CN114111886A - Power transformer defect online diagnosis method using operation information - Google Patents
Power transformer defect online diagnosis method using operation information Download PDFInfo
- Publication number
- CN114111886A CN114111886A CN202111273998.9A CN202111273998A CN114111886A CN 114111886 A CN114111886 A CN 114111886A CN 202111273998 A CN202111273998 A CN 202111273998A CN 114111886 A CN114111886 A CN 114111886A
- Authority
- CN
- China
- Prior art keywords
- transformer
- temperature
- voltage
- phase
- heat accumulation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003745 diagnosis Methods 0.000 title claims abstract description 37
- 238000009825 accumulation Methods 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000004804 winding Methods 0.000 claims description 24
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 210000002569 neuron Anatomy 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000001816 cooling Methods 0.000 claims description 4
- 230000005284 excitation Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
Abstract
The invention discloses a method for diagnosing defects of a power transformer on line by utilizing running information, which comprises the steps of collecting voltage and current data of each phase of a high-voltage side and a low-voltage side of the transformer in a period of time, carrying out parameter identification on equivalent circuit parameters of the transformer by adopting a parameter identification algorithm, automatically modeling, automatically learning and automatically training by collecting the voltage and current data and temperature data of each phase of the high-voltage side and the low-voltage side of the transformer, generating a proper heat accumulation model, inputting an effective value and a starting time temperature of the voltage and current of each phase of the high-voltage side and the low-voltage side of the transformer in a period of time into the heat accumulation model, and outputting an ending time temperature by the heat accumulation model; according to the deviation between the measured temperature of the transformer and the temperature output by the heat accumulation model and the equivalent circuit parameter identification result of the transformer, the types and the degrees of the defects and the faults of the transformer can be effectively judged, the online diagnosis of the defects of the transformer of the comprehensive electric and non-electric operation parameters is realized, and the accuracy of the defect and fault diagnosis is improved.
Description
Technical Field
The invention relates to the field of electrical equipment, in particular to an online diagnosis method for defects of a power transformer by using operation information.
Background
The power transformer is important equipment of a transformer substation, and the realization of defect diagnosis and health degradation evaluation of the transformer is the key for preventing accidental shutdown and realizing predictive maintenance. The method solves the following problems mainly existing in defect diagnosis of the transformer for a long time:
1) when the transformer is locally overheated due to partial discharge or other local insulation defects, the method of measuring temperature and setting a fixed alarm temperature threshold value cannot give an alarm in time;
2) when the load factor of the transformer is relatively low, the method of measuring temperature and setting a fixed alarm temperature threshold value cannot find abnormal problems of the cooling system in time and cannot find defects such as short circuit between iron chips in time;
3) defects such as poor contact of the tap changer or turn-to-turn short circuit and the like can not be alarmed in time by a method of measuring temperature and setting a fixed alarm temperature threshold value;
4) the partial discharge on-line monitoring and other means can only solve the partial discharge monitoring problem singly, and the diagnosis accuracy is related to a plurality of factors such as the installation position of the sensor;
5) the online analysis of oil chromatography can only explain the deterioration of oil singly.
The existing transformer fault diagnosis method usually judges the defect or fault degree of the transformer by a single means, cannot comprehensively reflect the defect or fault of the transformer, and is easy to cause misjudgment. Therefore, it is necessary to provide a method for online diagnosing defects of a power transformer by using operation information, so as to realize online diagnosis of defects of the transformer by integrating electrical and non-electrical operation parameters.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides the power transformer defect online diagnosis method by using the operation information, realizes the transformer defect online diagnosis of the comprehensive electric and non-electric operation parameters, and improves the accuracy of defect and fault diagnosis.
