Low-rated capacity transformer identification method, device, equipment and medium

Abstract

The application discloses a low-rated capacity transformer identification method, device, equipment and medium, first, the nameplate capacity value, transformer short-circuit resistance, short-circuit reactance per unit value and historical operation data of the target transformer are acquired. Then, the estimated capacity value of the target transformer is calculated according to the historical operation data, and the voltage regulation rate of the target transformer is calculated according to the transformer short-circuit resistance, short-circuit reactance per unit value and historical operation data. Finally, whether the target transformer has the first low-rated capacity suspicion is judged according to the estimated capacity value and the nameplate capacity value, and whether the target transformer has the second low-rated capacity suspicion is judged according to the voltage regulation rate; if the target transformer has the first low-rated capacity suspicion and the second low-rated capacity suspicion, the target transformer is determined as a low-rated capacity transformer. In summary, the application can realize the automatic screening of the low-rated capacity transformer, and the double suspicion judgment is made by comprehensively considering the nameplate capacity value, the estimated capacity value and the voltage regulation rate, and the occurrence of misjudgment is also effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and in particular to a method, device, equipment and medium for identifying a low-capacity transformer. Background Art

[0002] For a long time, there has been a situation where the distribution transformer capacity recorded in the distribution-related system or the capacity on the nameplate parameters does not match the actual capacity, which has resulted in the power supply system being unable to correctly collect basic electricity charges, causing considerable losses to the country and the power grid.

[0003] In the past, the development of distribution network automation was relatively backward, and the traditional capacity identification process was too complicated and prone to errors. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, equipment and medium for identifying low-standard capacity transformers to solve the problem that the traditional transformer capacity identification method is too complicated and prone to errors.

[0005] A method for identifying a low-capacity transformer, the method comprising:

[0006] Obtain the nameplate capacity value, transformer short-circuit resistance, short-circuit reactance per unit value, and historical operating data of the target transformer; wherein the historical operating data includes the voltage, current, power, load rate, and power factor data of the target transformer within a preset time period;

[0007] Calculating an estimated capacity value of the target transformer based on historical operating data, and calculating a voltage regulation rate of the target transformer based on the transformer short-circuit resistance, the per-unit short-circuit reactance, and historical operating data;

[0008] Determining whether the target transformer has a first low-capacity suspicion based on the estimated capacity value and the nameplate capacity value, and determining whether the target transformer has a second low-capacity suspicion based on the voltage regulation rate;

[0009] If the target transformer has the first suspected low-capacity and the second suspected low-capacity, it is determined that the target transformer is a low-capacity transformer.

[0010] In one embodiment, the calculating the estimated capacity value of the target transformer based on historical operating data includes:

[0011] Obtaining N operating parameter curve groups of a first target parameter from historical operating data; wherein the first target parameter is any one of power, load rate, and power factor, the operating parameter curve group includes multiple operating parameter curves for the same time period within a day, and the N operating parameter curve groups of the first target parameter are set for different time periods;

[0012] In the target operating parameter curve group, averaging the data of the operating parameter curves at the same time to obtain N calculated typical operating parameter curves corresponding to the first target parameter; wherein the target operating parameter curve group is any one of the N operating parameter curve groups;

[0013] The maximum value of a parameter in N typical operating parameter curves is used as the typical operating parameter of the first target parameter, and the estimated capacity value is calculated based on the typical operating parameters of all parameters.

[0014] In one embodiment, the calculating the voltage regulation rate of the target transformer according to the transformer short-circuit resistance, the per-unit value of the short-circuit reactance, and historical operating data includes:

[0015] Obtaining N typical operating parameter curves for calculating a second target parameter; wherein the second target parameter is any one of voltage and current;

[0016] The voltage regulation rate within a set time period is calculated according to the typical operating parameter curve of voltage, the typical operating parameter curve of current, the short-circuit resistance of the transformer and the per-unit value of the short-circuit reactance within the same set time period, and N calculated voltage regulation rates are obtained.

