CN117169657A - High-voltage cable state monitoring method and system based on artificial intelligence - Google Patents
High-voltage cable state monitoring method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117169657A CN117169657A CN202311450376.8A CN202311450376A CN117169657A CN 117169657 A CN117169657 A CN 117169657A CN 202311450376 A CN202311450376 A CN 202311450376A CN 117169657 A CN117169657 A CN 117169657A
- Authority
- CN
- China
- Prior art keywords
- data
- temperature
- current
- artificial intelligence
- voltage cable
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 16
- 230000005856 abnormality Effects 0.000 claims abstract description 12
- 238000002372 labelling Methods 0.000 claims abstract description 12
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 20
- 230000005611 electricity Effects 0.000 claims description 16
- 238000009826 distribution Methods 0.000 claims description 7
- 238000004040 coloring Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 abstract description 5
- 238000010422 painting Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 6
- 239000003086 colorant Substances 0.000 description 4
- 238000010183 spectrum analysis Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 239000011810 insulating material Substances 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005485 electric heating Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Abstract
The invention provides a high-voltage cable state monitoring method and system based on artificial intelligence, comprising the following steps: drawing a power grid topological graph, collecting historical voltage signals, current signals and temperature data of each reporting period of each detection point of each phase of power grid, and determining higher harmonic ratio and temperature increment value; changing the thickness of line segments in the topological graph according to the temperature increase value, painting the topological graph according to the higher harmonic ratio, and carrying out abnormal labeling on the image; training a neural network by using a historical monitoring image set, and collecting real-time data of a current period to obtain a current monitoring image; and inputting the current monitoring image into a first model, and detecting whether an abnormality exists. By the scheme, a complex mathematical model is not required to be established, so that the multi-branch power grid can be monitored.
Description
Technical Field
The invention relates to the field of high-voltage cable state monitoring, in particular to a high-voltage cable state monitoring method and system based on artificial intelligence.
Background
The high-voltage cable state monitoring refers to real-time monitoring of a high-voltage cable used in a power system so as to ensure normal operation and safety performance of the high-voltage cable. The high-voltage cable bears high voltage and high current in the process of transmitting electric energy, so that the state monitoring of the high-voltage cable is important for preventing faults and guaranteeing the stable operation of a power grid.
With the aging, damage, excessive electric field strength, accumulation of tip corona and other factors of the high-voltage cable insulating material, the problem of partial discharge is easy to occur. Partial discharge generates a current in the insulating material, and arcing and discharge phenomena occur. Partial discharge is a small-scale discharge phenomenon in cable insulation and may be an indication of potential failure. By monitoring partial discharge, problems of cable insulation can be found in advance, and the continuous development of large-scale faults is prevented.
Partial discharge monitoring is commonly performed in the prior art using partial discharge sensors that are mounted on a cable for capturing signals generated by the partial discharge. The sensors typically include electromagnetic sensors, capacitive sensors, ultrasonic sensors, etc. for detecting signals of electric fields, voltages, currents, sounds, etc., and after the corresponding signals are collected, information is subjected to high-frequency current transformer analysis, spectrum analysis, etc. using mathematical methods to locate specific fault points.
However, the method in the prior art generally requires a complex mathematical processing procedure, so that the analysis is generally performed only for a single cable, a complex mathematical model is required to be established for multi-branch multi-phase electricity, manual coarse positioning is required to be performed to a single cable in advance before the analysis in the prior art is used, and the method in the prior art is difficult to directly perform quick solution without manual participation.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a high-voltage cable state monitoring method and system based on artificial intelligence.