In order to achieve the purpose of the invention, the technical scheme adopted by the invention is as follows: an on-line diagnosis method for defects of a power transformer by using operation information,
step one, collecting operation parameters of a transformer: collecting electric parameters of each phase of the transformer through a current-voltage instrument and collecting temperature data of the transformer through a temperature sensor;
step two, identifying the equivalent circuit parameters of the transformer by adopting a parameter identification algorithm: according to the collected transformer electrical parameters, data preprocessing is carried out, and a plurality of groups of transformer electrical parameter data in a period of time are selected; according to the selected multiple groups of transformer electrical parameter data, the equivalent circuit parameters of each phase of the transformer ABC in the time interval are approximated by a least square method respectively;
step three, temperature rise modeling: establishing a temperature rise dependence relation of the electrical parameters of the transformer in the time interval, and performing approximation and training by adopting a non-parameter system identification method according to historical data of the electrical parameters and the temperature of each phase of the transformer to generate a heat accumulation model; inputting the effective value and the starting time temperature of each phase electric parameter of the transformer in the time interval into a heat accumulation model, and outputting the ending time temperature by the heat accumulation model;
step four, defect diagnosis: and acquiring the actual temperature of the transformer, judging whether the temperature rise of the transformer is abnormal or not according to the deviation of the actual temperature and the temperature output by the heat accumulation model, and judging the type and degree of the defects and faults of the transformer by combining the identification result of the equivalent circuit parameters of the transformer.
Preferably, the electrical parameters of the transformer comprise voltage and current data of ABC phases on the high-low voltage side of the transformer; the transformer equivalent circuit is a transformer T-shaped equivalent circuit, and the transformer equivalent circuit parameters comprise a primary winding resistor R1Reactance X of primary winding1And secondary winding resistance R'2And secondary winding reactance X'2And an excitation resistor RmAnd a field reactance Xm。
Preferably, in the second step, the specific process of identifying the transformer equivalent circuit parameter by using the parameter identification algorithm is as follows:
(1) according to the collected voltage and current data of each phase at the high-low voltage side of the transformer, data preprocessing is carried out, and N groups of voltage and current data of each phase at the high-low voltage side of the transformer in a period of time are selected, namely:
high-pressure side:
low-pressure side:
(2) selecting a reference direction of a voltage circuit of the transformer; the transformation ratio K of the transformer is determined through a transformer nameplate, and the voltage and current of the high-voltage side and the low-voltage side of the phase A at the moment K are expressed as follows:
(3) r of each phase of the transformer ABC in the period1,X1,R′2,X′2,Rm,XmThe approximation is carried out by a least square method in the form of a normal equation:
order:
then:
preferably, the heat accumulation model is built by adopting a three-layer BP neural network, and is represented as:
the objective function for training the heat accumulation model is:
the heat accumulation model includes three layers: the first layer is an input layer, and the number of nodes is M; the second layer is a hidden layer, the number of the neurons is I, the third layer is an output layer, and the number of the neurons is 1;
wherein y is the measured temperature of the transformer at a certain momentmFor heat accumulation of the mouldTemperature at the same time of the profile output; omegamiThe connection weight from the input layer node to the hidden layer node; omegaiThe connection weight from the hidden layer node to the output layer node; f () is the activation function of the hidden layer neurons, g () is the activation function of the output layer neurons; x is the model input, the input time interval [ t ]0,tQ]The voltage, the current and the initial winding temperature of each phase of the high-low voltage side of the inner transformer are specifically expressed as follows:
Preferably, the temperature rise of the transformer is determined according to the following:
if the (actual temperature-model temperature)/model temperature is less than the tracking threshold value, the temperature rise of the transformer is normal;
if the (actual temperature-model temperature)/model temperature is more than the tracking threshold, the temperature rise of the transformer is abnormal;
the tracking threshold is set according to the actual operation of the transformer, and the range of the tracking threshold is + 1% to + 10%.
Preferably, the judgment rule of the defect diagnosis is as follows:
(1) if the reactance value X of the transformer is identified1,X′2,XmIf all the changes occur, the coil deformation and the turn-to-turn short circuit are represented;
(2) if the winding resistance R of the transformer is identified1,R′2If the resistance value changes and the temperature rise is abnormal, the poor contact of the tap changer is indicated;
(3) if the temperature rise of the transformer is only diagnosed to be abnormal, the partial discharge of the coil, the blockage of an oil path or the cooling fault are shown.
Preferably, the heat accumulation model comprises an input layer, a hidden layer and an output layer, wherein the input layer inputs A, B, C effective current and voltage values of the high-voltage side and the low-voltage side in the time interval and the temperature of the transformer at the starting moment; the hidden layer processes the data input by the input layer and outputs the transformer temperature at the finishing moment through the output layer.
Preferably, the temperature data of the transformer includes, but is not limited to, winding temperature, core temperature, or oil level temperature.
