Transformer insulation state evaluation method and system based on analysis of gas dissolved in oil

Abstract

The invention discloses a transformer insulation state evaluation method and system based on analysis of gas dissolved in oil, and the method comprises the steps: obtaining normal historical data of a transformer, carrying out the preprocessing of the data, constructing a corresponding grid space set, calculating the relative entropy threshold value of all grids in each dimension of the grid space set, comparing the relative entropy of each grid with a corresponding relative entropy threshold value, carrying out grid adaptive division, comparing the number of normal historical data in each grid with a threshold value to determine normal data clusters, and calculating the centroids of all the normal data clusters as cluster centers; determining a normal state distance range according to the distance between all normal historical data and the cluster center; and obtaining real-time data of a to-be-evaluated transformer, preprocessing the real-time data, and determining the insulation state according to the relationship between the distance between the real-time data and the cluster center and the normal state distance range. The method is not influenced by a manually set threshold value, is high in adaptability, and does not need fault sample data.

Description

Technical Field

[0001] The present invention relates to transformer status assessment technology, and in particular to a transformer insulation status assessment method and system based on analysis of dissolved gas in oil. Background Art

[0002] Transformers are essential electrical equipment in power systems, and their operational reliability directly affects the safety of power systems. Dissolved Gas Analysis (DGA) technology is the main method for identifying transformer status. DGA technology can monitor multi-component gases dissolved in transformer insulating oil in real time, such as hydrogen (H2), carbon monoxide (CO), carbon dioxide (CO2), methane (CH4), ethane (C2H6), ethylene (C2H4), acetylene (C2H2), etc. Based on these real-time monitoring values, the evaluation system determines the operating status of the transformer by comparing the real-time gas concentration and its growth rate with the preset alarm threshold. Therefore, setting a reasonable warning threshold is crucial to ensure the reliability of the evaluation.

[0003] The current IEC 60599 standard collects more than 20,000 transformers from 25 power grids around the world. Based on the curve drawn from the dissolved gas data, the gas concentration threshold is obtained according to a certain percentage (i.e. 90%) of the total cumulative analysis. This standard does not take into account the differences between transformers, and the given "90%" percentage is relatively subjective. In response to this, domestic and foreign research institutions have proposed their own standards based on the IEC 60599 standard. For example, the GB / T 7252 standard divides transformers into "above 330 kV" and "below 220 kV", and gives warning values ​​respectively. This standard takes into account the different voltage levels of transformers, but the classification criteria are relatively vague and cannot provide assessment thresholds for all dissolved gases. Another study proposed new criteria such as the new three ratios based on DGA to obtain diagnostic results, overcoming the conflict of traditional interpretation techniques. Graphical technology based on characteristic gases has also been used for transformer fault diagnosis. The above-mentioned methods based on graph theory and new criteria can overcome some limitations, but it is difficult to completely solve the problem of fuzzy boundaries in evaluation. In addition, some artificial intelligence algorithms such as artificial neural networks, support vector machines, fuzzy logic, etc. are also widely used in transformer insulation status assessment, which can achieve high-accuracy assessment. However, there are problems such as the need for a large amount of sample data, large amount of calculation, and failure to consider transformer differentiation, which limit the application of the above methods in actual engineering.

[0004] In summary, the existing transformer insulation status assessment methods have the following technical problems: 1. The existing DGA-based transformer insulation status assessment method does not take into account the differences of transformers. For example, the gas concentration and gas growth rate thresholds for transformer insulation status assessment of different grades and different insulating oil types should be different. Using the same standard assessment threshold to diagnose the insulation status of different transformers is likely to result in low assessment accuracy, misjudgment, missed judgment, and reduce the reliability of the assessment system; 2. Artificial intelligence algorithms require a large amount of sample data and have high computational complexity, making them difficult to apply in engineering practice; 3. The existing evaluation algorithm requires fault sample data, and it is difficult to obtain fault samples during the actual operation of the transformer. Summary of the invention

