CN117148225A - Transformer fault detection method - Google Patents
Transformer fault detection method Download PDFInfo
- Publication number
- CN117148225A CN117148225A CN202311067782.6A CN202311067782A CN117148225A CN 117148225 A CN117148225 A CN 117148225A CN 202311067782 A CN202311067782 A CN 202311067782A CN 117148225 A CN117148225 A CN 117148225A
- Authority
- CN
- China
- Prior art keywords
- wire line
- transformer
- coefficient
- cable
- temperature
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 13
- 230000007613 environmental effect Effects 0.000 claims abstract description 11
- 238000013528 artificial neural network Methods 0.000 claims abstract description 10
- 230000008859 change Effects 0.000 claims description 36
- 238000003064 k means clustering Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims 7
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000001537 neural effect Effects 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 17
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 238000009413 insulation Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/003—Environmental or reliability tests
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/62—Testing of transformers
-
- 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
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Power Engineering (AREA)
- Environmental & Geological Engineering (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention discloses a transformer fault detection method, which comprises the following steps: solving a risk coefficient of each cable in the power-on use process of the electric wire line in the transformer based on the current stability coefficient and the temperature distribution coefficient; according to the environmental temperature information and the environmental humidity information, obtaining an influence coefficient of the environment on the service life of the wire line; according to the influence coefficient of the environment on the service life of the electric wire line and the risk coefficient of the electric wire line, a loss degree characteristic sequence of the electric wire line is obtained, and the trained TCN neural network is utilized to predict the loss degree characteristic of the electric wire line of the transformer at the next moment. According to the invention, the loss of the wire line in the use process is determined according to the stability coefficient and the spatial distribution characteristic of the wire line in time when the transformer outputs power and in combination with the influence of environmental factors in the transformer, and the TCN neural grid is adopted for prediction based on real-time monitoring data, so that problems can be found in time and risk early warning can be carried out.
Description
Technical Field
The invention relates to the technical field of power electronics, in particular to a technology for performing intelligent analysis and early warning on the risk of a transformer circuit based on a neural network, and particularly relates to a transformer fault detection method.
Background
In the use process of the wire line, frequent power on-off switching can cause large rise and fall of temperature, which can lead to fatigue of the wire line, increase plastic deformation and shrinkage, and influence the insulation life and performance. The temperature change of the wire sheath material is smaller than that of insulation, but fatigue creep can also influence the protection life of the wire line to a certain extent. In the prior art, the use condition of the transformer wire line can be monitored at regular intervals, the operation process is relatively complicated, and the emergency cannot be dealt with by regular monitoring, so that large-area faults of the power transmission system are caused, and the generation safety is influenced.
Disclosure of Invention
In view of the defects of the prior art, the invention provides a transformer fault detection method which can timely find problems and perform risk early warning based on real-time monitoring data.
The invention adopts the following technical means:
a transformer fault detection method, comprising:
acquiring temperature change data of an electric wire line in a transformer and acquiring temperature change data of the electric wire line of the transformer in space; solving the current stability coefficient of each cable when the transformer outputs current based on the temperature change data of the transformer wire line; based on the temperature change data of the transformer wire line in space, calculating the temperature distribution coefficient of each cable when the transformer outputs current; solving a risk coefficient of each cable in the power-on use process of the electric wire line in the transformer based on the current stability coefficient and the temperature distribution coefficient;
obtaining the similarity degree of different cables according to the total difference of the temperature change sequences among the cables and the absolute difference of the risk coefficients; calculating sample distances of risk similarities of different wires and lines according to the similarity degrees of different cables, clustering the risk similarities of the wires and lines based on a K-Means clustering method, so as to obtain line density groups, and respectively setting a threshold value for each line density group;
acquiring environment temperature information and environment humidity information when the transformer works, and obtaining an influence coefficient of the environment on the service life of the wire line according to the environment temperature information and the environment humidity information; obtaining a loss degree characteristic sequence of the wire line according to an influence coefficient of the environment on the service life of the wire line and a risk coefficient of the wire line;
and training the TCN neural network based on the loss degree characteristic sequence, and predicting the loss degree characteristic of the transformer wire line at the next moment by using the trained TCN neural network.
Compared with the prior art, the invention has the following advantages:
according to the method, loss in the use process of the wire line is determined according to the stability coefficient and the spatial distribution characteristic of the transformer on the time of outputting the power line and the influence of environmental factors in the transformer, and the TCN neural grid is used for prediction through real-time detection, so that problems can be found in time and risks can be early warned.