In one aspect of the invention, there is provided an artificial intelligence based high voltage cable condition monitoring method characterized in that the method comprises the steps of: step one, drawing a topological graph according to the actual distribution of a multi-branch power grid; step two, collecting historical voltage signals, current signals and temperature data of each reporting period of each phase of electricity of the multi-branch power grid at each detection point; step three, for the data of the same reporting period, determining the higher harmonic ratio according to the voltage signal and the current signal; determining the minimum temperature according to the temperature data, and subtracting the minimum temperature from other temperatures to obtain a temperature increase value; step four, changing the thickness of line segments in the topological graph according to the temperature increase value, determining RGB values according to respective higher harmonic ratios of three-phase power, and coloring the topological graph according to the determined RGB values to obtain a monitoring image; fifthly, if an abnormal state exists in the current period, marking the abnormal position on the monitored image; step six, repeating the steps three to five, and processing all historical data to obtain a historical monitoring image set; training a neural network by using the historical monitoring image set to obtain a first model; step seven, collecting real-time data of the current period; processing real-time data of the current period according to the third to fifth steps to obtain a current monitoring image; and inputting the current monitoring image into a first model, and detecting whether an abnormality exists.
Further, the changing the thickness of the line segment in the topological graph by the temperature increment value includes: new line thick = original line thick (1 + temperature increase value/5).
Further, the temperature between the two detection points is linearly interpolated.
Further, determining RGB values from respective higher harmonic ratios of the three-phase electricity includes: and (3) adopting Min-Max scaling to convert the higher harmonic ratio of each phase in the three-phase power into data of 0-255, and respectively corresponding the converted three data to three numbers in RGB values.
Further, the pixel color between the two detection points is linearly interpolated.
On the other hand, the invention also provides a high-voltage cable state monitoring system based on artificial intelligence, which is characterized by comprising the following modules: the drawing module is used for drawing a topological graph according to the actual distribution of the multi-branch power grid; the first collecting module is used for collecting historical voltage signals, current signals and temperature data of each reporting period of each phase of electricity of each detecting point of the multi-branch power grid; the calculation module is used for determining the higher harmonic ratio according to the voltage signal and the current signal for the data of the same reporting period; determining the minimum temperature according to the temperature data, and subtracting the minimum temperature from other temperatures to obtain a temperature increase value; the image processing module is used for changing the thickness of line segments in the topological graph according to the temperature increasing value, determining RGB values according to respective higher harmonic ratios of the three-phase power, and coloring the topological graph according to the determined RGB values to obtain a monitoring image; the labeling module is used for labeling the abnormal position on the monitored image if the abnormal state exists in the current period; the training module is used for operating the calculating module, the image processing module and the labeling module, processing all historical data and obtaining a historical monitoring image set; training a neural network by using the historical monitoring image set to obtain a first model; the detection module is used for collecting real-time data of the current period; processing real-time data of the current period according to the third to fifth steps to obtain a current monitoring image; and inputting the current monitoring image into a first model, and detecting whether an abnormality exists.
Further, the changing the thickness of the line segment in the topological graph according to the temperature increase value includes: new line thick = original line thick (1 + temperature increase value/5).
Further, the temperature between the two detection points is linearly interpolated.
Further, determining RGB values from respective higher harmonic ratios of the three-phase electricity includes: and (3) adopting Min-Max scaling to convert the higher harmonic ratio of each phase in the three-phase power into data of 0-255, and respectively corresponding the converted three data to three numbers in RGB values.
Further, the pixel color between the two detection points is linearly interpolated.
Through the technical scheme, the invention can produce the following beneficial effects:
the detection data of the power grid are converted into visual image data, so that abnormal point positions in the image can be conveniently identified by using a machine learning model. The mathematical model is prevented from being established manually by machine learning and automatic learning derivation, so that the abnormality of the complex multi-branch network can be identified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments 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 other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and detailed description.
The present embodiment solves the above problem by:
in one embodiment, referring to fig. 1, the present invention provides a high voltage cable state monitoring method based on artificial intelligence, specifically including:
and step one, drawing a topological graph according to the actual distribution of the multi-branch power grid.
A multi-branch grid refers to a grid structure in which there are multiple branches or branches in a power system. In an electrical power system, electrical energy is typically transmitted and distributed through multiple lines and transformers, forming a complex network of branch connections. Because in a multi-branch power grid, detected signals usually cross a plurality of nodes, so that the detected signals between different line segments are mutually interfered, a mathematical model is complex and difficult to model, the detection is usually carried out by a single cable in the prior art, and the embodiment can be directly applied to the multi-branch network. Since this embodiment only deals with the cable problem, when the topological graph is drawn according to the actual distribution of the power grid, only the cable structure can be drawn, and the three-phase electricity is regarded as one line segment.
Step two, collecting historical voltage signals, current signals and temperature data of each reporting period of each phase of electricity of the multi-branch power grid at each detection point.
Each phase of electricity refers to each electrical phase in a three-phase alternating current system. A three-phase electrical system, in which electrical energy is transmitted through three cabling, each of which is referred to as an electrical phase, offset 120 degrees from each other, is a common way to transmit and distribute electrical power with a high degree of efficiency and stability. The three electric phases are respectively A phase, B phase and C phase, each of which carries a part of the load in the power system, and are 120 degrees out of phase with each other to balance the load and current in the power system. Thus, the current, voltage and other parameters of each phase of electricity are taken into account when monitoring high voltage cables or performing power system analysis to ensure proper operation and fault detection of the power system.
For real-time monitoring of the power grid, detection points can be set at intervals in the power grid, and a voltage sensor, a current sensor and a temperature sensor are installed at each detection point of each phase of electricity in the multi-branch power grid to capture voltage, current and temperature data. The sensors are connected using appropriate data acquisition equipment to acquire real-time voltage, current and temperature data. Grid sensors are widely used in the existing power grid, and can acquire voltage signals, current signals and temperature data according to any existing technology. Further, in order to facilitate data analysis, it is also necessary to determine the frequency of data reporting, and since the power grid signal generally needs to be subjected to timing analysis, each reporting period is a timing sequence, and data in the reporting period is analyzed. The reporting period may be daily, hourly or more frequently, and may be adjusted as needed, which is not particularly limited in this embodiment.
For example, in each phase of electricity of the power grid, a group of sensors is arranged every 200 meters, data collected within 1 hour is reported every 1 hour, voltage and current can be time sequence data within 1 hour, and temperature can be average value or maximum value within 1 hour.
Further, for subsequent data analysis, the collected data is recorded in a database, including a time stamp, a numerical value, a detection point number, and the like. The data store may employ a database system, such as an SQL database or the like.
Step three, for the data of the same reporting period, determining the higher harmonic ratio according to the voltage signal and the current signal; determining the lowest temperature according to the temperature data, and subtracting the lowest temperature from other temperatures to obtain a temperature increase value.
The data in the same reporting period refers to the data of all detection points of the power grid to be analyzed in one collecting period, and the data in the same period reflect the state of the power grid in the reporting period.
The harmonic components can provide important information in diagnosing partial discharge problems, and partial discharge typically generates high frequency components and pulse signals, which are reflected in the harmonic components of current and voltage, and the harmonic ratio can be used to quantitatively evaluate the existence of the harmonic components, and when the ratio is high, partial discharge is likely to be represented, so the present embodiment selects the harmonic ratio as a detection index.
Determining the higher harmonic ratio involves performing a spectral analysis on the voltage signal and the current signal to identify the presence of different harmonic components and calculate the ratio thereof. The acquired signals are preprocessed, including removal of dc components, filtering, etc., in preparation for spectral analysis. And carrying out Fourier transform on the voltage signal and the current signal, converting the time domain signal into a frequency domain signal, analyzing the frequency spectrum after the Fourier transform, and identifying the frequency and the amplitude of each harmonic component. Higher harmonics generally refer to 3 harmonics and above, i.e., 3 times the fundamental frequency and above. Finding the corresponding harmonic frequency in the frequency spectrum and calculating the amplitude of the harmonic frequency; the ratio of the higher harmonics is calculated by comparing the amplitude of a particular higher harmonic with the amplitude of the fundamental frequency (50 Hz in china). The higher harmonic ratio can be expressed as: higher harmonic ratio = higher harmonic amplitude/fundamental frequency amplitude, so that the amplitude ratio of higher harmonics to fundamental frequency can be obtained.
When partial discharge exists, the temperature can be increased due to the electric heating effect, the temperature increase is one of indexes capable of reflecting the partial discharge, but the temperature detection error is large when the temperature is used alone due to the large external influence of the temperature, and the temperature is not usually used as a positioning index alone; the higher harmonic ratio is affected by different branches and different phases, and can not be completely and accurately positioned to an abnormal position; the present embodiment therefore uses harmonic and temperature positioning in combination.