[0005] The technical problem to be solved by the present invention is as follows: In view of the above-mentioned problems in the prior art, a method and system for evaluating the insulation status of a transformer based on analysis of dissolved gases in oil are provided, which have high reliability and scalability, are not affected by manually set thresholds, have high adaptability, and do not require fault sample data.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for evaluating transformer insulation status based on analysis of dissolved gas in oil comprises the following steps: Obtain normal historical data of dissolved gas detection in insulating oil of a specified type of transformer under normal operating conditions; Preprocessing the normal historical data, then establishing a coordinate system and constructing a corresponding grid space set, calculating the relative entropy threshold of all grids in each dimension of the grid space set, and finally performing grid adaptive division according to the comparison result of the relative entropy of each grid with the corresponding relative entropy threshold; The number of normal historical data in each grid in the adaptively divided grid space set is compared with the threshold to determine the normal data cluster, the centroid of all normal data clusters is calculated as the cluster center, and the distance between all normal historical data and the cluster center in the coordinate system is calculated, and the normal state distance range is determined according to the distance between all normal historical data and the cluster center; Real-time data of dissolved gas detection in insulating oil of a transformer to be evaluated under operating conditions is obtained, the real-time data is preprocessed, a coordinate system is established, and the distance between the real-time data and the cluster center in the coordinate system is calculated. The insulation state of the transformer to be evaluated is determined according to the relationship between the distance between the real-time data and the cluster center and the distance range of the normal state.

[0007] Furthermore, the transformer of the specified category specifically refers to a transformer of the same category as the transformer to be evaluated. Before obtaining the normal historical data of the detection of dissolved gas in the insulating oil of the transformer of the specified category under normal operating conditions, it also includes: classifying the transformer according to one or more parameters of voltage level, insulating oil type, volume, operating years, manufacturer, actual load, and equipment type.

[0008] Furthermore, the normal historical data is X 1× N 1-dimensional data set, the real-time data is X A 1-dimensional dataset, where X 1 indicates the number of gas types, N 1 represents the dimension of historical data under normal operating conditions. When the normal historical data is preprocessed and the real-time data is preprocessed, both of them include: calculating the feature quantity in the normal historical data or the real-time data, and reducing the dimension of the feature quantity by using the data reduction method, so that the normal historical data after dimension reduction is X 2× N 1-dimensional data set, the real-time data after dimensionality reduction is X A 2-dimensional dataset, where X 2 represents the dimension of the eigenvalue calculated based on the gas concentration.

[0009] Furthermore, when establishing a coordinate system and constructing a corresponding grid space set, it includes: setting the coordinate origin and establishing X 2D coordinate system, according to N 1 data in the i The range of values ​​of the dimension coordinates is set to the step size L i , i =1,2,…, X 2. According to the step length L i Divide the data set equally and construct a grid space set D={ d ij}, d ij Indicates i Wei Shangdi j The number of normal historical data in a grid.

[0010] Furthermore, when calculating the relative entropy threshold of all grids in each dimension of the grid space set, it includes: Calculate the grid space set i The relative entropy of each grid in dimension is expressed as follows:

[0011] in, d ijRepresents the grid space set i Wei Shangdi j A grid, s ( d ij ) is the ratio of the number of elements in the grid to the total grid space data set, It is i The number of grids in the dimension; Calculate the i The median of the relative entropy of all grids in the dimension i The relative entropy threshold is determined by the relative entropy and median of all grids in the dimension. The expression is as follows:

[0012] in, D i It is i The set of all grids in dimension, M i It is i The median relative entropy of the dimensional grid.

[0013] Furthermore, when adaptive grid division is performed based on the comparison result between the relative entropy of each grid and the corresponding relative entropy threshold, it includes: comparing the relative entropy of the current grid with the corresponding relative entropy threshold; if the relative entropy of the current grid is greater than the corresponding relative entropy threshold, merging the current grid with the previous grid in the same row, and then comparing the relative entropy of the next grid in the same row of the current grid with the corresponding relative entropy threshold; if the relative entropy of the current grid is less than the corresponding relative entropy threshold, directly comparing the relative entropy of the next grid in the same row of the current grid with the corresponding relative entropy threshold.