[0017] In one embodiment, determining whether the target transformer is suspected of having a second low capacity according to the voltage regulation rate includes:

[0018] Calculating the mean and standard deviation of N voltage regulation rates, determining whether the mean falls within a preset adjustment range, and determining whether the standard deviation is less than a preset adjustment threshold;

[0019] If the mean value does not fall within the preset adjustment range and the standard deviation value is greater than the preset adjustment threshold value, it is determined that the target transformer is suspected of having a second low standard capacity.

[0020] In one embodiment, determining whether the target transformer is suspected of having a first low-standard capacity according to the estimated capacity value and the nameplate capacity value includes:

[0021] Calculating a difference ratio between the estimated capacity value and the nameplate capacity value, and determining whether the difference ratio is greater than a preset difference ratio threshold; wherein the difference ratio is a ratio of an absolute value of the difference between the estimated capacity value and the nameplate capacity value to the nameplate capacity value;

[0022] If the phase difference ratio is greater than the phase difference ratio threshold, it is determined that the target transformer has a first low-standard capacity suspicion.

[0023] In one embodiment, the method further includes:

[0024] Invalid data in historical operating data is detected and eliminated based on the isolation forest algorithm; wherein, the invalid data includes abnormal data, fluctuating data and missing data.

[0025] In one embodiment, the method further includes:

[0026] Eliminate shutdown data from historical operation data based on start-stop sign signals; wherein the start-stop sign signals include sudden changes in voltage, current, and speed of the target transformer;

[0027] An improved vector machine method based on ant colony algorithm is used to eliminate overload operation data in historical operation data.

[0028] A low-capacity transformer identification device, comprising:

[0029] A data reading module is used to obtain the nameplate capacity value, transformer short-circuit resistance, short-circuit reactance per unit value and historical operating data of the target transformer; wherein the historical operating data includes the voltage, current, power, load rate and power factor data of the target transformer within a preset time period;

[0030] a data calculation module, configured to calculate an estimated capacity value of the target transformer based on historical operating data, and to calculate a voltage regulation rate of the target transformer based on the short-circuit resistance of the transformer, the per-unit value of the short-circuit reactance, and historical operating data;

[0031] A judgment module is used to judge whether the target transformer has a first low-standard capacity suspicion based on the estimated capacity value and the nameplate capacity value, and to judge whether the target transformer has a second low-standard capacity suspicion based on the voltage regulation rate; if the target transformer has the first low-standard capacity suspicion and the second low-standard capacity suspicion, then the target transformer is determined to be a low-standard capacity transformer.

[0032] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the steps of the above-mentioned low-capacity transformer identification method.

[0033] A low-capacity transformer identification device includes a memory and a processor, wherein the memory stores a computer program. When the computer program is executed by the processor, the processor performs the steps of the low-capacity transformer identification method.

[0034] The present invention provides a method, device, equipment and medium for identifying low-capacity transformers. First, data acquisition is performed, including obtaining the nameplate capacity value, transformer short-circuit resistance, short-circuit reactance per unit value and historical operating data of the target transformer. Next, data calculation is performed, including calculating the estimated capacity value of the target transformer based on the historical operating data, and calculating the voltage regulation rate of the target transformer based on the transformer short-circuit resistance, short-circuit reactance per unit value and historical operating data. Finally, a comprehensive judgment is performed, including judging whether the target transformer has a first low-capacity suspicion based on the estimated capacity value and the nameplate capacity value, and judging whether the target transformer has a second low-capacity suspicion based on the voltage regulation rate; if the target transformer has a first low-capacity suspicion and a second low-capacity suspicion, the target transformer is determined to be a low-capacity transformer. In summary, the present invention can realize automatic screening of low-capacity transformers, avoid the traditional overly complicated capacity identification process, and comprehensively perform double suspicion judgment by combining the nameplate capacity value, estimated capacity value and voltage regulation rate, which also effectively reduces the occurrence of misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] in:

[0037] Figure 1 1 is a flow chart of a method for identifying a low-capacity transformer in one embodiment;

[0038] Figure 2 2. It is a structural schematic diagram of a low-capacity transformer identification device in one embodiment;

[0039] Figure 3 FIG. 1 is a structural block diagram of a low-capacity transformer identification device in one embodiment. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0041] like Figure 1 As shown, Figure 1: This is a flow chart of a method for identifying a low-capacity transformer in one embodiment. The steps provided by the method for identifying a low-capacity transformer in this embodiment include:

[0042] Step 102: Obtain the nameplate capacity value, transformer short-circuit resistance, per-unit short-circuit reactance value, and historical operating data of the target transformer.

[0043] For all transformer groups in a certain area that need to be inspected for low-capacity transformers, the target transformer is any one of the transformer groups. The nameplate capacity, transformer short-circuit resistance, per-unit short-circuit reactance, and historical operating data of the target transformer are obtained from the database.

[0044] In this embodiment, the historical operating data includes data such as the voltage, current, power, load factor, and power factor of the target transformer within a preset time period. Optionally, data collected during the previous operation of the target transformer for 1-6 months can be used as the historical operating data. Of course, the preset time period can also be adjusted according to actual needs.

[0045] In order to improve the accuracy and efficiency of the subsequent data processing process, in this embodiment, the acquired data may be pre-processed, including:

[0046] In a specific embodiment, invalid data in historical operating data is detected and eliminated based on an isolation forest algorithm; wherein the invalid data includes abnormal data, fluctuating data, and missing data.

[0047] Specifically, during the isolation forest construction phase, randomly selected operational data with certain differences from the power system operating data is used as data samples for the isolation forest construction tree. The imported operational data is arranged according to the operating time period, and 100 data samples are selected as the root data. Based on this, the remaining data samples are separated, and the dataset is divided into multiple sub-datasets based on the value and frequency of occurrence, until each sub-dataset contains only one data point. A random value range is selected as the value extraction threshold and the data forest is partitioned according to the threshold. The partition results are judged based on the data density. The separation and partitioning of the training set are repeated until all data anomalies are eliminated.

[0048] In the application stage of the isolation forest, all historical operating data at the same sampling time point are first taken as a data group. In the subsequent elimination process, if any data in a data group is eliminated, all data in the data group will be eliminated.

[0049] In addition, you can also perform preliminary duplication reduction testing on the data to delete duplicate or redundant data with high similarity, which can reduce the impact of noise and other interfering data.

[0050] All historical operating data is then input into the constructed isolation forest model for data cleaning. A portion of the data is placed in the root data node of each binary tree. The isolation forest algorithm is used to randomly separate the data so that the data falls on the corresponding binary tree leaf nodes. The data is continuously partitioned based on the input data's value and frequency of occurrence until each sub-dataset contains only one piece of data. Because invalid data S is often rare and has little correlation with other data, it can be easily identified.

[0051] The following formula is used to calculate the distance and hierarchical relationship between the leaf node data where the invalid data S is located and the root node, and the average height of the binary tree is normalized to estimate the abnormality index of the invalid data S.

[0052]

[0053] H(n)=ln(n)+ξ,ξ=0.5772156649 (2)

[0054] In the above formula, C(n) represents the distance from the data S(x,n) to the root node, n represents the anomaly index of the data in the dataset, H(n) represents the average height of all binary trees during the computation, and ξ is the Euler index, which is 0.5772156649. The closer the normalized result is to 0, the less likely invalid data is.

[0055] Finally, the data whose normalized results fall within (0, 0.5] are regarded as normal data, and the data group whose normalized results fall within (0.5, 1] ​​are regarded as invalid data and eliminated.

[0056] In a specific embodiment, shutdown data in historical operation data is eliminated based on a start-stop marker signal; wherein the start-stop marker signal includes a sudden change in voltage, current and speed of the target transformer.

[0057] In a specific embodiment, an improved vector machine method based on an ant colony algorithm is used to eliminate overloaded operation data from historical operation data.

[0058] Specifically, all parameters collected at the same time each day are put into the same sample, and the operating load data in the sample is normalized first, expressed as:

[0059]

[0060] In the above formula, x is the operating load data, i represents the data at different collection times, min(x) represents the minimum load in the historical operating data of the target transformer, and max(x) represents the maximum load in the historical operating data of the target transformer.

[0061] Assume that the load data set is (x i,y i ), (i=0,1,2,.....,n), where n is the number of data sets, x i is the load data after normalization, y i ∈{+1,-1} is the data category. The decision function is:

[0062]

[0063]

[0064] In the above formula, K(x,y) is the kernel function, C is the penalty parameter, and σ is the kernel parameter. A larger penalty parameter C results in a smaller allowable error. The value of the kernel parameter σ is related to the data input space.

[0065] Initialize the parameters of the ant colony algorithm, including the number of iterations M, the number of ant colonies N, the pheromone volatility coefficient Rho, the step size lam, and randomly generate the initial position of each ant (C, σ). The corresponding accuracy model is obtained through vector machine learning.

[0066] Pheromone Update: Find the ant with the largest pheromone and save its corresponding pheromone information. Based on the pheromone value, determine each ant's next transfer probability. Establish a dynamic transfer factor. If the ant's transfer probability is lower than the dynamic transfer factor, perform a local search. If the transfer probability is higher than the dynamic transfer factor, perform a global search and update the ant's position. When the maximum number of iterations is reached, find the ant with the largest pheromone at that time and record its position (Ce, σe). This becomes the optimized parameters of the vector machine.

[0067] The optimized parameters are substituted into the vector machine, the load data is input to detect “outlier” data, and the data with lower frequency is eliminated as overload operation data.

[0068] Step 104 , calculating the estimated capacity value of the target transformer based on the historical operating data, and calculating the voltage regulation rate of the target transformer based on the per-unit short-circuit resistance and short-circuit reactance of the transformer and the historical operating data.

[0069] In a specific embodiment, the estimated capacity value of the target transformer is calculated in the following manner, including:

[0070] (1) Obtain N operating parameter curve groups of the first target parameter from historical operating data.

[0071] Among them, the first target parameter is any one of power, load rate and power factor, the operating parameter curve group includes multiple operating parameter curves in the same time period within a day, and the time periods set in the N operating parameter curve groups of the first target parameter are different.

[0072] The following uses power as an example. It's understood that the same principle applies to load rate and power factor. For example, assuming the historical data acquired includes six months of power curves, using a 4-hour division basis, the 24-hour power curve group can be divided into six groups, resulting in six operating parameter curve groups for the six months: 0-4, 4-8, 8-12, 12-16, 16-20, and 20-24. Of course, N here can be set based on actual needs.

[0073] (2) In the target operating parameter curve group, the data of the operating parameter curves at the same time are averaged to obtain N typical operating parameter curves corresponding to the first target parameter.

[0074] The target operating parameter curve group is any one of the N operating parameter curve groups.

[0075] For example, the aforementioned operating parameter curve group from 0 to 4 o'clock is used as a target operating parameter curve group, which includes the operating parameter curves from 0 to 4 o'clock over a period of six months. The data of the operating parameter curves at the same time is then averaged. For example, the data of one point in each operating parameter curve is averaged. Repeating this averaging operation yields a typical operating parameter curve corresponding to 0 to 4 o'clock.

[0076] By repeating the above operation of calculating typical operating parameter curves for all operating parameter curve groups, 6 typical operating parameter curves corresponding to power can be obtained.

[0077] (3) The maximum value of the parameter in the N typical operating parameter curves is used as the typical operating parameter of the first target parameter, and the estimated capacity value is calculated based on the typical operating parameters of all parameters.

[0078] In other words, the maximum value of the parameter in the six typical operating parameter curves of power is used as the typical operating parameter of power. Similarly, the typical operating parameters of load rate and power factor can be obtained.

[0079] Then, based on the following formula, the estimated capacity value can be calculated:

[0080] Estimated capacity value = typical operating parameters of power / typical operating parameters of load rate / typical operating parameters of power factor

[0081] In a specific embodiment, the voltage regulation rate of the target transformer is calculated in the following manner, including:

[0082] (1) Obtain N typical operating parameter curves for calculating the second target parameter.

[0083] The second target parameter is any one of voltage and current. The method for obtaining the N typical operating parameter curves is the same as above and will not be repeated here.

[0084] (2) Calculate the voltage regulation rate within a set time period based on the typical operating parameter curve of voltage, the typical operating parameter curve of current, the per-unit value of the transformer short-circuit resistance and the short-circuit reactance within the same set time period, and obtain N calculated voltage regulation rates.

[0085] For example, in the typical operating parameter curves of voltage and current at 0-4, 4-8, 8-12, 12-16, 16-20, and 20-24, the voltage regulation rate at 0-4 can be calculated based on the typical operating parameter curves of voltage and current, the per-unit values ​​of the transformer short-circuit resistance and short-circuit reactance. By repeating this operation to calculate the voltage regulation rate, six voltage regulation rates can be obtained. The formula for calculating the voltage regulation rate is:

[0086]

[0087] In the above formula, ΔU is the voltage regulation rate, U 2N is the secondary voltage rating within the typical operating parameter curve for voltage, I2 is the secondary current within the typical operating parameter curve for current, S N is the rated capacity of the transformer, represents the short-circuit resistance of the transformer, Indicates the per-unit short-circuit reactance of the transformer.

[0088] In the above specific embodiment, the estimated capacity value and voltage regulation rate are calculated by segmenting the historical operating data, taking into account the differences in operating characteristics in different time periods, that is, the impact of output fluctuations on low-standard capacity identification, which can further improve the accuracy of subsequent low-standard capacity identification.

[0089] Step 106 , determining whether the target transformer has a first suspicion of low capacity based on the estimated capacity value and the nameplate capacity value, and determining whether the target transformer has a second suspicion of low capacity based on the voltage regulation rate.

[0090] This embodiment performs a dual judgment on whether the target transformer is suspected of having a low-standard capacity, that is, judging whether there is a first suspicion of low-standard capacity and judging whether there is a second suspicion of low-standard capacity.

[0091] In a specific embodiment, the method for determining whether there is a suspicion of first low-standard capacity is:

[0092] (1) Calculate the difference ratio between the estimated capacity value and the nameplate capacity value, and determine whether the difference ratio is greater than a preset difference ratio threshold.

[0093] The calculation formula for the phase difference ratio is:

[0094]

[0095] The phase difference ratio threshold here can be set according to actual needs. It can be understood that the smaller the threshold, the stricter the requirements, and the larger the threshold, the looser the requirements. No specific limitation is made here.

[0096] (2) If the phase difference ratio is greater than the phase difference ratio threshold, it is determined that the target transformer has a first low-standard capacity suspicion.

[0097] In a specific embodiment, the method for determining whether there is a suspicion of second low capacity is:

[0098] (1) Calculate the mean and standard deviation of N voltage regulation rates, determine whether the mean falls within the preset adjustment range, and determine whether the standard deviation is less than the preset adjustment threshold.

[0099] The calculation formula of the mean is:

[0100]

[0101] The formula for calculating the standard deviation is:

[0102]

[0103] In the above formula, subscript i = [1, 2, ...., N] represents the i-th typical curve; subscript j = [1, 2, ..., M] corresponds to the voltage regulation rate data at different sampling points.

[0104] In this embodiment, the preset adjustment range is set to 1% to 4%, but other values ​​are also possible. The preset adjustment threshold here can be set according to actual needs. It is understood that the smaller the threshold, the stricter the requirements, and the larger the threshold, the looser the requirements. No specific limitation is made here.

[0105] (2) If the mean value does not fall within the preset adjustment range and the standard deviation value is greater than the preset adjustment threshold, it is determined that the target transformer is suspected of having the second lowest standard capacity.

[0106] Step 108 determines whether the target transformer has both a first and a second suspected low-capacity rating. If the target transformer has both a first and a second suspected low-capacity rating, step 110 is executed to determine that the target transformer is a low-capacity transformer. If the target transformer does not have both a first and a second suspected low-capacity rating, step 112 is executed to determine that the target transformer is not a low-capacity transformer.

[0107] Furthermore, when a substandard capacity transformer is discovered, an alarm can be issued, and the transformer's serial number, manufacturer, and user information can be reported to the power supply company for on-site verification. This can help prevent losses in a timely manner.

[0108] In one embodiment, Figure 2 As shown, a low-capacity transformer identification device is proposed, which includes:

[0109] The data reading module 202 is used to obtain the nameplate capacity value, transformer short-circuit resistance, short-circuit reactance per unit value and historical operation data of the target transformer; wherein the historical operation data includes the voltage, current, power, load rate and power factor data of the target transformer within a preset time period;

[0110] A data calculation module 204 is configured to calculate an estimated capacity value of a target transformer based on historical operating data, and to calculate a voltage regulation rate of the target transformer based on per-unit values ​​of the transformer short-circuit resistance and short-circuit reactance and historical operating data;

[0111] The judgment module 206 is used to judge whether the target transformer has a first low-capacity suspicion based on the estimated capacity value and the nameplate capacity value, and to judge whether the target transformer has a second low-capacity suspicion based on the voltage regulation rate; if the target transformer has the first low-capacity suspicion and the second low-capacity suspicion, the target transformer is determined to be a low-capacity transformer.

[0112] Figure 3 FIG. 1 shows an internal structure diagram of a low-capacity transformer identification device in one embodiment. Figure 3 As shown, the low-capacity transformer identification device includes a processor, a memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the low-capacity transformer identification device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement the low-capacity transformer identification method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may implement the low-capacity transformer identification method. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the low-capacity transformer identification device to which the solution of the present application is applied. The specific low-capacity transformer identification device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0113] A low-capacity transformer identification device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: obtaining the nameplate capacity value, the transformer short-circuit resistance, the per-unit short-circuit reactance value, and historical operating data of a target transformer; calculating the estimated capacity value of the target transformer based on the historical operating data, and calculating the voltage regulation rate of the target transformer based on the transformer short-circuit resistance, the per-unit short-circuit reactance value, and the historical operating data; judging whether the target transformer has a first low-capacity suspicion based on the estimated capacity value and the nameplate capacity value, and judging whether the target transformer has a second low-capacity suspicion based on the voltage regulation rate; if the target transformer has the first low-capacity suspicion and the second low-capacity suspicion, then determining that the target transformer is a low-capacity transformer.

[0114] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps: obtaining the nameplate capacity value, the transformer short-circuit resistance, the per-unit short-circuit reactance value, and historical operating data of a target transformer; calculating an estimated capacity value of the target transformer based on the historical operating data, and calculating a voltage regulation rate of the target transformer based on the transformer short-circuit resistance, the per-unit short-circuit reactance value, and the historical operating data; judging whether the target transformer has a first suspicion of low capacity based on the estimated capacity value and the nameplate capacity value, and judging whether the target transformer has a second suspicion of low capacity based on the voltage regulation rate; and if the target transformer has both the first suspicion of low capacity and the second suspicion of low capacity, determining that the target transformer is a low-capacity transformer.

[0115] It should be noted that the above-mentioned low-capacity transformer identification method, device, equipment and computer-readable storage medium belong to a general inventive concept, and the contents of the embodiments of the low-capacity transformer identification method, device, equipment and computer-readable storage medium are applicable to each other.

[0116] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, which can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0117] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for identifying a low-capacity transformer, characterized in that: The method comprises: Obtain the nameplate capacity value, transformer short-circuit resistance, short-circuit reactance per unit value, and historical operating data of the target transformer; wherein the historical operating data includes the voltage, current, power, load rate, and power factor data of the target transformer within a preset time period; Calculating an estimated capacity value of the target transformer based on historical operating data, and calculating a voltage regulation rate of the target transformer based on the transformer short-circuit resistance, the per-unit short-circuit reactance, and historical operating data; Determining whether the target transformer has a first low-capacity suspicion based on the estimated capacity value and the nameplate capacity value, and determining whether the target transformer has a second low-capacity suspicion based on the voltage regulation rate; If the target transformer has the first suspected low-capacity and the second suspected low-capacity, it is determined that the target transformer is a low-capacity transformer.