Since the temperature of the cable varies with the ambient temperature in different time periods, the effect of the ambient temperature is removed. The minimum temperature is determined according to the temperature data, namely the minimum temperature in the current reporting period, and can be regarded as the temperature without heat influence, the minimum temperature is approximate to the ambient temperature, and the temperature increment value is obtained by subtracting the minimum temperature from other temperatures.
For example, in a reporting period, the temperatures at several detection points are 23, 23, 22, 22, 22, 24, … …, where 22 degrees is the bottom temperature, the temperature increase value is 1,2,0,0,0,2 … ….
And fourthly, changing the thickness of line segments in the topological graph according to the temperature increase value, determining RGB values according to respective higher harmonic ratios of the three-phase power, and coloring the topological graph according to the determined RGB values to obtain a monitoring image.
The temperature increase is one of the indexes which can most reflect partial discharge, and in order to facilitate visual analysis of the temperature, the implementation represents the thickness of a line segment in a topological graph by using the temperature increase value. And determining the position without temperature increase as the original line thickness, and amplifying the position with temperature increase according to the temperature increase value by a certain proportion. Illustratively, new wire thickness = original wire thickness (1 + temperature increase value/5); the new line thickness is the adjusted line thickness, and the original line thickness is the line thickness of the original topological graph.
Further, since there is a certain distance between the sensors, in order to adjust all the line segments, the temperature between the two detection points is linearly interpolated.
Harmonics are components of the voltage or current signal that have frequencies that are integer multiples of the fundamental frequency. In a three-phase electrical system, the phase differences between the phases can cause harmonics to interact and affect between the different phases, much like the mixing between three colors. Therefore, to visualize the three-phase harmonics, the present implementation converts the harmonic ratio of the three-phase harmonics to RGB color, and illustratively maps the harmonic ratio of the a-phase to R color, the harmonic ratio of the B-phase to G color, and the harmonic ratio of the C-phase to B color.
In converting the higher harmonic ratio to RGB colors, it is first necessary to perform standardized conversion, and preferably, this embodiment converts the higher harmonic ratio to data of 0 to 255 using Min-Max scaling. The principle of the conventional method in Min-Max scaling data processing is not described in detail in this embodiment.
After scaling by Min-Max, the higher harmonic ratio is converted into pixel colors, i.e., three-phase electricity, each phase of electricity corresponds to a number of 0-255, and the three numbers correspond to three numbers in RGB, so that a color value of a pixel point is generated, and the pixel of the detection position is assigned by the pixel color.
Further, since there is a certain distance between the sensors, in order to adjust all the line segments, the pixel color between the two detection points is linearly interpolated.
Fifthly, if an abnormal state exists in the current period, marking the abnormal position on the monitoring image.
The time and the position of the cable with partial discharge abnormality can be determined from the historical data, if an abnormal state exists in the current period, the abnormal position on the monitoring image is marked in a manual mode, and the position with the abnormality is selected by using a block diagram tool frame provided by a marking tool. Labeling may be done in any manner known in the art. Such as using LabelImg, VGG Image Annotator (VIA) or the like. Clearly, if there is no anomaly, no labeling is required. The marked image can be used for learning by a machine learning model so as to carry out image recognition, and the unmarked image can also be used for verifying by the machine learning model.
Step six, repeating the steps three to five, and processing all historical data to obtain a historical monitoring image set; and training the neural network by using the historical monitoring image set to obtain a first model.
In order to obtain a sufficient number of training images, all the historical data are processed in the steps three to five, and the images with anomalies are marked, so that a historical monitoring image set is obtained and used as a training sample.
The training of the neural network by using the historical monitoring image set may use any means in the prior art, and the training process may also use any means in the prior art, such as performing training set, verification set classification, loss function setting, optimization selection, verification, parameter adjustment, and the like on the training data, where the above means all belong to conventional technical means in the prior art, and the embodiment is not limited specifically.