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 required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
Fig. 1 is a flowchart of a transformer fault detection method according to the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
As shown in fig. 1, the invention provides a transformer fault detection method, which mainly comprises the following steps:
s1, acquiring temperature change data of an electric wire line in a transformer and acquiring temperature change data of the electric wire line of the transformer in space; solving the current stability coefficient of each cable when the transformer outputs current based on the temperature change data of the transformer wire line; based on the temperature change data of the transformer wire line in space, calculating the temperature distribution coefficient of each cable when the transformer outputs current; and solving the risk coefficient of each cable in the power-on using process of the electric wire line in the transformer based on the current stability coefficient and the temperature distribution coefficient.
First, temperature change data information of an electric wire line in a transformer is collected. Because the electricity needs, lay a lot of electric wire lines in the transformer, when the current output in the transformer, a large amount of electric currents continue to export, this can cause electric wire line temperature to rise, and the electric wire line of itself will generate heat under the condition of circular telegram, and when long-term load operation, the too high temperature can accelerate the ageing of electric wire line self insulating layer, influences electric wire line's life, consequently need gather the temperature data of transformer electric wire line.
The embodiment of the invention preferably uses a temperature probe sensor for the temperature of the wire line in the transformerAnd collecting information. Taking one hour as a time length unit, the data refreshing frequency of the probe type temperature sensor is 1 minute, and a temperature change sequence T= { T of an electric wire line is obtained 1 ,T 2 ,.....,T i }。
Temperature change information of the transformer current output wire line in the time unit is calculated. According to the current output, when the current output is unstable for a period of time, the temperature of the wire line is maximum, and the service life of the wire line is also damaged most, so that:
wherein Q represents the current stability coefficient of each cable when the transformer outputs current, T= { T 1 ,T 2 ,.....,T i The temperature change sequence of one wire line is represented,represents the last acquisition value and n represents the number of acquisitions in one minute. According to the temperature variance of the wire line>To indicate a temperature change due to current fluctuation, and when the temperature change of the wire line per unit time is larger, to indicate that the damage to the wire line caused by frequent current fluctuation is larger, and to combine the average value of the temperature change per unit time, to thereby obtain Q to indicate a change in the stability of the current per unit time.
Secondly, temperature changes in the transformer cable space are collected. Based on the length of the wire line has a certain influence on the current, temperature probes are arranged at different positions of each wire line, temperature data information of each wire line in the transformer is acquired according to the probe type temperature sensor, the temperature difference between different wire lines is determined, and when the temperature difference of each wire line in space is larger, the insulation layer of the wire line is obviously damaged, so that the temperature data information in the space of the cable in the transformer is required to be acquired.
In the embodiment of the invention, a probe type temperature sensor is used for reading the temperature information of the wire line in the transformer, a temperature probe is set at a distance of 50cm (which can be set by an operator), and a sequence H= { H of a temperature distribution is obtained by taking 10 sections of distance as a length unit 1 ,H 2 ,.....,H i }。
And calculating the temperature difference of the temperature distribution of the transformer cables to obtain the temperature distribution coefficient of each cable.
Wherein W represents the temperature distribution coefficient of each cable when the transformer outputs current, and H= { H 1 ,H 2 ,.....,H i The temperature distribution sequence of one wire line is represented,represents the last segment of acquisition value, N represents the total acquisition number, H Max Represents the maximum value of the temperature in acquisition, H Min Representing the minimum temperature in the acquisition. According to the temperature variance collected by each section of each cable, determining the discrete degree among the sections in the length unit, wherein the larger the discrete degree is, the larger the temperature difference of the length unit is, the larger the electricity consumption risk of the electric wire line is, and determining the generated maximum temperature difference by combining the difference between the maximum value and the minimum value of the temperature change in the length unit, so that W is used for representing the temperature distribution coefficient in the unit length.
And then, according to the obtained current stability coefficient and the temperature distribution coefficient of each cable, obtaining the risk coefficient of the wire line in the transformer in the power-on use process. The risk coefficient of the wire line is as follows:
U＝Q*W
wherein U represents a risk coefficient of an electric wire line in the transformer in the use process, Q represents a current stability coefficient of each cable when the transformer outputs current, and W represents a temperature distribution coefficient of each cable when the transformer outputs current. The greater the difference in the stability change of the current per unit time, the greater the risk factor of the wire line, and the greater the risk factor of the wire line, the greater the change in U with the stability and the change in the temperature distribution factor. So far, the risk coefficient of the wire line is obtained.