2. The method according to claim 1, characterized in that Calculating the estimated capacity value of the target transformer based on historical operating data includes: Obtaining N operating parameter curve groups of a first target parameter from historical operating data; wherein the first target parameter is any one of power, load rate, and power factor, the operating parameter curve group includes multiple operating parameter curves for the same time period within a day, and the N operating parameter curve groups of the first target parameter are set for different time periods; In the target operating parameter curve group, averaging the data of the operating parameter curves at the same time to obtain N calculated typical operating parameter curves corresponding to the first target parameter; wherein the target operating parameter curve group is any one of the N operating parameter curve groups; The maximum value of a parameter in N typical operating parameter curves is used as the typical operating parameter of the first target parameter, and the estimated capacity value is calculated based on the typical operating parameters of all parameters.

3. The method according to claim 2, characterized in that Calculating the voltage regulation rate of the target transformer according to the transformer short-circuit resistance, the per-unit short-circuit reactance value, and historical operating data includes: Obtaining N typical operating parameter curves for calculating a second target parameter; wherein the second target parameter is any one of voltage and current; The voltage regulation rate within a set time period is calculated according to the typical operating parameter curve of voltage, the typical operating parameter curve of current, the short-circuit resistance of the transformer and the per-unit value of the short-circuit reactance within the same set time period, and N calculated voltage regulation rates are obtained.

4. The method according to claim 3, characterized in that The determining, based on the voltage regulation rate, whether the target transformer has a second low-capacity suspicion includes: Calculating the mean and standard deviation of N voltage regulation rates, determining whether the mean falls within a preset adjustment range, and determining whether the standard deviation is less than a preset adjustment threshold; If the mean value does not fall within the preset adjustment range and the standard deviation value is greater than the preset adjustment threshold value, it is determined that the target transformer is suspected of having a second low standard capacity.

5. The method according to claim 1, wherein The determining, based on the estimated capacity value and the nameplate capacity value, whether the target transformer has a first low-standard capacity suspicion includes: Calculating a difference ratio between the estimated capacity value and the nameplate capacity value, and determining whether the difference ratio is greater than a preset difference ratio threshold; wherein the difference ratio is a ratio of an absolute value of the difference between the estimated capacity value and the nameplate capacity value to the nameplate capacity value; If the phase difference ratio is greater than the phase difference ratio threshold, it is determined that the target transformer has a first low-standard capacity suspicion.

6. The method according to claim 1, characterized in that The method further comprises: Invalid data in historical operating data is detected and eliminated based on the isolation forest algorithm; wherein, the invalid data includes abnormal data, fluctuating data and missing data.

7. The method according to claim 1, characterized in that The method further comprises: Eliminate shutdown data from historical operation data based on start-stop sign signals; wherein the start-stop sign signals include sudden changes in voltage, current, and speed of the target transformer; An improved vector machine method based on ant colony algorithm is used to eliminate overload operation data in historical operation data.

8. A low-capacity transformer identification device, characterized in that: The device comprises: A data reading module is used to obtain the nameplate capacity value, transformer short-circuit resistance, short-circuit reactance per unit value and historical operating data of the target transformer; wherein the historical operating data includes the voltage, current, power, load rate and power factor data of the target transformer within a preset time period; a data calculation module, configured to calculate an estimated capacity value of the target transformer based on historical operating data, and to calculate a voltage regulation rate of the target transformer based on the short-circuit resistance of the transformer, the per-unit value of the short-circuit reactance, and historical operating data; A judgment module is used to judge whether the target transformer has a first low-standard capacity suspicion based on the estimated capacity value and the nameplate capacity value, and to judge whether the target transformer has a second low-standard capacity suspicion based on the voltage regulation rate; if the target transformer has the first low-standard capacity suspicion and the second low-standard capacity suspicion, then the target transformer is determined to be a low-standard capacity transformer.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A low-capacity transformer identification device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images