquire temperature characteristic data, current carrying characteristic data, and environmental characteristic data of a plurality of different power transmission lines as sample data in a test sample set after determining the defect discriminator; inputting the sample data in the test sample set into the defect discriminator to obtain the defect discrimination result of each test sample set; and judging whether the accuracy of the defect judgment result reaches a preset accuracy threshold, and if not, re-executing the process of pre-training the defect judger.
The defect diagnosis device for the power transmission line of the embodiment is used for implementing the defect diagnosis method for the power transmission line, and therefore, a specific implementation manner of the defect diagnosis device for the power transmission line can be seen in the foregoing embodiment section of the defect diagnosis method for the power transmission line, and is not described herein again.
The present application also provides an embodiment of a defect diagnosis apparatus for a power transmission line, which may include:
a memory for storing a computer program;
a processor for implementing the steps of the method for diagnosing a defect of the power transmission line according to any one of the above items when the computer program is executed.
The method for diagnosing the defects of the power transmission line implemented by the processor in the embodiment may include: collecting temperature characteristic data, current-carrying characteristic data and environment characteristic data of a power transmission line to be detected; inputting the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data into a defect discriminator obtained by pre-training to determine whether the power transmission line to be detected has defects; the defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, the current carrying characteristic data and the environment characteristic data of the power transmission line.
The device provided by the embodiment can predict the hidden danger of the defect fault of the power transmission line by acquiring the temperature characteristic data representing the defect of the power transmission line and referring to the current-carrying characteristic data and the environmental characteristic data which can cause the defect fault of the power transmission line and combining machine training based on the temperature characteristic data, the current-carrying characteristic data and the environmental characteristic data, so that the defect fault of the power transmission line can be timely processed and maintained on the basis of ensuring the accuracy of prediction of the fault of the power transmission line, and the normal working operation of the power transmission line is facilitated.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for diagnosing a defect of an electric transmission line as defined in any one of the above.
The computer-readable storage medium may include Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include elements inherent in the list. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element. In addition, parts of the above technical solutions provided in the embodiments of the present application, which are consistent with the implementation principles of corresponding technical solutions in the prior art, are not described in detail so as to avoid redundant description.
The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (10)
1. A method for diagnosing a defect of a power transmission line, comprising:
collecting temperature characteristic data, current-carrying characteristic data and environment characteristic data of a power transmission line to be detected;
inputting the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data into a defect discriminator obtained by pre-training to determine whether the power transmission line to be detected has defects;
the defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, the current carrying characteristic data and the environment characteristic data of the power transmission line.
2. The method for diagnosing the defects of the power transmission line according to claim 1, wherein the step of collecting the temperature characteristic data, the current-carrying characteristic data and the environmental characteristic data of the power transmission line to be tested comprises the steps of:
collecting temperature data, current data and environment data of the power transmission line to be detected;
obtaining the temperature characteristic data at least comprising a high-load lead temperature daily average value, a high-load lead temperature daily standard deviation, a low-load lead temperature daily average value, a low-load lead temperature daily standard deviation, a lead temperature daily average value, a lead temperature daily standard deviation, a high-load lead standard exceeding temperature time daily median value, a high-load lead standard exceeding temperature time daily average value, a high-load lead standard exceeding temperature daily time length standard deviation, a low-load lead standard exceeding temperature time daily median value, a low-load lead standard exceeding temperature time daily average value and a low-load lead standard exceeding temperature daily time length standard deviation according to the temperature data;
obtaining the current-carrying characteristic data at least comprising the current of the wire according to the current data;
and obtaining the environmental characteristic data at least comprising the environmental wind speed, the sunshine intensity and the environmental temperature according to the environmental data.
3. The method of diagnosing a defect in an electric transmission line according to claim 1, wherein the process of training the defect discriminator in advance comprises:
collecting historical temperature characteristic data, historical current-carrying characteristic data and historical environment characteristic data of a plurality of defective power transmission lines as sample data of a training sample set;
and establishing a clustering model, and adopting a K-means clustering algorithm to analyze and operate the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data of each sample point of the training sample set to determine the defect discriminator.
4. The method for diagnosing the defects of the power transmission line according to claim 3, wherein a clustering model is created, and a K-means clustering algorithm is adopted to perform analysis operation on the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environmental characteristic data of each sample point of the training sample set to determine the defect discriminator, and the method comprises the following steps:
analyzing and operating the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data corresponding to each sample point of the training sample set according to a K-means clustering algorithm, determining an optimal clustering number K and a clustering center point, and eliminating abnormal sample points;
and calculating the sum of the separation lengths from each effective sample point to the clustering center point after the abnormal sample points are removed from the training sample set, and determining a classification threshold value based on the incremental change of the sum of the separation lengths.