Further, since the present embodiment needs to process images as well as image colors, it is preferable to use a Convolutional Neural Network (CNN) or various variants thereof, such as ResNet, VGG, inception, etc.
Step seven, collecting real-time data of the current period; processing real-time data of the current period according to the third to fifth steps to obtain a current monitoring image; and inputting the current monitoring image into a first model, and detecting whether an abnormality exists.
After the model is trained, the model can be applied to actual detection, real-time data of the current period is collected through a sensor network, and the real-time data of the current period are processed in the steps three to five to obtain a current monitoring image (the temperature is used for adjusting the line thickness of the topology, and the harmonic data is used for adjusting the color); the first model has the capability of identifying the abnormal position in the image, and after the current monitoring image is input into the first model, if partial discharge abnormality exists, the first model can automatically label the image, so that the abnormal position is identified.
According to the embodiment, through the steps, the detection data of the power grid are converted into the visualized image data, so that abnormal points in the image can be conveniently identified by using a machine learning model. The mathematical model is prevented from being established manually by machine learning and automatic learning derivation, so that the abnormality of the complex multi-branch network can be identified.
On the other hand, the invention also provides a high-voltage cable state monitoring system based on artificial intelligence, which is characterized by comprising the following modules:
the drawing module is used for drawing a topological graph according to the actual distribution of the multi-branch power grid;
the first collecting module is used for collecting historical voltage signals, current signals and temperature data of each reporting period of each phase of electricity of each detecting point of the multi-branch power grid;
the calculation module is used for determining the higher harmonic ratio according to the voltage signal and the current signal for the data of the same reporting period; determining the minimum temperature according to the temperature data, and subtracting the minimum temperature from other temperatures to obtain a temperature increase value;
the image processing module is used for changing the thickness of line segments in the topological graph according to the temperature increasing value, determining RGB values according to respective higher harmonic ratios of the three-phase power, and coloring the topological graph according to the determined RGB values to obtain a monitoring image;
the labeling module is used for labeling the abnormal position on the monitored image if the abnormal state exists in the current period;
the training module is used for operating the calculating module, the image processing module and the labeling module, processing all historical data and obtaining a historical monitoring image set; training a neural network by using the historical monitoring image set to obtain a first model;
the detection module is used for collecting real-time data of the current period; processing real-time data of the current period according to the third to fifth steps to obtain a current monitoring image; and inputting the current monitoring image into a first model, and detecting whether an abnormality exists.
Further, the specific implementation method of the high-voltage cable state monitoring system based on the artificial intelligence is the same as the high-voltage cable state monitoring method based on the artificial intelligence, and all further technical schemes in the high-voltage cable state monitoring method based on the artificial intelligence are completely introduced into the high-voltage cable state monitoring system based on the artificial intelligence.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. The high-voltage cable state monitoring method based on artificial intelligence is characterized by comprising the following steps of:
step one, drawing a topological graph according to the actual distribution of a multi-branch power grid;
step two, collecting historical voltage signals, current signals and temperature data of each reporting period of each phase of electricity of the multi-branch power grid at each detection point;
step three, for the data of the same reporting period, determining the higher harmonic ratio according to the voltage signal and the current signal; determining the minimum temperature according to the temperature data, and subtracting the minimum temperature from other temperatures to obtain a temperature increase value;
step four, changing the thickness of line segments in the topological graph according to the temperature increase value, determining RGB values according to respective higher harmonic ratios of three-phase power, and coloring the topological graph according to the determined RGB values to obtain a monitoring image;
fifthly, if an abnormal state exists in the current period, marking the abnormal position on the monitored image;
step six, repeating the steps three to five, and processing all historical data to obtain a historical monitoring image set; training a neural network by using the historical monitoring image set to obtain a first model;
step seven, collecting real-time data of the current period; processing real-time data of the current period according to the third to fifth steps to obtain a current monitoring image; and inputting the current monitoring image into a first model, and detecting whether an abnormality exists.
2. The method for monitoring the state of the high-voltage cable based on artificial intelligence according to claim 1, wherein the changing the thickness of the line segment in the topological graph according to the temperature increase value comprises: new line thick = original line thick (1 + temperature increase value/5).