[0014] Further, when comparing the number of normal historical data in each grid in the adaptively divided grid space set with a threshold to determine a normal data cluster, it includes: The number of normal historical data in each grid whose number of normal historical data is greater than 0 in the adaptively divided grid space set is sorted in a specified order, and then the number of normal historical data in the grid with the specified ranking is selected as the threshold; Traverse the adaptively divided grid space set. If the number of normal historical data of the current grid is greater than or equal to the threshold, the normal historical data of the current grid is a normal data cluster. Then compare the number of normal historical data in other grids centered on the current grid with the threshold. If the number of normal historical data of the current grid is less than the threshold, the normal historical data of the current grid is noise.

[0015] Furthermore, when calculating the centroid of all normal data clusters as the cluster center, it includes: Calculate the centroid of the grid corresponding to each normal data cluster, and then determine the cluster center grid according to the centroid of the grid. The cluster center grid expression is as follows:

[0016] in, Indicates i dimensional cluster center grid coordinates, h s Indicates i The starting grid coordinates of the normal data cluster in dimension, h e Indicates i The ending grid coordinates of the normal data cluster in dimension, Indicates i Wei Shangdi h The grid coordinates of the centroids, Indicates h The number of normal historical data within a grid coordinate; The center position of the cluster center grid is taken as the cluster center.

[0017] Further, when determining the insulation state of the transformer to be evaluated according to the relationship between the distance between the real-time data and the cluster center and the normal state distance range, it includes: If the distance between the current real-time data and the cluster center is within the normal state distance range, the insulation state of the transformer to be evaluated is normal; If the distance between the current real-time data and the cluster center is outside the normal distance range, reduce the time interval for acquiring real-time data and acquire the next real-time data, pre-process the next data, and then establish a coordinate system and calculate the distance between the next real-time data and the cluster center in the coordinate system; If the distance between the next data and the cluster center is within the normal state distance range, the insulation state of the transformer to be evaluated is normal; if the distance between the next real-time data and the cluster center is outside the normal state distance range, the insulation state of the transformer to be evaluated is abnormal.

[0018] The present invention also proposes a transformer insulation status assessment system based on dissolved gas analysis in oil, comprising: Dissolved gas detection module in oil, used to detect dissolved gas in insulating oil; A monitoring cycle module, used to enable the dissolved gas detection module in oil according to a preset cycle; The insulation state evaluation module is used to execute any of the transformer insulation state evaluation methods based on dissolved gas analysis in oil to evaluate whether the insulation state of the transformer is abnormal.

[0019] Compared with the prior art, the advantages of the present invention are: The present invention calculates the cluster center based on normal historical data, and further calculates the range of the distance between the normal data and the cluster center as the normal state range, and then determines whether the transformer insulation state is abnormal by calculating the distance between the real-time detection data and the cluster center and judging the relationship between the calculation result and the normal state range. The transformer insulation state evaluation can be realized by judging the real-time measurement data without the need for fault sample data. When calculating the cluster center, the present invention constructs a grid space set for a data set of normal historical data and then calculates the relative entropy threshold of all grids in each dimension. Then, the grids are merged by comparing the relative entropy of each grid with the relative entropy threshold, thereby realizing adaptive grid division to effectively reduce the amount of calculation. Finally, the number of samples in the divided grid is compared with the threshold to realize data cleaning, and the centroid of the cleaned data is calculated as the cluster center. There is no need to manually set the threshold, and the adaptability is high.

[0020] The present invention adopts the same steps to realize adaptive threshold evaluation for each type of classified transformers, which can be applicable to insulation status evaluation under different voltage levels, different insulating oil types, and even different operating years of the same type of transformers, and can effectively improve the reliability and scalability of the evaluation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The figure is a flow chart of a method according to an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of a coordinate system established in an embodiment of the present invention.

