CN117310353B - Method and system for testing through-flow pressurization faults of primary and secondary circuits of transformer substation - Google Patents
Method and system for testing through-flow pressurization faults of primary and secondary circuits of transformer substation Download PDFInfo
- Publication number
- CN117310353B CN117310353B CN202311619237.3A CN202311619237A CN117310353B CN 117310353 B CN117310353 B CN 117310353B CN 202311619237 A CN202311619237 A CN 202311619237A CN 117310353 B CN117310353 B CN 117310353B
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- signal
- neural network
- extracting
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000002159 abnormal effect Effects 0.000 claims description 63
- 238000013528 artificial neural network Methods 0.000 claims description 43
- 238000013075 data extraction Methods 0.000 claims description 25
- 238000012790 confirmation Methods 0.000 claims description 24
- 238000003062 neural network model Methods 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 9
- 238000010998 test method Methods 0.000 claims description 8
- 230000001174 ascending effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 12
- 238000004088 simulation Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 239000012212 insulator Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241000272814 Anser sp. Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- 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
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Locating Faults (AREA)
Abstract
The invention discloses a method and a system for testing through-flow pressurization faults of a first and a second circuits of a transformer substation, which belong to the field of measuring electric variables.
Description
Technical Field
The invention belongs to the technical field of measuring electric variables, and particularly relates to a method and a system for testing through-flow pressurization faults of a primary circuit and a secondary circuit of a transformer substation.
Background
The primary circuit through-flow pressurization means that a certain voltage is applied to equipment in a primary circuit on the high-voltage side of a transformer substation, such as a circuit breaker and a disconnecting switch, and then a current flows in the primary circuit. The method can be used for detecting the static and dynamic characteristics of high-voltage side equipment and determining the normal working state of the equipment, and the secondary circuit through-flow pressurization refers to that after a certain voltage is applied to the equipment in the low-voltage side secondary circuit of the transformer substation, such as a relay, a protection device and the like, current flows in the secondary circuit. The method can be used for detecting the working state and performance of low-voltage side equipment to verify the correctness and reliability of a protection device, through-flow pressurization test is a test method commonly used in the operation of a transformer substation, by applying certain voltage, the current response and the working characteristics of the equipment in a detection loop and the action performance of the protection device ensure the normal operation of the transformer substation equipment and a protection system, and in the operation process of the transformer substation equipment, a large amount of noise and vibration of the equipment can cause interference on monitoring data, so that the data monitoring is inaccurate, in the test process, the data caused by a fault position possibly cause abnormality of the data of the next or the next monitoring position due to butterfly effect, the historical data and the test data cannot be connected to accurately position the fault position in the test process, and further the fault position cannot be accurately identified and early-warned, so that the fault position cannot be accurately identified in the prior art;
for example, a fault simulation test system of a transformer substation is disclosed in China patent with the application publication number of CN115629257A, and comprises a man-machine interaction module, an SCD analysis module, a main wiring drawing module, a test parameter setting module, a fault calculation simulation module, a test control module, a test result analysis display module, a time synchronization module, a GOOSE transceiver module and an SV sending module. According to the invention, the common primary main wiring diagram template library is established, the modeling speed is accelerated, the modeling difficulty is reduced, and the testing efficiency of on-site testers is improved by a convenient modeling method, so that the fault simulation testing process of the transformer substation can be simplified, the whole-station fault simulation test of the intelligent transformer substation is realized, and the safe operation reliability of the transformer substation is improved;
meanwhile, for example, in the chinese patent with the grant number of CN112800637B, an intelligent substation simulation test device and method are disclosed, and the application obtains source data received by a tested element and message data sent by the tested element after being processed by the tested element in the simulation operation process, and then performs data extraction on the source data and the message data according to the element type of the tested element and corresponding test item information, so as to obtain first test data and second test data, and determine a test result of data processing correctness of the tested element according to a comparison result of the first test data and the second test data, thereby solving the technical problem of low test efficiency of the intelligent substation simulation element.
The problems proposed in the background art exist in the above patents: because in the operation process of transformer station equipment, a large amount of noise and vibration of equipment operation can cause interference to monitoring data, data monitoring is inaccurate, in the test process, data caused by a fault position can possibly cause abnormality of the data of the next or next monitoring position due to butterfly effect, in the test process, historical data and test data cannot be connected to accurately position the fault position, and further the fault position cannot be accurately identified and early-warned, and in order to solve the problems, the application designs a transformer substation primary and secondary loop through-flow pressurization fault test method and system.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a transformer substation first and second loop through-flow pressurization fault testing method and system.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a transformer substation first and second loop through-flow pressurization fault test method comprises the following specific steps:
s1, a fault abnormal signal is obtained by a fault identification module arranged on a working node of a transformer substation;
s2, extracting fault signal data of the fault abnormal signal position, and extracting interference noise data of the fault abnormal signal position;
s3, importing fault signal data and interference noise data into a constructed real signal neural network model to extract real fault signal data;
s4, judging the real fault signal data, judging whether the real fault signal data are false fault signals, if yes, ignoring the fault abnormal signals, and if not, carrying out S5;
s5, importing the real fault signal into a preliminary fault position identification strategy to identify a preliminary fault position;
s6, extracting historical operation data of the element at the initial fault position, and importing the historical operation data into a fault position confirmation strategy to confirm the fault position.
