Method, device and equipment for determining measurement error of mutual inductor and storage medium

Abstract

The invention relates to a mutual inductor measurement error determination method and device, equipment and a storage medium, and belongs to the technical field of mutual inductors, and the method comprises the steps: predicting a measurement error of a target time mutual inductor through a first model, and obtaining a first measurement error; the first model is constructed based on change trend information of a first actual measurement error of the mutual inductor in historical time; predicting the residual error of the first measurement error through a second model to obtain a target residual error; the second model is constructed based on error fluctuation information of the first actual measurement error and a prediction residual error of the first model; and determining a target measurement error of the mutual inductor according to the first measurement error and the target residual error. According to the invention, the target measurement error is predicted based on the internal influence factors of the measurement error, such as the error change trend and the error fluctuation information, so that the predicted target measurement error is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of mutual inductor, and in particular to a method, device, equipment and storage medium for determining mutual inductor measurement errors. Background Art

[0002] The prediction of instrument transformer measurement error is an important part of the power system, which involves the stable operation of the power system, the effective transmission of energy, and the reliability of power consumption by users. As a key device in the power system, the instrument transformer is mainly used for measurement and protection, and its accuracy is directly related to the safe and economical operation of the power system.

[0003] As the scale and complexity of power systems continue to expand, the prediction and management of transformer measurement errors have become particularly important. Transformer errors may be caused by a variety of factors, such as equipment aging, environmental factors, and manufacturing processes. If these errors are not predicted and corrected in a timely manner, they may lead to inaccurate measurements, thereby affecting the normal operation of the power system. Traditional transformer measurement error prediction methods mainly rely on regular inspection and calibration, which is not only costly but also difficult to reflect the error status of the transformer in real time. Therefore, in recent years, data-driven transformer measurement error prediction methods have gradually attracted attention. These methods use a large amount of operating data and advanced machine learning algorithms to achieve fast and accurate prediction of transformer errors. However, these methods usually only consider the impact of external environmental factors such as temperature and humidity on transformer measurement errors. Summary of the invention

[0004] In view of this, it is necessary to provide a method, device, equipment and storage medium for determining a transformer measurement error, so as to solve the problem that the prior art only considers the influence of external environmental factors on the transformer measurement error.

[0005] In order to solve the above problems, in a first aspect, the present invention provides a method for determining a mutual inductor measurement error, comprising: Predicting the measurement error of the mutual inductor at the target time by using a first model to obtain a first measurement error; the first model is constructed based on the variation trend information of the first actual measurement error of the mutual inductor in the historical time; The residual of the first measurement error is predicted by a second model to obtain a target residual; the second model is constructed based on the error fluctuation information of the first actual measurement error and the predicted residual of the first model; A target measurement error of the mutual inductor is determined according to the first measurement error and the target residual.

[0006] Optionally, each date in the historical time corresponds to a first actual measurement error and multiple second actual measurement errors; the first actual measurement error corresponding to each date in the historical time is the average value of multiple second actual measurement errors corresponding to each date; and the change trend information of the first actual measurement error includes: the first actual measurement error corresponding to the target date, and the average value of the first actual measurement error in multiple time periods with the target date as the end date; the target date includes at least one.

[0007] Optionally, the error fluctuation information of the first actual measurement error includes at least one of a maximum error fluctuation, a minimum error fluctuation, an error fluctuation, a relative size of the error fluctuation, and a relative position of the error fluctuation corresponding to each date in the historical time; The error fluctuation information is calculated by the following formula: ,in, Indicates t The highest error fluctuation of the day; Indicates t The maximum actual measurement error of the day, According to t The second actual measurement error within a number of days corresponding to the date is determined, Indicates t The first actual measurement error corresponding to the day; ,in, Indicates t Minimum error fluctuation of the day; Indicates t The minimum actual measurement error of the day, According to t determining a plurality of said second actual measurement errors within a date corresponding to a day; ,in, Indicates t The error fluctuation of the day, Indicates The first actual measurement error corresponding to the day; ,in, Indicates t The relative magnitude of the daily error fluctuation; ,in, Indicates t The relative position of the day's error fluctuations.

[0008] Optionally, the second model is constructed in the following manner: Acquire environmental information in the historical time; the environmental information includes: at least one of temperature information, humidity information, and secondary load information of the mutual inductor; Constructing a first mapping relationship between the environmental information and the prediction residual based on the first sample set; The first sample set is represented by the following formula: ,in, represents the first sample set, They represent the environmental information corresponding to the t+1th day to the t+nth day in the historical time; respectively represent the prediction residuals obtained after the first model predicts the measurement error of the mutual inductor from the t+1th day to the t+nth day in the historical time; The first mapping relationship is expressed by the following formula: ,in, represents the first residual, Feature representation that represents environmental information, represents the first offset, represents the weight vector of the first hyperplane, and determining based on the first sample set; Constructing a second mapping relationship between the error fluctuation information and the prediction residual based on a second sample set; The second sample set is represented by the following formula: ,in, represents the second sample set, They represent the error fluctuation information corresponding to the tth day to the t+n-1th day in the historical time respectively; The second mapping relationship is expressed by the following formula: ,in, represents the second residual, The feature representation that represents the error fluctuation information, represents the second offset, represents the weight vector of the second hyperplane; and determining based on the second sample set; A second model is constructed according to the first mapping relationship and the second mapping relationship.

[0009] Optionally, predicting the residual of the first measurement error by using a second model to obtain a target residual includes: Determine a first residual of the first measurement error by using the first mapping relationship; Determine a second residual of the first measurement error by using the second mapping relationship; A target residual is determined according to the first residual and the second residual.

[0010] Optionally, determining a target residual according to the first residual and the second residual includes: determining a first weight of the first residual and a second weight of the second residual; The sum of the product of the first residual and the first weight and the product of the second residual and the second weight is taken as the target residual.

[0011] Optionally, determining a first weight of the first residual and a second weight of the second residual includes: Determine, according to the first mapping relationship, a first sub-prediction residual corresponding to each of the prediction residual times; Determining a first credibility and a first uncredibility of the first mapping relationship according to the prediction residual and the first sub-prediction residual; Determining a first weight of the first residual according to the first credibility and the first untrustworthiness; Determine, according to the second mapping relationship, a second sub-prediction residual corresponding to each of the prediction residual times; Determining a second credibility and a second uncredibility of the second mapping relationship according to the prediction residual and the second sub-prediction residual; A second weight of the second residual is determined according to the second credibility and the second uncredibility.

[0012] In a second aspect, the present invention further provides a device for determining a mutual inductor measurement error, comprising: A first measurement error prediction module, used to predict the measurement error of the mutual inductor at the target time through a first model to obtain a first measurement error; the first model is constructed based on the change trend information of the first actual measurement error of the mutual inductor in the historical time; A target residual prediction module, used to predict the residual of the first measurement error through a second model to obtain a target residual; the second model is constructed based on the error fluctuation information of the first actual measurement error and the prediction residual of the first model; The second measurement error determination module is used to determine a target measurement error of the mutual inductor according to the first measurement error and the target residual.

[0013] In a third aspect, the present invention further provides an electronic device comprising a memory and a processor, wherein the memory is used to store programs; and the processor is coupled to the memory and is used to execute the programs stored in the memory to implement the steps in the method for determining the mutual inductor measurement error described in any one of the above.

[0014] In a fourth aspect, the present invention further provides a computer-readable storage medium for storing a computer-readable program, wherein the program or instruction, when executed by a processor, can implement the steps in any one of the above-mentioned methods for determining a mutual inductor measurement error.

[0015] The beneficial effects of the present invention are: The measurement error of the mutual inductor at the target time is predicted by the first model to obtain the first measurement error; the first model is constructed based on the change trend information of the first actual measurement error of the mutual inductor in the historical time. The first model predicts the first measurement error of the mutual inductor at a certain time in the future (target time) based on the change trend information of the first actual measurement error.