Advantageous effects
Compared with the prior art, the invention has the following beneficial effects:
the method comprises the steps of collecting voltage and current data of each phase of the high-voltage side and the low-voltage side of the transformer within a period of time, performing parameter identification on equivalent circuit parameters of the transformer by adopting a parameter identification algorithm, automatically modeling, automatically learning and automatically training by collecting the voltage and current data and the temperature data of the high-voltage side and the low-voltage side of the transformer, generating a proper heat accumulation model, inputting voltage and current effective values and starting time temperatures of each phase of the high-voltage side and the low-voltage side of the transformer within a period of time into the heat accumulation model, and outputting ending time temperatures by the heat accumulation model; according to the deviation between the measured temperature of the transformer and the temperature output by the heat accumulation model and the equivalent circuit parameter identification result of the transformer, the types and the degrees of the defects and the faults of the transformer can be effectively judged, the online diagnosis of the defects of the transformer of the comprehensive electric and non-electric operation parameters is realized, and the accuracy of the defect and fault diagnosis is improved.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a circuit diagram of a transformer of the present invention;
FIG. 3 is a block diagram of an algorithmic implementation of the thermal accumulation model of the present invention;
FIG. 4 is an architecture diagram of the present invention implemented on an embedded device;
fig. 5 is an architecture diagram of the present invention implemented on an upper computer.
Detailed Description
The following further describes embodiments of the present invention with reference to the accompanying drawings:
as shown in fig. 1, the present invention provides an online diagnosis method for defects of a power transformer using operation information, the method comprising the steps of:
step one, collecting operation parameters of a transformer: collecting electric parameters of each phase of the transformer through a current-voltage instrument, and detecting temperature data of the transformer through a temperature sensor; the electrical parameters of the transformer comprise voltage and current data of each phase at the high-voltage side and the low-voltage side of the transformer; the temperature data of the transformer includes, but is not limited to, winding temperature, core temperature, and oil level temperature.
Step two, identifying the equivalent circuit parameters of the transformer by adopting a parameter identification algorithm:
(1) according to the collected voltage and current data of each phase at the high-low voltage side of the transformer (collection of the phasor of each phase at high voltage)
Acquisition of low-voltage phasors
) Carrying out data preprocessing, and selecting voltage and current data of each phase at the high-voltage side and the low-voltage side of N groups of transformers within a period of time, namely:
high-pressure side:
low-pressure side:
(2) selecting a reference direction of a voltage circuit of the transformer; as shown in fig. 2, for the equivalent circuit of the transformer, one of the voltage and current reference directions is taken, the transformation ratio K of the transformer is determined by a nameplate of the transformer, and taking phase a as an example, the voltage and current of the phase a at the high and low voltage sides at time K are represented as:
(3) r of each phase of the transformer ABC in the period1,X1,R′2,X′2,Rm,XmThe approximation is performed by a least squares method in the form of normal equations, respectively:
order:
then:
the transformer equivalent circuit is a transformer T-shaped equivalent circuit, and the transformer equivalent circuit parameters comprise a primary winding resistance R1Reactance X of primary winding1And secondary winding resistance R'2And secondary winding reactance X'2And an excitation resistor RmAnd a field reactance Xm。
Step three, temperature rise modeling: as shown in FIG. 3, a time interval t is established0,t]The dependency relationship of the voltage, the current and the temperature rise of the high-low voltage side of the transformer is trained by using historical data of the voltage, the current and the temperature rise of the high-low voltage side of the transformer, approximation and training are carried out by adopting a non-parameter system identification method (the training process is a parameter correction process), and a heat accumulation model is generated; input time interval [ t ] to thermal accumulation model0,t]The effective value of the voltage and the current of the high-low voltage side of each phase and the temperature at the time t0 are obtained, and the temperature at the time t is output by the heat accumulation model; in particular, the thermal accumulation model includes an input layer, a hidden layer, and an output layer, the input layer inputs over a time period [ t ]0,t]Voltage-current effective value and t of ABC phase on high-low voltage side of transformer0The temperature of the transformer at the moment; and the hidden layer processes the data input by the input layer and outputs the temperature of the transformer at the t moment through the output layer.