3. The high-voltage cable state monitoring method based on artificial intelligence according to claim 2, wherein the method comprises the following steps: the temperature between the two detection points is linearly interpolated.
4. The artificial intelligence based high voltage cable condition monitoring method of claim 1, wherein determining RGB values from respective higher harmonic ratios of the three-phase power comprises: and (3) adopting Min-Max scaling to convert the higher harmonic ratio of each phase in the three-phase power into data of 0-255, and respectively corresponding the converted three data to three numbers in RGB values.
5. The high-voltage cable state monitoring method based on artificial intelligence according to claim 4, wherein the method comprises the following steps: the pixel color between the two detection points is linearly interpolated.
6. The high-voltage cable state monitoring system based on artificial intelligence is characterized by comprising the following modules:
the drawing module is used for drawing a topological graph according to the actual distribution of the multi-branch power grid;
the first collecting module is used for collecting historical voltage signals, current signals and temperature data of each reporting period of each phase of electricity of each detecting point of the multi-branch power grid;
the calculation module is used for determining the higher harmonic ratio according to the voltage signal and the current signal for the data of the same reporting period; determining the minimum temperature according to the temperature data, and subtracting the minimum temperature from other temperatures to obtain a temperature increase value;
the image processing module is used for changing the thickness of line segments in the topological graph according to the temperature increasing value, determining RGB values according to respective higher harmonic ratios of the three-phase power, and coloring the topological graph according to the determined RGB values to obtain a monitoring image;
the labeling module is used for labeling the abnormal position on the monitored image if the abnormal state exists in the current period;
the training module is used for operating the calculating module, the image processing module and the labeling module, processing all historical data and obtaining a historical monitoring image set; training a neural network by using the historical monitoring image set to obtain a first model;
the detection module is used for collecting real-time data of the current period; processing real-time data of the current period according to the third to fifth steps to obtain a current monitoring image; and inputting the current monitoring image into a first model, and detecting whether an abnormality exists.
7. The artificial intelligence based high voltage cable condition monitoring system of claim 6, wherein said changing the thickness of the line segments in the topology based on the temperature increment value comprises: new line thick = original line thick (1 + temperature increase value/5).
8. The high voltage cable condition monitoring system based on artificial intelligence of claim 7, wherein: the temperature between the two detection points is linearly interpolated.
9. The artificial intelligence based high voltage cable condition monitoring system of claim 6, wherein determining RGB values from respective higher harmonic ratios of the three phase power comprises: and (3) adopting Min-Max scaling to convert the higher harmonic ratio of each phase in the three-phase power into data of 0-255, and respectively corresponding the converted three data to three numbers in RGB values.
10. The high voltage cable condition monitoring system based on artificial intelligence of claim 9, wherein: the pixel color between the two detection points is linearly interpolated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311450376.8A CN117169657B (en) | 2023-11-03 | 2023-11-03 | High-voltage cable state monitoring method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311450376.8A CN117169657B (en) | 2023-11-03 | 2023-11-03 | High-voltage cable state monitoring method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117169657A true CN117169657A (en) | 2023-12-05 |
| CN117169657B CN117169657B (en) | 2024-01-12 |
Family