Specifically, the step S1 includes the following specific steps:
s11, extracting node detection data at a working node of a transformer substation, and simultaneously extracting safety range data of the node detection data;
s12, comparing the node detection data with the corresponding safety range data, if the node detection data is in the safety range data corresponding to the position of the node detection data, not acquiring the fault abnormal signal, otherwise, acquiring the fault abnormal signal and transmitting the fault abnormal signal.
Specifically, the specific steps of S2 are as follows:
s21, extracting a fault signal data change curve in the corresponding time of the fault abnormal signal position, and simultaneously extracting equipment operation interference noise waveform data of the fault abnormal signal position in the corresponding time;
s22, constructing a fault signal data change curve and equipment operation interference noise waveform data which are input in an interference state, outputting a neural network model of the fault signal data change curve in a non-interference state, acquiring fault signal data waveforms measured by measuring equipment in the non-noise state, acquiring fault signal data waveforms measured by measuring equipment of the same type under the interference of the equipment operation interference noise waveforms and a plurality of equipment operation interference noise waveforms at the same time, and taking the peak value of waveform data of each waveform at different time points as a 70% coefficient training set and a 30% coefficient test set; construction of godInputting a 70% coefficient training set into the neural network model for training through the network prediction model to obtain an initial neural network prediction model; testing the neural network model by using 30% of coefficient test sets, and outputting an optimal initial neural network prediction model meeting the preset waveform test accuracy as a neural network prediction model, wherein the expression of the neural network prediction model is as follows:wherein->For the output of the (i+1) -th layer of the neural network, k is the number of the (i) -th layer of the neural network,/-th layer of the neural network>For the duty factor of the p-th data in the ith layer of the neural network,/for the data in the ith layer of the neural network>Input for the ith layer in the neural network, < >>Is the bias factor.
Specifically, the specific steps of S3 are as follows:
s31, extracting fault signal data of a fault abnormal signal time period, and extracting interference noise intensity data of the fault abnormal signal time period;
s32, the extracted fault signal data and interference noise intensity data are imported into a constructed neural network prediction model, and real fault signal data are output.
Specifically, the specific steps of S4 include the following:
and comparing the acquired real fault signal data with the corresponding safety range data, if the node detection data position is in the safety range data corresponding to the safety range data, ignoring the fault abnormal signal, otherwise, performing S5.
Specifically, the specific steps of the preliminary fault location identification strategy in S5 are as follows:
s51, liftingTaking real-time fault data of a working node, wherein the fault data comprise three-phase voltagesThree-phase currentZero sequence current->The content C of SF6 gas, and meanwhile, the fault data and the fault reason data of the historical working node are extracted;
s52, importing the fault data of the historical working node and the real-time fault data of the working node into a preliminary fault position searching formula to calculate a preliminary fault value, wherein the preliminary fault value formula is as follows:wherein->Is the ratio of three-phase voltage, +.>Is the three-phase current duty ratio coefficient +.>Is the zero sequence current duty ratio coefficient->Is the ratio of SF6 gas content, < ->For the j-th group, three-phase voltage acquisition values in the fault data of the working node, +.>For the j-th group, three-phase current acquisition values in the fault data of the working node, +.>For the j-th group historyZero sequence current acquisition value in fault data of working node,/->Collecting values for the SF6 gas content in the j-th group of historical fault data of the working node,；
and S53, arranging the calculated primary fault values corresponding to the fault data of the historical working node in a descending order or an ascending order, finding out the fault reason positions corresponding to the minimum three primary fault values as primary fault positions, and extracting the fault element operation data corresponding to the found fault reason positions.
Specifically, the specific steps of the fault location confirmation strategy of S6 are as follows:
s61, extracting an operation working data set of the element at the preliminary fault position, and extracting a corresponding normal operation working data range of the element;
s62, substituting the operation working data set and the normal operation working data range into a fault confirmation formula to calculate a fault confirmation value, wherein the fault confirmation formula is as follows:wherein->For the fault confirmation value, n is the number of data types in the running working data set, +.>For running the ith type data in the working data set, < > I->Nearest +.>Value of->Is->Corresponding normal operating data range, +.>Is->Is a duty cycle of (2);
s63, calculating a fault confirmation value of the primary fault position element, and finding out the maximum value, namely setting the maximum value as the fault position.