The model selectable by the heat accumulation model comprises various neural networks and a nonlinear fitting method based on parameters (such as a nonlinear least square method); various types of neural networks include: feed-forward neural networks (BP networks, RBF networks and the like), various feedback type neural networks (such as Elman networks, Boltzmann networks and the like), random neural networks, competitive neural networks, fuzzy neural networks, wavelet neural networks, deep neural networks, Support Vector Machines (SVM);
in this embodiment, taking a three-layer BP neural network as an example, as shown in fig. 3, a heat accumulation model is established, and the heat accumulation model is represented as:
the objective function for training the heat accumulation model is:
the heat accumulation model includes three layers: the first layer is an input layer, and the number of nodes is M; the second layer is a hidden layer, and the number of the neurons is I; the third layer is the output layer, and the number of neurons is 1.
Wherein y is the measured temperature of the transformer at a certain momentmThe temperature at the same time outputted by the heat accumulation model;
ωmithe connection weight from the input layer node to the hidden layer node; omegaiThe connection weight from the hidden layer node to the output layer node;
f () is the activation function of the hidden layer neuron, g () is the activation function of the output layer neuron, and sigmoid or relu and other functions can be actually taken according to needs.
x is the model input, the input time interval [ t ]0,tQ]The voltage, the current and the initial winding temperature of each phase of the high-low voltage side of the inner transformer are specifically expressed as follows:
In order to achieve better prediction effect in practical application, the types of the neural networks can be different, and the number of layers of the neural networks is correspondingly increased.
Step four, defect diagnosis: the method comprises the steps of obtaining the actual temperature of the transformer, judging whether the temperature rise of the transformer is abnormal or not according to the deviation of the actual temperature and the temperature output by the heat accumulation model, and judging the type and the degree of defects and faults of the transformer by combining the identification result of equivalent circuit parameters of the transformer.
Specifically, the judgment of the abnormal temperature rise of the transformer is based on the following steps:
if the (actual temperature-model temperature)/model temperature is less than the tracking threshold value, the temperature rise of the transformer is normal;
if the (actual temperature-model temperature)/model temperature is more than the tracking threshold, the temperature rise of the transformer is abnormal;
the tracking threshold is set according to the actual operation of the transformer, and the range of the tracking threshold is + 1% to + 10%.
Specifically, the judgment rule of the defect diagnosis is as follows:
1) if the reactance value X of the transformer is identified1,X′2,XmIf all the changes occur, the coil deformation and the turn-to-turn short circuit are represented;
2) if the winding resistance R of the transformer is identified1,R′2If the resistance value changes and the temperature rise is abnormal, the poor contact of the tap changer is indicated;
3) if the temperature rise of the transformer is diagnosed to be abnormal, the partial discharge of the coil, the blockage of an oil path and the cooling fault are shown.
The invention has the beneficial effects that:
the method comprises the steps of collecting voltage and current data of each phase of the high-voltage side and the low-voltage side of the transformer within a period of time, performing parameter identification on equivalent circuit parameters of the transformer by adopting a parameter identification algorithm, automatically modeling, automatically learning and automatically training by collecting the voltage and current data and the temperature data of the high-voltage side and the low-voltage side of the transformer, generating a proper heat accumulation model, inputting voltage and current effective values and starting time temperatures of each phase of the high-voltage side and the low-voltage side of the transformer within a period of time into the heat accumulation model, and outputting ending time temperatures by the heat accumulation model; according to the deviation between the measured temperature of the transformer and the temperature output by the heat accumulation model and the equivalent circuit parameter identification result of the transformer, the types and the degrees of the defects and the faults of the transformer can be effectively judged, the online diagnosis of the defects of the transformer of the comprehensive electric and non-electric operation parameters is realized, and the accuracy of the defect and fault diagnosis is improved.
As shown in fig. 4, the present invention can also be implemented on an embedded device, and the functional architecture includes an application layer, an intermediate layer, and a device layer; the device layer, the middle layer and the application layer are sequentially connected from bottom to top; the equipment layer comprises the following equipment: the intelligent instrument synchronously collects voltage and current of the high-voltage side and the low-voltage side of the transformer, the instrument collects the temperature of the transformer, and collects electricity and non-electricity data in real time;
the intermediate layer comprises the following devices: the embedded mainboard or industrial personal computer is provided with network port communication, supports various internet communication protocols and completes temporary storage of data, defect diagnosis operation and judgment;
the application layer comprises the following devices: various workstation computers, intelligent mobile equipment and the like display results to users.
Specifically, the device layer synchronously acquires voltage and current data of the high-voltage side and the low-voltage side of the transformer and transmits the voltage and current data to the intermediate layer, the intermediate layer performs parameter identification on the received voltage and current data of the high-voltage side and the low-voltage side of the transformer by adopting an equivalent circuit parameter identification algorithm, the device layer acquires temperature data of the transformer and transmits the temperature data to the intermediate layer, the intermediate layer automatically models, automatically learns and trains according to the received voltage and current data of the high-voltage side and the low-voltage side of the transformer and the temperature data to generate a proper heat accumulation model, namely a temperature rise model, according to the deviation between the actually measured temperature of the transformer and the temperature output by the heat accumulation model, and in combination with the parameter identification of the transformer, the types and the degrees of the defects and the faults of the transformer can be effectively judged, the online diagnosis of the defects of the transformer of the comprehensive electric and non-electric operation parameters is realized, and the online diagnosis of the defects of the transformer of the comprehensive electric and non-electric operation parameters is realized by a computer or an intelligent mobile device of a workstation of the application layer, the diagnostic structure is presented to the user.
As shown in fig. 5, the present invention can also be implemented on an upper computer, and the specific architecture is consistent with the MVC architecture, including: the method comprises the steps that a Model layer, a Controller layer and a View layer are stored, various data and Model parameters are stored in a database (Model), methods needing operation such as an equivalent circuit parameter identification algorithm, a Model training method and a Model application method are placed in a Controller (Controller), and results of transformer defect or fault diagnosis are displayed on a browser web interface (View). The method has the advantages that a proper heat accumulation model is generated by collecting temperature data of the transformer, automatically modeling, automatically learning and automatically training, the types and the degrees of the defects and the faults of the transformer can be effectively judged according to the deviation of the measured temperature of the transformer and the temperature output by the heat accumulation model and by combining parameter identification of the transformer, the online diagnosis of the defects of the transformer of comprehensive electric and non-electric operation parameters is realized, and the accuracy of the defect and fault diagnosis is improved.
The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present application. Variations and modifications to the above-described embodiments may occur to those skilled in the art, which fall within the scope and spirit of the above description. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and variations of the present invention should fall within the scope of the claims of the present invention. Furthermore, although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.
Claims (7)
1. A power transformer defect online diagnosis method using operation information is characterized in that:
step one, collecting operation parameters of a transformer: collecting electric parameters of each phase of the transformer through a current-voltage instrument and collecting temperature data of the transformer through a temperature sensor;
step two, identifying the equivalent circuit parameters of the transformer by adopting a parameter identification algorithm: according to the collected transformer electrical parameters, data preprocessing is carried out, and a plurality of groups of transformer electrical parameter data in a period of time are selected; according to the selected multiple groups of transformer electrical parameter data, the equivalent circuit parameters of each phase of the transformer ABC in the time interval are approximated by a least square method respectively;
step three, temperature rise modeling: establishing a temperature rise dependence relation of the electrical parameters of the transformer in the time interval, and performing approximation and training by adopting a non-parameter system identification method according to historical data of the electrical parameters and the temperature of each phase of the transformer to generate a heat accumulation model; inputting the effective value and the starting time temperature of each phase electric parameter of the transformer in the time interval into a heat accumulation model, and outputting the ending time temperature by the heat accumulation model;
step four, defect diagnosis: and acquiring the actual temperature of the transformer, judging whether the temperature rise of the transformer is abnormal or not according to the deviation of the actual temperature and the temperature output by the heat accumulation model, and judging the type and degree of the defects and faults of the transformer by combining the identification result of the equivalent circuit parameters of the transformer.