[0023] Figure 3 It is a schematic diagram of a grid space set constructed in an embodiment of the present invention.

[0024] Figure 4 Schematic diagram of a grid that is adaptively divided in an embodiment of the present invention.

[0025] Figure 5 Schematic diagram of a cluster center grid in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The present invention is further described below in conjunction with the accompanying drawings and specific preferred embodiments, but the protection scope of the present invention is not limited thereby.

[0027] Embodiment 1 This embodiment proposes a transformer insulation status assessment method based on dissolved gas analysis in oil, which can be applied to insulation status assessment of transformers of different voltage levels, different insulating oil types, and even different operating years of the same type, and can effectively improve the reliability and scalability of the assessment system. Figure 1 As shown, the method of this embodiment includes the following steps: S1) Classify transformers; S2) obtaining normal historical data of dissolved gas detection in insulating oil of a transformer of a specified category under normal operating conditions. In this embodiment, the transformer of the specified category specifically refers to a transformer of the same category as the transformer to be evaluated; S3) preprocessing the normal historical data; S4) establishing a coordinate system for the normal historical data after preprocessing and constructing a corresponding grid space set, calculating the relative entropy threshold of all grids in each dimension of the grid space set, and performing grid adaptive division according to the comparison result between the relative entropy of each grid and the corresponding relative entropy threshold; S5) comparing the number of normal historical data in each grid in the adaptively divided grid space set with a threshold to determine a normal data cluster, calculating the centroid of all normal data clusters as the cluster center, and calculating the distance between all normal historical data and the cluster center in the coordinate system, and determining the normal state distance range according to the distance between all normal historical data and the cluster center; S6) obtaining real-time data of dissolved gas detection in insulating oil under the operating state of the transformer to be evaluated; S7) preprocessing the real-time data, establishing a coordinate system for the preprocessed real-time data and calculating the distance between the real-time data and the cluster center in the coordinate system, and determining the insulation state of the transformer to be evaluated according to the relationship between the distance between the real-time data and the cluster center and the normal state distance range.

[0028] The following is a detailed description of each major step.

[0029] In step S1 of this embodiment, the basis for classifying the transformers includes but is not limited to one or more parameters of voltage level, insulating oil type, volume, service life, manufacturer, actual load, and equipment type. Based on these parameters, parameter intervals corresponding to different categories can be divided through expert discussion to classify transformers with different parameter values.

[0030] In steps S2 and S6 of this embodiment, dissolved gas detection includes but is not limited to detection of carbon monoxide, carbon dioxide, methane, ethane, ethylene, acetylene, hydrogen, etc. Correspondingly, the normal historical data is X 1× N 1-dimensional data set, real-time data is X A 1-dimensional dataset, where X 1 indicates the number of gas types detected by dissolved gas. N 1 indicates the dimension of historical data under normal operating conditions.

[0031] In step S3 and step S7 of this embodiment, the preprocessing process specifically includes first calculating the carbon dioxide / carbon monoxide ratio, the acetylene / hydrogen ratio, the total hydrocarbon content and other characteristic quantities, and then using principal component analysis, streamline learning, support vector machine and other data dimensionality reduction methods to reduce the dimensions of the aforementioned characteristic quantities, so that the normal historical data after dimensionality reduction is X 2× N 1-dimensional data set, the real-time data after dimensionality reduction is X A 2-dimensional dataset, where X 2 represents the eigenvalue dimension calculated based on the gas concentration, and X 2< X 1.

[0032] In step S4 of this embodiment, when establishing a coordinate system and constructing a corresponding grid space set, it includes: Establish a coordinate system: set the coordinate origin and establish X 2D coordinate system, such as Figure 2 As shown, when X When 2=2, a two-dimensional coordinate system is established with the first dimension as the horizontal axis and the second dimension as the vertical axis. Then, according to the value of each dimension of the normal historical data, each normal historical data is plotted in the coordinate system as a normal state sample. Construct grid space set: The normal historical data after preprocessing is X 2× N 1D data set, according to N 1 data sample in the i The range of values ​​of the dimension coordinates is set to the step size L i , i =1,2,…, X 2. According to the step length L i Divide the data set equally and construct a grid space set D={ d ij}, d ij Indicates i Wei Shangdi j The number of normal historical data in a grid, such as Figure 3 As shown, for example i =1-dimensional fifth grid has two normal state samples, then d 15 =2.

[0033] In step S4 of this embodiment, when calculating the relative entropy threshold of all grids in each dimension of the grid space set, it includes: S41) calculates the grid space set i The relative entropy of each grid in dimension is expressed as follows:

[0034] in, d ij Represents the grid space set i Wei Shangdi j A grid, s ( d ij ) is the ratio of the number of elements in the grid to the total grid space data set, It is i The number of grids in the dimension; S42) Calculate the i The relative entropy of all grids in dimension is expressed as follows:

[0035] in, D i It is i The set of all grids in dimension; S43) Calculate the i The median of the relative entropy of all grids in the dimension i The relative entropy threshold is determined by the relative entropy and median of all grids in the dimension. The expression is as follows:

[0036] in, M i It is i The median relative entropy of the dimensional grid.

[0037] In step S4 of this embodiment, when adaptively dividing the grids according to the comparison result between the relative entropy of each grid and the corresponding relative entropy threshold, it includes: Traverse the grid space i The relative entropy of all grids in dimension e ( d ij ), compare the relative entropy of each grid e ( d ij ) and the corresponding relative entropy threshold T The size of e ( d ij )> T , that is, the relative entropy of the current grid is greater than the corresponding relative entropy threshold, then the current grid is merged with the previous grid in the same row, and then the relative entropy of the next grid in the same row of the current grid is compared with the corresponding relative entropy threshold; if e ( d ij )< T, that is, if the relative entropy of the current grid is less than the corresponding relative entropy threshold, then the relative entropy of the next grid in the same row of the current grid is directly compared with the corresponding relative entropy threshold.

[0038] For each dimension of the grid space set, after executing steps S41 to S44, grid adaptive division is performed according to the comparison result between the relative entropy of each grid in this dimension and the corresponding relative entropy threshold, and finally the grid space set after adaptive division is obtained. ,in Indicates i Wei Shangdi j The number of normal state samples in a grid, such as Figure 4 shown.

[0039] In step S5 of this embodiment, when comparing the number of normal historical data in each grid in the adaptively divided grid space set with the threshold to determine a normal data cluster, it includes: S51) sorting the number of normal historical data in each grid whose number of normal historical data in the adaptively divided grid space set is greater than 0 in a specified order, and then selecting the number of normal historical data in the grid with the specified ranking as the threshold; in this embodiment, the grid space set The number of non-zero normal state samples in Arrange in descending order, and take the 95% ranking* N The number corresponding to 2 is used as the density threshold T 2, where N 2 is the grid space set The number of non-zero normal state samples in The number of S52) traverse the adaptively divided grid space set, if the number of normal historical data of the current grid is the number of normal state samples Greater than or equal to density threshold T 2, the normal historical data of the current grid is a normal data cluster, and then the number of normal historical data in other grids centered on the current grid is compared with the threshold; if the number of normal historical data of the current grid is less than the threshold, the normal historical data of the current grid is noise; mark the visited grids, and after traversing all grids, the normal data clusters and noise in the normal historical data can be obtained, such as Figure 5 As shown, the black dots represent normal data clusters and the white dots represent noise.

