Transformer operation and maintenance method based on digital twinning technology

Abstract

The invention discloses a transformer operation and maintenance method based on a digital twinning technology, and the method comprises the following steps: constructing a digital twinning model of a transformer, and constructing fault sample vectors for a plurality of parts; periodically acquiring actual values of various operation state indexes of the transformer, and comparing the actual values with normal values; establishing an abnormal state vector according to a result of the comparison step; matching the abnormal state vector with all fault sample vectors one by one; if the matched fault sample vector exists, sending out a part fault prompt, and if the matched fault sample vector does not exist, sending out an index abnormity prompt. Different parts have different influences on various operation state indexes of the transformer when having problems, the various operation state indexes of the transformer are compared with the fault sample vectors of the parts to judge which parts cannot work normally, and then the maintenance personnel are reminded, so that the maintenance efficiency of the transformer is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power transformers, and in particular to a transformer operation and maintenance method based on digital twin technology. Background Art

[0002] Transformers are common equipment in power systems and are one of the important hubs of power grid transmission. Since transformers are prone to failure during use, they need to be operated, maintained and inspected regularly. With the gradual maturity of various types of sensor technologies, it has become very convenient to monitor various indicators and parameters during transformer operation in real time. Therefore, real-time monitoring and status analysis of transformers have been studied more and more deeply. At present, the main means of monitoring the operating status of transformers are the characteristic gas method and the three-ratio method, both of which analyze the components of the gas generated by the transformer oil in the transformer to determine whether the transformer is faulty or abnormal. However, the analysis of these two methods can only determine the type of transformer fault, such as arc discharge, partial discharge, spark discharge, high temperature overheating, etc., and cannot accurately determine which specific component has failed. When maintenance personnel find that the transformer is in an abnormal state, they need to check the components one by one, which brings inconvenience to maintenance work. Summary of the invention

[0003] In order to solve the technical problem that the existing transformer monitoring technology cannot accurately determine the working status of each component, the present application provides a transformer operation and maintenance method based on digital twin technology, including the following steps: S1. Build a digital twin model of the transformer and construct fault sample vectors for multiple components. S2. Periodically obtain the actual value of each operating status indicator of the transformer, and compare the actual value with the normal value corresponding to the operating status indicator; S3, establishing an abnormal state vector according to the result of the above comparison step; S4, matching the abnormal state vector with all the fault sample vectors one by one; S5. If there is a matching fault sample vector, a component fault prompt is issued; if there is no matching fault sample vector, an indicator abnormality prompt is issued.

[0004] When problems occur in different parts, they will have different impacts on the various operating status indicators of the transformer. Therefore, by analyzing the differences between the various operating status indicators and the normal values, it is possible to accurately determine which parts are working abnormally, and then remind maintenance personnel to inspect and maintain the transformer in a timely manner, effectively improving the maintenance efficiency of the transformer.

[0005] Specifically, the fault sample vector is obtained by the following method: S11. For a component, multiple pieces of historical fault data are obtained, and a corresponding historical fault vector is constructed according to each piece of historical fault data, wherein each component of the historical fault vector corresponds to a state value of an operating state indicator of the transformer when the transformer fails; S12, calculating the weight of each of the operating status indicators according to the number of abnormalities of each of the operating status indicators in all the historical fault vectors; S13, calculating a weighted average vector of a plurality of the historical fault vectors; S14. Correct the weighted average vector to obtain the fault sample vector.

[0006] Considering that the severity of damage to a component will cause different changes in the transformer's operating status indicators, when the same component fails each time, not always the same operating status indicators will be abnormal. By calculating the proportion of abnormal times of each operating status indicator in the failure, the weight of each operating status indicator is changed to make the judgment result more accurate.

[0007] Furthermore, step S14 further includes: S141, obtaining new historical fault vectors, and fitting all the historical fault vectors using a neural network to obtain historical fault fitting vectors; S142, constructing a loss function according to the historical fault fitting vector and the weighted average vector; S143. Correct the weighted average vector according to the loss function to obtain the fault sample vector.

[0008] New faults will occur during the use of the transformer. Machine learning is used to correct the original fault sample vector based on the new historical fault vector to further improve the accuracy of the judgment result.

[0009] Furthermore, the normal value is obtained by the following method: S21, acquiring the operating load data and external environment data of the transformer in real time; S22, bringing the operating load data and the external environment data into the digital twin model to obtain predicted values ​​of various operating status indicators of the transformer; S23. Correct the predicted value to obtain the normal value.

[0010] The various operating status indicators of the transformer are determined by the operating load data of the transformer and the external environment data. Therefore, based on the geometric model of the transformer and combined with mechanics, electromagnetism, thermodynamics, etc., the digital twin model of the transformer can calculate the predicted values ​​of various operating status indicators based on the operating load data and external environment data. This predicted value can be used as a basis for judging whether the various operating status indicators of the transformer are normal.

[0011] Furthermore, step S23 further includes: S231, calculating the fitting value of the operating status indicator using a neural convolution network according to the historical data of the operating status indicator; S232, constructing a loss function according to the fitted value and the predicted value; S233. Correct the predicted value according to the loss function to obtain the normal value.

[0012] Considering that the digital twin model is an idealized model of the transformer, there will be a certain deviation between the predicted value obtained by it and the actual value. Therefore, through machine learning, the predicted value is corrected according to the historical data of the operating status indicators to make the obtained normal value more accurate.

[0013] Furthermore, the abnormal state vector is obtained by the following steps: S31, constructing an empty vector, wherein the dimension of the empty vector is the same as the dimension of the fault sample vector, and the operating status indicator corresponding to each component of the empty vector is the same as that of the fault sample vector; S32, for the actual value of each of the operating status indicators obtained, calculating the absolute difference between the actual value and the normal value, and comparing the absolute difference with a first threshold; S33. If the absolute difference is greater than the first threshold, the component in the empty vector corresponding to the actual value is recorded as abnormal; if the absolute difference is less than the first threshold, the component in the empty vector corresponding to the actual value is recorded as normal.

[0014] Specifically, in step S4, the process of matching the abnormal state vector with all the fault sample vectors one by one includes: S41, calculating the modulus of the abnormal state vector and the modulus of the fault sample vector, and calculating the absolute difference between the moduli of the two vectors; S42, calculating the angle between the abnormal state vector and the fault sample vector; S43: When the absolute difference between the modules of the two vectors is smaller than the second threshold, and the angle between the two vectors is smaller than the third threshold, it is determined that the abnormal state vector matches the fault sample vector.

[0015] Furthermore, the step of issuing an indicator abnormality prompt in step S5 includes: S51. Constructing a visualization model of the transformer according to the digital twin model and the geometric model of the transformer; S52: issuing a component failure prompt through the visualization model.

[0016] The digital twin model can easily visualize the working status of the transformer, so that maintenance personnel can observe the status of the transformer more directly.

[0017] Furthermore, the step of issuing an indicator abnormality prompt in step S5 includes: S53: issuing an indicator abnormality prompt through the visualization model.

[0018] Furthermore, the step of issuing an indicator abnormality prompt in step S5 includes: S54, calculating the percentage of the ratio of the actual value to the normal value; S55. Issue an indicator abnormality prompt through the visualization model and display the percentage.

[0019] In some special cases, when only one operating status indicator is abnormal and the specific faulty component cannot be accurately determined, maintenance personnel need to be reminded for further confirmation.

[0020] Technical effects and advantages of the present invention: 1. By establishing a digital twin model of the transformer, the normal values ​​of various operating status indicators of the transformer are calculated according to the load status of the transformer, and the actual values ​​of various operating status indicators of the transformer are compared with the normal values ​​to determine which operating status indicator of the transformer is abnormal. The faulty parts of the transformer are judged based on the abnormal operating status indicators, thereby reminding maintenance personnel to perform precise maintenance; 2. Through machine learning, the normal values ​​of various operating status indicators are continuously corrected according to the historical operating data of the transformer to improve the accuracy of judging component failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a schematic diagram of the overall operation and maintenance process of the transformer of the present invention; Figure 2 A schematic diagram of a process for obtaining normal values ​​of various operating status indicators of a transformer according to the present invention; Figure 3 A schematic diagram of a process for obtaining a fault sample vector of any component of a transformer according to the present invention; Figure 4 It is a schematic diagram of the process of correcting the fault sample vector of any component of the transformer according to the present invention; Figure 5 The figure is a schematic diagram of the process of correcting the predicted values ​​of various operating status indicators according to the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Embodiment 1 refer to Figure 1 Embodiment 1 of the present invention provides a transformer operation and maintenance method based on digital twin technology, comprising the following steps: S1. Build a digital twin model of the transformer and construct fault sample vectors for multiple components. S2. Periodically obtain the actual value of each operating status indicator of the transformer in real time, and compare the actual value with the normal value corresponding to the operating status indicator; S3, establishing an abnormal state vector according to the result of the above comparison step; S4, matching the abnormal state vector with all fault sample vectors one by one; S5. If there is a matching fault sample vector, a component fault prompt is issued; if there is no matching fault sample vector, an indicator abnormality prompt is issued.

[0024] The digital twin model is a mathematical model of the transformer established based on the geometric model of the transformer, combined with mechanics, electromagnetism, thermodynamics, etc., so that the various operating status indicators of the transformer can be accurately calculated according to the load data of the transformer. The various operating status indicators of the transformer can include transformer oil temperature, transformer oil level, core temperature, winding temperature, core grounding current, etc. The load data of the transformer includes high-voltage side voltage, high-voltage side current, low-voltage side voltage, low-voltage side current, ambient temperature, and ambient humidity, etc.

[0025] When the various components of the transformer are working normally, the various operating status indicators of the transformer under specific load conditions can be accurately predicted through the digital twin model. When a certain component of the transformer has a problem, it will cause several specific operating status indicators to deviate from the normal value. When different components have problems, they will have different effects on the various operating status indicators of the transformer. Therefore, by analyzing the differences between the various operating status indicators and the normal values, it is possible to accurately determine which components are working abnormally.

[0026] In summary, if Figure 2As shown, the normal value can be obtained by: S21, obtaining the operating load data and external environment data of the transformer in real time; S22, bringing the operating load data and external environment data into the digital twin model to obtain the predicted values ​​of various operating status indicators of the transformer; S23. Correct the predicted value to obtain the normal value.

[0027] Specifically, Figure 3 As shown, the fault sample vector is obtained by the following method: S11. For a component, multiple pieces of historical fault data are obtained, and a corresponding historical fault vector is constructed according to each piece of historical fault data, wherein each component of the historical fault vector corresponds to a state value of an operating state indicator when a transformer fails; S12. Calculate the weight of each operating status indicator according to the number of abnormalities of each operating status indicator in all historical fault vectors; S13, calculating a weighted average vector of multiple historical fault vectors; S14. Correct the weighted average vector to obtain a fault sample vector.

[0028] When problems occur in different parts, they will have different impacts on the various operating status indicators of the transformer. Therefore, by analyzing the differences between the various operating status indicators and the normal values, it is possible to accurately determine which parts are working abnormally, and then remind maintenance personnel to inspect and maintain the transformer in a timely manner, effectively improving the maintenance efficiency of the transformer.

[0029] The status value of each operating status indicator can be an actual value, such as current value, voltage value, temperature, etc., or a judgment value of whether it is abnormal, such as 1 when abnormal and 0 when normal. For example, the transformer operating status indicators detected include transformer oil temperature , Transformer oil level , core temperature , Winding temperature , Core grounding current When there is a problem with the transformer seal, it will cause transformer oil leakage, causing the transformer oil level to Deviates from the normal value, but because the transformer oil leakage is small, the transformer oil temperature is not abnormal, so the historical fault vector corresponding to the problem of this seal is: When there are multiple historical fault vectors of seals, the severity of each seal failure is different, resulting in different abnormal operating status indicators. Therefore, a weighted average vector needs to be calculated to improve the accuracy of fault diagnosis.

[0030] Specifically, the abnormal state vector can be obtained by the following steps: S31, constructing a null vector, the dimension of the null vector is the same as the dimension of the fault sample vector, and the operating status indicator corresponding to each component of the null vector is the same as that of the fault sample vector; S32, for the actual value of each operating status indicator obtained, calculating the absolute difference between the actual value and the normal value, and comparing the absolute difference with the first threshold; S33. If the absolute difference is greater than the first threshold, the component in the empty vector corresponding to the actual value is recorded as abnormal; if the absolute difference is less than the first threshold, the component in the empty vector corresponding to the actual value is recorded as normal.

[0031] For example, each component of the abnormal state vector corresponds to the components of the above-mentioned fault sample vector. When it deviates from the normal value, the abnormal state vector is ; The components of the abnormal state vector may also be operating state parameter values, such as current value, voltage value, temperature, etc.

[0032] Furthermore, in step S4, the process of matching the abnormal state vector with all fault sample vectors one by one includes: S41, calculating the modulus of the abnormal state vector and the modulus of the fault sample vector, and calculating the absolute difference between the moduli of the two vectors; S42, calculating the angle between the abnormal state vector and the fault sample vector; S43: When the absolute difference between the modules of the two vectors is smaller than the second threshold value, and the angle between the two vectors is smaller than the third threshold value, it is determined that the abnormal state vector matches the fault sample vector.

[0033] The basis for judging whether two vectors are equal is whether their moduli are the same and whether the angle is zero. Since the fault sample vector is obtained by weighted calculation, the abnormal state vector cannot be completely equal to the fault sample vector. A certain deviation should be allowed between the two during judgment. When the deviation is less than a certain value, it can be considered that the two are matched.

[0034] A major advantage of the digital twin model is visualization. The digital twin model can easily display the status of the transformer in an animated way, allowing maintenance personnel to obtain the operating status of the transformer more intuitively.

[0035] For example, in step S5, a component failure prompt may be issued through the visualization model, or an indicator abnormality prompt may be issued through the visualization model. Furthermore, the percentage of the actual value of the abnormal operating status indicator to the normal value may be calculated to prompt the maintenance personnel the degree of deviation of this indicator from the normal value.

[0036] Embodiment 2 When calculating the fault sample vector, considering that new faults may occur during the use of the transformer, it is necessary to continuously revise the fault sample vector based on new data to improve the accuracy of the judgment result. Machine learning can fit the data very accurately and continuously revise the fitting data based on the difference between the predicted value and the actual value.

[0037] Specifically, Figure 4 As shown, step S14 also includes: S141, obtaining a new historical fault vector, and fitting all the historical fault vectors using a neural network to obtain a historical fault fitting vector; S142, constructing a loss function according to the historical fault fitting vector and the weighted average vector; S143. Correct the weighted average vector according to the loss function to obtain a fault sample vector.

[0038] Similarly, machine learning can be used to correct the predicted values ​​when calculating normal values ​​to improve the accuracy of normal values.

[0039] Specifically, Figure 5 As shown, step S23 also includes: S231, calculating the fitting value of the operating status indicator using a neural convolution network according to the historical data of the operating status indicator; S232, constructing a loss function according to the fitted value and the predicted value; S233. Correct the predicted value according to the loss function to obtain a normal value.

[0040] Considering that the digital twin model is an idealized model of the transformer, there will be a certain deviation between the predicted value obtained by it and the actual value. Therefore, through machine learning, the predicted value is corrected according to the historical data of the operating status indicators to make the obtained normal value more accurate.

[0041] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A transformer operation and maintenance method based on digital twin technology, characterized in that: The following steps are involved: S1. Build a digital twin model of the transformer and construct fault sample vectors for multiple components. S2. Periodically obtain the actual value of each operating status indicator of the transformer, and compare the actual value with the normal value corresponding to the operating status indicator; S3, establishing an abnormal state vector according to the result of the above comparison step; S4, matching the abnormal state vector with all the fault sample vectors one by one; S5. If there is a matching fault sample vector, a component fault prompt is issued; if there is no matching fault sample vector, an indicator abnormality prompt is issued.

2. The transformer operation and maintenance method based on digital twin technology according to claim 1 is characterized in that: The fault sample vector is obtained by the following method: S11. For a component, multiple pieces of historical fault data are obtained, and a corresponding historical fault vector is constructed according to each piece of historical fault data, wherein each component of the historical fault vector corresponds to a state value of an operating state indicator of the transformer when the transformer fails; S12, calculating the weight of each of the operating status indicators according to the number of abnormalities of each of the operating status indicators in all the historical fault vectors; S13, calculating a weighted average vector of a plurality of the historical fault vectors; S14. Correct the weighted average vector to obtain the fault sample vector.

3. The transformer operation and maintenance method based on digital twin technology according to claim 2 is characterized in that: Step S14 also includes: S141, obtaining new historical fault vectors, and fitting all the historical fault vectors using a neural network to obtain historical fault fitting vectors; S142, constructing a loss function according to the historical fault fitting vector and the weighted average vector; S143. Correct the weighted average vector according to the loss function to obtain the fault sample vector.

4. The transformer operation and maintenance method based on digital twin technology according to claim 1 is characterized in that: The normal value is obtained by the following method: S21, acquiring the operating load data and external environment data of the transformer in real time; S22, bringing the operating load data and the external environment data into the digital twin model to obtain predicted values ​​of various operating status indicators of the transformer; S23. Correct the predicted value to obtain the normal value.

5. The transformer operation and maintenance method based on digital twin technology according to claim 4 is characterized in that: Step S23 also includes: S231, calculating the fitting value of the operating status indicator using a neural convolution network according to the historical data of the operating status indicator; S232, constructing a loss function according to the fitted value and the predicted value; S233. Correct the predicted value according to the loss function to obtain the normal value.

6. The transformer operation and maintenance method based on digital twin technology according to claim 1 is characterized in that: The abnormal state vector is obtained by the following steps: S31, constructing an empty vector, wherein the dimension of the empty vector is the same as the dimension of the fault sample vector, and the operating status indicator corresponding to each component of the empty vector is the same as that of the fault sample vector; S32, for the actual value of each of the operating status indicators obtained, calculating the absolute difference between the actual value and the normal value, and comparing the absolute difference with a first threshold; S33. If the absolute difference is greater than the first threshold, the component in the empty vector corresponding to the actual value is recorded as abnormal; if the absolute difference is less than the first threshold, the component in the empty vector corresponding to the actual value is recorded as normal.

7. The transformer operation and maintenance method based on digital twin technology according to claim 1 is characterized in that: In step S4, the process of matching the abnormal state vector with all the fault sample vectors one by one includes: S41, calculating the modulus of the abnormal state vector and the modulus of the fault sample vector, and calculating the absolute difference between the moduli of the two vectors; S42, calculating the angle between the abnormal state vector and the fault sample vector; S43: When the absolute difference between the modules of the two vectors is smaller than the second threshold, and the angle between the two vectors is smaller than the third threshold, it is determined that the abnormal state vector matches the fault sample vector.

8. The transformer operation and maintenance method based on digital twin technology according to claim 1 is characterized in that: The step of issuing an indicator abnormality prompt in step S5 includes: S51. Constructing a visualization model of the transformer according to the digital twin model and the geometric model of the transformer; S52: issuing a component failure prompt through the visualization model.

9. The transformer operation and maintenance method based on digital twin technology according to claim 8 is characterized in that: The step of issuing an indicator abnormality prompt in step S5 includes: S53: issuing an indicator abnormality prompt through the visualization model.

10. The transformer operation and maintenance method based on digital twin technology according to claim 9 is characterized in that: The step of issuing an indicator abnormality prompt in step S5 includes: S54, calculating the percentage of the ratio of the actual value to the normal value; S55. Issue an indicator abnormality prompt through the visualization model and display the percentage.

Images