2. The method for on-line diagnosis of defects of power transformer using operation information as claimed in claim 1, wherein: the electrical parameters of the transformer comprise voltage and current data of ABC phases on the high-voltage side and the low-voltage side of the transformer; the transformer equivalent circuit is a transformer T-shaped equivalent circuit, and the transformer equivalent circuit parameters comprise a primary winding resistor R1Reactance X of primary winding1And secondary winding resistance R'2And secondary winding reactance X'2And an excitation resistor RmAnd a field reactance Xm。
3. The method for on-line diagnosis of defects of power transformer using operation information as claimed in claim 2, wherein: in the second step, the specific process of identifying the equivalent circuit parameters of the transformer by adopting a parameter identification algorithm is as follows:
(1) according to the collected voltage and current data of each phase at the high-low voltage side of the transformer, data preprocessing is carried out, and N groups of voltage and current data of each phase at the high-low voltage side of the transformer in a period of time are selected, namely:
high-pressure side:
low-pressure side:
(2) selecting a reference direction of a voltage circuit of the transformer; the transformation ratio K of the transformer is determined through a transformer nameplate, and the voltage and current of the high-voltage side and the low-voltage side of the phase A at the moment K are expressed as follows:
(3) r of each phase of the transformer ABC in the period1,X1,R2′,X2′,Rm,XmThe approximation is carried out by a least square method in the form of a normal equation:
order:
then:
4. a method for on-line diagnosing defects of a power transformer using operation information as claimed in claim 3, wherein: the heat accumulation model is established by adopting a three-layer BP neural network and is expressed as follows:
the objective function for training the heat accumulation model is:
the heat accumulation model includes three layers: the first layer is an input layer, and the number of nodes is M; the second layer is a hidden layer, the number of the neurons is I, the third layer is an output layer, and the number of the neurons is 1;
wherein y is the measured temperature of the transformer at a certain momentmThe temperature at the same time outputted by the heat accumulation model; omegamiThe connection weight from the input layer node to the hidden layer node; omegaiThe connection weight from the hidden layer node to the output layer node; f () is the activation function of the hidden layer neurons, g () is the activation function of the output layer neurons; x is the model input, the input time interval [ t ]0,tQ]The voltage, the current and the initial winding temperature of the ABC phase on the high-low voltage side of the inner transformer are specifically expressed as follows:
5. The method for on-line diagnosis of defects of power transformer using operation information as claimed in claim 4, wherein: the judgment basis of the abnormal temperature rise of the transformer is as follows:
if the (actual temperature-model temperature)/model temperature is less than the tracking threshold value, the temperature rise of the transformer is normal;
if the (actual temperature-model temperature)/model temperature is more than the tracking threshold, the temperature rise of the transformer is abnormal;
the tracking threshold is set according to the actual operation of the transformer, and the range of the tracking threshold is + 1% to + 10%.
6. The method for on-line diagnosis of defects of power transformer using operation information as claimed in claim 5, wherein: the judgment rule of the defect diagnosis is as follows:
(1) if the reactance value X of the transformer is identified1,X2′,XmAll of them are changed, they indicate the deformation and turn-to-turn of the coilShort-circuiting;
(2) if the winding resistance R of the transformer is identified1,R2When the resistance value changes and the temperature rises abnormally, the tap changer is in poor contact;
(3) if the temperature rise of the transformer is only diagnosed to be abnormal, the partial discharge of the coil, the blockage of an oil path or the cooling fault are shown.
7. The method for on-line diagnosis of defects of power transformer using operation information as claimed in claim 1, wherein: the temperature data of the transformer includes, but is not limited to, winding temperature, core temperature, or oil level temperature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111273998.9A CN114111886A (en) | 2021-10-29 | 2021-10-29 | Power transformer defect online diagnosis method using operation information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111273998.9A CN114111886A (en) | 2021-10-29 | 2021-10-29 | Power transformer defect online diagnosis method using operation information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114111886A true CN114111886A (en) | 2022-03-01 |
Family
ID=80379607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111273998.9A Pending CN114111886A (en) | 2021-10-29 | 2021-10-29 | Power transformer defect online diagnosis method using operation information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114111886A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102721897A (en) * | 2012-06-13 | 2012-10-10 | 江苏省电力公司南京供电公司 | Diagnosis method and system of turn-to-turn short circuit fault of power transformer winding |
| CN202735463U (en) * | 2012-06-13 | 2013-02-13 | 江苏省电力公司南京供电公司 | Power transformer winding interturn short circuit fault diagnosis system |
| CN103412217A (en) * | 2013-08-02 | 2013-11-27 | 中科天工电气控股有限公司 | Box-type substation intelligent online failure diagnosis system |
| WO2015176564A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method of transformer internal fault diagnosis based on monitoring on virtual parameter changes |
| CN106443316A (en) * | 2016-10-12 | 2017-02-22 | 国网辽宁省电力有限公司电力科学研究院 | Power transformer winding deformation state multi-information detection method and device |
| US20170115335A1 (en) * | 2015-05-04 | 2017-04-27 | General Electric Company | Systems and methods for monitoring and diagnosing transformer health |
| US20200241066A1 (en) * | 2019-01-30 | 2020-07-30 | State Grid Zhejiang Electric Power Company Limited Electric Power Research Institute | Intelligent on-line diagnosis and positioning method for winding deformation of power transformers |
-
2021
- 2021-10-29 CN CN202111273998.9A patent/CN114111886A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102721897A (en) * | 2012-06-13 | 2012-10-10 | 江苏省电力公司南京供电公司 | Diagnosis method and system of turn-to-turn short circuit fault of power transformer winding |
| CN202735463U (en) * | 2012-06-13 | 2013-02-13 | 江苏省电力公司南京供电公司 | Power transformer winding interturn short circuit fault diagnosis system |
| CN103412217A (en) * | 2013-08-02 | 2013-11-27 | 中科天工电气控股有限公司 | Box-type substation intelligent online failure diagnosis system |
| WO2015176564A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method of transformer internal fault diagnosis based on monitoring on virtual parameter changes |
| US20170115335A1 (en) * | 2015-05-04 | 2017-04-27 | General Electric Company | Systems and methods for monitoring and diagnosing transformer health |
| CN106443316A (en) * | 2016-10-12 | 2017-02-22 | 国网辽宁省电力有限公司电力科学研究院 | Power transformer winding deformation state multi-information detection method and device |
| US20200241066A1 (en) * | 2019-01-30 | 2020-07-30 | State Grid Zhejiang Electric Power Company Limited Electric Power Research Institute | Intelligent on-line diagnosis and positioning method for winding deformation of power transformers |
Non-Patent Citations (1)
| Title |
|---|
| 李海 等: "配电变压器 T 型等效电路参数在线识别方法", 《变压器》, vol. 56, no. 1, 31 January 2019 (2019-01-31), pages 41 - 45 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Žarković et al. | Analysis of artificial intelligence expert systems for power transformer condition monitoring and diagnostics | |
| KR102092185B1 (en) | Platform for analyzing electric motor health and analysis method using the same | |
| Nurmanova et al. | A new transformer FRA measurement technique to reach smart interpretation for inter-disk faults | |
| Cherif et al. | Early detection and localization of stator inter-turn faults based on discrete wavelet energy ratio and neural networks in induction motor | |
| Moradzadeh et al. | Locating inter-turn faults in transformer windings using isometric feature mapping of frequency response traces | |
| CN107843718A (en) | A kind of method that transformer insulation oil ageing state is assessed | |
| CN104914327A (en) | Transformer fault maintenance prediction method based on real-time monitoring information | |
| CN107831415A (en) | The Interval Valued Fuzzy diversity method that a kind of transformer insulating paper ageing state is assessed | |
| CN102663412A (en) | Power equipment current-carrying fault trend prediction method based on least squares support vector machine | |
| Zhang et al. | An architecture based on digital twins for smart power distribution system | |
| CN107831300A (en) | A kind of transformer insulation oil based on three-dimensional trapezoidal Probabilistic Fuzzy collection deteriorates appraisal procedure | |
| CN115238831B (en) | Fault prediction method, device, computer equipment and storage medium | |
| CN107843816A (en) | A kind of transformer insulated defect state appraisal procedure for considering load factor and influenceing | |
| CN107808044A (en) | A kind of transformer insulating paper deterioration appraisal procedure for considering running temperature and influenceing | |
| CN110083951A (en) | A kind of solid insulation life-span prediction method based on transformer correlation operation data | |
| JPH11212637A (en) | Method and device for preventive maintenance | |
| Sun et al. | A temperature-based fault pre-warning method for the dry-type transformer in the offshore oil platform | |
| CN104102214A (en) | Transformer and transformer peripheral circuit fault control method | |
| Jaiswal et al. | Intelligent condition monitoring system for distribution transformer and health status diagnosis | |
| MansourLakouraj et al. | Event classification in active distribution grids using physics-informed graph neural network and PMU measurements | |
| CN114111886A (en) | Power transformer defect online diagnosis method using operation information | |
| Tran et al. | Building Machine learning datasets for oil-immersed service transformer health assessment using Fuzzy logic method | |
| Tippannavar et al. | Smart Transformer-An Analysis of Recent Technologies for Monitoring Transformer | |
| CN114111892B (en) | Distribution transformer monitoring and early warning device and method for uncertainty information fusion | |
| Jaiswal et al. | ANN based methodology for determination of distribution transformer health status |
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 |