[0040] In step S5 of this embodiment, when calculating the centroids of all normal data clusters as cluster centers, the process includes: S501) Calculate the centroid of the grid corresponding to each normal data cluster, and then determine the cluster center grid, i.e., the grid coordinates where the cluster center is located, according to the centroid of the grid. The cluster center grid expression is as follows:

[0041] in, Indicates i dimensional cluster center grid coordinates, h s Indicates i The starting grid coordinates of the normal data cluster in dimension, h e Indicates i The ending grid coordinates of the normal data cluster in dimension, Indicates i Wei Shangdi h grid coordinates, Indicates h The number of normal historical data within a grid coordinate; S502) The center position of the cluster center grid is used as the cluster center C normal ,like Figure 5 As shown, the cluster center grid calculated by step S501 is grid A, and its coordinates are a , b , c , d , then the coordinates of the cluster center are [( a + b ) / 2,( c + d ) / 2].

[0042] In step S5 of this embodiment, calculating the distance between all normal historical data and the cluster center in the coordinate system is specifically calculating the Euclidean distance between all normal historical data and the cluster center in the coordinate system, and determining the normal state distance range based on the distance between all normal historical data and the cluster center is specifically selecting the maximum value of the Euclidean distance between all normal historical data and the cluster center. d max and minimum value d min , as the upper and lower limits of the normal state distance range.

[0043] In step S7 of this embodiment, when establishing a coordinate system for the preprocessed real-time data and calculating the distance between the real-time data in the coordinate system and the cluster center, it includes: Establish a coordinate system: set the coordinate origin and establish X 2D coordinate system, and then plot the real-time data in the coordinate system according to the value of each dimension of the preprocessed real-time data; Calculate the distance between the real-time data and the cluster center in the coordinate system: Calculate the Euclidean distance between the real-time data and the cluster center based on the coordinates of the real-time data and the cluster center in the coordinate system d r .

[0044] In step S7 of this embodiment, when determining the insulation state of the transformer to be evaluated according to the relationship between the distance between the real-time data and the cluster center and the normal state distance range, it includes: calculate ; like ρ ≥0 and d r ≠ d max , that is, the distance between the current real-time data and the cluster center d r If it is within the normal state distance range, the insulation state of the transformer to be evaluated is normal; like ρ <0 and d r ≠ d max , that is, the distance between the current real-time data and the cluster center is outside the normal distance range, reduce the time interval for acquiring real-time data and acquire the next real-time data for rapid measurement, pre-process the next data, and then establish a coordinate system and calculate the distance between the next real-time data in the coordinate system and the cluster center d’ r ; calculate ; like ρ ≥0 and d’ r ≠ d max , that is, the distance between the next data and the cluster center is within the normal state distance range, then the insulation state of the transformer to be evaluated is normal; if ρ <0 and d’ r ≠ d max , that is, the distance between the next real-time data and the cluster center is outside the normal state distance range, indicating that the measurement result of the rapid measurement does not meet the judgment condition, and it is judged that the insulation state of the transformer to be evaluated is abnormal.

[0045] Embodiment 2 This embodiment provides a transformer insulation status assessment system based on dissolved gas analysis in oil, including: Central processing module, used for system control, data processing, display and storage, evaluation information transmission, etc.; Dissolved gas detection module in oil, used to detect dissolved gas in insulating oil, including but not limited to gas precipitation unit based on transformer insulating oil, gas detection unit, etc., wherein the detection principle of the gas detection unit includes but is not limited to gas chromatography, photoacoustic spectroscopy, tunable semiconductor laser absorption spectroscopy, etc.; A monitoring cycle module, which is used to enable the dissolved gas detection module in oil according to a preset cycle. The monitoring cycle module includes a periodic monitoring mode and a rapid monitoring mode. The periodic monitoring mode is a monitoring cycle set by the user, which is measured once every 24 hours by default. The rapid detection mode starts the system immediately after the current measurement is completed to perform a second measurement; The insulation state evaluation module is used to execute the transformer insulation state evaluation method based on dissolved gas analysis in oil described in the first embodiment to evaluate whether the transformer insulation state is abnormal.

[0046] In summary, the present invention discloses a transformer insulation status assessment method and system based on dissolved gas analysis in oil, which has the following advantages: The present invention provides an adaptive threshold evaluation, which can be applicable to insulation status evaluation under different voltage levels, different insulating oil types, and even different operating years of the same type of transformer, and can effectively improve the reliability and scalability of the evaluation system.

[0047] The present invention is based on the historical data of the normal operation status of the transformer. First, the data dimension is reduced by using the data preprocessing method; then, the data samples are adaptively gridded, the number of samples in the grid is compared with the threshold to achieve data cleaning, and finally, the centroid of the cleaned data is calculated as the cluster center. The implementation process of this method does not require manual setting of thresholds, has high adaptability, and effectively reduces the amount of calculation by reducing the data dimension and adaptively dividing the grid.

[0048] The present invention implements transformer insulation status evaluation based on the existing normal operation sample set by judging the subordinate relationship between real-time measurement data and the normal sample set, without the need for fault sample data.

[0049] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A transformer insulation condition assessment method based on dissolved gas analysis in oil, characterized in that: The following steps are involved: Obtain normal historical data of dissolved gas detection in insulating oil of a specified type of transformer under normal operating conditions; Preprocessing the normal historical data, then establishing a coordinate system and constructing a corresponding grid space set, calculating the relative entropy threshold of all grids in each dimension of the grid space set, and finally performing grid adaptive division according to the comparison result of the relative entropy of each grid with the corresponding relative entropy threshold; The number of normal historical data in each grid in the adaptively divided grid space set is compared with the threshold to determine the normal data cluster, the centroid of all normal data clusters is calculated as the cluster center, and the distance between all normal historical data and the cluster center in the coordinate system is calculated, and the normal state distance range is determined according to the distance between all normal historical data and the cluster center; Real-time data of dissolved gas detection in insulating oil of a transformer to be evaluated under operating conditions is obtained, the real-time data is preprocessed, a coordinate system is established, and the distance between the real-time data and the cluster center in the coordinate system is calculated. The insulation state of the transformer to be evaluated is determined according to the relationship between the distance between the real-time data and the cluster center and the distance range of the normal state.

2. The transformer insulation condition assessment method based on dissolved gas analysis in oil according to claim 1, characterized in that: The transformer of the specified category specifically refers to a transformer of the same category as the transformer to be evaluated. Before obtaining the normal historical data of the detection of dissolved gas in the insulating oil of the transformer of the specified category under normal operating conditions, it also includes: classifying the transformer according to one or more parameters of voltage level, insulating oil type, volume, operating years, manufacturer, actual load, and equipment type.

3. The transformer insulation condition assessment method based on dissolved gas analysis in oil according to claim 1, characterized in that: The normal historical data is X 1× N 1-dimensional data set, the real-time data is X A 1-dimensional dataset, where X 1 indicates the number of gas types, N 1 represents the dimension of historical data under normal operating conditions. When the normal historical data is preprocessed and the real-time data is preprocessed, both of them include: calculating the feature quantity in the normal historical data or the real-time data, and reducing the dimension of the feature quantity by using the data reduction method, so that the normal historical data after dimension reduction is X 2× N 1-dimensional data set, the real-time data after dimensionality reduction is X A 2-dimensional dataset, where X 2 represents the dimension of the eigenvalue calculated based on the gas concentration.

4. The transformer insulation condition assessment method based on dissolved gas analysis in oil according to claim 3, characterized in that: When establishing a coordinate system and constructing the corresponding grid space set, it includes: setting the coordinate origin and establishing X 2D coordinate system, according to N 1 data in the i The range of values ​​of the dimension coordinates is set to the step size L i , i =1,2,…, X 2. According to the step length L i Divide the data set equally and construct a grid space set D={ d ij }, d ij Indicates i Wei Shangdi j The number of normal historical data in a grid.