S2, obtaining the similarity degree of different cables according to the total difference of the temperature change sequences among the cables and the absolute difference value of the risk coefficient; and calculating sample distances of risk similarities of different wires and lines according to the similarity degrees of different cables, clustering the risk similarities of the wires and lines based on a K-Means clustering method, so as to obtain line density groups, and respectively setting a threshold value for each line density group.
First, the degree of aggregation of the wire lines within the transformer is collected. Based on the fact that the wire lines in the transformer generate heat when the transformer is electrified, the current is proportional to the heat generated by the wires, when the wire lines are laid, some wire lines may need to be bundled together according to real-time conditions, the bundled length and the bundled number are set according to practical situations of an operator, and when the wire lines are bundled together, the temperature is much higher than that of a single wire line due to poor heat dissipation, and the service life of the wire lines is naturally damaged to some extent. When the wire lines are bundled longer, therefore, the greater the number, the greater the risk of wire lines,
thus grouping the density of the cables, when the current stability fluctuations are close, the closer the distance of the wire lines is, the closer the risk factor of the cables is. Dividing the current stability in the wire line into a group close to the risk coefficient of the wire line, and calculating the similarity degree between different cables:
wherein R (A, B) represents the degree of similarity between the cable A and the cable B, A, B are two non-identicalSame wire cable, COV (T A ,T B ) The larger the difference is, the lower the pearson correlation coefficient is, and conversely, the larger is the overall difference in the temperature change sequences within the two wire lines. abs (U) A -U B ) The absolute difference of the risk coefficients of the two electric wire lines A and B is larger, and the similarity is lower. Delta, delta A Represents the density coefficient, delta, of the cable set A B Representing the cable set B density coefficient. The density coefficient of the cable is obtained according to the concentration degree of the cable. So far, the degree of similarity of the different cables is obtained.
Secondly, calculating sample distances among the cables based on the obtained similarity degree among different cables, and grouping the cable densities according to the sample distances, wherein the sample distances are as follows:
where D represents the sample distance of the similarity of cable a and cable B, and R (a, B) represents the similarity of cable a and cable B. The greater the similarity of different wire lines, the smaller the sample distance thereof. The larger the opposite is.
Based on the sample distance, each density wire line is grouped using a K-Means clustering method.
In this embodiment, the K value is defined as 3, and all the density wires are grouped into groups of different densities:
high density group. The electric wire lines of the group have larger aggregation degree, larger density and highest risk coefficient,
medium density group. The group of electric wire lines has a common concentration degree and a medium risk coefficient.
Low density group. The group of electric wire lines are rare in aggregation degree, small in density and low in risk coefficient.
Different thresholds are set for different groups. Due to temperature variations and wire line density, it is necessary to set different thresholds for wire lines of different densities. Reasons for setting different thresholds: if a threshold is set, the damage to the wire line caused by different groups each time is different, errors can occur, and the wire line is caused to be faulty, so that three groups are set with three different thresholds according to actual conditions.
S3, acquiring environment temperature information and environment humidity information when the transformer works, and obtaining an influence coefficient of the environment on the service life of the wire line according to the environment temperature information and the environment humidity information; and obtaining a loss degree characteristic sequence of the wire line according to the influence coefficient of the environment on the service life of the wire line and the risk coefficient of the wire line.
Specifically, environmental information is collected, and the loss degree of the wire line is determined according to the environmental information and the risk coefficient. Because of the long-time high-temperature insolation or humid climate, the loss of the wire line insulator is accelerated, and therefore, the environmental change factors of the transformer are required to be collected.
First, the temperature of the transformer is acquired. An initial temperature is set which affects the wire line, and the larger the temperature is, the larger the impact on the wire line is. The ambient temperature is acquired according to the method in S1, and an ambient temperature change sequence P= { P is obtained 1 ,P 2 ,.....,P i }。
Secondly, collecting humidity information of the transformer, and setting an initial humidity to obtain a humidity change sequence L= { L 1 ,L 2 ,.....,L i }。
When the environment temperature in the transformer is larger and the humidity is larger, the service life damage influence on the electric wire line is larger, so that the influence degree of the environment of the transformer on the service life of the electric wire line is calculated:
s is an environmental factor influence coefficient. Depending on the effect of different humidity and temperature, the greater the ambient temperature within the transformer, the greater the effect of life damage to the wire line.
According to environmental factors, combining risk factors of the wire lines to obtain the loss degree of the wire lines:
Y＝U*S
y is the loss degree of the wire line, the loss degree of the wire line changes along with the change of the risk coefficient and the environmental factor of the line, and the relationship is positively correlated. So far, the loss degree of the wire line in the transformer is obtained
Repeating the above operation, and collecting the loss degree of the wire line for a plurality of days to obtain a change sequence Y= { Y of the loss degree of the wire line 1 ,Y 2 ,.....,Y i }.
And S4, training the TCN neural network based on the loss degree characteristic sequence, and predicting the loss degree characteristic of the transformer wire line at the next moment by using the trained TCN neural network.
Specifically, the TCN neural network training is used to predict the transformer wire line loss level, and the transformer wire line loss level at the next moment is predicted. And taking the obtained transformer wire line loss degree sequence as the front part of the characteristic sequence, and inputting the obtained transformer wire line loss degree sequence into the TCN neural network for training. The obtained next value is used as a label, so that TCNs can learn the next predicted value of the current sequence. And obtaining a sequence of the loss degree of the wire line of the residual transformer.
The loss function of TCN is the mean square error loss. For this sample sequence, confidence is used with confidence C i As a quality score, and normalized to a sample weight c= { C added to 1 1 ,..,C i }。
Where C is the mass fraction after normalization as a loss weight.To predict the samples, y i Is a characteristic sample. The aim is to ensure that the loss function converges, the loss is reduced through continuous training, and the predicted trend is accurate.
And so on, different temperature changes correspond to different predictions.
The TCN can be used for predicting the subsequent loss degree result of the transformer wire line through the data from small to large of the temperature difference condition when training the meaning of the TCN. For the predicted result, the user can perform risk early warning according to the fact that the transformer wire line loss degree reaches the output standard of TCN, and the transformer wire line loss degree at the moment is about to reach the threshold value. Based on the set three threshold standards, according to the detection of the wire line loss degree of the three types of transformers in real time, when the wire line loss degree of each type of transformer reaches the set threshold, risk early warning is carried out. The threshold value is set by the practitioner according to the actual situation. Thus, the prediction result of the loss degree of the transformer wire line is obtained.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (8)
1. A method for detecting a transformer fault, comprising:
acquiring temperature change data of an electric wire line in a transformer and acquiring temperature change data of the electric wire line of the transformer in space; solving the current stability coefficient of each cable when the transformer outputs current based on the temperature change data of the transformer wire line; based on the temperature change data of the transformer wire line in space, calculating the temperature distribution coefficient of each cable when the transformer outputs current; solving a risk coefficient of each cable in the power-on use process of the electric wire line in the transformer based on the current stability coefficient and the temperature distribution coefficient;
obtaining the similarity degree of different cables according to the total difference of the temperature change sequences among the cables and the absolute difference of the risk coefficients; calculating sample distances of risk similarities of different wires and lines according to the similarity degrees of different cables, clustering the risk similarities of the wires and lines based on a K-Means clustering method, so as to obtain line density groups, and respectively setting a threshold value for each line density group;
acquiring environment temperature information and environment humidity information when the transformer works, and obtaining an influence coefficient of the environment on the service life of the wire line according to the environment temperature information and the environment humidity information; obtaining a loss degree characteristic sequence of the wire line according to an influence coefficient of the environment on the service life of the wire line and a risk coefficient of the wire line;
and training the TCN neural network based on the loss degree characteristic sequence, and predicting the loss degree characteristic of the transformer wire line at the next moment by using the trained TCN neural network.
2. The method for detecting a transformer fault according to claim 1, wherein the current stability coefficient of each cable when the transformer outputs a current is obtained according to the following calculation:
wherein Q represents the current stability coefficient of each cable when the transformer outputs current, T= { T 1 ,T 2 ,.....,T i The temperature change sequence of one wire line is represented,represents the last acquisition value and n represents the number of acquisitions in one minute.
3. The method for detecting a transformer fault according to claim 1, wherein the temperature distribution coefficient of each cable when the transformer outputs a current is obtained according to the following calculation:
wherein W represents the temperature distribution coefficient of each cable when the transformer outputs current, and H= { H 1 ,H 2 ,.....,H i The temperature distribution sequence of one wire line is represented,represents the last segment of acquisition value, N represents the total acquisition number, H Max Represents the maximum value of the temperature in acquisition, H Min Representing the minimum temperature in the acquisition.
4. The method for detecting faults of transformers according to claim 1, wherein risk coefficients of the electric wire lines in the transformers in the power-on using process are calculated according to the following calculation:
U＝Q*W
wherein U represents a risk coefficient of an electric wire line in the transformer in the use process, Q represents a current stability coefficient of each cable when the transformer outputs current, and W represents a temperature distribution coefficient of each cable when the transformer outputs current.
5. The method of claim 1, wherein determining the degree of similarity of the different cables comprises obtaining the degree of similarity of the two cables according to the following calculation:
wherein R (A, B) represents the degree of similarity between cable A and cable B, COV (T A ,T B ) Representing the overall difference in the sequence of temperature changes in the two cables, abs (U A -U B ) Representing the absolute difference, delta, of the two cable risk coefficients A Represents the density coefficient, delta, of the cable set A B Representing the cable set B density coefficient.
6. The transformer fault detection method according to claim 1, wherein the sample distances of the different wire-line risk similarities are obtained according to the following calculation:
where D represents the sample distance of the similarity of cable a and cable B, and R (a, B) represents the similarity of cable a and cable B.
7. The transformer fault detection method according to claim 1, wherein the influence coefficient of the environment on the service life of the electric wire line is obtained according to the following calculation:
wherein S represents the influence coefficient of the environment on the service life of the wire line, and P= { P 1 ,P 2 ,.....,P i The sequence of environmental temperature changes, l= { L 1 ,L 2 ,...Li } represents an ambient humidity change sequence, P Min Represents the highest value of the ambient temperature, P in the sample Max Represents the minimum value of the ambient temperature in the sample, L Min Represents the highest value of the ambient humidity in the sample, L Max Representing the minimum ambient humidity in the sample.
8. The transformer fault detection method according to claim 1, wherein the loss level characteristics of the electric wire line are obtained according to the following calculation:
Y＝U*S
wherein Y represents the loss degree characteristic of the wire line, U represents the risk coefficient of the wire line in the transformer in the use process, and S represents the influence coefficient of the environment on the service life of the wire line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311067782.6A CN117148225A (en) | 2023-08-23 | 2023-08-23 | Transformer fault detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311067782.6A CN117148225A (en) | 2023-08-23 | 2023-08-23 | Transformer fault detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117148225A true CN117148225A (en) | 2023-12-01 |
Family
ID=88903753
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311067782.6A Pending CN117148225A (en) | 2023-08-23 | 2023-08-23 | Transformer fault detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117148225A (en) |
-
2023
- 2023-08-23 CN CN202311067782.6A patent/CN117148225A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832914B (en) | Power transmission line structure health assessment method and system based on digital twinning | |
| CN116304778B (en) | Maintenance data processing method for miniature circuit breaker | |
| CN117093879A (en) | Intelligent operation management method and system for data center | |
| CN111025097B (en) | Intelligent method for evaluating leakage current difference factor of XLPE cable after aging | |
| CN117421687B (en) | Method for monitoring running state of digital power ring main unit | |
| CN115271000B (en) | State monitoring method and system for cable tunnel | |
| JP5562287B2 (en) | Remaining life diagnosis method and remaining life diagnosis device for power distribution equipment | |
| CN109711687B (en) | Insulator state fuzzy evaluation method based on improved entropy method | |
| CN115034606A (en) | Method for evaluating running state of low-voltage busbar insulating sheath of transformer | |
| CN114781906A (en) | Power cable operation early warning method based on artificial intelligence | |
| CN117031182B (en) | Method and system for detecting abnormal telemetering value of substation terminal | |
| CN117269655B (en) | Transformer substation power equipment temperature anomaly monitoring method, system, terminal and medium | |
| Balango et al. | Predicting conductor sag of power lines in a new model of dynamic line rating | |
| CN113379005A (en) | Intelligent energy management system and method for power grid power equipment | |
| CN116990621B (en) | Dynamic fault monitoring system for electric power safety tools | |
| CN117150244B (en) | Intelligent power distribution cabinet state monitoring method and system based on electrical parameter analysis | |
| CN110108983B (en) | Intelligent cable state online measurement and control management method | |
| CN117148225A (en) | Transformer fault detection method | |
| CN115859667A (en) | Automobile cable loss prediction method and device based on neural network and storage medium | |
| CN115796395A (en) | Power grid cable laying environment prediction system | |
| CN115479631A (en) | Method and system for diagnosing mechanical fault and electrical fault of high-voltage alternating-current submarine cable | |
| CN115713229A (en) | Risk early warning analysis method for insulator performance loss based on neural network | |
| CN112946369B (en) | Cable aging identification method using power line communication device | |
| CN114325260A (en) | Insulation state evaluation method and device of high-voltage cable based on thermal resistance change | |
| CN114184903A (en) | 10kV XLPE cable aging state evaluation method based on electric tree state evaluation factor |
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 |