5. The method of diagnosing a defect in an electric transmission line according to claim 3, further comprising, after determining the defect discriminator:
randomly acquiring temperature characteristic data, current carrying characteristic data and environment characteristic data of a plurality of different power transmission lines as sample data in a test sample set;
inputting the sample data in the test sample set into the defect discriminator to obtain the defect discrimination result of each test sample set;
and judging whether the accuracy of the defect judgment result reaches a preset accuracy threshold, and if not, re-executing the process of pre-training the defect judger.
6. A defect diagnosis apparatus for an electric transmission line, comprising:
the data acquisition module is used for acquiring temperature characteristic data, current-carrying characteristic data and environment characteristic data of the power transmission line to be detected;
the defect judging module is used for inputting the temperature characteristic data, the current-carrying characteristic data and the environment characteristic data into a defect discriminator obtained by pre-training to determine whether the power transmission line to be detected has defects; the defect discriminator is a model of the corresponding relation between the defects of the power transmission line and the temperature characteristic data, the current carrying characteristic data and the environment characteristic data of the power transmission line.
7. The defect diagnosis device of the power transmission line according to claim 6, wherein the data acquisition module is configured to acquire temperature data, current data and environmental data of the power transmission line to be detected; obtaining the temperature characteristic data at least comprising a high-load lead temperature daily average value, a high-load lead temperature daily standard deviation, a low-load lead temperature daily average value, a low-load lead temperature daily standard deviation, a lead temperature daily average value, a lead temperature daily standard deviation, a high-load lead standard exceeding temperature time daily median value, a high-load lead standard exceeding temperature time daily average value, a high-load lead standard exceeding temperature daily time length standard deviation, a low-load lead standard exceeding temperature time daily median value, a low-load lead standard exceeding temperature time daily average value and a low-load lead standard exceeding temperature daily time length standard deviation according to the temperature data; obtaining the current-carrying characteristic data at least comprising the current of the wire according to the current data; and obtaining the environmental characteristic data at least comprising the environmental wind speed, the sunshine intensity and the environmental temperature according to the environmental data.
8. The apparatus of claim 6, further comprising a model training module, configured to collect historical temperature characteristic data, historical current-carrying characteristic data, and historical environmental characteristic data of the plurality of defective power transmission lines as sample data of a training sample set; and establishing a clustering model, and adopting a K-means clustering algorithm to analyze and operate the historical temperature characteristic data, the historical current-carrying characteristic data and the historical environment characteristic data of each sample point of the training sample set to determine the defect discriminator.
9. A defect diagnosis apparatus for an electric transmission line, characterized by comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for diagnosing defects of an electric transmission line according to any one of claims 1 to 5 when executing said computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for diagnosing defects of an electric transmission line according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011342125.4A CN112417763A (en) | 2020-11-25 | 2020-11-25 | Defect diagnosis method, device and equipment for power transmission line and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011342125.4A CN112417763A (en) | 2020-11-25 | 2020-11-25 | Defect diagnosis method, device and equipment for power transmission line and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417763A true CN112417763A (en) | 2021-02-26 |
Family
ID=74842415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011342125.4A Pending CN112417763A (en) | 2020-11-25 | 2020-11-25 | Defect diagnosis method, device and equipment for power transmission line and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417763A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114091705A (en) * | 2021-11-26 | 2022-02-25 | 国网四川省电力公司电力科学研究院 | Power system instability analysis method and device, electronic equipment and storage medium |
| CN114201884A (en) * | 2021-12-16 | 2022-03-18 | 中国电力科学研究院有限公司 | Relay protection defect diagnosis method and device based on expert rule deduction |
| CN116054414A (en) * | 2023-03-06 | 2023-05-02 | 广东电网有限责任公司佛山供电局 | Line defect hidden danger monitoring method, device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784392A (en) * | 2017-10-27 | 2018-03-09 | 华北电力科学研究院有限责任公司 | A kind of the defects of transmission line of electricity based on machine learning Forecasting Methodology and device |