Specifically, the invention also provides a transformer substation first and second loop through-flow pressurization fault test system, which is realized based on the transformer substation first and second loop through-flow pressurization fault test method, and specifically comprises the following steps: the system comprises a control module, a fault abnormal signal acquisition module, a data extraction module, a neural network construction module, a judging module, a preliminary fault position searching module and a fault position confirming module, wherein the control module is used for controlling the operation of the fault abnormal signal acquisition module, the data extraction module, the neural network construction module, the judging module, the preliminary fault position searching module and the fault position confirming module, the fault abnormal signal acquisition module is used for acquiring fault abnormal signals through a fault identification module arranged on a working node of a transformer substation, the data extraction module is used for extracting fault signal data of a fault abnormal signal position, meanwhile extracting interference noise data of the fault abnormal signal position, the neural network construction module is used for constructing a neural network model which is input into a fault signal data change curve and equipment operation interference noise waveform data in an interference-free state, the judging module is used for guiding the fault signal data and the interference noise data into the constructed real signal neural network model to extract the real fault signal data, judging whether the real fault signal data are false fault signals or not, the preliminary fault position searching module is used for guiding the real fault signals into a fault position identification strategy for carrying out preliminary fault position identification, and the judging module is used for guiding the fault position into the preliminary fault position confirming strategy for confirming.
Specifically, the data extraction module comprises a fault signal data extraction unit and an interference noise data extraction unit, wherein the fault signal data extraction unit is used for extracting a fault signal data change curve in the corresponding time of the fault abnormal signal position, and the interference noise data extraction unit is used for extracting equipment operation interference noise waveform data of the fault abnormal signal position in the corresponding time.
Specifically, the invention also discloses an electronic device, which comprises: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes the first and second loop through-flow pressurization fault test method of the transformer substation by calling the computer program stored in the memory.
The invention also discloses a computer readable storage medium, which stores instructions that, when run on a computer, cause the computer to execute the method for testing the through-flow pressurization faults of the primary and secondary circuits of the transformer substation.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the fault abnormal signal is obtained through the fault identification module arranged on the working node of the transformer substation, the fault signal data of the fault abnormal signal position is extracted, meanwhile, the interference noise data of the fault abnormal signal position is extracted, the fault signal data and the interference noise data are imported into the constructed real signal neural network model to extract the real fault signal data, the real fault signal data are judged, whether the fault signal is a false fault signal or not is judged, the real fault signal is imported into the preliminary fault position identification strategy to identify the preliminary fault position, the historical operation data of the element at the preliminary fault position is extracted, and the historical operation data of the element at the preliminary fault position is imported into the fault position identification strategy to confirm the fault position, so that the judgment accuracy of fault components is effectively improved, and the fault identification effect is effectively enhanced.
Drawings
FIG. 1 is a schematic flow chart of a method for testing through-flow pressurization faults of a primary circuit and a secondary circuit of a transformer substation;
FIG. 2 is a schematic diagram of a specific flow of step S1 of a method for testing through-flow pressurization faults of a primary circuit and a secondary circuit of a transformer substation;
FIG. 3 is a schematic diagram of a specific flow of step S5 of the method for testing the through-flow pressurization fault of the primary and secondary circuits of the transformer substation;
FIG. 4 is a schematic diagram of the overall architecture of the primary and secondary loop through-flow pressurization fault test system of the transformer substation;
fig. 5 is a schematic diagram of a data extraction module of a transformer substation primary and secondary loop through-flow pressurization fault test system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Example 1
Referring to fig. 1-3, an embodiment of the present invention is provided: a transformer substation first and second loop through-flow pressurization fault test method comprises the following specific steps:
s1, a fault abnormal signal is obtained by a fault identification module arranged on a working node of a transformer substation;
in this embodiment, S1 includes the following specific steps:
s11, extracting node detection data at a working node of a transformer substation, and simultaneously extracting safety range data of the node detection data;
s12, comparing the node detection data with the corresponding safety range data, if the node detection data is in the safety range data corresponding to the position of the node detection data, not acquiring a fault abnormal signal, otherwise acquiring the fault abnormal signal and transmitting the fault abnormal signal;
s2, extracting fault signal data of the fault abnormal signal position, and extracting interference noise data of the fault abnormal signal position;
in order to ensure the accuracy of the fault abnormal signals, a neural network model is arranged to output a fault signal data change curve in a non-interference state;