ID=88939870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311450376.8A Active CN117169657B (en) | 2023-11-03 | 2023-11-03 | High-voltage cable state monitoring method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117169657B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117435947A (en) * | 2023-12-20 | 2024-01-23 | 山东和兑智能科技有限公司 | Lightning arrester state monitoring system and method |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194058A (en) * | 2011-05-16 | 2011-09-21 | 中国电力科学研究院 | Wide-area-measurement-system (WAMS)-based power grid safety and stability visualization method |
| CN110703006A (en) * | 2019-09-04 | 2020-01-17 | 国网浙江省电力有限公司金华供电公司 | Three-phase power quality disturbance detection method based on convolutional neural network |
| CN111079861A (en) * | 2019-12-31 | 2020-04-28 | 国网北京市电力公司 | Power distribution network voltage abnormity diagnosis method based on image rapid processing technology |
| CN111426406A (en) * | 2020-06-02 | 2020-07-17 | 国家电网有限公司 | Cable detection device based on temperature-sensitive color change of cable coating and detection method thereof |
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
| US20210048487A1 (en) * | 2019-08-12 | 2021-02-18 | Wuhan University | Power transformer winding fault positioning method based on deep convolutional neural network integrated with visual identification |
| CN112990445A (en) * | 2021-05-13 | 2021-06-18 | 国网浙江省电力有限公司金华供电公司 | Intelligent analysis machine learning method for monitoring information of power distribution network |
| CN113554010A (en) * | 2021-09-22 | 2021-10-26 | 广东电网有限责任公司东莞供电局 | Power grid line fault recognition model training method |
| US20220198244A1 (en) * | 2020-12-18 | 2022-06-23 | Wuhan University | Method for diagnosing open-circuit fault of switching transistor of single-phase half-bridge five-level inverter |
| KR20220147911A (en) * | 2021-04-28 | 2022-11-04 | 주식회사 파인브이티 | Process monitoring apparatus for judging the defectiveness of cables produced through harness cable production process, and the operating method thereof |
| CN115470811A (en) * | 2022-07-25 | 2022-12-13 | 温州大学 | Non-invasive load anomaly identification method and system for power utilization system |
| US20230186503A1 (en) * | 2021-12-14 | 2023-06-15 | Wuhan University | Method for troubleshooting hidden dangers of trees near power transmission lines by combining icesat-2 with jl-1 images |
| CN116524200A (en) * | 2023-05-05 | 2023-08-01 | 东南大学 | High-voltage circuit breaker fault diagnosis method based on image recognition |
| CN116679159A (en) * | 2023-05-24 | 2023-09-01 | 广州番禺电缆集团(新兴)有限公司 | Cable line history abnormal node management system and method |
| CN116778856A (en) * | 2023-08-18 | 2023-09-19 | 深圳市巴科光电科技股份有限公司 | Intelligent LED display device and method applied to power system |
| US20230296654A1 (en) * | 2020-12-08 | 2023-09-21 | Zhejiang University | Non-intrusive load monitoring method based on v-i trajectory and neural network |
| CN116846059A (en) * | 2023-03-07 | 2023-10-03 | 云南电网有限责任公司玉溪供电局 | Edge detection system for power grid inspection and monitoring |
-
2023
- 2023-11-03 CN CN202311450376.8A patent/CN117169657B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194058A (en) * | 2011-05-16 | 2011-09-21 | 中国电力科学研究院 | Wide-area-measurement-system (WAMS)-based power grid safety and stability visualization method |
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
| US20210048487A1 (en) * | 2019-08-12 | 2021-02-18 | Wuhan University | Power transformer winding fault positioning method based on deep convolutional neural network integrated with visual identification |
| CN110703006A (en) * | 2019-09-04 | 2020-01-17 | 国网浙江省电力有限公司金华供电公司 | Three-phase power quality disturbance detection method based on convolutional neural network |
| CN111079861A (en) * | 2019-12-31 | 2020-04-28 | 国网北京市电力公司 | Power distribution network voltage abnormity diagnosis method based on image rapid processing technology |
| CN111426406A (en) * | 2020-06-02 | 2020-07-17 | 国家电网有限公司 | Cable detection device based on temperature-sensitive color change of cable coating and detection method thereof |
| US20230296654A1 (en) * | 2020-12-08 | 2023-09-21 | Zhejiang University | Non-intrusive load monitoring method based on v-i trajectory and neural network |
| US20220198244A1 (en) * | 2020-12-18 | 2022-06-23 | Wuhan University | Method for diagnosing open-circuit fault of switching transistor of single-phase half-bridge five-level inverter |
| KR20220147911A (en) * | 2021-04-28 | 2022-11-04 | 주식회사 파인브이티 | Process monitoring apparatus for judging the defectiveness of cables produced through harness cable production process, and the operating method thereof |