| CN109579914A (en) * | 2018-12-24 | 2019-04-05 | 国网山西省电力公司检修分公司 | A kind of operation conditions determination method, device, equipment and the medium of transmission line of electricity |
| KR20190066207A (en) * | 2017-12-05 | 2019-06-13 | 주식회사 레딕스 | Traditional Market Electrical Fire Prevention System and Method |
| CN110334127A (en) * | 2019-07-04 | 2019-10-15 | 国网江苏省电力有限公司 | A kind of distribution network line fault law mining method, system and storage medium |
| CN110533331A (en) * | 2019-08-30 | 2019-12-03 | 广东电网有限责任公司江门供电局 | A kind of fault early warning method and system based on transmission line of electricity data mining |
| CN111652448A (en) * | 2020-07-08 | 2020-09-11 | 广东电网有限责任公司清远供电局 | Method, device and system for predicting defect rate of power transmission line |
-
2020
- 2020-11-25 CN CN202011342125.4A patent/CN112417763A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784392A (en) * | 2017-10-27 | 2018-03-09 | 华北电力科学研究院有限责任公司 | A kind of the defects of transmission line of electricity based on machine learning Forecasting Methodology and device |
| KR20190066207A (en) * | 2017-12-05 | 2019-06-13 | 주식회사 레딕스 | Traditional Market Electrical Fire Prevention System and Method |
| CN109579914A (en) * | 2018-12-24 | 2019-04-05 | 国网山西省电力公司检修分公司 | A kind of operation conditions determination method, device, equipment and the medium of transmission line of electricity |
| CN110334127A (en) * | 2019-07-04 | 2019-10-15 | 国网江苏省电力有限公司 | A kind of distribution network line fault law mining method, system and storage medium |
| CN110533331A (en) * | 2019-08-30 | 2019-12-03 | 广东电网有限责任公司江门供电局 | A kind of fault early warning method and system based on transmission line of electricity data mining |
| CN111652448A (en) * | 2020-07-08 | 2020-09-11 | 广东电网有限责任公司清远供电局 | Method, device and system for predicting defect rate of power transmission line |
Non-Patent Citations (4)
| Title |
|---|
| 曹文思;吴擎;徐铭铭;牛荣泽;: "基于分形理论与聚类分析的小电阻接地***高阻接地保护方法", 电力自动化设备, no. 04 * |
| 田浩;章涵;王海涛;何君;范鹏;郭钧天;罗飞;: "聚合时空特征的新疆750 kV特高压输电线路缺陷关联分析", 电力***保护与控制, no. 06 * |
| 郑茂然;余江;陈宏山;高宏慧;张静伟;吕梁;刘智勇;: "基于大数据的输电线路故障预警模型设计", 南方电网技术, no. 04 * |
| 金鼎;: "输电线路综合在线监测***关键技术分析", 科技风, no. 09 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114091705A (en) * | 2021-11-26 | 2022-02-25 | 国网四川省电力公司电力科学研究院 | Power system instability analysis method and device, electronic equipment and storage medium |
| CN114201884A (en) * | 2021-12-16 | 2022-03-18 | 中国电力科学研究院有限公司 | Relay protection defect diagnosis method and device based on expert rule deduction |
| CN116054414A (en) * | 2023-03-06 | 2023-05-02 | 广东电网有限责任公司佛山供电局 | Line defect hidden danger monitoring method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112417763A (en) | Defect diagnosis method, device and equipment for power transmission line and storage medium | |
| CN112505549B (en) | New energy automobile battery abnormity detection method based on isolated forest algorithm | |
| US6088658A (en) | Statistical pattern analysis methods of partial discharge measurements in high voltage insulation | |
| WO2018028005A1 (en) | Fault detection algorithm for battery panel in large-scale photovoltaic power station | |
| CN108802535B (en) | Screening method, main interference source identification method and device, server and storage medium | |
| CN116304766A (en) | Multi-sensor-based quick assessment method for state of switch cabinet | |
| CN115048985B (en) | Electrical equipment fault discrimination method | |
| CN116739829B (en) | Big data-based power data analysis method, system and medium | |
| CN115865649A (en) | Intelligent operation and maintenance management control method, system and storage medium | |
| CN111579121A (en) | Method for diagnosing temperature fault in new energy automobile battery pack on line based on big data | |
| CN112904148A (en) | Intelligent cable operation monitoring system, method and device | |
| CN113125903A (en) | Line loss anomaly detection method, device, equipment and computer-readable storage medium | |
| CN115526258A (en) | Power system transient stability evaluation method based on Spearman correlation coefficient feature extraction | |
| CN113236595B (en) | Fan fault analysis method, device, equipment and readable storage medium | |
| CN110689324A (en) | Auxiliary judging method for detection result of distribution transformer | |
| CN114487705A (en) | Power grid equipment fault positioning detection method | |
| CN117491813A (en) | Insulation abnormality detection method for power battery system of new energy automobile | |
| CN116520068B (en) | Diagnostic method, device, equipment and storage medium for electric power data | |
| CN113220799A (en) | Big data early warning management system | |
| CN117318614A (en) | Photovoltaic inverter fault prediction method | |
| CN116865672A (en) | Photovoltaic module abnormality recognition method and device and computer readable storage medium | |
| CN115809805A (en) | Power grid multi-source data processing method based on edge calculation | |
| CN114997375A (en) | Insulator surface metal pollution model building system in air type switch cabinet | |
| CN114597886A (en) | Power distribution network operation state evaluation method based on interval type two fuzzy clustering analysis | |
| CN113591909A (en) | Abnormality detection method, abnormality detection device, and storage medium for power system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |