CN108680811B - Transformer fault state evaluation method - Google Patents
Transformer fault state evaluation method Download PDFInfo
- Publication number
- CN108680811B CN108680811B CN201810692629.5A CN201810692629A CN108680811B CN 108680811 B CN108680811 B CN 108680811B CN 201810692629 A CN201810692629 A CN 201810692629A CN 108680811 B CN108680811 B CN 108680811B
- Authority
- CN
- China
- Prior art keywords
- transformer
- oil
- data set
- paper
- fault state
- 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.)
- Active
Links
Images
Classifications
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Housings And Mounting Of Transformers (AREA)
- Testing Relating To Insulation (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention relates to a transformer fault state evaluation method, which comprises the following steps: firstly, constructing a data set of transformer insulating oil characteristic class, insulating paper characteristic class, gas characteristic class, temperature characteristic class, capacitance characteristic class and partial discharge characteristic class and calculating corresponding probability numerical values; then, calculating average values of oil, paper, gas, temperature, capacitance and partial discharge characteristic values reflecting the fault state of the transformer; then, constructing a fault state evaluation function of the transformer; finally, evaluating the fault state of the transformer; the method can evaluate the fault state of the transformer, reflect the uncertainty of the characteristic value of the fault state of the transformer, provide theoretical guidance for the evaluation of the fault state of the transformer and provide necessary technical support for the operation and maintenance of the power distribution network.
Description
Technical Field
The invention relates to the technical field of power systems and automation thereof, in particular to a transformer fault state evaluation method.
Background
The traditional main equipment of the distribution network is usually required to be subjected to post maintenance and regular scheduled maintenance, a large amount of manpower and material resources are required to be invested, and the cost performance of maintenance is not high. As the degree of automation of the equipment increases, the time-dependent failure modes of the equipment account for only 6% of all failure modes of the equipment, so that the time-based periodic maintenance strategy is only effective for 6% of the failure modes of the equipment. The maintenance mode of prolonging or shortening the maintenance period is determined by taking the regular maintenance as the main combination experience, and a certain effect is achieved.
With the increasing number of power equipment, the association relationship among the equipment becomes more and more complex, the social requirement on the power supply reliability becomes higher and higher, and the arrangement of power failure maintenance becomes increasingly difficult; the distribution network equipment quantity is large, the running state is complex and changeable, the state of the distribution network main equipment is difficult to detect and evaluate in time, the traditional maintenance strategy pays more attention to test data and pays less attention to running data, and the requirement of increasingly lean state maintenance management cannot be met.
The number of transformers is large, deterioration and defects of different degrees exist, and the transformers are familial and concealed, and are difficult to detect and evaluate in time. Due to the fact that the operation years, the environment, the overhaul and the like are greatly different and are influenced by multiple factors, the difficulty and the complexity of transformer fault state evaluation are increased, and the higher requirements of precise and intelligent evaluation cannot be met.
The safe and reliable operation of the transformer firstly needs strict quality guarantee and also needs enough maintenance and overhaul guarantee. Although regular preventive maintenance can prevent the occurrence of a failure accident event due to deterioration or defect problems to some extent, it is difficult to find defects or the like having extremely high potential and concealment. Troubleshooting is a passive mode of maintenance, has great stress and uncertainty, and is also prone to cause the problem of over-repair or overhaul. The state maintenance has pertinence and rationality, can effectively overcome the problems of overhauling and overhauling caused by regular maintenance, can prevent the expansion and the seriousness of the deterioration or defect problems of the distribution equipment, and is the trend of the development of the equipment maintenance in future.
Traditionally, the fault state of the transformer is estimated by a single factor data calculation and analysis method such as dissolved gas in oil, and potential defects of the gradually developed transformer can be accurately and reliably found; the method can accurately and reliably evaluate the deterioration, degradation and defect states of the transformer by processing, calculating and analyzing single factor data by using mathematical methods such as a wavelet network method, a neural network method, a fuzzy clustering method, a gray clustering method, a support vector machine, a rough set method, an evidence reasoning method, a Bayesian network classifier and the like. Although the neural network method utilizes the pre-self-training and self-learning modes to process and calculate the high-risk data, the neural network method is seriously influenced by the state value of a system or parameters, retraining and learning are needed once the state changes, the adaptability is weak and the analysis result is influenced; the fault tree method is used for carrying out detailed decomposition on faults according to a certain rule so as to analyze the fault types and reasons thereof, the integrity and the correctness of very detailed fault information are required, and potential faults are difficult to discover; the support vector machine method adopts a certain rule to carry out layered processing on data, and the problems of wrong division, wrong division and the like are easy to occur when the data amount is large; the rough set and fuzzy theory method has unique advantages in the aspect of processing randomness and fuzzy data, but the rough set can only process discrete data, and the fuzzy theory method has no self-learning and self-adaption capability; the Bayesian network classification method can well process incomplete data, but key attribute data of a system or parameters are required to be provided completely, otherwise, the calculation and evaluation accuracy is low; the evidence reasoning theory can process the redundant information or data better and accurately, but the event discrimination applied to the evidence has great limitation when the information or the data are contradictory.
The evaluation accuracy is low easily caused by using experience, single parameters or a small amount of data, and the problems of overhauling or overhauling and the like are further caused. On the basis of fusion of multi-source data of delivery, monitoring, testing, routing inspection, operation, metering, automation and the like, classification evaluation is carried out according to equipment types, operation conditions and application environments, a transformer fault state model based on data driving is established, state evaluation is carried out by means of redundancy analysis and correlation analysis of key indexes, technical support is provided for reliable operation of the transformer, and risk early warning is provided for fault occurrence of the transformer.
The factors causing the transformer fault include insulation moisture, iron core fault, current loop overheat, winding fault, partial discharge, oil flow discharge, arc discharge, insulation deterioration and insulation oil deterioration, and the fault state of the transformer is influenced by insulation oil dielectric loss, water content in oil, oil breakdown voltage, insulation resistance absorption ratio, polarization index, volume resistivity, H2Content, core insulation resistance, etc. The differential operation and maintenance of the transformer needs overall evaluation, the state evaluation relates to ledger information, routing inspection information, live detection and online monitoring data, offline test data and the like, the data volume is large, the influence mechanism is different, the conventional evaluation method focuses on some layers or index research, and the requirements of multi-dimensional and large data cannot be met. By adopting a big data technology, the state change of the main equipment can be comprehensively reflected, and the characteristics and key parameters of the main equipment can be determined. Establishing a database of main distribution network equipment such as a transformer, a circuit breaker, a lightning arrester, a capacitor and the like by using static data such as factory test data, defect and accident records, regular and irregular test data and the like, dynamic data such as online detection data and real-time operation information of the equipment, including real-time operation information such as voltage, current and power and the like, fault information such as short-circuit fault, lightning jump and familial defect and the like, inspection information such as infrared temperature measurement, sealing and pollution and the like, state data such as power failure detection information such as direct current resistance, insulation resistance, oil chromatography and dielectric loss and the like, researching a main equipment state characteristic evaluation method by adopting a big data technology, and clarifying the state of the main equipment and hydrolysis and pyrolysisAnd (4) extracting the state characteristics of the main equipment by adopting a fuzzy C-means clustering analysis method according to the incidence relation.
The parameters related to the insulating oil such as oil dielectric loss, water content in oil, gas content in oil, oil breakdown voltage, oil volume resistivity, oil conductivity, acid value in oil, oil breakdown voltage, total acid value of oil, furfural content in oil, oil color and luster and the like, the parameters related to the insulating paper such as paper dielectric loss, water content in paper, paper breakdown voltage, paper conductivity, acid value in paper, paper polymerization degree, total acid value of paper, furfural content in paper, paper luster and the like, and H2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2The parameters related to gas such as relative gas production rate, total hydrocarbon and the like, the parameter data related to iron cores such as iron core insulation resistance, iron core grounding current and the like, the parameters related to windings such as winding direct current resistance, insulation resistance absorption ratio, winding direct current resistance and unbalance rate thereof, winding short-circuit impedance initial value difference, winding insulation dielectric loss, winding capacitance initial value difference and the like, the parameters related to capacitance values such as high-voltage side A-phase capacitance value, high-voltage side B-phase capacitance value, high-voltage side C-phase capacitance value, low-voltage side a-phase capacitance value, low-voltage side B-phase capacitance value, low-voltage side C-phase capacitance value and the like, the parameters related to temperature such as hot spot temperature at typical load, hot spot temperature at high load, oil temperature and the like, the parameters related to local discharge such as local discharge amount, deflection slope, steepness, cross correlation coefficient, phase asymmetry number and the like have different values under different environments and meteorological conditions, with random and fuzzy uncertainty, it can be said that a transformer fault is a random and fuzzy uncertainty accident or event, and these factors are also parameters of random and fuzzy uncertainty. These influencing factors are typically random or fuzzy uncertainty, or both random and fuzzy uncertainty, often present as random and fuzzy uncertainty events or quantities. Therefore, the uncertainty and randomness of the influence factors are not considered comprehensively in the prior art of the traditional transformer fault state assessment, and the applicability, the practicability and the applicability of the calculation method are difficult to meet.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a transformer fault state evaluation method, aiming at solving the problems of how to process big data with multiple types, large quantity and complex interrelation related to transformer fault state evaluation, the big data is processed and analyzed by adopting a data clustering principle on the basis of establishing a big database; and (3) processing and analyzing random and fuzzy uncertainty parameters related to the fault state evaluation of the transformer by adopting a probability fuzzy set theory.
The transformer fault state assessment method is based on the basic principle that a large database of parameters related to insulating oil, insulating paper, an iron core and a winding is established by utilizing multi-source data of delivery, monitoring, testing, routing inspection, operation, metering, automation and the like, a large database of parameters related to gas, capacitance, temperature and partial discharge in the oil is established, a large database of weather such as temperature, wind power, humidity, precipitation and the like is established, and an operation database of current, voltage, power, load rate and the like of a transformer is established; carrying out probability fuzzy modeling on parameters which have random uncertainty or fuzzy uncertainty and cause transformer fault states by adopting a probability fuzzy set theory; constructing a transformer fault state characteristic class probability fuzzy set by using mass data of results related to a transformer fault state evaluation method in a public document; constructing a transformer fault state test class probability fuzzy set by using mass data of a transformer fault state test; and (3) constructing a distance measure function between the transformer test class and the characteristic class data probability fuzzy set, and calculating a comprehensive attribute value between a random uncertainty or fuzzy uncertainty parameter and the transformer fault state so as to determine the transformer fault state.
The technical scheme of the invention is realized as follows:
a transformer fault state evaluation method comprises the following steps:
s1: constructing a data set of transformer insulating oil characteristic classes and calculating probability numerical values of the data set;
s2: constructing a data set of transformer insulation paper characteristic classes and calculating probability numerical values of the data set;
s3: constructing a data set of transformer gas characteristic classes and calculating probability values of the data set;
s4: constructing a data set of the transformer temperature characteristic class and calculating a probability value of the data set;
s5: constructing a data set of the transformer capacitance characteristic class and calculating a probability value of the data set;
s6: constructing a data set of the partial discharge characteristic class of the transformer and calculating a probability value of the data set;
s7: calculating the average values of the characteristic values of oil, paper, gas, temperature, capacitance and partial discharge which reflect the fault state of the transformer;
s8: constructing a fault state evaluation function of the transformer;
s9: and evaluating the fault state of the transformer.
5. Further, the transformer insulating oil feature class data set constructed in step S1 is:
in the formula (I), the compound is shown in the specification,
the method is a data set related to dielectric loss of transformer oil, water content in oil, gas content in oil, breakdown voltage of oil, volume resistivity of oil, conductivity of oil, acid value in oil, oil breakdown voltage, total acid value of oil, furfural content in oil and color of oil, and NSOThe number of the transformer oil characteristic class data sets;
acquiring data information of transformer insulating oil detection, testing and the like from a related database system, and determining the mean value and the variance of transformer oil dielectric loss, water content in oil, gas content in oil, oil breakdown voltage, oil volume resistivity, oil conductivity, acid value in oil, oil breakdown voltage, total acid value of oil, furfural content in oil and oil color change according to a normal distribution rule by adopting a simulation method;
the transformer insulation paper characteristic data set constructed in the step S2 is:
in the formula (I), the compound is shown in the specification,
is a data set related to the dielectric loss of transformer paper, the water content in the paper, the breakdown voltage of the paper, the conductivity of the paper, the acid value in the paper, the polymerization degree of the paper, the total acid value of the paper, the amount of furfural in the paper and the color of the paper, NSPThe number of the transformer paper feature class data sets;
acquiring data information of transformer insulation paper detection and test from a related database system, and determining the mean value and variance of transformer paper dielectric loss, water content in paper, paper breakdown voltage, paper conductivity, acid value in paper, paper polymerization degree, total paper acid value, furfural content in paper and paper color which respectively change according to a normal distribution rule by adopting a simulation method;
the transformer gas characteristic class data set constructed in the step S3 is:
in the formula (I), the compound is shown in the specification,
to and from transformer H2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2Relative gas production rate, total hydrocarbon related data set, NSGThe number of the transformer gas characteristic class data sets;
acquiring data information of transformer gas detection and test from related database system, and determining transformer H by adopting simulation method2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2Relative gas production rate, total hydrocarbonsThe mean and variance of each change according to a normal distribution rule;
the transformer temperature characteristic data set constructed in the step S4 is:
in the formula (I), the compound is shown in the specification,
is a data set related to the hot spot temperature at the typical load, the hot spot temperature at the high load and the oil temperature of the transformer, NSTThe number of the data sets of the temperature characteristic class of the transformer;
acquiring data information of transformer temperature detection and test from a related database system, and determining the mean value and the variance of the temperature of a hot spot under typical load, the temperature of the hot spot under high load and the oil temperature of the transformer according to a normal distribution rule by adopting a simulation method;
the transformer capacitance feature data set constructed in the step S5 is:
in the formula (I), the compound is shown in the specification,
is a data set related to the capacitance value of A phase at the high voltage side, the capacitance value of B phase at the high voltage side, the capacitance value of C phase at the high voltage side, the capacitance value of a phase at the low voltage side, the capacitance value of B phase at the low voltage side and the capacitance value of C phase at the low voltage side of the transformer, NSCThe number of the data sets of the capacitance characteristic class of the transformer;
acquiring data information of transformer capacitance detection and test from a related database system, and determining the mean value and the variance of the A-phase capacitance value, the B-phase capacitance value, the C-phase capacitance value, the a-phase capacitance value, the B-phase capacitance value and the C-phase capacitance value of the high-voltage side of the transformer according to the normal distribution rule by adopting a simulation method;
the partial discharge characteristic data set of the transformer constructed in the step S6 is:
in the formula (I), the compound is shown in the specification,
is the number of elements of the data set, N, related to the partial discharge, skewness, steepness, cross-correlation coefficient, phase asymmetry of the transformerSDThe number of the partial discharge characteristic class data sets of the transformer;
data information of partial discharge detection and test of the transformer is obtained from a related database system, and the mean value and the variance of partial discharge quantity, skewness, steepness, cross-correlation coefficient and phase asymmetry of the transformer are determined by a simulation method according to the change of a normal distribution rule.
Further, the specific process of calculating the average value of the oil, paper, gas, temperature, capacitance and partial discharge characteristic values reflecting the fault state of the transformer in step S7 is as follows:
s7-1: calculating an average value of oil characteristic values reflecting the fault state of the transformer:
in the formula, yDOa(xSOa) Is the mean value of characteristic values of the a-th transformer insulating oil characteristic class data set related to the fault state of the transformer, fDOa(xSOai) Probability density function of the data set of the a-th oil characteristic class for a fault state of the transformer, NDOkThe number of oil characteristics associated with a fault condition of the transformer in k years, Pr (y ═ k! y! kD) The probability of the fault state of the transformer in k years is shown;
s7-2: calculating the average value of the paper characteristic values reflecting the fault state of the transformer:
in the formula, yDPa(xDPa) Is the mean value of characteristic values of the a-th insulation paper characteristic class data set related to the fault state of the transformer, fDPa(xDPai) Probability density function of the data set of the alpha-th paper characteristic class for causing a fault condition in a transformer, NDPkThe number of the paper characteristic values related to the fault state of the transformer in k years is obtained;
s7-3: calculating the average value of the gas characteristic values reflecting the fault state of the transformer:
in the formula, yDGa(xDGa) Is the mean value of characteristic values of the a-th insulation paper characteristic class data set related to the fault state of the transformer, fDGa(xDGai) Probability density function of the data set of the alpha-th paper characteristic class for causing a fault condition in a transformer, NDGkThe quantity of the gas characteristic values related to the fault state of the transformer in k years is obtained;
s7-4: calculating the average value of the temperature characteristic values reflecting the fault state of the transformer:
in the formula, yDTa(xDTa) Is the mean value of characteristic values of the a-th temperature characteristic class data set related to the fault state of the transformer, fDTa(xDTai) Probability density function of the data set of the a-th temperature profile for a fault condition of the transformer, NDTkThe number of temperature characteristic values related to the fault state of the transformer in k years is shown;
s7-5: calculating the average value of the capacitance characteristic values reflecting the fault state of the transformer:
in the formula, yDCa(xDCa) Is the mean value of characteristic values of the a-th capacitance characteristic class data set related to the fault state of the transformer, fDCa(xDCai) Probability density function of the a-th capacitance characteristic class data set for causing a fault condition in a transformer, NDCkThe capacitance characteristic value quantity related to the fault state of the transformer in k years is obtained;
s7-6: calculating the average value of the partial discharge characteristic values reflecting the fault state of the transformer:
in the formula, yDDa(xDDa) Is the mean value of characteristic values of the a-th partial discharge characteristic class data set related to the fault state of the transformer, fDDa(xDDai) Probability density function (determined by mean and variance) of data set of a (a) th partial discharge characteristic class for causing transformer fault state, NDDkThe number of partial discharge characteristic values related to the fault state of the transformer in k years is shown.
Further, the step S8 of constructing the transformer fault state evaluation function specifically includes:
introducing a weight coefficient, and carrying out quotient comparison on oil, paper, gas, temperature, capacitance and partial discharge test data and an average value of characteristic values of the oil, the paper, the gas, the temperature, the capacitance and the partial discharge to construct a fault state evaluation function of the transformer:
wherein y is a comprehensive index value reflecting the fault state of the transformer, and kTOaWeight coefficient, k, for the a-th dataset of the oil-feature classTPaIs a weight coefficient, k, with the a-th data set of the paper feature classTGaIs a weight coefficient, k, with the a-th data set of the gas characteristics classTTaWeight coefficient, k, for the a-th data set of the temperature profile classTCaWeight coefficient, k, for the a-th data set of the capacitive characteristics classTDaWeight coefficient, x, of the a-th data set corresponding to the partial discharge characteristicsTOa、xTPa、xTGa、xTTa、xTCa、xTDaRespectively with oil, paper, gas, temperature, capacitance, partial discharge test or detection or monitoring data.
Further, when the transformer fault state is evaluated in step S9, if the integrated index value y reflecting the transformer fault state is smaller than the set value y0The transformer is considered to be in a fault state.
Compared with the prior art, the method and the device have the advantages that the large data are processed and analyzed by adopting a data clustering principle on the basis of establishing a large database aiming at how to process the large data problems of multiple types, large quantity and complex interrelation related to the fault state evaluation of the transformer; and (3) processing and analyzing random and fuzzy uncertainty parameters related to the fault state evaluation of the transformer by adopting a probability fuzzy set theory. The transformer fault state evaluation method and the transformer fault state evaluation system can evaluate the transformer fault state, reflect the uncertainty of the transformer fault state characteristic value, provide theoretical guidance for transformer fault state evaluation, and provide necessary technical support for operation and maintenance of the power distribution network.
Drawings
Fig. 1 is a flow chart of a transformer fault state evaluation method according to the present invention.
Detailed Description
Embodiments of the present invention will be described in further detail below with reference to the accompanying drawings in conjunction with examples.
Step S1 in fig. 1 describes the process of data set construction and probability value calculation for transformer insulating oil feature classes:
constructing a transformer insulating oil characteristic data set x from elements such as oil medium loss, water content in oil, gas content in oil, oil breakdown voltage, oil volume resistivity, oil conductivity, acid value in oil, oil breakdown voltage, furfural content in oil, oil color and the likeSOComprises the following steps:
in the formula (I), the compound is shown in the specification,
the method is a data set related to dielectric loss of transformer oil, water content in oil, gas content in oil, breakdown voltage of oil, volume resistivity of oil, conductivity of oil, acid value in oil, oil breakdown voltage, total acid value of oil, furfural content in oil and color of oil, and NSOThe number of characteristic class data sets for the transformer oil.
Acquiring data information of transformer insulating oil detection, test and the like from a related database system, and determining medium loss, water content in oil, gas content in oil, oil breakdown voltage, oil volume resistivity, oil conductivity, acid value in oil, oil breakdown voltage, total acid value of oil, furfural content in oil and mean value mu of oil color change according to normal distribution rule by adopting a simulation methodSQ1Sum variance σSO1Mean value of μSO2Sum variance σSO2Mean value of μSO3Sum variance σSO3Mean value of μSO4Sum variance σSO4Mean value of μSO5Sum variance σSO5Mean value of μSO6Sum variance σSO6Mean value of μSO7Sum variance σSO7Mean value of μSO8Sum variance σSO8Mean value of μSO9Sum variance σSO9Mean value of μSO10Sum variance σSO10Mean value of μSO11Sum variance σSO11。
Step S2 in fig. 1 describes the process of data set construction and probability value calculation for the transformer insulation paper feature class:
constructing a transformer insulation paper characteristic data set x by using elements such as paper dielectric loss, water content in paper, paper breakdown voltage, paper conductivity, acid value in paper, paper polymerization degree, total paper acid value, furfural content in paper, paper color and the likeSPComprises the following steps:
in the formula (I), the compound is shown in the specification,
is a data set related to the dielectric loss of transformer paper, the water content in the paper, the breakdown voltage of the paper, the conductivity of the paper, the acid value in the paper, the polymerization degree of the paper, the total acid value of the paper, the amount of furfural in the paper and the color of the paper, NSPNumber of feature class datasets for transformer paper.
Obtaining data information of transformer insulation paper detection, test and the like from a related database system, and determining the average value mu of the medium loss, the water content in paper, the paper breakdown voltage, the paper conductivity, the acid value in paper, the paper polymerization degree, the total acid value of paper, the furfural content in paper and the paper color change according to a normal distribution rule by adopting a simulation methodSP1Sum variance σSP1Mean value of μSP2Sum variance σSP2Mean value of μSP3Sum variance σSP3Mean value of μSP4Sum variance σSP4Mean value of μSP5Sum variance σSP5Mean value of μSP6Sum variance σSP6Mean value of μSP7Sum variance σSP7Mean value of μSP8Sum variance σSP8Mean value of μSP9Sum variance σSP9。
Step S3 in fig. 1 describes the process of data set construction and probability value calculation for the transformer gas feature class:
from H2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2Relative gas production rate,Constructing a transformer gas characteristic class data set x by using gas elements such as total hydrocarbonSGComprises the following steps:
in the formula (I), the compound is shown in the specification,
to and from transformer H2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2Relative gas production rate, number of elements of the total hydrocarbon related data set, NSGThe number of data sets for the transformer gas signature class.
Acquiring data information of transformer gas detection, test and the like from a related database system, and determining a transformer H by adopting a simulation method2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2Relative gas production rate, mean value mu of total hydrocarbon changing according to normal distribution ruleSG1Sum variance σSG1Mean value of μSG2Sum variance σSG2Mean value of μSG3Sum variance σSG3Mean value of μSG4Sum variance σSG4Mean value of μSG5Sum variance σSG5Mean value of μSG6Sum variance σSG6Mean value of μSG7Sum variance σSG7Mean value of μSG8Sum variance σSG8。
Step S4 in fig. 1 describes the process of data set construction and probability value calculation for the transformer temperature characteristic class:
constructing a transformer temperature characteristic data set x by temperature elements such as typical load time hot spot temperature, high load time hot spot temperature, oil temperature and the likeSTComprises the following steps:
in the formula
The number of elements of the data set related to the hot spot temperature at the typical load, the hot spot temperature at the high load and the oil temperature of the transformer, NSTThe number of data sets is classified for the temperature characteristics of the transformer.
Acquiring data information of transformer temperature detection, test and the like from a related database system, and determining the average value mu of the change of the hot spot temperature at the typical load, the hot spot temperature at the high load and the oil temperature according to the normal distribution rule of the transformer by adopting a simulation methodST1Sum variance σST1Mean value of μST2Sum variance σST2Mean value of μST3Sum variance σST3。
Step S5 in fig. 1 describes the process of data set construction and probability value calculation for the transformer capacitance feature class:
constructing a transformer capacitance characteristic data set x by using gas elements such as a high-voltage side A-phase capacitance value, a high-voltage side B-phase capacitance value, a high-voltage side C-phase capacitance value, a low-voltage side a-phase capacitance value, a low-voltage side B-phase capacitance value and a low-voltage side C-phase capacitance valueSCComprises the following steps:
in the formula (I), the compound is shown in the specification,
the number of elements of the data set related to the high-voltage side A-phase capacitance value, the high-voltage side B-phase capacitance value, the high-voltage side C-phase capacitance value, the low-voltage side a-phase capacitance value, the low-voltage side B-phase capacitance value and the low-voltage side C-phase capacitance value of the transformer, NSCThe number of data sets is classified for the capacitance characteristics of the transformer.
Obtaining data information of transformer capacitance detection, test and the like from a related database system, and determining the capacitance value of A phase at the high-voltage side and the B phase at the high-voltage side of the transformer by adopting a simulation methodMean value mu of capacitance value, high-voltage side C-phase capacitance value, low-voltage side a-phase capacitance value, low-voltage side b-phase capacitance value and low-voltage side C-phase capacitance value changing according to normal distribution ruleSC1Sum variance σSC1Mean value of μSC2Sum variance σSC2Mean value of μSC3Sum variance σSC3Mean value of μSC4Sum variance σSC4Mean value of μSC5Sum variance σSC5Mean value of μSC6Sum variance σSC6。
Step S6 in fig. 1 describes the process of data set construction and probability value calculation for the transformer partial discharge characteristic class:
the transformer partial discharge characteristic data set x is constructed by gas elements such as partial discharge quantity, skewness, steepness, cross correlation coefficient, phase asymmetry number and the likeSDComprises the following steps:
in the formula (I), the compound is shown in the specification,
is the number of elements of the data set, N, related to the partial discharge, skewness, steepness, cross-correlation coefficient, phase asymmetry of the transformerSDThe number of feature class datasets for partial discharge of a transformer.
Obtaining data information of partial discharge detection, test and the like of the transformer from a related database system, and determining the average value mu of partial discharge quantity, skewness, steepness, cross-correlation coefficient and phase asymmetry number of the transformer according to the change of a normal distribution rule by adopting a simulation methodSD1Sum variance σSD1Mean value of μSD2Sum variance σSD2Mean value of μSD3Sum variance σSD3Mean value of μSD4Sum variance σSD4Mean value of μSD5Sum variance σSD5。
Step S7 in fig. 1 describes the process of calculating the average value of the characteristic values of oil, paper, gas, temperature, capacitance and partial discharge reflecting the fault state of the transformer, which is as follows:
s7-1: calculating an average value of oil characteristic values reflecting the fault state of the transformer:
the average value of the characteristic values of the transformer insulating oil characteristic data set which reflects the fault state of the transformer and is composed of the elements such as oil medium loss, water content in oil, gas content in oil, oil breakdown voltage, oil volume resistivity, oil conductivity, acid value in oil, oil breakdown voltage, furfural content in oil, oil color and luster and the like is as follows:
in the formula, yDOa(xDOa) Is the mean value of characteristic values of the a-th transformer insulating oil characteristic class data set related to the fault state of the transformer, fDOa(xDOai) Probability density function (determined by mean and variance) for the a-th oil characteristic class dataset leading to transformer fault condition, NDOkThe number of oil characteristics associated with a fault condition of the transformer in k years, Pr (y ═ k! y! kD) Is the probability that the transformer has a fault state within k years.
S7-2: calculating the average value of the paper characteristic values reflecting the fault state of the transformer:
the average value of the characteristic values of the transformer insulation paper characteristic data set which reflects the fault state of the transformer and is composed of elements such as paper dielectric loss, water content in paper, paper breakdown voltage, paper conductivity, acid value in paper, paper polymerization degree, total paper acid value, furfural content in paper, paper color and the like is as follows:
in the formula, yDPa(xDPa) Is the mean value of characteristic values of the a-th insulation paper characteristic class data set related to the fault state of the transformer, fDPa(xDPai) Probability density function (determined by mean and variance) of the data set of the alpha-th paper feature class for causing a fault condition in the transformer, NDPkThe number of paper characteristic values related to the fault state of the transformer in k years.
S7-3: calculating the average value of the gas characteristic values reflecting the fault state of the transformer:
h for reflecting fault state of transformer2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2The average value of characteristic values of the transformer insulating gas characteristic data set formed by elements such as relative gas production rate, total hydrocarbon and the like is as follows:
in the formula, yDGa(xDGa) Is the mean value of characteristic values of the a-th insulation paper characteristic class data set related to the fault state of the transformer, fDGa(xDGai) Probability density function (determined by mean and variance) of the data set of the alpha-th paper feature class for causing a fault condition in the transformer, NDGkIs the number of gas characteristic values related to the fault state of the transformer in k years.
S7-4: calculating the average value of the temperature characteristic values reflecting the fault state of the transformer:
the average value of the characteristic values of the transformer temperature characteristic class data set which reflects the fault state of the transformer and consists of elements such as typical load hot spot temperature, high load hot spot temperature, oil temperature and the like is as follows:
in the formula, yDTa(xDTa) Is the mean value of characteristic values of the a-th temperature characteristic class data set related to the fault state of the transformer, fDTa(xDTai) Probability density function (determined by mean and variance) of the data set of the a-th temperature characteristic class for causing a fault condition of the transformer, NDTkThe number of temperature characteristic values related to the fault state of the transformer in k years is shown.
S7-5: calculating the average value of the capacitance characteristic values reflecting the fault state of the transformer:
the average value of the characteristic values of the transformer capacitance characteristic data set, which reflects the fault state of the transformer and is composed of elements such as a phase capacitance value at the high-voltage side, a phase capacitance value at the low-voltage side, and a phase capacitance value at the low-voltage side:
in the formula, yDCa(xDCa) Is the mean value of characteristic values of the a-th capacitance characteristic class data set related to the fault state of the transformer, fDCa(xDCai) Probability density function (determined by mean and variance) of the data set of the a-th capacitance characteristic class for causing a fault condition in the transformer, NDCkThe capacitance characteristic value quantity related to the degradation state of the transformer oil in k years.
S7-6: calculating the average value of the partial discharge characteristic values reflecting the fault state of the transformer:
the average value of the characteristic values of the partial discharge characteristic class data set of the transformer, which reflects the fault state of the transformer, is composed of elements such as partial discharge quantity, skewness, steepness, cross correlation coefficient, phase asymmetry number and the like, is as follows:
in the formula, yDDa(xDDa) Is the mean value of characteristic values of the a-th partial discharge characteristic class data set related to the fault state of the transformer, fDDa(xDDai) Probability density function (determined by mean and variance) of data set of a (a) th partial discharge characteristic class for causing transformer fault state, NDDkThe number of partial discharge characteristic values related to the fault state of the transformer in k years is shown.
Step S8 in fig. 1 describes the process of constructing the transformer fault status evaluation function:
introducing a weight coefficient, and carrying out quotient comparison on oil, paper, gas, temperature, capacitance and partial discharge test data and an average value of characteristic values of the oil, the paper, the gas, the temperature, the capacitance and the partial discharge to construct a fault state evaluation function of the transformer:
wherein y is a comprehensive index value reflecting the fault state of the transformer, and kTOaWeight coefficient, k, for the a-th dataset of the oil-feature classTPaIs a weight coefficient, k, with the a-th data set of the paper feature classTGaIs a weight coefficient, k, with the a-th data set of the gas characteristics classTTaWeight coefficient, k, for the a-th data set of the temperature profile classTCaWeight coefficient, k, for the a-th data set of the capacitive characteristics classTDaIs the weight coefficient of the a-th data set of the partial discharge characteristic class.
Step S9 in fig. 1 describes a process and method of transformer fault condition assessment. And (3) reflecting the comprehensive index value of the fault state of the transformer:
y＜y0
if the integrated index value is less than the set value y0Then the transformer is considered to be in a fault condition.
Aiming at how to deal with the problems of large types, large quantity and complex interrelation of big data related to the fault state evaluation of the transformer, the embodiment adopts a data clustering principle to process and analyze the big data on the basis of establishing a big database; random and fuzzy uncertainty parameters related to transformer fault state evaluation are processed and analyzed by adopting a probability fuzzy set theory; according to the transformer fault state evaluation method and device, the fault state of the transformer can be evaluated, uncertainty of characteristic values of the fault state of the transformer is reflected, theoretical guidance is provided for transformer fault state evaluation, and necessary technical support is provided for operation and maintenance of a power distribution network.
The above-mentioned embodiments are merely preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, so that variations based on the shape and principle of the present invention should be covered within the scope of the present invention.
Claims (3)
1. A transformer fault state evaluation method is characterized by comprising the following steps:
s1: constructing a data set of transformer insulating oil characteristic classes and calculating probability numerical values of the data set;
s2: constructing a data set of transformer insulation paper characteristic classes and calculating probability numerical values of the data set;
s3: constructing a data set of transformer gas characteristic classes and calculating probability values of the data set;
s4: constructing a data set of the transformer temperature characteristic class and calculating a probability value of the data set;
s5: constructing a data set of the transformer capacitance characteristic class and calculating a probability value of the data set;
s6: constructing a data set of the partial discharge characteristic class of the transformer and calculating a probability value of the data set;
s7: calculating the average values of the characteristic values of oil, paper, gas, temperature, capacitance and partial discharge which reflect the fault state of the transformer;
s8: constructing a fault state evaluation function of the transformer;
s9: carrying out fault state evaluation on the transformer;
the specific process of calculating the average value of the oil, paper, gas, temperature, capacitance and partial discharge characteristic values reflecting the fault state of the transformer in the step S7 is as follows:
s7-1: calculating an average value of oil characteristic values reflecting the fault state of the transformer:
in the formula, yDOa(xSOa) Is the mean value of characteristic values of the a-th transformer insulating oil characteristic class data set related to the fault state of the transformer, fDOa(xSOai) Probability density function of the data set of the a-th oil characteristic class for a fault state of the transformer, NDOkThe number of oil characteristics associated with a fault condition of the transformer in k years, Pr (y ═ k! y! kD) Is the probability of the transformer in fault state in k years, NSOThe number of the transformer oil characteristic class data sets;
s7-2: calculating the average value of the paper characteristic values reflecting the fault state of the transformer:
in the formula, yDPa(xDPa) Is the mean value of characteristic values of the a-th insulation paper characteristic class data set related to the fault state of the transformer, fDPa(xDPai) Probability density function of the data set of the alpha-th paper characteristic class for causing a fault condition in a transformer, NDPkNumber of paper characteristic values, N, associated with a fault condition of the transformer in k yearsSPThe number of the transformer paper feature class data sets;
s7-3: calculating the average value of the gas characteristic values reflecting the fault state of the transformer:
in the formula (I), the compound is shown in the specification,yDGa(xDGa) Is the mean value of characteristic values of the a-th insulation paper characteristic class data set related to the fault state of the transformer, fDGa(xDGai) Probability density function of the data set of the alpha-th paper characteristic class for causing a fault condition in a transformer, NDGkNumber of gas characteristic values, N, associated with a fault condition of the transformer in k yearsSGThe number of the transformer gas characteristic class data sets;
s7-4: calculating the average value of the temperature characteristic values reflecting the fault state of the transformer:
in the formula, yDTa(xDTa) Is the mean value of characteristic values of the a-th temperature characteristic class data set related to the fault state of the transformer, fDTa(xDTai) Probability density function of the data set of the a-th temperature profile for a fault condition of the transformer, NDTkFor the number of temperature characteristic values, N, associated with a fault condition of the transformer in k yearsSTThe number of the data sets of the temperature characteristic class of the transformer;
s7-5: calculating the average value of the capacitance characteristic values reflecting the fault state of the transformer:
in the formula, yDCa(xDCa) Is the mean value of characteristic values of the a-th capacitance characteristic class data set related to the fault state of the transformer, fDCa(xDCai) Probability density function of the a-th capacitance characteristic class data set for causing a fault condition in a transformer, NDCkTo fail with the transformer within k yearsNumber of state-dependent capacitance characteristic values, NSCThe number of the data sets of the capacitance characteristic class of the transformer;
s7-6: calculating the average value of the partial discharge characteristic values reflecting the fault state of the transformer:
in the formula, yDDa(xDDa) Is the mean value of characteristic values of the a-th partial discharge characteristic class data set related to the fault state of the transformer, fDDa(xDDai) Probability density function of the data set of the a-th partial discharge characteristic class for causing a fault condition in a transformer, NDDkNumber of partial discharge characteristics, N, associated with a fault condition of the transformer in k yearsSDThe number of the partial discharge characteristic class data sets of the transformer;
the step S8 of constructing the transformer fault state evaluation function specifically includes:
introducing a weight coefficient, and carrying out quotient comparison on oil, paper, gas, temperature, capacitance and partial discharge test data and an average value of characteristic values of the oil, the paper, the gas, the temperature, the capacitance and the partial discharge to construct a fault state evaluation function of the transformer:
wherein y is a comprehensive index value reflecting the fault state of the transformer, and kTOaWeight coefficient, k, for the a-th dataset of the oil-feature classTPaIs a weight coefficient, k, with the a-th data set of the paper feature classTGaIs a weight coefficient, k, with the a-th data set of the gas characteristics classTTaWeight coefficient, k, for the a-th data set of the temperature profile classTCaWeight coefficient, k, for the a-th data set of the capacitive characteristics classTDaWeight coefficient, x, of the a-th data set corresponding to the partial discharge characteristicsTOa、xTPa、xTGa、xTTa、xTCa、xTDaRespectively with oil, paper, gas, temperature, capacitance, partial discharge test or detection or monitoring data.
2. The transformer fault state evaluation method according to claim 1, wherein the transformer insulating oil characteristic class data set constructed in the step S1 is:
in the formula, xSO1、xSO2、xSO3、...、
The method is a data set related to dielectric loss of transformer oil, water content in oil, gas content in oil, breakdown voltage of oil, volume resistivity of oil, conductivity of oil, acid value in oil, oil breakdown voltage, total acid value of oil, furfural content in oil and color of oil, and NSOThe number of the transformer oil characteristic class data sets;
acquiring data information of transformer insulating oil detection and test from a related database system, and determining the mean value and the variance of transformer oil dielectric loss, water content in oil, gas content in oil, oil breakdown voltage, oil volume resistivity, oil conductivity, acid value in oil, oil breakdown voltage, total acid value of oil, furfural content in oil and oil color change according to a normal distribution rule by adopting a simulation method;
the transformer insulation paper characteristic data set constructed in the step S2 is:
in the formula, xSP1、xSP2、xSP3、...、
Is a data set related to the dielectric loss of transformer paper, the water content in the paper, the breakdown voltage of the paper, the conductivity of the paper, the acid value in the paper, the polymerization degree of the paper, the total acid value of the paper, the amount of furfural in the paper and the color of the paper, NSPThe number of the transformer paper feature class data sets;
acquiring data information of transformer insulation paper detection and test from a related database system, and determining the mean value and variance of transformer paper dielectric loss, water content in paper, paper breakdown voltage, paper conductivity, acid value in paper, paper polymerization degree, total paper acid value, furfural content in paper and paper color which respectively change according to a normal distribution rule by adopting a simulation method;
the transformer gas characteristic class data set constructed in the step S3 is:
in the formula, xSG1、xSG2、...、
To and from transformer H2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2Relative gas production rate, total hydrocarbon related data set, NSGThe number of the transformer gas characteristic class data sets;
acquiring data information of transformer gas detection and test from related database system, and determining transformer H by adopting simulation method2Content, C2H2Content, C2H6Content, C2H4Content, CH4Content, relative gas production rate of CO, CO2The relative gas production rate and the mean value and the variance of the total hydrocarbons which respectively change according to the normal distribution rule;
the transformer temperature characteristic data set constructed in the step S4 is:
in the formula, xST1、xST2、...、
Is a data set related to the hot spot temperature at the typical load, the hot spot temperature at the high load and the oil temperature of the transformer, NSTThe number of the data sets of the temperature characteristic class of the transformer;
acquiring data information of transformer temperature detection and test from a related database system, and determining the mean value and the variance of the temperature of a hot spot under typical load, the temperature of the hot spot under high load and the oil temperature of the transformer according to a normal distribution rule by adopting a simulation method;
the transformer capacitance feature data set constructed in the step S5 is:
in the formula, xSC1、xSC2、...、
Is a data set related to the capacitance value of A phase at the high voltage side, the capacitance value of B phase at the high voltage side, the capacitance value of C phase at the high voltage side, the capacitance value of a phase at the low voltage side, the capacitance value of B phase at the low voltage side and the capacitance value of C phase at the low voltage side of the transformer, NSCThe number of the data sets of the capacitance characteristic class of the transformer;
acquiring data information of transformer capacitance detection and test from a related database system, and determining the mean value and the variance of the A-phase capacitance value, the B-phase capacitance value, the C-phase capacitance value, the a-phase capacitance value, the B-phase capacitance value and the C-phase capacitance value of the high-voltage side of the transformer according to the normal distribution rule by adopting a simulation method;
the partial discharge characteristic data set of the transformer constructed in the step S6 is:
in the formula, xSD1、xSD2、...、
Is the number of elements of the data set, N, related to the partial discharge, skewness, steepness, cross-correlation coefficient, phase asymmetry of the transformerSDThe number of the partial discharge characteristic class data sets of the transformer;
data information of partial discharge detection and test of the transformer is obtained from a related database system, and the mean value and the variance of partial discharge quantity, skewness, steepness, cross-correlation coefficient and phase asymmetry of the transformer are determined by a simulation method according to the change of a normal distribution rule.
3. The transformer fault state evaluation method according to claim 1, wherein in the step S9, when the transformer fault state is evaluated, if the value y of the composite index reflecting the transformer fault state is smaller than the set value y0The transformer is considered to be in a fault state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810692629.5A CN108680811B (en) | 2018-06-29 | 2018-06-29 | Transformer fault state evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810692629.5A CN108680811B (en) | 2018-06-29 | 2018-06-29 | Transformer fault state evaluation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108680811A CN108680811A (en) | 2018-10-19 |
| CN108680811B true CN108680811B (en) | 2021-04-06 |
Family
ID=63812759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810692629.5A Active CN108680811B (en) | 2018-06-29 | 2018-06-29 | Transformer fault state evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108680811B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109856488A (en) * | 2019-03-15 | 2019-06-07 | 长沙理工大学 | A kind of Transformer State Assessment and fault detection method based on multisource data fusion |
| CN110110784B (en) * | 2019-04-30 | 2020-03-24 | 贵州电网有限责任公司 | Transformer fault identification method based on transformer related operation data |
| CN110058103A (en) * | 2019-05-23 | 2019-07-26 | 国电南京自动化股份有限公司 | Intelligent transformer fault diagnosis system based on Vxworks platform |
| CN110376462A (en) * | 2019-07-16 | 2019-10-25 | 东华大学 | A kind of power transformer fusion diagnosis method |
| CN112636642B (en) * | 2020-12-17 | 2023-03-24 | 广东工业大学 | Method and device for evaluating performance state of numerical control cutting tool bit made of flexible material |
| CN112861430A (en) * | 2021-01-20 | 2021-05-28 | 合肥工业大学 | Transformer state evaluation method under FCA-RST-multidimensional state cloud model |
| CN113255795B (en) * | 2021-06-02 | 2021-10-26 | 杭州安脉盛智能技术有限公司 | Equipment state monitoring method based on multi-index cluster analysis |
| CN114692787B (en) * | 2022-05-31 | 2022-08-19 | 广东电网有限责任公司佛山供电局 | Multi-source data-based three-winding main transformer event analysis processing method and system |
| CN115683230B (en) * | 2022-11-17 | 2024-03-29 | 广东电网有限责任公司 | Method, device, equipment, medium and system for detecting faults of oil immersed transformer |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251564A (en) * | 2008-04-08 | 2008-08-27 | 昆明理工大学 | Method for diagnosis failure of power transformer using extendible horticulture and inelegance collection theory |
| CN102662113A (en) * | 2012-04-17 | 2012-09-12 | 国网电力科学研究院 | Comprehensive diagnosis method of oil-immersed transformer based on fault tree |
| CN102981108A (en) * | 2012-11-29 | 2013-03-20 | 重庆大学 | Transformer internal insulation aging diagnosis method based on multi-feature information fusion technology |
| CN105405066A (en) * | 2015-11-18 | 2016-03-16 | 中国电力科学研究院 | Distribution transformer health index determination method |
| CN106295240A (en) * | 2016-10-25 | 2017-01-04 | 国家电网公司 | A kind of Condition Assessment for Power Transformer method based on fuzzy mathematics |
| CN106896218A (en) * | 2017-03-28 | 2017-06-27 | 浙江大学 | Based on the oil-immersed transformer fault diagnosis method that genetic planning and logical language are returned |
| CN106908674A (en) * | 2017-02-17 | 2017-06-30 | 国网上海市电力公司 | A kind of Transformer condition evaluation based on the prediction of multimode amount |
| CN107831415A (en) * | 2017-10-20 | 2018-03-23 | 广东电网有限责任公司河源供电局 | The Interval Valued Fuzzy diversity method that a kind of transformer insulating paper ageing state is assessed |
| CN107843718A (en) * | 2017-10-20 | 2018-03-27 | 广东电网有限责任公司河源供电局 | A kind of method that transformer insulation oil ageing state is assessed |
| CN107843816A (en) * | 2017-10-20 | 2018-03-27 | 广东电网有限责任公司河源供电局 | A kind of transformer insulated defect state appraisal procedure for considering load factor and influenceing |
-
2018
- 2018-06-29 CN CN201810692629.5A patent/CN108680811B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251564A (en) * | 2008-04-08 | 2008-08-27 | 昆明理工大学 | Method for diagnosis failure of power transformer using extendible horticulture and inelegance collection theory |
| CN102662113A (en) * | 2012-04-17 | 2012-09-12 | 国网电力科学研究院 | Comprehensive diagnosis method of oil-immersed transformer based on fault tree |
| CN102981108A (en) * | 2012-11-29 | 2013-03-20 | 重庆大学 | Transformer internal insulation aging diagnosis method based on multi-feature information fusion technology |
| CN105405066A (en) * | 2015-11-18 | 2016-03-16 | 中国电力科学研究院 | Distribution transformer health index determination method |
| CN106295240A (en) * | 2016-10-25 | 2017-01-04 | 国家电网公司 | A kind of Condition Assessment for Power Transformer method based on fuzzy mathematics |
| CN106908674A (en) * | 2017-02-17 | 2017-06-30 | 国网上海市电力公司 | A kind of Transformer condition evaluation based on the prediction of multimode amount |
| CN106896218A (en) * | 2017-03-28 | 2017-06-27 | 浙江大学 | Based on the oil-immersed transformer fault diagnosis method that genetic planning and logical language are returned |
| CN107831415A (en) * | 2017-10-20 | 2018-03-23 | 广东电网有限责任公司河源供电局 | The Interval Valued Fuzzy diversity method that a kind of transformer insulating paper ageing state is assessed |
| CN107843718A (en) * | 2017-10-20 | 2018-03-27 | 广东电网有限责任公司河源供电局 | A kind of method that transformer insulation oil ageing state is assessed |
| CN107843816A (en) * | 2017-10-20 | 2018-03-27 | 广东电网有限责任公司河源供电局 | A kind of transformer insulated defect state appraisal procedure for considering load factor and influenceing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108680811A (en) | 2018-10-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108680811B (en) | Transformer fault state evaluation method | |
| CN107843718B (en) | Method for evaluating aging state of transformer insulating oil | |
| CN108802584B (en) | Method for evaluating aging state of transformer insulation paper | |
| CN107831415B (en) | Interval value fuzzy set method for transformer insulation paper aging state evaluation | |
| Afrasiabi et al. | Integration of accelerated deep neural network into power transformer differential protection | |
| CN107843816B (en) | Transformer insulation defect state evaluation method considering load rate influence | |
| Moradzadeh et al. | Hybrid CNN-LSTM approaches for identification of type and locations of transmission line faults | |
| Chakravorti et al. | Recent trends in the condition monitoring of transformers | |
| CN107831300B (en) | Transformer insulating oil degradation evaluation method based on three-dimensional trapezoidal probability fuzzy set | |
| Abbasi et al. | Transformer winding faults detection based on time series analysis | |
| Guo et al. | Transformer failure diagnosis using fuzzy association rule mining combined with case‐based reasoning | |
| Nosratian Ahour et al. | Determination and localisation of turn‐to‐turn fault in transformer winding using frequency response analysis | |
| Li et al. | Condition assessment of power transformers using a synthetic analysis method based on association rule and variable weight coefficients | |
| Nagpal et al. | Artificial neural network approaches for fault classification: comparison and performance | |
| CN107808044A (en) | A kind of transformer insulating paper deterioration appraisal procedure for considering running temperature and influenceing | |
| CN108681835B (en) | Method for evaluating degradation state of transformer insulating oil | |
| Wani et al. | Diagnosis of incipient dominant and boundary faults using composite DGA method | |
| Lira et al. | Metal-oxide surge arrester monitoring and diagnosis by self-organizing maps | |
| Ma et al. | Fractal‐based autonomous partial discharge pattern recognition method for MV motors | |
| CN109086483A (en) | A kind of evidence fusion and Method of Set Pair Analysis of the assessment of transformer ageing state | |
| CN108805467A (en) | A kind of Probabilistic Fuzzy set method of transformer ageing state assessment | |
| Qi et al. | Rapid transformer health state recognition through canopy cluster-merging of dissolved gas data in high-dimensional space | |
| CN109033198A (en) | A kind of more element Fuzzy Analysis that transformer insulating paper recognizes extremely | |
| Yang | Comprehensive method detecting the status of the transformer based on the artificial intelligence | |
| CN109086484A (en) | A kind of evidence fusion and Method of Set Pair Analysis of transformer health state evaluation |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Tang Huiling Inventor after: Wu Jiekang Inventor before: Wu Jiekang |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |