CN111562458B - Power transformer fault diagnosis method and power transformer fault diagnosis device - Google Patents
Power transformer fault diagnosis method and power transformer fault diagnosis device Download PDFInfo
- Publication number
- CN111562458B CN111562458B CN202010521994.7A CN202010521994A CN111562458B CN 111562458 B CN111562458 B CN 111562458B CN 202010521994 A CN202010521994 A CN 202010521994A CN 111562458 B CN111562458 B CN 111562458B
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- transformer
- module
- power transformer
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
-
- 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Power Engineering (AREA)
- Housings And Mounting Of Transformers (AREA)
- Protection Of Transformers (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention belongs to the technical field of power transformer fault diagnosis, and discloses a power transformer fault diagnosis method and a power transformer fault diagnosis device, wherein the power transformer fault diagnosis device comprises: the device comprises a voltage detection module, a temperature detection module, a main control module, a fault detection module, a signal processing module, a data transmission module, a data analysis module, a fault identification module, a fault early warning module, a fault data storage module and a display module. According to the transformer fault identification method, more relevant operation data are added through the fault identification module, reasonable training is carried out on the classifier according to the influence weight of the data on fault identification, and relevant training data can be input according to requirements to adjust the parameters and the accuracy of the classifier, so that the transformer fault can be identified reasonably; the data analysis module is more targeted, and the power department can realize effective management of the distribution transformer according to the transformer data analysis report, so that the level of managing the distribution transformer is improved.
Description
Technical Field
The invention belongs to the technical field of power transformer fault diagnosis, and particularly relates to a power transformer fault diagnosis method and a power transformer fault diagnosis device.
Background
A Transformer (Transformer) is a device that changes an alternating-current voltage by using the principle of electromagnetic induction, and main components are a primary coil, a secondary coil, and an iron core (magnetic core). The main functions are as follows: voltage transformation, current transformation, impedance transformation, isolation, voltage stabilization (magnetic saturation transformer), and the like. According to the application, the method can be divided into: power transformers and special transformers (furnace transformers, rectification transformers, power frequency test transformers, voltage regulators, mining transformers, audio transformers, intermediate frequency transformers, high frequency transformers, impact transformers, transformers for instruments, electronic transformers, reactors, mutual inductors, etc.). The circuit symbols are usually T as the beginning of the number, e.g., T01, T201, etc. However, the existing power transformer fault diagnosis method and power transformer fault diagnosis device have inaccurate fault identification, inaccurate fault diagnosis model, and uncertain possible influence weight of each operation parameter on the occurrence of the fault of the transformer; meanwhile, the analysis of the transformer data is inaccurate, and the pertinence is poor.
In summary, the problems of the prior art are as follows: the existing power transformer fault diagnosis method and the power transformer fault diagnosis device have inaccurate fault identification, inaccurate fault diagnosis model, uncertain possible influence weight of each operation parameter on the fault of the transformer, and the like; meanwhile, the analysis of the transformer data is inaccurate, and the pertinence is poor.
The significance of solving the problems and the defects is as follows: when the fault of the power transformer occurs, the power supply is interrupted if the fault is light, the power utilization reliability of power consumers is influenced, and the production continuity is influenced if industrial consumers exist; the serious ignition transformer is in fire and explosion accidents, and serious equipment damage and casualties are generated.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a power transformer fault diagnosis method and a power transformer fault diagnosis device.
The invention is realized in such a way that the power transformer fault diagnosis method comprises the following steps:
detecting operating voltage data of a power transformer by a voltage detection module through a voltmeter; utilize temperature sensor to detect power transformer's operating temperature data through temperature detection module, the fault detection module detects power transformer's relevant data through the various devices of fault detection, power transformer's relevant data such as: variations in vibration and noise, partial discharge data of the transformer, and dissolved gases (H) in oil2、CO、CO2、CH4、C2H4、C2H2) Iron core grounding current parameters; the normal operation of each module of the power transformer fault diagnosis device is controlled by a controller through a main control module, and an intelligent control algorithm, such as an expert system, a genetic algorithm and the like, is combined with the support of an operation state database;
step two, sending a working state query instruction to a working node chip of the power transformer through a controller, and sequentially forwarding the working state query instruction by the working node chip of the power transformer;
judging whether the chip address of each node chip is matched with the chip address specified in the working state query instruction or not by using a fault detection circuit through a fault detection module; if not, judging that the power transformer has a fault, and simultaneously generating a fault signal;
amplifying the voltage amplitude corresponding to the fault signal generated in the step three by using a signal processing device through a signal processing module, and filtering noise in the fault signal by using the sum of absolute values of the amplified voltages of each sampling point in unit time as a threshold;
fifthly, uploading the fault signal data subjected to the enhancement processing in the fourth step to a controller for fault analysis by using an optical fiber through a data transmission module according to a data transmission device;
the specific method adopted by the fault analysis comprises the following steps:
collecting regular inspection data of a transformer to be diagnosed and a formed preliminary fault attribute set and decision set;
reducing transformer fault information, and establishing a transformer fault object model and a current object model by using the reduced information;
calculating extension correlation function values of the fault matter element model and the current state matter element model, determining a fault diagnosis weight coefficient and outputting a fault diagnosis result;
step six, acquiring historical monitoring data of the transformer through monitoring equipment, and acquiring real-time fault signal data of the transformer transmitted in the step five; screening effective fault data in historical monitoring data of the transformer and real-time fault signal data of the transformer by a data analysis module according to a preset data reduction standard by utilizing an analysis program;
analyzing the fault information of the power transformer according to the effective fault data of the transformer and by combining the voltage data and the temperature data of the power transformer operation detected in the step one, generating a fault analysis report, and uploading the fault analysis report to a database server;
step eight, reading in a transformer fault analysis report from a database server by using an identification program through a fault identification module, numbering transformer fault analysis data types according to data names, and setting the data types to A, B and C1～An、B1～Bm、C1～Ck.., numbering; setting the fault type of the transformer to be F, and pressing the fault type of the transformer to be F1～FtNumbering;
performing data preprocessing on the data with the numbers of A, B and C.the obtained in the step eight, namely performing missing value filling and denoising on the data, and then performing normalization processing on the data according to the classes;
step ten, carrying out weight analysis on different data types by using a principal component analysis method to obtain weight coefficients, and solving a characteristic root Evalaue and a characteristic vector Eectror according to the covariance matrix, wherein the normalized value of the characteristic root is the weight WOE of the relevant operating data of each transformer, namely the contribution rate of each characteristic root, and the method is similarly applicable to various data of different types;
step eleven, weighting the support vector machine, and training fault data by using a weighted support vector machine method to obtain a classifier model; inputting relevant operation data of a transformer used for training a classifier and the corresponding fault type into a weighting support vector machine to obtain the classifier;
step twelve, continuously inputting test data into the weighting support vector machine to adjust and improve parameters of the classifier, finally inputting data required to be identified to identify faults of the power transformer according to a fault analysis report, generating a fault identification result, and predicting the faults which are likely to occur in advance;
thirteen, the fault early warning module carries out early warning notification according to fault information by utilizing an acousto-optic early warning device, carries out advanced prediction and warning on the faults which are about to occur, sends out warning signals, prompts maintainers to carry out directional overhaul and maintenance, and avoids further serious accidents of the transformer; the fault data storage module is used for storing the detected voltage data, temperature data, fault analysis reports, fault identification results and early warning information by using a memory;
and step fourteen, displaying the detected voltage data, temperature data, fault analysis report, fault identification result and real-time data of early warning information by using a display through a display module.
Further, in step three, the method for determining whether the chip address of each node chip matches with the chip address specified in the working state query instruction includes:
if the chip address of the node chip is matched with the chip address specified in the working state query command, returning transformer data;
and if the detection shows that the transformer data returned by the node chip matched with the chip address specified in the working state query command is not received, judging that the power transformer has a fault, and generating a fault signal.
Further, in the fourth step, the noise filtering is performed asynchronously twice, the first time is performed with noise filtering from the starting time, and half of the duration time of the second time is used as the starting time for noise filtering.
Further, in the sixth step, the method for screening the historical monitoring data of the transformer and the effective fault data in the real-time fault signal data of the transformer according to the preset data reduction standard includes:
(I) cleaning historical monitoring data of the transformer and real-time fault data of the transformer based on a characteristic reduction standard;
(II) determining effective fault data of the transformer according to the cleaned historical monitoring data of the transformer and the real-time fault data of the transformer.
Further, in step seven, the method for analyzing the fault information of the power transformer according to the effective fault data of the transformer and by combining the detected voltage data, temperature data and the related operating parameters of the power transformer to generate the fault analysis report includes:
(1) classifying the effective fault data of the transformer according to a preset classification standard; the preset classification standard comprises classifying the effective fault data according to different work analysis requirements, wherein the work analysis requirements comprise energy efficiency analysis, energy-saving suggestion analysis and fault early warning analysis;
(2) storing effective fault data of the transformer and generating an effective fault data list;
(3) analyzing effective fault data of various transformers to generate transformer fault analysis reports; the transformer fault analysis report comprises a transformer fault analysis report, a transformer energy efficiency analysis report, a transformer energy-saving suggestion analysis report and a transformer fault early warning analysis report.
Further, in step ten, the method for calculating the weight WOE of the transformer related operation data includes:
wherein WOE represents the weight of the transformer-related operation data, P1 represents a characteristic root Evalaue, and P2 represents a characteristic vector Eectror.
Further, in the eleventh step, the method for training fault data by using a weighted support vector machine method to obtain a classifier model includes:
1) acquiring a plurality of transformer fault sample data, wherein the plurality of transformer fault sample data comprise a plurality of characteristic values of a plurality of original variables;
2) for each sample data in a plurality of transformer fault sample data, when the sample data accords with a classification condition corresponding to any classifier in a plurality of trained classifiers, taking a class corresponding to the classifier as a derivative variable of the sample data;
3) taking the characteristic value of the classifier as the characteristic value of the derived variable to obtain the characteristic value of at least one derived variable of the sample data, wherein the characteristic value of the classifier is determined based on the quantity of positive sample data and the quantity of negative sample data for training the classifier;
4) and training based on the characteristic values of the original variables, the categories and the characteristic values of the derived variables of the plurality of sample data to obtain the classifier model.
Another object of the present invention is to provide a power transformer fault diagnosis apparatus to which the power transformer fault diagnosis method is applied, the power transformer fault diagnosis apparatus including:
the voltage detection module is connected with the main control module and used for detecting the operating voltage data of the power transformer through a voltmeter;
the temperature detection module is connected with the main control module and used for detecting working temperature data of the power transformer through a temperature sensor, for example, the oil temperature of the oil-immersed power transformer is mainly detected;
the main control module is connected with the voltage detection module, the temperature detection module, the fault detection module, the signal processing module, the data transmission module, the data analysis module, the fault identification module, the fault early warning module, the fault data storage module and the display module and is used for controlling the normal operation of each module of the power transformer fault diagnosis device through the controller; the support of an intelligent control algorithm, such as an expert system, a genetic algorithm and the like, and an operation state database is combined;
the fault detection module is connected with the main control module and used for detecting relevant data of the power transformer through various fault detection devices, wherein the relevant data of the power transformer are as follows: variations in vibration and noise, partial discharge data of the transformer, and dissolved gases (H) in oil2、CO、CO2、CH4、C2H4、 C2H2) The iron core grounding current parameter;
the signal processing module is connected with the main control module and used for enhancing the detected fault signal of the power transformer through the signal processing device;
the data transmission module is connected with the main control module and used for uploading the processed fault signal to the controller for fault analysis by using the optical fiber through the data transmission device;
the data analysis module is connected with the main control module and used for analyzing the fault information of the power transformer according to the detected voltage data and temperature data of the power transformer operation through an analysis program and generating a fault analysis report;
the fault identification module is connected with the main control module and used for identifying the faults of the power transformer according to the fault analysis report through an identification program to generate a fault identification result and predicting the probable faults in advance according to the detected data;
the fault early warning module is connected with the main control module and used for predicting and alarming in advance according to the faults which are likely to occur through the acousto-optic early warning device, sending out an alarm signal and prompting maintainers to carry out directional overhaul and maintenance so as to avoid further serious accidents of the transformer;
the fault data storage module is connected with the main control module and used for storing the detected voltage data, temperature data, fault analysis reports, fault identification results and early warning information through a memory;
and the display module is connected with the main control module and used for displaying the detected voltage data, temperature data, fault analysis reports, fault identification results and real-time data of early warning information through a display.
Another object of the present invention is to provide a computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the power transformer fault diagnosis method when executed on an electronic device.
Another object of the present invention is to provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the power transformer fault diagnosis method.
By combining all the technical schemes, the invention has the advantages and positive effects that: according to the invention, the signal processing module is used for filtering noise by adopting the voltage absolute value in unit time, so that irregular noise can be filtered, and noise with the same frequency can be filtered; after signal amplification, noise is effectively filtered, and a compensation method is adopted to effectively compensate the start and end stages of the fault signal for two calibration sections (+/-2T time), so that the loss of the start and end stages of small signals of the fault signal caused by noise filtering is directly avoided, and the continuity of the fault signal is ensured.
According to the transformer fault identification method, more relevant operation data are added through the fault identification module, reasonable training is carried out on the classifier according to the influence weight of the data on fault identification, and relevant training data can be input according to requirements to adjust the parameters and the accuracy of the classifier, so that the transformer fault can be identified reasonably; meanwhile, a large amount of historical monitoring data and real-time monitoring data are utilized through a data analysis module, data cleaning is carried out on the historical monitoring data and the real-time monitoring data based on a preset data reduction standard, effective monitoring data are screened out, a transformer data analysis report is generated according to the effective monitoring data, and the transformer data analysis report is pushed; the transformer data analysis report obtained in the mode considers historical monitoring data and real-time monitoring data, so that the transformer data analysis report is more targeted, and a power department can effectively manage the distribution transformer according to the transformer data analysis report, so that the level of managing the distribution transformer is improved.
The method for diagnosing the fault of the power transformer has the characteristics and advantages that the method can predict and alarm the possible fault in advance by detecting and monitoring the running state data of the transformer and combining an intelligent control algorithm, such as an expert system, a genetic algorithm and the like, with the support of a running state database, and sends an alarm signal to prompt a maintainer to carry out directional overhaul and maintenance, thereby avoiding further serious accidents of the transformer.
Drawings
Fig. 1 is a flowchart of a power transformer fault diagnosis method according to an embodiment of the present invention.
Fig. 2 is a block diagram of a power transformer fault diagnosis apparatus according to an embodiment of the present invention;
in the figure: 1. a voltage detection module; 2. a temperature detection module; 3. a main control module; 4. a fault detection module; 5. a signal processing module; 6. a data transmission module; 7. a data analysis module; 8. a fault identification module; 9. a fault early warning module; 10. a failure data storage module; 11. and a display module.
Fig. 3 is a flowchart of a method for detecting and enhancing a fault signal of a power transformer according to an embodiment of the present invention.
Fig. 4 is a flowchart of a method for analyzing power transformer fault information according to voltage data and temperature data of detected power transformer operation and generating a fault analysis report by an analysis program according to an embodiment of the present invention.
Fig. 5 is a flowchart of a method for identifying a fault of a power transformer according to a fault analysis report by an identification procedure to generate a fault identification result according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In view of the problems in the prior art, the present invention provides a method for diagnosing a fault of a power transformer and a device for diagnosing a fault of a power transformer, and the present invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, a method for diagnosing a fault of a power transformer according to an embodiment of the present invention includes the following steps:
s101, detecting the operating voltage data of the power transformer by using a voltmeter through a voltage detection module; detecting working temperature data of the power transformer by using a temperature sensor through a temperature detection module; the fault detection module detects relevant data of the power transformer through various fault detection devices, wherein the relevant data of the power transformer comprises the following data: variations in vibration and noise, partial discharge data of the transformer, and dissolved gases (H) in oil2、CO、CO2、CH4、C2H4、C2H2) And the like, iron core grounding current parameters.
And S102, according to the detected data, the main control module controls the normal operation of the power transformer fault diagnosis device by using the controller, and combines an intelligent control algorithm, such as an expert system, a genetic algorithm and the like, with the support of an operation state database.
And S103, performing enhancement processing on the detected fault signal of the power transformer by using the signal processing device through the signal processing module.
And S104, uploading the processed fault signal to a controller for fault analysis by using the data transmission device through the data transmission module and using an optical fiber.
And S105, analyzing the fault information of the power transformer according to the detected voltage data and temperature data of the power transformer operation by using an analysis program through a data analysis module, and generating a fault analysis report.
S106, identifying the fault of the power transformer by the fault identification module according to the fault analysis report through an identification program, and generating a fault identification result; and advance predictions of impending failures are made.
S107, the fault early warning module carries out early warning notification according to fault information by utilizing the acousto-optic early warning device, carries out early prediction and warning on the faults which are about to occur, sends out warning signals, prompts maintainers to carry out directional overhaul and maintenance, and avoids further serious accidents of the transformer; and the fault data storage module is used for storing the detected voltage data, temperature data, fault analysis reports, fault identification results and early warning information by using a memory.
And S108, displaying the detected voltage data, temperature data, fault analysis reports, fault identification results and real-time data of early warning information by using a display through a display module.
In S104, a specific method adopted for fault analysis provided by the embodiment of the present invention includes:
collecting regular inspection data of a transformer to be diagnosed and a formed preliminary fault attribute set and decision set;
reducing transformer fault information, and establishing a transformer fault object model and a current state object model by using the reduced information;
and calculating extension correlation function values of the fault object-element model and the current object-element model, determining a fault diagnosis weight coefficient and outputting a fault diagnosis result.
The transformer fault information reduction adopts two modes:
a. the difference between the two dependence degrees is used for determining the importance:
k(D)＝rB(D)-rB-B′(D)
wherein: b is an attribute set; b' is a subset in the attribute set; r is a radical of hydrogenB(D) Is the dependency of B on D; r isB-B’(D) Is the dependence of B-B' on D; k (D) is the importance value between the two attribute subsets;
b. quotient representation of positive domains using equivalence relation of two
Wherein: posB(D) Is the equivalence relation of B to D; posB-B’(D) Is B-equivalence of B' to D; n (D) is the importance of both.
As shown in fig. 2, the power transformer fault diagnosis apparatus provided in the embodiment of the present invention includes: the device comprises a voltage detection module 1, a temperature detection module 2, a main control module 3, a fault detection module 4, a signal processing module 5, a data transmission module 6, a data analysis module 7, a fault identification module 8, a fault early warning module 9, a fault data storage module 10 and a display module 11.
The voltage detection module 1 is connected with the main control module 3 and used for detecting the operating voltage data of the power transformer through a voltmeter;
the temperature detection module 2 is connected with the main control module 3 and used for detecting working temperature data of the power transformer through a temperature sensor, for example, the oil temperature of the oil-immersed power transformer is mainly detected;
the main control module 3 is connected with the voltage detection module 1, the temperature detection module 2, the fault detection module 4, the signal processing module 5, the data transmission module 6, the data analysis module 7, the fault identification module 8, the fault early warning module 9, the fault data storage module 10 and the display module 11, and is used for controlling the normal operation of each module of the power transformer fault diagnosis device through the controller; the support of an intelligent control algorithm, such as an expert system, a genetic algorithm and the like, and an operation state database is combined;
and the fault detection module 4 is connected with the main control module 3 and used for detecting relevant data of the power transformer through various fault detection devices, wherein the relevant data of the power transformer is as follows: variations in vibration and noise, partial discharge data of the transformer, and dissolved gases (H) in oil2、CO、CO2、CH4、C2H4、 C2H2) And the like, iron core grounding current parameters;
the signal processing module 5 is connected with the main control module 3 and used for performing enhancement processing on the detected fault signal of the power transformer through the signal processing device;
the data transmission module 6 is connected with the main control module 3 and used for uploading the processed fault signal to a controller for fault analysis by using an optical fiber through a data transmission device;
the data analysis module 7 is connected with the main control module 3 and used for analyzing the fault information of the power transformer according to the detected voltage data and temperature data of the power transformer operation through an analysis program and generating a fault analysis report;
the fault identification module 8 is connected with the main control module 3 and used for identifying the faults of the power transformer according to the fault analysis report through an identification program, generating a fault identification result and predicting the possible faults in advance according to the detected data;
the fault early warning module 9 is connected with the main control module 3 and used for predicting and alarming in advance according to the faults which are likely to occur through the acousto-optic early warning device, sending out an alarm signal and prompting maintainers to carry out directional overhaul and maintenance so as to avoid further serious accidents of the transformer;
the fault data storage module 10 is connected with the main control module 3 and used for storing the detected voltage data, temperature data, fault analysis reports, fault identification results and early warning information through a memory;
and the display module 11 is connected with the main control module 3 and used for displaying the detected voltage data, temperature data, fault analysis reports, fault identification results and real-time data of early warning information through a display.
The invention is further described with reference to specific examples.
Example 1
As shown in fig. 1 and fig. 3, as a preferred embodiment, the method for diagnosing a fault of a power transformer according to an embodiment of the present invention includes:
s201, judging whether the chip address of each node chip is matched with the chip address specified in the working state query instruction or not by using fault detection equipment through a fault detection module; if not, the power transformer is judged to be in fault, and a fault signal is generated at the same time.
And S202, amplifying the voltage amplitude corresponding to the fault signal generated in the step three by using a signal processing device through a signal processing module, and filtering noise in the fault signal by using the sum of the absolute values of the amplified voltages of all sampling points in unit time as a threshold.
In step S201 provided in the embodiment of the present invention, the method for determining whether the chip address of each node chip matches the chip address specified in the working status query instruction includes:
if the chip address of the node chip is matched with the chip address specified in the working state query command, returning transformer data;
and if the detection shows that the transformer data returned by the node chip matched with the chip address specified in the working state query command is not received, judging that the power transformer has a fault, and generating a fault signal.
In step S202 provided in the embodiment of the present invention, the noise filtering is performed asynchronously twice, where the first time is performed with noise filtering from the starting time, and half of the duration time of the second time is used as the starting time for noise filtering.
Example 2
As shown in fig. 1, and as a preferred embodiment, as shown in fig. 4, a method for analyzing fault information of a power transformer according to detected voltage data, temperature data and related operating parameters of the power transformer by an analysis program and generating a fault analysis report according to an embodiment of the present invention includes:
s301, historical monitoring data of the transformer are obtained through the monitoring equipment, and real-time fault signal data of the transformer transmitted by the data transmission device are obtained.
S302, screening the historical monitoring data of the transformer and the effective fault data in the real-time fault signal data of the transformer by using an analysis program through a data analysis module according to a preset data reduction standard.
And S303, analyzing the fault information of the power transformer according to the effective fault data of the transformer and by combining the detected voltage data, temperature data and related operation parameters of the power transformer, generating a fault analysis report, and uploading the fault analysis report to a database server.
In step S302 provided in the embodiment of the present invention, the method for screening historical monitoring data of a transformer and effective fault data in real-time fault signal data of the transformer according to a preset data reduction standard includes:
(I) and cleaning historical monitoring data of the transformer and real-time fault data of the transformer based on a characteristic reduction standard.
(II) determining effective fault data of the transformer according to the cleaned historical monitoring data of the transformer and the real-time fault data of the transformer.
In step S303 provided in the embodiment of the present invention, the method for generating a fault analysis report by analyzing fault information of a power transformer according to valid fault data of the transformer and by combining detected voltage data and temperature data includes:
(1) classifying the effective fault data of the transformer according to a preset classification standard; the preset classification standard comprises classifying the effective fault data according to different work analysis requirements, wherein the work analysis requirements comprise energy efficiency analysis, energy-saving suggestion analysis and fault early warning analysis;
(2) storing effective fault data of the transformer and generating an effective fault data list;
(3) analyzing effective fault data of various transformers to generate transformer fault analysis reports; the transformer fault analysis report comprises a transformer fault analysis report, a transformer energy efficiency analysis report, a transformer energy-saving suggestion analysis report and a transformer fault early warning analysis report.
Example 3
As shown in fig. 1, and as a preferred embodiment, as shown in fig. 5, the method for identifying a fault of a power transformer according to a fault analysis report by an identification program to generate a fault identification result according to an embodiment of the present invention includes:
s401, reading in a transformer fault analysis report from a database server by using an identification program through a fault identification module, numbering transformer fault analysis data types according to data names, and setting the data types as A, B and C1～An、B1～Bm、C1～Ck.., numbering; setting the fault type of the transformer to be F, and pressing the fault type of the transformer to be F1～FtNumbering is performed.
S402, performing data preprocessing on the data numbered A, B and c. obtained in S401, that is, performing missing value padding and denoising on the data, and then performing normalization processing on the data according to classes.
And S403, carrying out weight analysis on different data types by using a principal component analysis method to obtain weight coefficients, and solving a characteristic root Evalaue and a characteristic vector Eectror according to the covariance matrix, wherein the normalized value of the characteristic root is the weight WOE of the related operation data of each transformer, namely the contribution rate of each characteristic root, and the method is similarly applicable to various data of different types.
S404, weighting the support vector machine, and training fault data by using a weighted support vector machine method to obtain a classifier model; and inputting the relevant operation data of the transformer used for training the classifier and the corresponding fault type into a weighting support vector machine to obtain the classifier.
S405, test data are continuously input into the weighting support vector machine to adjust and improve parameters of the classifier, finally data required to be identified are input to identify faults of the power transformer according to the fault analysis report, and a fault identification result is generated.
In step S403 provided in the embodiment of the present invention, the method for calculating the weight WOE of the transformer related operation data includes:
wherein WOE represents the weight of the transformer-related operation data, P1 represents a characteristic root Evalaue, and P2 represents a characteristic vector Eectror.
In step S404 provided in the embodiment of the present invention, the method for training fault data by using a weighted support vector machine method to obtain a classifier model includes:
1) acquiring a plurality of transformer fault sample data, wherein the plurality of transformer fault sample data comprise a plurality of characteristic values of a plurality of original variables;
2) for each sample data in a plurality of transformer fault sample data, when the sample data accords with a classification condition corresponding to any classifier in a plurality of trained classifiers, taking a class corresponding to the classifier as a derivative variable of the sample data;
3) taking the characteristic value of the classifier as the characteristic value of the derived variable to obtain the characteristic value of at least one derived variable of the sample data, wherein the characteristic value of the classifier is determined based on the quantity of positive sample data and the quantity of negative sample data for training the classifier;
4) and training based on the characteristic values of the original variables, the categories and the characteristic values of the derived variables of the plurality of sample data to obtain the classifier model.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A power transformer fault diagnosis method is characterized by comprising the following steps:
detecting operating voltage data of a power transformer by a voltage detection module through a voltmeter; utilize temperature sensor to detect power transformer's operating temperature data through temperature detection module, the fault detection module detects power transformer's relevant data through various devices of fault detection, power transformer's relevant data: vibration and noise variation, partial discharge (partial discharge) data of the transformer, and parameters of the fused gas in the oil and the grounding current of the iron core; the normal operation of each module of the power transformer fault diagnosis device is controlled by the controller through the main control module, and the support of an intelligent control algorithm and an operation state database is combined;
step two, sending a working state query instruction to a working node chip of the power transformer through a controller, and sequentially forwarding the working state query instruction by the working node chip of the power transformer;
judging whether the chip address of each node chip is matched with the chip address specified in the working state query instruction or not by using a fault detection circuit through a fault detection module; if not, judging that the power transformer has a fault, and simultaneously generating a fault signal;
the method for judging whether the chip address of each node chip is matched with the chip address specified in the working state query instruction comprises the following steps:
if the chip address of the node chip is matched with the chip address specified in the working state query command, returning transformer data;
if the transformer data returned by the node chip matched with the chip address specified in the working state query command is not received through detection, judging that the power transformer has a fault, and generating a fault signal;
amplifying the voltage amplitude corresponding to the fault signal generated in the step three by using a signal processing device through a signal processing module, and filtering noise in the fault signal by using the sum of absolute values of the amplified voltages of each sampling point in unit time as a threshold;
fifthly, uploading the fault signal data subjected to the enhancement processing in the fourth step to a controller for fault analysis by using an optical fiber through a data transmission module according to a data transmission device;
the specific method adopted by the fault analysis comprises the following steps:
collecting regular inspection data of a transformer to be diagnosed and a formed preliminary fault attribute set and decision set;
reducing transformer fault information, and establishing a transformer fault object model and a current object model by using the reduced information;
calculating extension correlation function values of the fault matter element model and the current state matter element model, determining a fault diagnosis weight coefficient and outputting a fault diagnosis result;
step six, acquiring historical monitoring data of the transformer through monitoring equipment, and acquiring real-time fault signal data of the transformer transmitted in the step five; screening effective fault data in historical monitoring data of the transformer and real-time fault signal data of the transformer by a data analysis module according to a preset data reduction standard by utilizing an analysis program;
analyzing the fault information of the power transformer according to the effective fault data of the transformer and by combining the voltage data and the temperature data of the power transformer operation detected in the step one, generating a fault analysis report, and uploading the fault analysis report to a database server;
step eight, reading in a transformer fault analysis report from a database server by using an identification program through a fault identification module, numbering transformer fault analysis data types according to data names, and setting the data types to A, B and C1～An、B1～Bm、C1～Ck.., numbering; setting the fault type of the transformer to be F, and pressing the fault type of the transformer to be F1～FtNumbering;
performing data preprocessing on the data with the numbers of A, B and C.the obtained in the step eight, namely performing missing value filling and denoising on the data, and then performing normalization processing on the data according to the classes;
step ten, carrying out weight analysis on different data types by using a principal component analysis method to obtain weight coefficients, and solving a characteristic root Evalaue and a characteristic vector Eectror according to the covariance matrix, wherein the normalized value of the characteristic root is the weight WOE of the related operation data of each transformer, namely the contribution rate of each characteristic root, and the method is similarly suitable for various data of different types;
step eleven, weighting the support vector machine, and training fault data by using a weighted support vector machine method to obtain a classifier model; inputting relevant operation data of a transformer used for training a classifier and the corresponding fault type into a weighting support vector machine to obtain the classifier;
step twelve, continuously inputting test data into the weighted support vector machine to adjust and improve parameters of the classifier, finally inputting data to be identified to identify faults of the power transformer according to the fault analysis report, generating a fault identification result, and predicting the faults which are likely to happen in advance;
thirteen, the fault early warning module carries out early warning notification according to fault information by utilizing an acousto-optic early warning device, carries out advanced prediction and warning on the faults which are about to occur, sends out warning signals, prompts maintainers to carry out directional overhaul and maintenance, and avoids further serious accidents of the transformer; the fault data storage module is used for storing the detected voltage data, temperature data, fault analysis reports, fault identification results and early warning information by using a memory;
and step fourteen, displaying the detected voltage data, temperature data, fault analysis report, fault identification result and real-time data of early warning information by using a display through a display module.
2. The power transformer fault diagnosis method according to claim 1, wherein in step five, the transformer fault information reduction adopts two modes:
a. the difference between the two dependence degrees is used for determining the importance:
k(D)＝rB(D)-rB-B′(D)
wherein: b is an attribute set; b' is a subset in the attribute set; r isB(D) Is the dependency of B on D; r isB-B’(D) Is the dependence of B-B' on D; k (D) is the importance value between the two attribute subsets;
b. quotient representation of positive domains using equivalence relation of two
Wherein: posB(D) Is the equivalence relation of B to D; posB-B’(D) Is the equivalence relation of B-B' to D; n (D) is the importance of both.
3. A power transformer fault diagnosis method according to claim 1, characterized in that in step four, the noise filtering is performed asynchronously in two times, the first time is performed with noise filtering from the starting time, and half of the duration of the second time is performed with noise filtering as the starting time.
4. A power transformer fault diagnosis method according to claim 1, wherein in step six, the method for screening the historical monitoring data of the transformer and the effective fault data in the real-time fault signal data of the transformer according to the preset data reduction standard comprises:
(I) cleaning historical monitoring data of the transformer and real-time fault data of the transformer based on a characteristic reduction standard;
(II) determining effective fault data of the transformer according to the cleaned historical monitoring data of the transformer and the real-time fault data of the transformer.
5. A power transformer fault diagnosis method according to claim 1, characterized in that in step seven, said method for analyzing fault information of a power transformer according to valid fault data of said transformer and combining detected voltage data, temperature data and related operating parameters of the power transformer to generate a fault analysis report comprises:
(1) classifying the effective fault data of the transformer according to a preset classification standard; the preset classification standard comprises classifying the effective fault data according to different work analysis requirements, wherein the work analysis requirements comprise energy efficiency analysis, energy-saving suggestion analysis and fault early warning analysis;
(2) storing effective fault data of the transformer and generating an effective fault data list;
(3) analyzing effective fault data of various transformers to generate transformer fault analysis reports; the transformer fault analysis report comprises a transformer fault analysis report, a transformer energy efficiency analysis report, a transformer energy-saving suggestion analysis report and a transformer fault early warning analysis report.
6. A power transformer fault diagnosis method according to claim 1, characterized in that in the tenth step, the method for calculating the weight WOE of the transformer related operation data is:
wherein WOE represents the weight of the transformer-related operation data, P1 represents a characteristic root Evalaue, and P2 represents a characteristic vector Eectror.
7. The power transformer fault diagnosis method according to claim 1, wherein in step eleven, the method for training fault data by using a weighted support vector machine method to obtain a classifier model comprises:
1) acquiring a plurality of transformer fault sample data, wherein the plurality of transformer fault sample data comprise a plurality of characteristic values of a plurality of original variables;
2) for each sample data in a plurality of transformer fault sample data, when the sample data accords with a classification condition corresponding to any classifier in a plurality of trained classifiers, taking a class corresponding to the classifier as a derivative variable of the sample data;
3) taking the characteristic value of the classifier as the characteristic value of the derived variable to obtain the characteristic value of at least one derived variable of the sample data, wherein the characteristic value of the classifier is determined based on the quantity of positive sample data and the quantity of negative sample data for training the classifier;
4) and training based on the characteristic values of the original variables, the categories and the characteristic values of the derived variables of the plurality of sample data to obtain the classifier model.
8. A power transformer fault diagnosis apparatus to which the power transformer fault diagnosis method according to any one of claims 1 to 7 is applied, the power transformer fault diagnosis apparatus comprising:
the voltage detection module is connected with the main control module and used for detecting the operating voltage data of the power transformer through a voltmeter;
the temperature detection module is connected with the main control module and used for detecting the working temperature data of the power transformer through the temperature sensor;
the main control module is connected with the voltage detection module, the temperature detection module, the fault detection module, the signal processing module, the data transmission module, the data analysis module, the fault identification module, the fault early warning module, the fault data storage module and the display module and is used for controlling the normal operation of each module of the power transformer fault diagnosis device through the controller; combining the support of an intelligent control algorithm and an operation state database;
the fault detection module is connected with the main control module and used for detecting the relevant data of the power transformer through various fault detection devices, wherein the relevant data of the power transformer are as follows: vibration and noise variation, partial discharge (partial discharge) data of the transformer, and parameters of the fused gas in the oil and the grounding current of the iron core;
the signal processing module is connected with the main control module and used for enhancing the detected fault signal of the power transformer through the signal processing device;
the data transmission module is connected with the main control module and used for uploading the processed fault signal to the controller for fault analysis by using the optical fiber through the data transmission device;
the data analysis module is connected with the main control module and used for analyzing the fault information of the power transformer according to the detected voltage data and temperature data of the power transformer operation through an analysis program and generating a fault analysis report;
the fault identification module is connected with the main control module and used for identifying the faults of the power transformer according to the fault analysis report through an identification program to generate a fault identification result and predicting the probable faults in advance according to the detected data; reading in a transformer fault analysis report from a database server by using an identification program through a fault identification module, numbering transformer fault analysis data types according to data names, and setting the data types to be A, B and C1～An、B1～Bm、C1～Ck.., carrying outNumbering; setting the fault type of the transformer to be F, and pressing the fault type of the transformer to be F1～FtNumbering;
data preprocessing is carried out on the data with numbers of A, B and C.obtained in the step eight, namely missing value filling and denoising processing are carried out on the data, and then normalization processing is carried out on the data according to classes;
carrying out weight analysis on different data types by using a principal component analysis method to obtain weight coefficients, and solving a characteristic root Evalaue and a characteristic vector Eectror according to a covariance matrix, wherein the normalized value of the characteristic root is the weight WOE of the related operation data of each transformer, namely the contribution rate of each characteristic root, and the method is similarly applicable to various data of different types;
weighting the support vector machine, and training fault data by using a weighted support vector machine method to obtain a classifier model; inputting relevant operation data of a transformer used for training a classifier and the corresponding fault type into a weighting support vector machine to obtain the classifier;
continuously inputting test data into the weighted support vector machine to adjust and improve parameters of the classifier, finally inputting data to be identified to identify faults of the power transformer according to the fault analysis report, generating a fault identification result, and predicting the faults which are likely to occur in advance;
the fault early warning module is connected with the main control module and used for predicting and alarming in advance according to the faults which are likely to occur through the acousto-optic early warning device, sending out an alarm signal and prompting maintainers to carry out directional overhaul and maintenance so as to avoid further serious accidents of the transformer;
the fault data storage module is connected with the main control module and used for storing the detected voltage data, temperature data, fault analysis reports, fault identification results and early warning information through a memory;
and the display module is connected with the main control module and used for displaying the detected voltage data, temperature data, fault analysis reports, fault identification results and real-time data of early warning information through a display.
9. A computer readable storage medium storing instructions which, when executed on a computer, cause the computer to perform a power transformer fault diagnosis method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010521994.7A CN111562458B (en) | 2020-06-10 | 2020-06-10 | Power transformer fault diagnosis method and power transformer fault diagnosis device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010521994.7A CN111562458B (en) | 2020-06-10 | 2020-06-10 | Power transformer fault diagnosis method and power transformer fault diagnosis device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111562458A CN111562458A (en) | 2020-08-21 |
| CN111562458B true CN111562458B (en) | 2022-05-27 |
Family
ID=72070045
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010521994.7A Active CN111562458B (en) | 2020-06-10 | 2020-06-10 | Power transformer fault diagnosis method and power transformer fault diagnosis device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111562458B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112398218A (en) * | 2020-09-28 | 2021-02-23 | 国网山东省电力公司冠县供电公司 | Power grid safety and stability analysis device and method |
| CN112414949A (en) * | 2020-10-29 | 2021-02-26 | 国网山西省电力公司电力科学研究院 | Gas relay for detecting transformer fault in real time and diagnosis method |
| CN112379200B (en) * | 2020-11-10 | 2024-02-13 | 深圳市康必达控制技术有限公司 | Fault positioning and solving method |
| CN112562698B (en) * | 2020-12-02 | 2022-11-04 | 国网山西省电力公司大同供电公司 | Power equipment defect diagnosis method based on fusion of sound source information and thermal imaging characteristics |
| WO2022116111A1 (en) * | 2020-12-03 | 2022-06-09 | Boe Technology Group Co., Ltd. | Computer-implemented method for defect analysis, computer-implemented method of evaluating likelihood of defect occurrence, apparatus for defect analysis, computer-program product, and intelligent defect analysis system |
| CN112731026A (en) * | 2020-12-21 | 2021-04-30 | 国网上海市电力公司 | Based on transformer noise fault detection recognition device |
| CN112733033B (en) * | 2021-01-20 | 2023-11-10 | 渭南双盈未来科技有限公司 | Information processing method and system |
| CN112884089A (en) * | 2021-04-12 | 2021-06-01 | 国网上海市电力公司 | Power transformer fault early warning system based on data mining |
| CN113375729B (en) * | 2021-07-15 | 2023-10-31 | 贵州电网有限责任公司 | Intelligent detection and early warning method for user transformer |
| CN113848418A (en) * | 2021-08-10 | 2021-12-28 | 广东新电电力科技有限公司 | Electric energy quality online detection method, device, equipment and storage medium |
| CN114034956A (en) * | 2021-11-10 | 2022-02-11 | 国网甘肃省电力公司陇南供电公司 | Fault monitoring and early warning method for dry-type air-core reactor |
| CN114422884A (en) * | 2021-11-26 | 2022-04-29 | 北京智芯微电子科技有限公司 | Distribution transformer fault sample collection method, device and system |
| CN114062774A (en) * | 2021-12-09 | 2022-02-18 | 华能定边新能源发电有限公司 | Remote monitoring system and monitoring method for leakage current of transformer core and clamping piece |
| CN115660478B (en) * | 2022-10-25 | 2023-06-20 | 贵州电网有限责任公司 | Transformer-based health state monitoring method, device, equipment and storage medium |
| CN116295661B (en) * | 2023-05-22 | 2023-08-01 | 济南西电特种变压器有限公司 | Transformer fault early warning system based on Internet of things |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1484034A (en) * | 2002-09-18 | 2004-03-24 | 新疆特变电工股份有限公司 | On-line intelligent monitoring system for transformer and intelligent analysis diagnosis method thereof |
| FR2860593A1 (en) * | 2003-10-03 | 2005-04-08 | Alstom T & D Sa | Winding fault diagnosing method for three-phase power transformer, involves determining relative variation of resonant frequency greater than specific frequency by comparing two voltage gains |
| KR20140033944A (en) * | 2012-09-11 | 2014-03-19 | 엘에스전선 주식회사 | System and method for monitoring-diagnose wind power transformer |
| CN105223453A (en) * | 2015-11-03 | 2016-01-06 | 广东电网有限责任公司佛山供电局 | Based on substation transformer trouble-shooter and the method for multiple attribute synthetical evaluation |
| CN206274265U (en) * | 2016-11-28 | 2017-06-23 | 山东科技大学 | A kind of transformer online monitoring device |
| CN108021945A (en) * | 2017-12-07 | 2018-05-11 | 广东电网有限责任公司电力科学研究院 | A kind of transformer state evaluation model method for building up and device |
| CN108414877A (en) * | 2018-03-21 | 2018-08-17 | 广东电网有限责任公司电力科学研究院 | One kind to transformer fault for carrying out pre-warning system and method |
-
2020
- 2020-06-10 CN CN202010521994.7A patent/CN111562458B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1484034A (en) * | 2002-09-18 | 2004-03-24 | 新疆特变电工股份有限公司 | On-line intelligent monitoring system for transformer and intelligent analysis diagnosis method thereof |
| FR2860593A1 (en) * | 2003-10-03 | 2005-04-08 | Alstom T & D Sa | Winding fault diagnosing method for three-phase power transformer, involves determining relative variation of resonant frequency greater than specific frequency by comparing two voltage gains |
| KR20140033944A (en) * | 2012-09-11 | 2014-03-19 | 엘에스전선 주식회사 | System and method for monitoring-diagnose wind power transformer |
| CN105223453A (en) * | 2015-11-03 | 2016-01-06 | 广东电网有限责任公司佛山供电局 | Based on substation transformer trouble-shooter and the method for multiple attribute synthetical evaluation |
| CN206274265U (en) * | 2016-11-28 | 2017-06-23 | 山东科技大学 | A kind of transformer online monitoring device |
| CN108021945A (en) * | 2017-12-07 | 2018-05-11 | 广东电网有限责任公司电力科学研究院 | A kind of transformer state evaluation model method for building up and device |
| CN108414877A (en) * | 2018-03-21 | 2018-08-17 | 广东电网有限责任公司电力科学研究院 | One kind to transformer fault for carrying out pre-warning system and method |
Non-Patent Citations (1)
| Title |
|---|
| 可拓关联函数与属性约简相结合的变压器故障诊断方法;胡泽江 等;《2011年云南电力技术论坛论文集》;20111115;第860-866页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111562458A (en) | 2020-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111562458B (en) | Power transformer fault diagnosis method and power transformer fault diagnosis device | |
| CN107907778B (en) | Transformer comprehensive fault diagnosis method based on multiple characteristic parameters | |
| JP2000512766A (en) | Statistical pattern analysis method for partial discharge measurement in high voltage insulation | |
| US10488384B2 (en) | System and method for assessing power transformers | |
| KR20200014129A (en) | Diagnosis method of electric transformer using Deep Learning | |
| CN110940374A (en) | Transformer health grade evaluation system and method based on big data fusion | |
| JP5456582B2 (en) | Transformer soundness diagnosis method, soundness diagnosis device, and soundness diagnosis program | |
| CN116295661A (en) | Transformer fault early warning system based on Internet of things | |
| CN111678992A (en) | Nondestructive testing method for identifying damage type of concrete structure | |
| CN117041029A (en) | Network equipment fault processing method and device, electronic equipment and storage medium | |
| CN114255784A (en) | Substation equipment fault diagnosis method based on voiceprint recognition and related device | |
| JP2020086495A (en) | Maintenance apparatus and maintenance method of electrical device | |
| KR20180097282A (en) | Semiconductor GP Prediction Method and System | |
| CN117706943A (en) | Self-adaptive control method and system for converter transformer valve side sleeve end screen voltage divider | |
| CN117074852A (en) | Power distribution network electric energy monitoring and early warning management method and system | |
| CN116007742A (en) | Transformer abnormal sound detection method, device, equipment and storage medium | |
| Palhares et al. | Bayesian network and compact genetic algorithm approach for classifying partial discharges in power transformers | |
| Viereck et al. | The use of digital data for a new innovative quality level of asset mangement for transformer | |
| JP3858887B2 (en) | Failure judgment system and judgment method | |
| CN110927488B (en) | Transformer running state monitoring method based on membership function | |
| CN118100447B (en) | Intelligent monitoring method and system for high-voltage distribution line based on Internet of things | |
| CN117875945B (en) | Power grid equipment maintenance prediction method, system and medium | |
| Zhu et al. | Assessment method of distribution network health level based on multivariate information | |
| CN114322917B (en) | Transformer winding detection method and device, electronic equipment and storage medium | |
| CN111487562B (en) | Early warning and decision-making assisting method for power transformer state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200821 Assignee: CHANGDE TIANMA ELECTRIC CO.,LTD. Assignor: HUNAN University OF ARTS AND SCIENCE Contract record no.: X2023980036347 Denomination of invention: A Power Transformer Fault Diagnosis Method and Power Transformer Fault Diagnosis Device Granted publication date: 20220527 License type: Common License Record date: 20230608 |
|
| EE01 | Entry into force of recordation of patent licensing contract |