| CN112990445A (en) * | 2021-05-13 | 2021-06-18 | 国网浙江省电力有限公司金华供电公司 | Intelligent analysis machine learning method for monitoring information of power distribution network |
| CN113554010A (en) * | 2021-09-22 | 2021-10-26 | 广东电网有限责任公司东莞供电局 | Power grid line fault recognition model training method |
| US20230186503A1 (en) * | 2021-12-14 | 2023-06-15 | Wuhan University | Method for troubleshooting hidden dangers of trees near power transmission lines by combining icesat-2 with jl-1 images |
| CN115470811A (en) * | 2022-07-25 | 2022-12-13 | 温州大学 | Non-invasive load anomaly identification method and system for power utilization system |
| CN116846059A (en) * | 2023-03-07 | 2023-10-03 | 云南电网有限责任公司玉溪供电局 | Edge detection system for power grid inspection and monitoring |
| CN116524200A (en) * | 2023-05-05 | 2023-08-01 | 东南大学 | High-voltage circuit breaker fault diagnosis method based on image recognition |
| CN116679159A (en) * | 2023-05-24 | 2023-09-01 | 广州番禺电缆集团(新兴)有限公司 | Cable line history abnormal node management system and method |
| CN116778856A (en) * | 2023-08-18 | 2023-09-19 | 深圳市巴科光电科技股份有限公司 | Intelligent LED display device and method applied to power system |
Non-Patent Citations (2)
| Title |
|---|
| 居一峰，等: "基于DCNN的输电线路隐患区域图像识别方法", 《电子设计工程》, vol. 31, no. 19 * |
| 李帷韬，等: "基于强化学习和Transformer的输电线路缺陷智能检测方法研究", 《高电压技术》, vol. 49, no. 8 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117435947A (en) * | 2023-12-20 | 2024-01-23 | 山东和兑智能科技有限公司 | Lightning arrester state monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117169657B (en) | 2024-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bíscaro et al. | Integrated fault location and power-quality analysis in electric power distribution systems | |
| CN117169657B (en) | High-voltage cable state monitoring method and system based on artificial intelligence | |
| CN108683180B (en) | Three-phase low-voltage power distribution network topology reconstruction method | |
| CN109444667B (en) | Power distribution network early fault classification method and device based on convolutional neural network | |
| EP3757583B1 (en) | System for determining electric parameters of an electric power grid | |
| CN109406949B (en) | Power distribution network early fault detection method and device based on support vector machine | |
| US9448086B2 (en) | Method for analyzing the electricity consumption of a site provided with a plurality of electrical devices | |
| CN107942192A (en) | A kind of controller switching equipment CT automatic test approach and system | |
| CN110618314B (en) | Harmonic wave responsibility division method for resisting short-circuit fault interference of power distribution system | |
| CN113050017A (en) | Intelligent error state monitoring and fault diagnosis system for electronic transformer | |
| Music et al. | Integrated power quality monitoring system and the benefits of integrating smart meters | |
| CN111257820A (en) | Three-phase intelligent electric meter wiring remote detection method | |
| CN110988600B (en) | Power distribution network line break fault section positioning method | |
| CN108318732B (en) | On-line monitoring device and method for grounding current of transformer core | |
| CN111999695B (en) | State evaluation and abnormity diagnosis method for metering device of transformer substation | |
| CN110058127B (en) | Single-phase earth fault point identification method for non-effectively-grounded power distribution network | |
| CN112505610A (en) | Voltage transformer insulation and metering performance integrated test device and method for metering of 35kV and below | |
| CN114720765A (en) | Situation awareness-based harmonic algorithm of active power distribution network and control system thereof | |
| CN207675919U (en) | A kind of controller switching equipment CT automatic testing equipments | |
| CN107144761A (en) | A kind of wiring faults detecting system and method based on sampling module | |
| CN109507468B (en) | Header box branch current detection method and system based on correlation characteristics | |
| CN109782064A (en) | A kind of wind power plant output impedance frequency characteristic test analysis method | |
| CN112816836A (en) | Fault detection system, partial discharge online monitoring device and method | |
| CN112865300A (en) | ZigBee-based power quality monitoring system and method | |
| Li et al. | Cable Fault on-Line Monitoring Based on Transient Traveling Wave Signal Analysis Technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |