A method for evaluating the state of a data acquisition device based on support vector data descriptor

Abstract

The present invention provides a method for assessing the status of a power concentrator based on a support vector data descriptor (SVR), which relates to the field of power information collection terminal status assessment. The method comprises obtaining and normalizing five categories of nine power quality measurement indicators from a concentrator; constructing a first hypersphere using the normalized five categories of nine power quality measurement indicators; setting a scaling ratio and scaling the first hypersphere to obtain a second hypersphere; introducing an abnormal sample set and iteratively correcting the second hypersphere based on a SVR to construct a third hypersphere; and assessing the status of the power concentrator based on the position of the normalized nine-dimensional data of the concentrator's measurement values ​​within the first and third hyperspheres. The present invention solves the problem of automatically determining the status of a power concentrator based on images.

Description

Technical Field

[0001] The present invention belongs to the field of power consumption information collection terminal status evaluation, and in particular relates to a power consumption information collection terminal status evaluation method based on a support vector data descriptor. Background Art

[0002] With the rapid development of new power systems, the dual-high characteristics of power distribution networks are becoming increasingly prominent, posing new challenges to the collection of electricity usage information. Current methods for assessing the status of power information collection concentrators, key devices for transmitting collected information, often rely on pre-set thresholds and simple rules to determine the concentrator's operating status by monitoring individual operating data such as voltage, current, and frequency. While these methods can effectively detect serious concentrator faults, they ignore the inherent coupling of various operating data points, making it difficult to detect complex, subtle fault patterns or abnormal conditions based on single-data status assessments.

[0003] To address this issue, some regional power systems have introduced neural networks, which have, to a certain extent, achieved the application of the inherent correlation of data and partially improved the accuracy and adaptability of state assessment. However, due to the uninterpretability of neural networks and the large demand for computing resources, they are not suitable for fast computing and edge computing, and it is difficult to meet the technical requirements of existing concentrator state assessment. Summary of the Invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a method for evaluating the state of a collection concentrator based on a support vector data descriptor, which solves the problem of automatic judgment of the state of a collection concentrator based on an image.

[0005] In order to achieve the above objectives, the technical solution adopted by the present invention is: a method for evaluating the state of a data acquisition device based on a support vector data descriptor, comprising the following steps:

[0006] S1. Obtain 9 power quality measurement indicators of 5 categories of the concentrator and perform normalization processing on them;

[0007] S2. constructing a first hypersphere using the normalized 9 power quality measurement indicators of 5 categories;

[0008] S3. Setting a scaling ratio, scaling the first hypersphere to obtain a second hypersphere;

[0009] S4, introducing an abnormal sample set, and iteratively correcting the second hypersphere based on the support vector data descriptor to construct a third hypersphere;

[0010] S5. Evaluate the status of the collection concentrator according to the positions of the normalized 9-dimensional data of the measurement values ​​of the collection concentrator falling in the first hypersphere and the third hypersphere.

[0011] The beneficial effects of the present invention are as follows: the present invention uses the nine power quality measurement indicators of the concentrator as the source data for status assessment, preliminarily constructs a first hypersphere by normalizing the data and limiting the measurement indicators, and then uses the abnormal sample set of the collection concentrator whose measurement data does not exceed the limit as iterative data. Based on the preliminarily constructed first hypersphere, further iteration is performed to obtain an optimized third hypersphere. The status of the collection concentrator can be evaluated based on the relationship between the position of the 9-dimensional data in space after normalization of the collection concentrator measurement values ​​and each hypersphere. The present invention utilizes various types of power quality measurement data from various concentrators and fully considers the coupling relationship between various types of data. At the same time, it uses various power quality indicators to optimize the initial value of the support vector data descriptor, reducing the iterative computational complexity and avoiding abnormal solutions during the iteration process. A large amount of computing power is only required when training the support vector data descriptor. After the construction of each hypersphere is completed based on the support vector data descriptor, the collected power quality measurement data only needs to be normalized in a relatively simple way, and the relationship between its coordinate space and each hypersphere can be compared to determine the concentrator status. The computing power requirement is low, the hypersphere construction can be completed in the cloud, and the concentrator status can be determined on the edge computing device. It is suitable for the construction of a new "cloud-edge" combined acquisition system application.

[0012] Furthermore, the expression for the normalization process in S1 is as follows:

[0013]

[0014]

[0015] in, 、 、 、 、 、 、 、 and The normalized results of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate are respectively. Indicates the i A hypersphere, k Indicates the first k The elements of the sample, 、 、 、 、 、 、 、 and Respectively represent the measured values ​​of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st order current total harmonic distortion rate, and 2nd to 21st order voltage total harmonic distortion rate. 、 、 、 、 、 、 and They represent the true values ​​of voltage RMS, current RMS, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion, and 2nd to 21st voltage total harmonic distortion. represents the relaxation coefficient, 、 、 、 、 、 、 、 and They represent the error limits of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate, respectively. 、 、 、 、 、 、 、 and Respectively represent the maximum allowable upper limits of the measured values ​​of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate. 、 、 、 、 、 、 、 and They respectively represent the minimum allowable lower limits of the measured values ​​of the effective value of voltage, effective value of current, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate.

[0016] The beneficial effect of the above further solution is that after normalization according to the above formula, the data expression can be enhanced, the calculation process can be made more accurate, and the influence between data of different magnitudes can be unified.

[0017] Furthermore, the S2 is specifically:

[0018] Generate a data set for constructing the first hypersphere based on the normalized 9 power quality measurement indicators of 5 categories;

[0019] Using the dataset of the first hypersphere, construct the first hypersphere:

[0020]

[0021] in, represents the radius of the first hypersphere, represents the center of the first hypersphere, Representation sample To the center of the first hypersphere distance, Indicates the first data.

[0022] The beneficial effect of the above further scheme is that the first hypersphere is used to locate the multidimensional coordinate system of the calculation, giving the entire SVDD an initial input, and locating the center of the hypersphere at zero point reduces the complexity of the calculation.

[0023] Furthermore, the expression of the second hypersphere is as follows:

[0024] ,

[0025]

[0026] in, represents the center of the second hypersphere, represents the radius of the first hypersphere, represents the radius of the first hypersphere obtained by calculation, Indicates the first The independent variable under dimension, .

[0027] The beneficial effect of the above further solution is: in the present invention, the second hypersphere is iterated using normal data, the hypersphere is roughly constructed based on the first hypersphere, the radius and center of the hypersphere are iteratively calculated to obtain a second hypersphere for judging normal data.

[0028] Furthermore, the S4 is specifically:

[0029] Obtain an abnormal sample set containing 9 power quality test data of 5 categories that do not exceed the maximum limit and have abnormalities at the acquisition terminal;

[0030] Normalizing the abnormal sample set to obtain a sample set for iteratively correcting the second hypersphere, wherein, when performing the normalization process and selecting the slack variable, it should be ensured that the data in the sample set of the second hypersphere falls between the second hypersphere and the first hypersphere to the maximum extent;

[0031] Using the sample set of the second hypersphere, a third hypersphere is constructed;

[0032] An iterative calculation is performed on the third hypersphere to obtain a revised third hypersphere, thereby completing the construction of the third hypersphere.

[0033] The beneficial effect of the above-mentioned further solution is that the third hypersphere in the present invention is iteratively constructed using a dataset containing abnormal data and based on the second hypersphere. The radius and center of the third hypersphere are fine-tuned, and the edge of the third hypersphere is further refined, resulting in a third hypersphere that can detect both normal and abnormal data. If one or two hyperspheres are omitted, the computational difficulty and required computing resources will be significantly increased. In addition, the simultaneous input of training data increases the possibility of data inconsistencies during the calculation process, increasing the risk of computational crashes by approximately 25%.

[0034] Furthermore, the expression of the third hypersphere is as follows:

[0035]

[0036] in, represents the radius of the third hypersphere, represents the center of the third hypersphere, represents the data number in the second hypersphere, represents the elastic modulus, Indicates the The amount of deviation allowed for each sample, Indicates the number of data sets whose sample clusters of the second hypersphere are between the second hypersphere and the first hypersphere, represents the data input to the second hypersphere iteration formula, that is, the abnormal sample data set, represents the slack variable.

[0037] Furthermore, the expression for iterative calculation of the third hypersphere is as follows:

[0038]

[0039] in, and All represent the data numbers in the second hypersphere, Indicates the number of data sets whose sample clusters of the second hypersphere are between the second hypersphere and the first hypersphere, and are coefficients in the iterative process, and Respectively represented as the Data and data, Represents the intermediate parameters used to solve the optimization iterative process.

[0040] The beneficial effect of the above further scheme is that the third hypersphere constructed by the present invention can be added with new data for iterative training in future actual production work. In the process of continuous iteration with the addition of new data, the hypersphere for judging abnormal data will be continuously improved. Compared with other Deep-SVDD, the introduction of new data requires re-combination with historical data for calculation, which requires a lot of time and computing power. The algorithm proposed by the present invention only needs to input new data for iteration, which greatly reduces the calculation time and computing power.

[0041] Furthermore, the S5 is specifically as follows:

[0042] Collect the normalized 9-dimensional data of the concentrator measurement values, where the normalized 9-dimensional data is the normalized 9-item power quality measurement data of 5 categories;

[0043] In response to the normalized 9-dimensional data falling into the inner area of ​​the third hypersphere, that is, , then the collection concentrator is in normal state, where represents the radius of the third hypersphere, represents the center of the third hypersphere;

[0044] In response to the normalized 9-dimensional data falling within the inner region of the first hypersphere and the outer region of the third hypersphere, that is, , then the collection concentrator is in an abnormal state, where represents the radius of the first hypersphere;

[0045] In response to the normalized 9-dimensional data falling into the outer area of ​​the first hypersphere, that is, , the collection concentrator is in a fault state. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Flow chart of the method of the present invention.

[0047] Figure 2 3D is the projection diagram of the first hypersphere S1 in this embodiment.

[0048] Figure 3 3D is the projection diagram of the second hypersphere S2 in this embodiment.

[0049] Figure 4 FIG. 4 is a schematic diagram of the third hypersphere S3 in this embodiment.

[0050] Figure 5 Schematic diagram of the state of the collector used in this embodiment. DETAILED DESCRIPTION

[0051] The specific embodiments of the present invention are described below to facilitate understanding of the present invention by those skilled in the art. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the appended claims, these changes are obvious, and all inventions and creations utilizing the concepts of the present invention are protected.

[0052] Example 1

[0053] like Figure 1 As shown, the present invention provides a method for evaluating the state of a data acquisition device based on a support vector data descriptor, and its implementation method is as follows:

[0054] S1. Obtain 9 power quality measurement indicators of 5 categories of the concentrator and perform normalization processing on them;

[0055] S2. Using the normalized 5 categories and 9 power quality measurement indicators, construct the first hypersphere, which is specifically:

[0056] Generate a data set for constructing the first hypersphere based on the normalized 9 power quality measurement indicators of 5 categories;

[0057] constructing the first hypersphere using the data set of the first hypersphere;

[0058] S3. Setting a scaling ratio, scaling the first hypersphere to obtain a second hypersphere;

[0059] S4. Introduce an abnormal sample set and iteratively modify the second hypersphere based on the support vector data descriptor to construct a third hypersphere, which is specifically as follows:

[0060] Obtain an abnormal sample set containing 9 power quality test data of 5 categories that do not exceed the maximum limit and have abnormalities at the acquisition terminal;

[0061] Normalizing the abnormal sample set to obtain a sample set for iteratively correcting the second hypersphere, wherein, when performing the normalization process and selecting the slack variable, it should be ensured that the data in the sample set of the second hypersphere falls between the second hypersphere and the first hypersphere to the maximum extent;

[0062] Using the sample set of the second hypersphere, a third hypersphere is constructed;

[0063] Iteratively calculating the third hypersphere to obtain a revised third hypersphere, thereby completing the construction of the third hypersphere;

[0064] S5. Evaluate the status of the acquisition concentrator based on the position of the normalized 9-dimensional data of the acquisition concentrator measurement value falling within the first hypersphere and the third hypersphere, which is specifically as follows:

[0065] Collect the normalized 9-dimensional data of the concentrator measurement values, where the normalized 9-dimensional data is the normalized 9-item power quality measurement data of 5 categories;

[0066] In response to the normalized 9-dimensional data falling into the inner area of ​​the third hypersphere, that is, , then the collection concentrator is in normal state, where represents the radius of the third hypersphere, represents the center of the third hypersphere;

[0067] In response to the normalized 9-dimensional data falling within the inner region of the first hypersphere and the outer region of the third hypersphere, that is, , then the collection concentrator is in an abnormal state, where represents the radius of the first hypersphere;

[0068] In response to the normalized 9-dimensional data falling into the outer area of ​​the first hypersphere, that is, , the collection concentrator is in a fault state.

[0069] In this embodiment, the present invention uses nine power quality measurement indicators from five categories of concentrators as source data for status assessment, categorizing the concentrator status into three categories: normal, abnormal, and faulty. First, using the standard values ​​of the nine power quality measurement indicators, a nine-dimensional first hypersphere is constructed with the origin as the core. The first hypersphere serves as the boundary for distinguishing between faulty and normal conditions (abnormal and normal). Second, a scaling factor is set to scale the first hypersphere to obtain a second hypersphere, which serves as the original boundary between normal and abnormal conditions. An abnormal sample set D is then introduced. This sample set consists of concentrators whose power quality measurement indicators are normal but actually have defects. Data in this sample set D is cleaned, removing data items that fall outside the first hypersphere and inside the third hypersphere. Finally, using the second hypersphere as the initial solution, abnormal sample set D is iteratively modified using the Support Vector Data Descriptor (SVDD) to obtain the third hypersphere. The outer area of ​​the first hypersphere is the fault space, the area between the inner area of ​​the first hypersphere and the third hypersphere is the abnormal space, and the inner area of ​​the third hypersphere is the normal space. The status of the acquisition concentrator is determined by the position in the space where the normalized 9-dimensional data of the acquisition concentrator measurement value falls.

[0070] In this embodiment, the performance data of the concentrator evaluated in the present invention are: 1. Voltage RMS 2. Current effective value 3. Frequency ; 4. Three-phase current zero sequence imbalance ; 5. Three-phase current negative sequence imbalance ;6. Three-phase voltage zero sequence imbalance ; 7. Three-phase voltage negative sequence imbalance ;8. 2nd to 21st order total harmonic distortion rate of current ;9. 2nd to 21st voltage total harmonic distortion rate The performance data of the concentrator must be normalized before being used to construct the first hypersphere. The above 9 types of data can be normalized in turn as follows: , and its formula is shown in Equation 1.

[0071] (1)

[0072] ~ As shown in formula (2):

[0073] (2)

[0074] in, 、 、 、 、 、 、 、 and The normalized results of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate are respectively. Indicates the i A hypersphere, k Indicates the first k The elements of the sample, 、 、 、 、 、 、 、 and Respectively represent the measured values ​​of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st order current total harmonic distortion rate, and 2nd to 21st order voltage total harmonic distortion rate. 、 、 、 、 、 、 and They represent the true values ​​of voltage RMS, current RMS, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion, and 2nd to 21st voltage total harmonic distortion. represents the relaxation coefficient, 、 、 、 、 、 、 、 and They represent the error limits of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate, respectively. 、 、 、 、 、 、 、 and Respectively represent the maximum allowable upper limits of the measured values ​​of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate. 、 、 、 、 、 、 、 and They respectively represent the minimum allowable lower limits of the measured values ​​of the effective value of voltage, effective value of current, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate.

[0075] In this embodiment, the above data are normalized to obtain a data set for constructing the first hypersphere. The data used in the first hypersphere is in 、 、 、 、 、 、 、 、 The values ​​are all allowed limits, that is, the one between the maximum allowable upper limit and the minimum allowable lower limit that has a larger absolute value of the deviation from the measured value. Take the value as 0 and substitute it into are all 1, and this is used as the boundary length of each dimension to generate the data set used to construct the first hypersphere , :

[0076] in, (Right now is a 9-dimensional real vector), , , , , , , ,......, , .

[0077] Then the first hypersphere can be constructed as:

[0078] (3)

[0079] in, represents the radius of the first hypersphere, represents the center of the first hypersphere, Representation sample To the center of the first hypersphere distance, Indicates the first data.

[0080] The first hypersphere can be solved:

[0081] , (4)

[0082] (5)

[0083] in, Indicates the first Dimensional independent variables.

[0084] In this embodiment, the first hypersphere is scaled to obtain the second hypersphere, and the scaling ratio is , whose value range is (0.5, 0.6), the second hypersphere can be obtained:

[0085] , (6)

[0086] (7)

[0087] in, represents the center of the second hypersphere, represents the radius of the first hypersphere, represents the radius of the first hypersphere obtained by calculation, Indicates the first The independent variable under dimension, .

[0088] In this embodiment, by means of data screening, an abnormal data set containing 9 power quality test data that does not exceed the maximum limit but has abnormalities in the acquisition terminal is collected. ,in, Indicates the The samples contain 9 types of power quality test data values, namely is a 9-dimensional vector, Representation dataset The number of samples included, represents the set of real numbers.

[0089] The abnormal data set After normalization according to formula (2), the sample set used for iterative correction of the second hypersphere is obtained , in choosing the slack variable Appropriate adjustments should be made to ensure that the sample set As many points as possible fall between the second hypersphere and the first hypersphere, For the sample set The number of data sets falling between the second hypersphere and the first hypersphere, :

[0090] (8)

[0091] Among them, samples , ,in, Indicates the data number in the second hypersphere.

[0092] The hypersphere that can be constructed is:

[0093] (9)

[0094] in, represents the radius of the third hypersphere, represents the center of the third hypersphere, represents the slack variable, represents the data number in the second hypersphere, Indicates the The amount of deviation allowed for each sample, Indicates the number of data sets whose sample clusters of the second hypersphere are between the second hypersphere and the first hypersphere, represents the data input to the second hypersphere iteration formula, that is, the abnormal sample data set, represents the slack variable, is the elastic coefficient, and its value range is .

[0095] In the initial value setting of the iterative calculation, , . Indicates the The amount of deviation allowed for a sample is usually 2%, so .

[0096] Then the Lagrange multiplier is introduced and , construct the Lagrangian function:

[0097] (10)

[0098] in, and They all represent the coefficients in the iterative process.

[0099] The Lagrangian function is respectively 、 、 Take the derivative and set it to zero:

[0100] right Take the derivative:

[0101] (11)

[0102] right Take the derivative:

[0103] (12)

[0104] right Take the derivative:

[0105] (13)

[0106] Then introduce the KKT condition and construct the constraint conditions as follows:

[0107] , , (14)

[0108] In summary, the entire iterative process of the third hypersphere can be simplified to the following optimization problem:

[0109] (15)

[0110] in, and All represent the data numbers in the second hypersphere, Indicates the number of data sets whose sample clusters of the second hypersphere are between the second hypersphere and the first hypersphere, and are coefficients in the iterative process, and Respectively represented as the Data and data, Represents the intermediate parameters used to solve the optimization iterative process.

[0111] By solving this optimization problem, the radius of the modified third hypersphere can be obtained with the center The inclusion relationship of the three hyperspheres is that the first hypersphere contains the third hypersphere, and the third hypersphere contains the second hypersphere. Therefore, the state of the collection concentrator can be determined by the position of the normalized 9-dimensional data of the collection concentrator measurement value in space:

[0112] When the normalized 9-dimensional data falls within the inner region of the third hypersphere, that is, , the collection concentrator is in normal state, in which the concentrator functions normally and the measurement value does not exceed the limit;

[0113] When the normalized 9-dimensional data falls inside the first hypersphere and outside the third hypersphere, that is, , the collection concentrator is in an abnormal state, in which the concentrator functions abnormally but the measurement value does not exceed the limit;

[0114] When the normalized 9-dimensional data falls outside the first hypersphere, that is, , the collection concentrator is in a faulty state, in which the concentrator function fails and the measurement value exceeds the limit.

[0115] That is: abnormal state: the area inside the first hypersphere and outside the third hypersphere; fault state: the area outside the first hypersphere, that is By calculating the position of the normalized 9-dimensional data in the space, we can get a formula for determining the state of the collector:

[0116] (16).

[0117] In summary, the present invention utilizes various types of power quality measurement data from various types of concentrators, and fully considers the coupling relationship between various types of data. At the same time, it optimizes the initial value of the support vector data descriptor using various power quality indicators, reduces the amount of iterative calculations, and avoids abnormal solutions during the iterative process. Compared with the closest existing technology in the third article, this method only requires a large amount of computing power when training the support vector data descriptor. After the construction of each hypersphere is completed based on the support vector data descriptor, the collected power quality measurement data only needs to be normalized relatively simply, and the relationship between its coordinate space and each hypersphere can be compared to determine the concentrator status. The computing power requirement is relatively low, the hypersphere construction can be completed in the cloud, and the concentrator status can be determined on the edge computing device. It is suitable for the construction of a new acquisition system application that combines "cloud and edge", and the entire method process is explainable and there is no black box model.

[0118] Example 2

[0119] To facilitate understanding of the present invention, the technical points of the above method are demonstrated using the 24-version acquisition terminal as an example, as follows:

[0120] S1: The maximum allowable upper and lower limits of the 9 types of power quality measurement values ​​of the 24 version acquisition terminal are:

[0121] (17)

[0122] According to the above method, we can obtain:

[0123] (18)

[0124] Use this as the benchmark value to normalize the various measurement values ​​of the acquisition terminal.

[0125] S2: Construct the hypersphere S1, based on the above method 、 、 、 、 、 、 、 、 The values ​​are all allowed limits, and the slack variables Take the value as 0 and substitute it into are all 1, and this is used as the boundary length of each dimension to generate the data set used to construct the first hypersphere , the first hypersphere can be solved by the method in S2 above:

[0126] (19)

[0127] Since the nine-dimensional hypersphere cannot be displayed, the first hypersphere is The projection under three-dimensional coordinates is as follows Figure 2 shown.

[0128] S3: Scaling the first hypersphere to obtain the second hypersphere, with a scaling ratio of 0.5, yields the second hypersphere:

[0129] (20)

[0130] The second hypersphere The projection under three-dimensional coordinates is as follows Figure 3 shown.

[0131] S4: Through data screening, 163 data groups with measurement data that do not exceed the maximum limit are selected from the 24th version of the acquisition terminal with abnormal functions, and the abnormal data set is constructed based on this. , slack variables Take 0.03, after normalization There are 161 groups of data items that fall between the first hypersphere and the second hypersphere.

[0132] (twenty one)

[0133] Using this sample set as iterative data, the third hypersphere can be iterated based on the first hypersphere, such as Figure 4 shown.

[0134] like Figure 5As shown, when the normalized 9-dimensional data of the acquisition concentrator measurement value falls within the third hypersphere, the state of the acquisition concentrator is normal; when the normalized 9-dimensional data of the acquisition concentrator measurement value falls between the third hypersphere and the first hypersphere, the state of the acquisition concentrator is abnormal; when the normalized 9-dimensional data of the acquisition concentrator measurement value falls outside the first hypersphere, the state of the acquisition concentrator is faulty, wherein, Figures 2 to 5 In each case, S1 represents the first hypersphere, S2 represents the second hypersphere, and S3 represents the third hypersphere.

Claims

1. A method for evaluating the state of a data acquisition device based on support vector data descriptor, characterized in that: The following steps are involved: S1. Obtain 9 power quality measurement indicators of 5 categories of the concentrator and perform normalization processing on them; S2. constructing a first hypersphere using the normalized 9 power quality measurement indicators of 5 categories; S3. Setting a scaling ratio, scaling the first hypersphere to obtain a second hypersphere; S4, introducing an abnormal sample set, and iteratively correcting the second hypersphere based on the support vector data descriptor to construct a third hypersphere; The S4 is specifically: Obtain an abnormal sample set containing 9 power quality test data of 5 categories that do not exceed the maximum limit and have abnormalities at the acquisition terminal; Normalizing the abnormal sample set to obtain a sample set for iteratively correcting the second hypersphere, wherein, when performing the normalization process and selecting the slack variable, it should be ensured that the data in the sample set of the second hypersphere falls between the second hypersphere and the first hypersphere to the maximum extent; Using the sample set of the second hypersphere, a third hypersphere is constructed; Iteratively calculating the third hypersphere to obtain a revised third hypersphere, thereby completing the construction of the third hypersphere; S5. Evaluate the status of the collection concentrator according to the positions of the normalized 9-dimensional data of the measurement values ​​of the collection concentrator falling in the first hypersphere and the third hypersphere.

2. The method for evaluating the state of a data acquisition device based on support vector data descriptor according to claim 1, characterized in that: The expression of the normalization process in S1 is as follows: in, 、 、 、 、 、 、 、 and The normalized results of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate are respectively. Indicates the i A hypersphere, k Indicates the first k The elements of the sample, 、 、 、 、 、 、 、 and Respectively represent the measured values ​​of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st order current total harmonic distortion rate, and 2nd to 21st order voltage total harmonic distortion rate. 、 、 、 、 、 、 and They represent the true values ​​of voltage RMS, current RMS, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion, and 2nd to 21st voltage total harmonic distortion. represents the relaxation coefficient, 、 、 、 、 、 、 、 and They represent the error limits of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate, respectively. 、 、 、 、 、 、 、 and Respectively represent the maximum allowable upper limits of the measured values ​​of voltage RMS, current RMS, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate. 、 、 、 、 、 、 、 and They respectively represent the minimum allowable lower limits of the measured values ​​of the effective value of voltage, effective value of current, frequency, three-phase current zero-sequence unbalance, three-phase current negative-sequence unbalance, three-phase voltage zero-sequence unbalance, three-phase voltage negative-sequence unbalance, 2nd to 21st current total harmonic distortion rate, and 2nd to 21st voltage total harmonic distortion rate.

3. The method for evaluating the state of a user data acquisition device based on support vector data descriptor according to claim 1, characterized in that: The S2 is specifically: Generate a data set for constructing the first hypersphere based on the normalized five categories and nine power quality measurement indicators; Using the dataset of the first hypersphere, construct the first hypersphere: in, represents the radius of the first hypersphere, represents the center of the first hypersphere, Represents a sample To the center of the first hypersphere distance, Indicates the first data.

4. The method for evaluating the state of a user data acquisition device based on support vector data descriptor according to claim 1, characterized in that: The expression of the second hypersphere is as follows: ， in, represents the center of the second hypersphere, represents the radius of the first hypersphere, represents the radius of the first hypersphere obtained by calculation, Indicates the first The independent variable under dimension, .

5. The method for evaluating the state of a user data collector based on support vector data descriptor according to claim 1, characterized in that: The expression of the third hypersphere is as follows: in, represents the radius of the third hypersphere, represents the center of the third hypersphere, represents the data number in the second hypersphere, represents the elastic modulus, Indicates the The amount of deviation allowed for each sample, Indicates the number of data sets whose sample clusters of the second hypersphere are between the second hypersphere and the first hypersphere, represents the data input to the second hypersphere iteration formula, that is, the abnormal sample data set, represents the slack variable.

6. The method for evaluating the state of a user data collector based on support vector data descriptor according to claim 5, characterized in that: The expression for iterative calculation of the third hypersphere is as follows: in, and All represent the data numbers in the second hypersphere, Indicates the number of data sets whose sample clusters of the second hypersphere are between the second hypersphere and the first hypersphere, and are coefficients in the iterative process, and Represented as the first Data and data, Represents the intermediate parameters used to solve the optimization iterative process.

7. The method for evaluating the state of a user data acquisition device based on support vector data descriptor according to claim 1, characterized in that: The S5 is specifically: Collect the normalized 9-dimensional data of the concentrator measurement values, where the normalized 9-dimensional data is the normalized 9-item power quality measurement data of 5 categories; In response to the normalized 9-dimensional data falling into the inner area of ​​the third hypersphere, that is, , then the collection concentrator is in normal state, where represents the radius of the third hypersphere, represents the center of the third hypersphere; In response to the normalized 9-dimensional data falling within the inner region of the first hypersphere and the outer region of the third hypersphere, that is, , then the collection concentrator is in an abnormal state, where represents the radius of the first hypersphere; In response to the normalized 9-dimensional data falling into the outer area of ​​the first hypersphere, that is, , the collection concentrator is in fault state.

Images