in this embodiment, the specific steps of S2 are as follows:
s21, extracting a fault signal data change curve in the corresponding time of the fault abnormal signal position, and simultaneously extracting equipment operation interference noise waveform data of the fault abnormal signal position in the corresponding time;
s22, constructing a fault signal data change curve and equipment operation interference noise waveform data which are input in an interference state, outputting a neural network model of the fault signal data change curve in a non-interference state, acquiring fault signal data waveforms measured by measuring equipment in the non-noise state, acquiring fault signal data waveforms measured by measuring equipment of the same type under the interference of the equipment operation interference noise waveforms and a plurality of equipment operation interference noise waveforms at the same time, and taking the peak value of waveform data of each waveform at different time points as a 70% coefficient training set and a 30% coefficient test set; constructing a neural network prediction model, and inputting a 70% coefficient training set into the neural network model for training to obtain an initial neural network prediction model; testing the neural network model by using 30% of coefficient test sets, and outputting an optimal initial neural network prediction model meeting the preset waveform test accuracy as a neural network prediction model, wherein the expression of the neural network prediction model is as follows:wherein->For the output of the i+1th layer of the neural network, k is the number of the i th layer of the neural network,for the duty factor of the p-th data in the ith layer of the neural network,/for the data in the ith layer of the neural network>Input for the ith layer in the neural network, < >>Is a bias coefficient;
the specific code of the neural network model is expressed as: the neural network model is used for constructing a fault signal data change curve under the interference state and equipment operation interference noise waveform data and outputting the fault signal data change curve under the non-interference state.
The following example discloses a specific set of code for a neural network model that can implement the above functions, the code being programmed using python.
```python
import numpy as np
import tensorflow as tf
# build input data
Fault signal data profile and device operation disturbance noise waveform data in input_data=np.range.rand (1000, 10) # disturbance state
# build output data
Fault signal data profile in the output_data=np.range.rand (1000, 10) # no disturbance state
# division training set and test set
train_size = int(0.7 * len(input_data))
train_input = input_data[:train_size]
train_output = output_data[:train_size]
test_input = input_data[train_size:]
test_output = output_data[train_size:]
# definition neural network model
model = tf.keras.Sequential([
tf.keras.layers.Dense(64, activation='relu', input_shape=(10,)),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(10)
])
# compiling model
model.compile(optimizer='adam',
loss=tf.keras.losses.MeanSquaredError(),
metrics=['mse'])
Training model #
model.fit(train_input, train_output, epochs=10, batch_size=32)
# evaluation model
test_loss, test_mse = model.evaluate(test_input, test_output)
print('Test Loss:', test_loss)
print('Test MSE:', test_mse)
```
Note that the structure and parameters of the model may need to be adjusted according to the actual situation, and this example uses a fully connected neural network with two hidden layers, and uses the mean square error as the loss function, and according to the characteristics and requirements of the data, the network structure, the loss function and other super parameters may need to be adjusted in the actual operation to obtain better model performance;
s3, importing fault signal data and interference noise data into a constructed real signal neural network model to extract real fault signal data;
in this embodiment, the specific steps of S3 are as follows:
s31, extracting fault signal data of a fault abnormal signal time period, and extracting interference noise intensity data of the fault abnormal signal time period;
s32, importing the extracted fault signal data and interference noise intensity data into a constructed neural network prediction model, and outputting real fault signal data;
the real fault signal data are obtained, and the influence of interference noise in the transformer substation on the test is reduced;
s4, judging the real fault signal data, judging whether the real fault signal data are false fault signals, if yes, ignoring the fault abnormal signals, and if not, carrying out S5; the method comprises the following steps: comparing the acquired real fault signal data with the corresponding safety range data, if the node detection data position is in the safety range data corresponding to the safety range data, ignoring the fault abnormal signal, otherwise, performing S5;
s5, importing the real fault signal into a preliminary fault position identification strategy to identify a preliminary fault position;
in this embodiment, the specific steps of the preliminary fault location identification policy in S5 are:
s51, extracting real-time fault data of the working node, wherein the fault data comprise three-phase voltagesThree-phase currentZero sequence current->The content C of SF6 gas, and meanwhile, the fault data and the fault reason data of the historical working node are extracted;
s52, importing the fault data of the historical working node and the real-time fault data of the working node into a preliminary fault location finding formula to calculate a preliminary fault value, wherein the preliminary fault value formula is as follows:wherein->Is the ratio of three-phase voltage, +.>Is the three-phase current duty ratio coefficient +.>Is the zero sequence current duty ratio coefficient->Is the ratio of SF6 gas content, < ->For the j-th group calendarThree-phase voltage acquisition value in fault data of the working node>For the j-th group, three-phase current acquisition values in the fault data of the working node, +.>For the j-th group, zero sequence current collection value in fault data of the working node, < + >>Collecting values for the SF6 gas content in the j-th group of historical fault data of the working node,；
s53, arranging the calculated primary fault values corresponding to the fault data of the historical working node in a descending order or an ascending order, finding out the fault reason positions corresponding to the minimum three primary fault values as primary fault positions, and extracting the fault element operation data corresponding to the found fault reason positions;
s6, extracting historical operation data of the element at the initial fault position, and importing the historical operation data into a fault position confirmation strategy to confirm the fault position;
in this embodiment, the specific steps of the fault location confirmation policy of S6 are:
s61, extracting an operation working data set of the element at the preliminary fault position, and extracting a corresponding normal operation working data range of the element;
it should be noted here that the operation data of the elements are flexibly set according to the specific elements thereof;
1. transformer data: the method comprises rated capacity, operating current, operating temperature, cooling mode, insulation resistance, oil level and humidity of the transformer;
2. breaker data: the method comprises rated current, voltage class, action time, contact resistance and working state of the circuit breaker;
3. lightning arrester data: the lightning arrester comprises the current capacity, the working voltage class and the overvoltage tolerance capacity of the lightning arrester;
4. insulator data: the working voltage class, the insulation resistance and the cleanliness of the insulator are included;
5. current Transformer (CT) data: including the rated current ratio, accuracy, and phase angle error of CT;
6. voltage Transformer (VT) data: rated voltage ratio, accuracy, phase angle error including VT;
7. battery pack data: the method comprises the steps of voltage, capacity, charge and discharge states and internal resistance of the battery pack;
s62, substituting the operation working data set and the normal operation working data range into a fault confirmation formula to calculate a fault confirmation value, wherein the fault confirmation formula is as follows:wherein->For the fault confirmation value, n is the number of data types in the running working data set, +.>For running the ith type data in the working data set, < > I->Nearest +.>Value of->Is->Corresponding normal operating data range, +.>Is->Is a duty cycle of (2);
s63, calculating a fault confirmation value of the primary fault position element, and finding out the maximum value, namely setting the maximum value as a fault position;
the fault recognition module is used for acquiring fault abnormal signals, extracting fault signal data of fault abnormal signal positions, extracting interference noise data of the fault abnormal signal positions, importing the fault signal data and the interference noise data into a constructed real signal neural network model to extract real fault signal data, judging whether the real fault signal data is a false fault signal or not, importing the real fault signal into a preliminary fault position recognition strategy to recognize the preliminary fault positions, extracting historical operation data of elements at the preliminary fault positions, importing the historical operation data of elements at the preliminary fault positions into a fault position recognition strategy to confirm the fault positions, effectively improving the accuracy of fault component judgment and effectively enhancing the fault recognition effect.
Example 2
As shown in fig. 4 to 5, a transformer substation first and second circuit through-flow pressurization fault test system is implemented based on the transformer substation first and second circuit through-flow pressurization fault test method, and specifically includes: the system comprises a control module, a fault abnormal signal acquisition module, a data extraction module, a neural network construction module, a judgment module, a preliminary fault location finding module and a fault location confirmation module, wherein the control module is used for controlling the operation of the fault abnormal signal acquisition module, the data extraction module, the neural network construction module, the judgment module, the preliminary fault location finding module and the fault location confirmation module;
in this embodiment, the data extraction module includes a fault signal data extraction unit and an interference noise data extraction unit, where the fault signal data extraction unit is configured to extract a fault signal data change curve in a corresponding time of the fault abnormal signal position, and the interference noise data extraction unit is configured to extract equipment operation interference noise waveform data of the fault abnormal signal position in the corresponding time.
Example 3
The present embodiment provides an electronic device including: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes the method for testing the through-flow pressurization faults of the primary and secondary circuits of the transformer substation by calling the computer program stored in the memory.
The electronic device can generate larger difference due to different configurations or performances, and can comprise one or more processors (Central Processing Units, CPU) and one or more memories, wherein at least one computer program is stored in the memories, and the computer program is loaded and executed by the processors to realize the transformer substation one-secondary loop through-flow pressurization fault testing method provided by the method embodiment. The electronic device can also include other components for implementing the functions of the device, for example, the electronic device can also have wired or wireless network interfaces, input-output interfaces, and the like, for inputting and outputting data. The present embodiment is not described herein.
Example 4
The present embodiment proposes a computer-readable storage medium having stored thereon an erasable computer program;
when the computer program runs on the computer equipment, the computer equipment is caused to execute the method for testing the through-flow and pressurization faults of the primary and secondary circuits of the transformer substation.
For example, the computer readable storage medium can be Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), compact disk Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), magnetic tape, floppy disk, optical data storage device, etc.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It should be understood that determining B from a does not mean determining B from a alone, but can also determine B from a and/or other information.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by way of wired or/and wireless networks from one website site, computer, server, or data center to another. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain one or more collections of 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. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely one, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (6)
1. A transformer substation first and second loop through-flow pressurization fault testing method is characterized by comprising the following specific steps:
s1, a fault abnormal signal is obtained by a fault identification module arranged on a working node of a transformer substation;
s2, extracting fault signal data of the fault abnormal signal position, and extracting interference noise data of the fault abnormal signal position;
s3, importing fault signal data and interference noise data into a constructed real signal neural network model to extract real fault signal data;
s4, judging the real fault signal data, judging whether the real fault signal data are false fault signals, if yes, ignoring the fault abnormal signals, and if not, carrying out S5;
s5, importing the real fault signal into a preliminary fault position identification strategy to identify a preliminary fault position;
s6, extracting historical operation data of the element at the initial fault position, and importing the historical operation data into a fault position confirmation strategy to confirm the fault position; the S1 comprises the following specific steps:
s11, extracting node detection data at a working node of a transformer substation, and simultaneously extracting safety range data of the node detection data;
s12, comparing the node detection data with corresponding safety range data, if the position of the node detection data is corresponding to the safety range data, not acquiring a fault abnormal signal, otherwise acquiring the fault abnormal signal and transmitting the fault abnormal signal; the specific steps of the S2 are as follows:
s21, extracting a fault signal data change curve in the corresponding time of the fault abnormal signal position, and simultaneously extracting equipment operation interference noise waveform data of the fault abnormal signal position in the corresponding time;
s22, constructing a fault signal data change curve and equipment operation interference noise waveform data which are input in an interference state, outputting a neural network model of the fault signal data change curve in a non-interference state, acquiring fault signal data waveforms measured by measuring equipment in the non-noise state, acquiring fault signal data waveforms measured by measuring equipment of the same type under the interference of the equipment operation interference noise waveforms and a plurality of equipment operation interference noise waveforms at the same time, and taking the peak value of waveform data of each waveform at different time points as a 70% coefficient training set and a 30% coefficient test set; constructing a neural network prediction model, and inputting a 70% coefficient training set into the neural network model for training to obtain an initial neural network prediction model; testing the neural network model by using 30% coefficient test set, and outputting an optimal initial neural network prediction model meeting the preset waveform test accuracy as a neural network prediction model, wherein the neural network is used for testing the neural network modelThe expression of the predictive model is:wherein->For the output of the i+1th layer of the neural network, k is the number of the i th layer of the neural network,for the duty factor of the p-th data in the ith layer of the neural network,/for the data in the ith layer of the neural network>Input for the ith layer in the neural network, < >>Is a bias coefficient; the specific steps of the S3 are as follows:
s31, extracting fault signal data of a fault abnormal signal time period, and extracting interference noise intensity data of the fault abnormal signal time period;
s32, importing the extracted fault signal data and interference noise intensity data into a constructed neural network prediction model, and outputting real fault signal data; the specific steps of S4 include the following:
comparing the acquired real fault signal data with the corresponding safety range data, if the position of the node detection data is corresponding to the safety range data, ignoring the fault abnormal signal, otherwise, performing S5; the specific steps of the preliminary fault location identification strategy in the step S5 are as follows:
s51, extracting real-time fault data of the working node, wherein the fault data comprise three-phase voltagesThree-phase current->Zero sequence current->The content C of SF6 gas, and meanwhile, the fault data and the fault reason data of the historical working node are extracted;
s52, importing the fault data of the historical working node and the real-time fault data of the working node into a preliminary fault position searching formula to calculate a preliminary fault value, wherein the preliminary fault value formula is as follows:wherein->Is the ratio of three-phase voltage, +.>Is the three-phase current duty ratio coefficient +.>Is the zero sequence current duty ratio coefficient->Is the ratio of the SF6 gas content,for the j-th group, three-phase voltage acquisition values in the fault data of the working node, +.>For the j-th group, three-phase current acquisition values in the fault data of the working node, +.>For the j-th group, zero sequence current collection value in fault data of the working node, < + >>SF6 gas in fault data for j-th group of historical working nodesIs used for acquiring the content acquisition value of the (a),；
s53, arranging the calculated primary fault values corresponding to the fault data of the historical working node in a descending order or an ascending order, finding out the fault reason positions corresponding to the minimum three primary fault values as primary fault positions, and extracting the fault element operation data corresponding to the found fault reason positions; the fault location confirmation policy in S6 includes:
s61, extracting an operation working data set of the element at the preliminary fault position, and extracting a normal operation working data range corresponding to the element;
s62, substituting the operation working data set and the normal operation working data range into a fault confirmation formula to calculate a fault confirmation value, wherein the fault confirmation formula is as follows:wherein->For the fault confirmation value, n is the number of data types in the running working data set, +.>For running the ith type data in the working data set, < > I->Nearest +.>Value of->Is->Corresponding normal operating data range, +.>Is->Is a duty cycle of (2);
s63, calculating a fault confirmation value of the primary fault position element, and finding out the maximum value, namely setting the maximum value as the fault position.
2. The transformer substation first and second loop through-flow pressurization fault test system is realized based on the transformer substation first and second loop through-flow pressurization fault test method according to claim 1, and is characterized by comprising the following steps: the system comprises a control module, a fault abnormal signal acquisition module, a data extraction module, a neural network construction module, a judgment module, a preliminary fault location finding module and a fault location confirming module, wherein the control module is used for controlling the operation of the fault abnormal signal acquisition module, the data extraction module, the neural network construction module, the judgment module, the preliminary fault location finding module and the fault location confirming module, the fault abnormal signal acquisition module is used for acquiring fault abnormal signals through a fault identification module arranged on a working node of a transformer substation, the data extraction module is used for extracting fault signal data of the fault abnormal signal location and extracting interference noise data of the fault abnormal signal location, and the neural network construction module is used for constructing a neural network model which is input into a fault signal data change curve and equipment operation interference noise waveform data under an interference state and outputting the fault signal data change curve under an interference-free state.
3. The transformer substation one-secondary loop through-flow pressurization fault test system according to claim 2, wherein the judging module is used for extracting real fault signal data by importing the fault signal data and interference noise data into a constructed real signal neural network model, judging whether the real fault signal data is a false fault signal or not, the preliminary fault position searching module is used for importing the real fault signal into a preliminary fault position identification strategy to identify a preliminary fault position, and the fault position confirming module is used for extracting historical operation data of elements at the preliminary fault position and importing the historical operation data into the fault position confirmation strategy to confirm the fault position.
4. The transformer substation one-and-two-circuit through-flow pressurization fault test system according to claim 3, wherein the data extraction module comprises a fault signal data extraction unit and an interference noise data extraction unit, the fault signal data extraction unit is used for extracting a fault signal data change curve in a corresponding time of a fault abnormal signal position, and the interference noise data extraction unit is used for extracting equipment operation interference noise waveform data of the fault abnormal signal position in the corresponding time.
5. An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes the transformer substation primary and secondary loop through-flow pressurization fault testing method according to claim 1 by calling the computer program stored in the memory.
6. A computer-readable storage medium, characterized by: instructions are stored which, when run on a computer, cause the computer to perform a method for testing a transformer substation primary and secondary loop through-flow pressurization fault as claimed in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311619237.3A CN117310353B (en) | 2023-11-30 | 2023-11-30 | Method and system for testing through-flow pressurization faults of primary and secondary circuits of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311619237.3A CN117310353B (en) | 2023-11-30 | 2023-11-30 | Method and system for testing through-flow pressurization faults of primary and secondary circuits of transformer substation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117310353A CN117310353A (en) | 2023-12-29 |
| CN117310353B true CN117310353B (en) | 2024-02-09 |
Family
ID=89281613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311619237.3A Active CN117310353B (en) | 2023-11-30 | 2023-11-30 | Method and system for testing through-flow pressurization faults of primary and secondary circuits of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117310353B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117851954B (en) * | 2024-03-06 | 2024-05-24 | 大连海泰轴承制造有限公司 | Bearing machining equipment operation quality detection system and method based on data analysis |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106940407A (en) * | 2017-03-15 | 2017-07-11 | 湘潭大学 | A kind of positioning of distribution network system electrical energy power quality disturbance and recognition methods |
| CN112380782A (en) * | 2020-12-07 | 2021-02-19 | 重庆忽米网络科技有限公司 | Rotating equipment fault prediction method based on mixed indexes and neural network |
| CN113759199A (en) * | 2021-09-26 | 2021-12-07 | 淮安苏达电气有限公司 | Testing device and testing method for primary and secondary fusion equipment acting on power distribution network |
| CN114510164A (en) * | 2022-02-17 | 2022-05-17 | 上海科世达-华阳汽车电器有限公司 | Electromagnetic interference noise suppression method, device, equipment and storage medium |
| CN116973819A (en) * | 2023-09-22 | 2023-10-31 | 上海优立检测技术股份有限公司 | Three-dimensional testing method, system and storage medium for microwave electromagnetic parameters |
| WO2023216553A1 (en) * | 2022-05-11 | 2023-11-16 | 广东电网有限责任公司东莞供电局 | Multi-fault diagnosis method for power distribution network, and system |
| CN117093941A (en) * | 2023-08-22 | 2023-11-21 | 广东电网有限责任公司 | Vibration wave filtering method, system, equipment and medium for eliminating environmental noise |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11740275B2 (en) * | 2021-09-16 | 2023-08-29 | Hunan University Of Science And Technology | Method for intelligent fault detection and location of power distribution network |
-
2023
- 2023-11-30 CN CN202311619237.3A patent/CN117310353B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106940407A (en) * | 2017-03-15 | 2017-07-11 | 湘潭大学 | A kind of positioning of distribution network system electrical energy power quality disturbance and recognition methods |
| CN112380782A (en) * | 2020-12-07 | 2021-02-19 | 重庆忽米网络科技有限公司 | Rotating equipment fault prediction method based on mixed indexes and neural network |
| CN113759199A (en) * | 2021-09-26 | 2021-12-07 | 淮安苏达电气有限公司 | Testing device and testing method for primary and secondary fusion equipment acting on power distribution network |
| CN114510164A (en) * | 2022-02-17 | 2022-05-17 | 上海科世达-华阳汽车电器有限公司 | Electromagnetic interference noise suppression method, device, equipment and storage medium |
| WO2023216553A1 (en) * | 2022-05-11 | 2023-11-16 | 广东电网有限责任公司东莞供电局 | Multi-fault diagnosis method for power distribution network, and system |
| CN117093941A (en) * | 2023-08-22 | 2023-11-21 | 广东电网有限责任公司 | Vibration wave filtering method, system, equipment and medium for eliminating environmental noise |
| CN116973819A (en) * | 2023-09-22 | 2023-10-31 | 上海优立检测技术股份有限公司 | Three-dimensional testing method, system and storage medium for microwave electromagnetic parameters |
Non-Patent Citations (1)
| Title |
|---|
| 基于数字孪生技术的变电站设备故障定位预警;周展利 等;《电脑编程技巧与维护》;173-176 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117310353A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shukla et al. | DC offset estimation‐based fault detection in transmission line during power swing using ensemble of decision tree | |
| CN117310353B (en) | Method and system for testing through-flow pressurization faults of primary and secondary circuits of transformer substation | |
| CN102221651B (en) | Fault on-line diagnosis and early warning method of flameproof dry-type transformer for mine | |
| CN108459295B (en) | CVT on-line monitoring system and method based on distributed data acquisition processing | |
| CN108508320A (en) | Arc grounding fault identification method based on harmonic energy and wave distortion feature | |
| Lira et al. | MOSA monitoring technique based on analysis of total leakage current | |
| Nosratian Ahour et al. | Determination and localisation of turn‐to‐turn fault in transformer winding using frequency response analysis | |
| CN105467971A (en) | Electric power secondary equipment monitoring system and method | |
| CN106773993A (en) | Field data acquiring terminal and system | |
| CN110118900A (en) | A kind of remained capacity and power frequency series arc faults detection method | |
| CN107515339A (en) | A kind of Risk Identification Method and system based on DC current distribution situation | |
| CN112305319A (en) | Method and system for online monitoring of converter transformer valve side sleeve parameters | |
| CN112909939A (en) | Power system transient stability assessment method based on load flow characteristics before and after fault | |
| CN117849558B (en) | Method and device for on-line monitoring breakdown fault of main capacitor of capacitive voltage transformer | |
| CN117748507A (en) | Distribution network harmonic access uncertainty assessment method based on Gaussian regression model | |
| CN111525495A (en) | Relay protection fixed value online checking method and system and computer storage medium | |
| CN109522615B (en) | Method and device for evaluating zero-sequence inrush current tolerance of relay protection of power system | |
| Zhang et al. | Incipient fault identification of distribution networks based on feature matching of power disturbance data | |
| Abasi et al. | Broken conductor fault location in power transmission lines using GMDH function and single-terminal data independent of line parameters | |
| CN103364669B (en) | GIS equipment operational condition online test method and system | |
| CN117526561A (en) | Digital twinning-based transformer substation equipment abnormality monitoring and early warning method and system | |
| Bin et al. | Research on mechanical fault diagnosis method of power transformer winding | |
| CN105116323B (en) | A kind of electrical fault detection method based on RBF | |
| Li et al. | Real time evaluation algorithm for measurement performance of substation voltage transformer based on artificial neural network | |
| Babayomi et al. | Intelligent fault diagnosis in a power distribution network |
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 |