[0016] The residual of the first measurement error is predicted by the second model to obtain the target residual; the second model is constructed based on the error fluctuation information of the first actual measurement error and the prediction residual of the first model. The second model studies the influence of the error fluctuation information of the first actual measurement error on the prediction residual when the first model is predicted, and predicts the residual of the first measurement error through the relationship between the error fluctuation information of the first actual measurement error and the prediction residual of the first model to obtain the target residual. Finally, the first measurement error is corrected according to the target residual to obtain the target measurement error, that is, the measurement error of the transformer finally determined.

[0017] The present invention proposes a new prediction idea, which mainly considers the internal influencing factors of the mutual inductor, such as the influence of the error change trend and error fluctuation information on the mutual inductor measurement error, so as to make the predicted target measurement error more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic flow chart of an embodiment of a method for determining a mutual inductor measurement error provided by the present invention; Figure 2 A schematic diagram of a flow chart of an embodiment of the second model building method provided by the present invention; Figure 3 A schematic diagram of a prediction effect provided by the present invention; Figure 4 A schematic structural diagram of an embodiment of a device for determining a mutual inductor measurement error provided by the present invention. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise specified, “plurality” means two or more than two.

[0021] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] Before showing the embodiments, the following terms are explained: Transformer: An electrical device used primarily in power systems to convert voltage or current from one level to another, measure current or voltage in circuit systems, protect circuits, regulate current or voltage, etc.

[0024] The secondary load of the transformer: refers to the total impedance of the electrical equipment or circuit connected to the secondary side of the transformer. Connecting to the secondary side of the transformer means connecting through the secondary winding of the transformer.

[0025] Residual: The difference between the model's prediction and the true value.

[0026] The present invention provides a method, device, equipment and storage medium for determining a mutual inductor measurement error, which are respectively described below.

[0027] Reference Figure 1 , shows a flow chart of an embodiment of a method for determining a mutual inductor measurement error provided by the present invention, the method comprising: Step S101, predicting the measurement error of the mutual inductor at the target time by using a first model to obtain a first measurement error; the first model is constructed based on the variation trend information of the first actual measurement error of the mutual inductor in the historical time.

[0028] Step S102, predicting the residual of the first measurement error through the second model to obtain a target residual; the second model is constructed based on the error fluctuation information of the first actual measurement error and the predicted residual of the first model.

[0029] Step S103: determining a target measurement error of the mutual inductor according to the first measurement error and the target residual error.

[0030] The first model may be a measurement error prediction model of the mutual inductor, and the first model may be a neural network model, such as a bidirectional long short-term memory model (BiLSTM). The first model may be trained based on the variation trend information of the first actual measurement error of the mutual inductor in the historical time.

[0031] The first actual measurement error may be an actual measurement error of the mutual inductor measured in a historical time. For example, the historical time may be from day 0 to day t. A first actual measurement error may be measured for each day from day 0 to day t.

[0032] In an example, each date (each day) in the historical time may correspond to a first actual measurement error, and may also correspond to multiple second actual measurement errors; the first actual measurement error corresponding to each date may be the average value of the multiple second actual measurement errors corresponding to each date.

[0033] For example, for the tth day, the true value of the target parameter and the measured value of the mutual inductor for the target parameter can be obtained once every hour. For 24 hours a day, a total of 24 sets of true values ​​and measured values ​​are obtained. According to the 24 sets of true values ​​and measured values, 24 second actual measurement errors can be calculated. The second actual measurement error can be a ratio error. Specifically, the second actual measurement error is calculated as shown in the following formula: The second actual measurement error=(the true value of the target parameter−the measurement value of the target parameter by the transformer) / the true value of the target parameter; wherein the target parameter includes the current or voltage in the power system.

[0034] Then, a first actual measurement error may be obtained by calculating an average value of the 24 second actual measurement errors. The first actual measurement error is the first actual measurement error corresponding to the t-th day.

[0035] The first actual measurement errors include a plurality of errors, and the variation trend information of the first actual measurement errors can be obtained by analyzing the first actual measurement errors. The first actual measurement errors sorted in the order of measurement time can represent their variation trend information.

[0036] Alternatively, the variation trend information of the first actual measurement error may further include: the first actual measurement error corresponding to the target date, and the average value of the first actual measurement error in multiple time periods with the target date as the end date; the target date includes at least one. That is, the variation trend information of the first actual measurement error is characterized by the first actual measurement error corresponding to the target date and the average value of the first actual measurement error in multiple time periods with the target date as the end date.

[0037] For example, when the target date is day t, the changing trend information of the first actual measurement error can be represented by the first actual measurement error on day t, the average value of the first actual measurement errors from day t-4 to day t, the average value of the first actual measurement errors from day t-9 to day t, and the average value of the first actual measurement errors from day t-19 to day t.

[0038] In this example, the change trend information can be expressed by the following formula: ; represents the average value of the first actual measurement error from day t-4 to day t, represents the first actual measurement error on the i-th day; ; It represents the average value of the first actual measurement error from day t-9 to day t; ; Represents the average value of the first actual measurement error from day t-19 to day t.

[0039] The target date may also include the t+1 day, the t+2 day, etc., and multiple time periods with the target date as the end date may also be set as needed.

[0040] This embodiment does not specifically limit the method for characterizing the variation trend information of the first actual measurement error.

[0041] The second model may be a residual prediction model. Specifically, the second model may be a support vector machine model (SVR). The second model may be constructed based on the error fluctuation information of the first actual measurement error and the prediction residual of the first model.

[0042] According to each first actual measurement error, error fluctuation information of the first actual measurement error can be analyzed and obtained. The error fluctuation information of the first actual measurement error can be represented by various methods such as skewness, kurtosis, range, standard deviation, variance, etc. of the first actual measurement error.

[0043] In one example, the error fluctuation information may include at least one of the highest error fluctuation, the lowest error fluctuation, the error fluctuation, the relative size of the error fluctuation, and the relative position of the error fluctuation corresponding to each date in the historical time; the error fluctuation information is calculated by the following formula: ,in, Indicates t The highest error fluctuation of the day; Indicates t The maximum actual measurement error of the day, According to t The second actual measurement error within a number of days corresponding to the date is determined, Indicates t The first actual measurement error corresponding to the day; ,in, Indicates t Minimum error fluctuation of the day; Indicates t The minimum actual measurement error of the day, According to t determining a plurality of said second actual measurement errors within a date corresponding to a day; ,in, Indicates t The error fluctuation of the day, Indicates The first actual measurement error corresponding to the day; ,in, Indicates t The relative magnitude of the daily error fluctuation; ,in, Indicates t The relative position of the day's error fluctuations.

[0044] This embodiment does not specifically limit the method for characterizing the error fluctuation information of the first actual measurement error.

[0045] After the first model is constructed based on the change trend information of the first actual measurement error of the mutual inductor in the historical time, the first model can predict the measurement error of the mutual inductor in the historical time to obtain at least one second measurement error. Each predicted second measurement error corresponds to a first actual measurement error; the difference between the second measurement error and the first actual measurement error corresponding to the second measurement error is calculated to obtain the prediction residual corresponding to the second measurement error. The second model is constructed based on the error fluctuation information of the first actual measurement error and the prediction residual of the first model, that is, the second model is used to study the influence of the error fluctuation information on the prediction accuracy (prediction residual) of the first model, and determine the mapping relationship between the error fluctuation information and the prediction residual of the first model.

[0046] For example, the first model can predict the measurement error of the mutual inductor on day t+1 based on the following change trend information, and obtain the second measurement error corresponding to day t+1: Then, combined with the first actual measurement error corresponding to day t+1 , we can get the forecast residual for day t+1 The change trend information is represented by the following matrix: , Where is the first actual measurement error on the t-th day, the t-th day is a day in the first historical time, L is the number of days, and represents the first actual measurement error L days before the t-th day.

[0047] The second model can be used to study the impact of the error fluctuation information corresponding to the tth day on the prediction residual of the t+1th day.

[0048] The measurement error of the target time transformer is predicted by the first model to obtain the first measurement error, and the residual of the first measurement error is predicted by the second model to obtain the target residual. The sum of the first measurement error and the target residual can be used as the target measurement error, that is, the measurement error of the transformer finally determined.

[0049] In the present invention, the first model predicts the first measurement error of the mutual inductor at a certain time in the future (target time) based on the change trend information of the first actual measurement error. The second model predicts the residual of the first measurement error based on the mapping relationship between the error fluctuation information of the first actual measurement error and the prediction residual of the first model to obtain the target residual. Finally, the first measurement error is corrected according to the target residual to obtain the target measurement error. The present invention mainly considers the internal influencing factors of the mutual inductor, such as the influence of the error change trend and error fluctuation information on the mutual inductor measurement error, which can make the predicted target measurement error more accurate.

[0050] In one embodiment, the prediction residual of the first model can be obtained as follows: (1) Obtain the historical error sequence of the transformer .

[0051] (2) Based on the historical error sequence and change trend information, construct the matrix E:

[0052] (3) Considering the different dimensions of the data, the data in the matrix E is normalized and preprocessed to obtain the matrix .

[0053] (4) Using CNN-BiLSTM model to train matrix Make short-term forecasts.

[0054] Multi-dimensional feature extraction through Convolutional Neural Network (CNN): ;in, .

[0055] The BiLSTM model uses a gated unit (forget gate , Input Gate , output gate ), read and modify the memory unit information according to the formula:

[0056] in, , and Provide proofs for the weights of the forget gate, input gate, and output gate respectively; , , is the corresponding bias term, is the input unit state weight matrix, is the input unit state bias term, is the Sigmoid activation function, which transforms the output to the interval [0,1]; It is a hyperbolic tangent activation function, which transforms the output elements into the interval [-1,1].

[0057] Then, the hidden layer output for:

[0058] Compared with the standard unidirectional LSTM, BiLSTM can obtain the relevance of historical and current information at the same time, improving the prediction ability. The complete BiLSTM hidden element provides the output link vector of the forward and reverse processes as follows:

[0059] Will Input Gets Output .

[0060] ,in, represents the prediction measurement error, and Output the corresponding weights and bias terms for the model respectively.

[0061] (5) Obtain the prediction residual.

[0062]

[0063] in, is the forecast residual for day t+1, is the second measurement error on day t+1, is the first actual measurement error on day t+1.

[0064] Similarly, the first model is based on the historical error series , predicted , then calculate .

[0065] (6) According to the above process, the residual set is constructed .

[0066] Reference Figure 2 , shows a flow chart of an embodiment of the second model construction method provided by the present invention. The second model can be constructed in the following manner: Step S201, obtaining environmental information in historical time; the environmental information includes: at least one of temperature information, humidity information, and secondary load information of the transformer.

[0067] Step S202: construct a first mapping relationship between environmental information and prediction residuals based on the first sample set.

[0068] The first sample set can be expressed by the following formula: ,in, represents the first sample set, They represent the environmental information corresponding to the t+1th day to the t+nth day in the historical time; They respectively represent the prediction residuals obtained after the first model predicts the measurement error of the mutual inductor from the t+1th day to the t+nth day in the historical time.

[0069] In one example, the environmental information corresponding to the t+1th day can be expressed as: , represents the temperature data of day t+1, represents the humidity data on day t+1, Indicates the secondary load data of the transformer on the t+1 day; the environmental information corresponding to the t+2 day to the t+n day ~ And so on.

[0070] The first mapping relationship can be expressed by the following formula: ,in, represents the first residual, Feature representation that represents environmental information, represents the first offset, represents the weight vector of the first hyperplane, and Determined based on a first sample set.

[0071] In one example, and It can be determined by minimizing the objective function in the first regression function, which is: ; ; Among them, C1 represents the penalty factor in the first regression function, represents the slack variable in the first regression function, The error requirement of the first regression function is specified, j=t+1, t+2,…, t+n, which represents the number of samples.

[0072] Step S203: constructing a second mapping relationship between error fluctuation information and prediction residual based on the second sample set.

[0073] The second sample set can be expressed by the following formula: ,in, represents the second sample set, They respectively represent the error fluctuation information corresponding to the tth day to the t+n-1th day in the historical time.

[0074] In one example, the error fluctuation information corresponding to the tth day can be expressed as: , the error fluctuation information corresponding to the t+1th day to the t+n-1th day ~ And so on.

[0075] The second mapping relationship is expressed by the following formula: ,in, represents the second residual, The feature representation that represents the error fluctuation information, represents the second offset, represents the weight vector of the second hyperplane; and Determined based on the second sample set.

[0076] In one example, and It can be determined by minimizing the objective function in the second regression function, which is:

[0077]

[0078] Among them, C2 represents the penalty factor in the second regression function, represents the slack variable in the second regression function, The error requirement of the second regression function is specified, j=t+1, t+2,…, t+n, which represents the number of samples.

[0079] Step S204: construct a second model according to the first mapping relationship and the second mapping relationship.

[0080] In this embodiment, on the one hand, a first mapping relationship between environmental information and prediction residuals is constructed, and the first mapping relationship characterizes the influence of environmental information on the prediction residuals of the first model. On the other hand, based on the construction of a second mapping relationship between error fluctuation information and prediction residuals, the second mapping relationship characterizes the influence of error fluctuation information on the prediction residuals of the first model. Finally, a second model is constructed based on the first mapping relationship and the second mapping relationship, and the second model can comprehensively evaluate the influence of environmental information and error fluctuation information on the prediction residuals of the first model.

[0081] In this embodiment, step S102 may specifically include: determining a first residual of the first measurement error through a first mapping relationship; determining a second residual of the first measurement error through a second mapping relationship; and determining a target residual according to the first residual and the second residual.

[0082] In one embodiment, the step of determining the target residual based on the first residual and the second residual may specifically include: determining a first weight of the first residual and a second weight of the second residual; and taking the sum of the product of the first residual and the first weight and the product of the second residual and the second weight as the target residual.

[0083] In one embodiment, the step of determining a first weight of the first residual and a second weight of the second residual may specifically include: determining, according to the first mapping relationship, The method further comprises: determining the first weight of the first residual according to the second mapping relationship, and determining the first reliability and the first unreliability of the first residual according to the first reliability and the first unreliability of the first residual. The corresponding second sub-prediction residual; determining the second credibility and the second uncredibility of the second mapping relationship according to each prediction residual and the second sub-prediction residual; determining the second weight of the second residual according to the second credibility and the second uncredibility.

[0084] In this embodiment, It can be the model prediction residual when the first model determined according to steps (1) to (6) in the above embodiment predicts the measurement error of the mutual inductor from day t+1 to day t+n, and The corresponding first sub-prediction residual can be understood as: the model prediction residual when the first model determined according to the first mapping relationship predicts the measurement error of the mutual inductor from the t+1th day to the t+nth day: The corresponding second sub-prediction residual can be understood as: the model prediction residual when the first model determined according to the second mapping relationship predicts the measurement error of the mutual inductor from the t+1th day to the t+nth day.

[0085] According to each prediction residual and each first sub-prediction residual, the first credibility and the first unreliability of the first mapping relationship can be determined. According to each prediction residual and each second sub-prediction residual, the second credibility and the second unreliability of the second mapping relationship can be determined. Then, based on the credibility and unreliability of the first mapping relationship and the credibility and unreliability of the second mapping relationship, weights are further allocated to the first relationship and the second mapping relationship, thereby completing the fusion of the results of the two mapping relationships.

[0086] In this embodiment, the first weight and the second weight may be determined in the following manner: (1) Determine the credibility of the first mapping relationship and the credibility of the second mapping relationship.

[0087] First sub-prediction residual and the prediction residuals Distance between: ,in, is the first sub-prediction residual of the j-th sample, is the prediction residual of the jth sample.

[0088] First sub-prediction residual Similarity:

[0089] First sub-prediction residual Credibility (credibility of the first mapping relationship):

[0090] Similarly, the credibility of the second mapping relationship can be obtained , is the second sub-prediction residual.

[0091] (2) Normalize the two credibility levels respectively.

[0092]

[0093]

[0094] (3) Determine the unreliability of the first mapping relationship and the unreliability of the second mapping relationship.

[0095]

[0096] , is the second sub-prediction residual of the j-th sample.

[0097] (4) Normalize the two unreliability levels respectively.

[0098]

[0099]

[0100] (5) Determine a first weight and a second weight based on the two trustworthinesses and two untrustworthinesses after the normalization process.

[0101] , , is the first weight.

[0102] , , is the second weight.

[0103] After the first weight and the second weight are determined, the residual of the measurement error predicted by the first model can be predicted by the second model.

[0104] For example, for day t+1, the residual corresponding to day t+1 is:

[0105] The measurement error of the transformer finally determined on day t+1 is:

[0106] Table 1 Comparison of actual measurement error and model measurement error

[0107] Referring to Table 1, the comparison results of the actual measurement error of the mutual inductor obtained by the test of the present invention and the measurement error predicted by the model are shown. The measurement error predicted by the model in Table 1 refers to the target measurement error obtained by combining the prediction results of the first model and the prediction results of the second model. The difference between the two refers to the difference between the actual measurement error of the mutual inductor and the measurement error predicted by the model. According to Table 1, the deviation between the measurement error obtained based on the prediction of the present invention and the actual measurement error of the mutual inductor is small.

[0108] Reference Figure 3 , showing a schematic diagram of a prediction effect provided by the present invention. Figure 3 The vertical axis is the error value, and the horizontal axis is the sample number. Figure 3 The measurement error of the model prediction is the target measurement error obtained by combining the prediction results of the first model and the prediction results of the second model. Figure 3 It can be seen that the deviation between the measurement error predicted by the present invention and the actual measurement error of the mutual inductor is small.

[0109] Reference Figure 4 , shows a schematic structural diagram of an embodiment of a device for determining a mutual inductor measurement error provided by the present invention, the device 300 comprises: A first measurement error prediction module 301 is used to predict the measurement error of the mutual inductor at the target time through a first model to obtain a first measurement error; the first model is constructed based on the change trend information of the first actual measurement error of the mutual inductor in the historical time; A target residual prediction module 302 is used to predict the residual of the first measurement error through a second model to obtain a target residual; the second model is constructed based on the error fluctuation information of the first actual measurement error and the prediction residual of the first model; The second measurement error determination module 303 is used to determine a target measurement error of the mutual inductor according to the first measurement error and the target residual error.

[0110] It should be noted that the implementation principle or implementation process of the above modules can refer to the embodiment of the above-mentioned method for determining the measurement error of the mutual inductor, and will not be described one by one here.

[0111] In one embodiment, the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of any of the above-mentioned methods for determining a mutual inductor measurement error are implemented.

[0112] In one embodiment, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by the processor, the steps of any one of the above-mentioned methods for determining a mutual inductor measurement error are implemented.

[0113] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0114] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for determining a mutual inductor measurement error, characterized in that: include: Predicting the measurement error of the mutual inductor at the target time by using a first model to obtain a first measurement error; the first model is constructed based on the variation trend information of the first actual measurement error of the mutual inductor in the historical time; Predicting the residual of the first measurement error by using a second model to obtain a target residual; The second model is constructed based on the error fluctuation information of the first actual measurement error and the prediction residual of the first model; A target measurement error of the mutual inductor is determined according to the first measurement error and the target residual.

2. The method for determining mutual inductor measurement error according to claim 1, characterized in that: Each date in the historical time corresponds to a first actual measurement error and multiple second actual measurement errors; the first actual measurement error corresponding to each date in the historical time is the average value of the multiple second actual measurement errors corresponding to each date; And, the variation trend information of the first actual measurement error includes: the first actual measurement error corresponding to the target date, and an average value of the first actual measurement error in multiple time periods with the target date as the end date; The target date includes at least one.

3. The method for determining mutual inductor measurement error according to claim 2, characterized in that: The error fluctuation information of the first actual measurement error includes at least one of the highest error fluctuation, the lowest error fluctuation, the error fluctuation, the relative size of the error fluctuation, and the relative position of the error fluctuation corresponding to each date in the historical time; The error fluctuation information is calculated by the following formula: ,in, Indicates t The highest error fluctuation of the day; Indicates t The maximum actual measurement error of the day, According to t The second actual measurement error within a number of days corresponding to the date is determined, Indicates t The first actual measurement error corresponding to the day; ,in, Indicates t Minimum error fluctuation of the day; Indicates t The minimum actual measurement error of the day, According to t determining a plurality of said second actual measurement errors within a date corresponding to a day; ,in, Indicates t The error fluctuation of the day, Indicates The first actual measurement error corresponding to the day; ,in, Indicates t The relative magnitude of the daily error fluctuation; ,in, Indicates t The relative position of the day's error fluctuations.

4. The method for determining mutual inductor measurement error according to claim 1, characterized in that: The second model is constructed in the following way: Acquire environmental information in the historical time; the environmental information includes: at least one of temperature information, humidity information, and secondary load information of the mutual inductor; Constructing a first mapping relationship between the environmental information and the prediction residual based on the first sample set; The first sample set is represented by the following formula: ,in, represents the first sample set, They represent the environmental information corresponding to the t+1th day to the t+nth day in the historical time; respectively represent the prediction residuals obtained after the first model predicts the measurement error of the mutual inductor from the t+1th day to the t+nth day in the historical time; The first mapping relationship is expressed by the following formula: ,in, represents the first residual, Feature representation that represents environmental information, represents the first offset, represents the weight vector of the first hyperplane, and determining based on the first sample set; Constructing a second mapping relationship between the error fluctuation information and the prediction residual based on a second sample set; The second sample set is represented by the following formula: ,in, represents the second sample set, They represent the error fluctuation information corresponding to the tth day to the t+n-1th day in the historical time respectively; The second mapping relationship is expressed by the following formula: ,in, represents the second residual, The feature representation that represents the error fluctuation information, represents the second offset, represents the weight vector of the second hyperplane; and determining based on the second sample set; A second model is constructed according to the first mapping relationship and the second mapping relationship.

5. The method for determining mutual inductor measurement error according to claim 4, characterized in that: The step of predicting the residual of the first measurement error by using the second model to obtain a target residual includes: Determine a first residual of the first measurement error by using the first mapping relationship; Determine a second residual of the first measurement error by using the second mapping relationship; A target residual is determined according to the first residual and the second residual.

6. The method for determining mutual inductor measurement error according to claim 5, characterized in that: The determining a target residual according to the first residual and the second residual comprises: determining a first weight of the first residual and a second weight of the second residual; The sum of the product of the first residual and the first weight and the product of the second residual and the second weight is taken as the target residual.

7. The method for determining mutual inductor measurement error according to claim 6, characterized in that: The determining a first weight of the first residual and a second weight of the second residual comprises: Determine, according to the first mapping relationship, a first sub-prediction residual corresponding to each of the prediction residual times; Determining a first credibility and a first uncredibility of the first mapping relationship according to the prediction residual and the first sub-prediction residual; Determining a first weight of the first residual according to the first credibility and the first untrustworthiness; Determine, according to the second mapping relationship, a second sub-prediction residual corresponding to each of the prediction residual times; Determining a second credibility and a second uncredibility of the second mapping relationship according to the prediction residual and the second sub-prediction residual; A second weight of the second residual is determined according to the second credibility and the second uncredibility.

8. A device for determining a mutual inductor measurement error, characterized in that: include: A first measurement error prediction module, used to predict the measurement error of the mutual inductor at the target time through a first model to obtain a first measurement error; the first model is constructed based on the change trend information of the first actual measurement error of the mutual inductor in the historical time; A target residual prediction module, used for predicting the residual of the first measurement error by using a second model to obtain a target residual; The second model is constructed based on the error fluctuation information of the first actual measurement error and the prediction residual of the first model; The second measurement error determination module is used to determine a target measurement error of the mutual inductor according to the first measurement error and the target residual.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for determining the mutual inductor measurement error as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer-readable program, wherein when the program or instruction is executed by a processor, the steps in the method for determining a mutual inductor measurement error described in any one of claims 1 to 7 can be implemented.

Images