5. The transformer insulation condition assessment method based on dissolved gas analysis in oil according to claim 4 is characterized in that: When calculating the relative entropy threshold of all grids in each dimension of the grid space set, it includes: Calculate the grid space set i The relative entropy of each grid in dimension is expressed as follows: in, d ij Represents the grid space set i Wei Shangdi j A grid, s ( d ij ) is the ratio of the number of elements in the grid to the total grid space data set, It is i The number of grids in the dimension; Calculate the i The median of the relative entropy of all grids in the dimension i The relative entropy threshold is determined by the relative entropy and median of all grids in the dimension. The expression is as follows: in, D i It is i The set of all grids in dimension, M i It is i The median relative entropy of the dimensional grid.

6. The transformer insulation condition assessment method based on dissolved gas analysis in oil according to claim 1, characterized in that: When adaptively dividing the grid according to the comparison result between the relative entropy of each grid and the corresponding relative entropy threshold, it includes: comparing the relative entropy of the current grid with the corresponding relative entropy threshold; if the relative entropy of the current grid is greater than the corresponding relative entropy threshold, merging the current grid with the previous grid in the same row, and then comparing the relative entropy of the next grid in the same row of the current grid with the corresponding relative entropy threshold; if the relative entropy of the current grid is less than the corresponding relative entropy threshold, directly comparing the relative entropy of the next grid in the same row of the current grid with the corresponding relative entropy threshold.

7. The transformer insulation condition assessment method based on dissolved gas analysis in oil according to claim 1, characterized in that: When comparing the number of normal historical data in each grid in the adaptively divided grid space set with the threshold to determine the normal data cluster, it includes: The number of normal historical data in each grid whose number of normal historical data is greater than 0 in the adaptively divided grid space set is sorted in a specified order, and then the number of normal historical data in the grid with the specified ranking is selected as the threshold; Traverse the adaptively divided grid space set. If the number of normal historical data of the current grid is greater than or equal to the threshold, the normal historical data of the current grid is a normal data cluster. Then compare the number of normal historical data in other grids centered on the current grid with the threshold. If the number of normal historical data of the current grid is less than the threshold, the normal historical data of the current grid is noise.

8. The transformer insulation condition assessment method based on dissolved gas analysis in oil according to claim 1, characterized in that: When calculating the centroid of all normal data clusters as cluster centers, it includes: Calculate the centroid of the grid corresponding to each normal data cluster, and then determine the cluster center grid according to the centroid of the grid. The cluster center grid expression is as follows: in, Indicates i dimensional cluster center grid coordinates, h s Indicates i The starting grid coordinates of the normal data cluster in dimension, h e Indicates i The ending grid coordinates of the normal data cluster in dimension, Indicates i Wei Shangdi h grid coordinates, Indicates h The number of normal historical data within a grid coordinate; The center position of the cluster center grid is taken as the cluster center.

9. The transformer insulation condition assessment method based on dissolved gas analysis in oil according to claim 1, characterized in that: When determining the insulation state of the transformer to be evaluated based on the relationship between the distance between the real-time data and the cluster center and the normal state distance range, it includes: If the distance between the current real-time data and the cluster center is within the normal state distance range, the insulation state of the transformer to be evaluated is normal; If the distance between the current real-time data and the cluster center is outside the normal distance range, reduce the time interval for acquiring real-time data and acquire the next real-time data, pre-process the next data, and then establish a coordinate system and calculate the distance between the next real-time data and the cluster center in the coordinate system; If the distance between the next data and the cluster center is within the normal state distance range, the insulation state of the transformer to be evaluated is normal; if the distance between the next real-time data and the cluster center is outside the normal state distance range, the insulation state of the transformer to be evaluated is abnormal.

10. A transformer insulation status assessment system based on dissolved gas analysis in oil, characterized in that: include: Dissolved gas detection module in oil, used to detect dissolved gas in insulating oil; A monitoring cycle module, used to enable the dissolved gas detection module in oil according to a preset cycle; An insulation state assessment module is used to execute the transformer insulation state assessment method based on dissolved gas analysis in oil as described in any one of claims 1 to 9 to assess whether the transformer insulation state is abnormal.

Images