Transformer winding temperature monitoring method and system

Abstract

The invention discloses a transformer winding temperature monitoring method and system, and belongs to the technical field of transformer winding temperature monitoring, and the transformer winding temperature monitoring method comprises the steps: obtaining an image of a transformer winding; extracting temperature data of the image through infrared weak target detection and constructing a grey-scale map; calculating temperature change data between two adjacent frames or different frames of the transformer winding through the grey-scale map; and calculating an edge wheel characteristic value and a compensatory measurement index, and carrying out normalization processing on the characteristic quantity. According to the method, the gray-scale map of the transformer winding is obtained, temperature transmission data between two adjacent frames or different frames of the transformer winding is obtained, normalization processing is carried out on the characteristic quantity, and real-time monitoring on the transformer winding is achieved in a data mode.

Description

Technical Field

[0001] The invention relates to the technical field of transformer winding temperature monitoring, and in particular to a transformer winding temperature monitoring method and system. Background Art

[0002] As an important equipment in the power system, the transformer will show various fault forms during long-term operation due to the influence of various factors. Once a fault occurs in the transformer (such as winding deformation, winding heating, etc.), it will affect the stability of the power system operation.

[0003] The transmission and distribution of electric energy within the power system requires the efficiency and stability of the entire system, and no failures can occur in any link, which also leads to the long-term high maintenance costs of the power system.

[0004] At present, there is no simpler and safer way to solve the problem of winding heating except using infrared thermometers to observe the temperature. Overheating of power transformer windings will lead to insulation aging, affecting the stability and safety of power system operation.

[0005] For temperature detection, on-site observation and temperature measurement are only carried out through infrared temperature measuring instruments, which is time-consuming and laborious. In addition, entering the work site also increases the risk of power grid accidents. In addition, the temperature measurement results are only visual, and cannot be analyzed through precise data, nor can they be presented more intuitively through a system. Summary of the invention

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides a transformer winding temperature monitoring method and system to solve the problem that the current system can only be visualized but cannot be analyzed through accurate data, nor can it more intuitively display temperature anomalies through a system.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for monitoring the temperature of a transformer winding, comprising: acquiring an image of a transformer winding; extracting temperature data of the image through infrared weak target detection and constructing a grayscale image; calculating the temperature change data between two adjacent frames or different frames of the transformer winding through the grayscale image; calculating edge wheel eigenvalues ​​and compensatory measurement indicators, and normalizing the feature quantities.

[0010] As a preferred solution of the transformer winding temperature monitoring method of the present invention, it also includes temperature variation analysis:

[0011] Select any area in the grayscale image; obtain multiple frames and extract the average temperature value of all pixels in the selected area; calculate the temperature difference between two or more adjacent frames, expressed as:

[0012] ΔT=T new -T old

[0013] Among them, T new is the average temperature value of all pixels in the selected area of ​​the next frame, T old The average temperature value of all pixels in the selected area of ​​the previous frame.

[0014] As a preferred solution of the transformer winding temperature monitoring method of the present invention, it also includes temperature change rate analysis: selecting any area in the grayscale image; acquiring multiple frames and extracting temperature data in the selected area; calculating the average temperature value T(t) in the selected area of ​​each frame in the acquired multiple frames, and recording the timestamp t of each frame image; calculating the temperature change rate between two consecutive frames, expressed as:

[0015]

[0016] Among them, t2 and t1 are the timestamps of adjacent frames respectively.

[0017] As a preferred solution of the transformer winding temperature monitoring method of the present invention, it also includes temperature curve analysis: selecting any area or single pixel point in the grayscale image; acquiring multiple frames and extracting the average temperature or single-point temperature value of the selected area; establishing a two-dimensional coordinate of the temperature change over time and constructing a temperature curve; and analyzing the temperature change trend over time through linear regression.

[0018] As a preferred solution of the transformer winding temperature monitoring method of the present invention, it also includes: spatial temperature distribution analysis: obtaining the temperature value of each pixel from the grayscale image and forming a two-dimensional temperature matrix, the number of rows and columns of the two-dimensional temperature matrix corresponds to the number of rows and columns of the grayscale image pixels; calculating the statistical characteristics of the temperature distribution through the two-dimensional temperature matrix, the statistical characteristics include the maximum temperature, the minimum temperature, the average temperature, the temperature standard deviation and the degree of discreteness of the temperature distribution; or displaying the temperature contour lines of different areas through a contour map.

[0019] As a preferred solution of the transformer winding temperature monitoring method of the present invention, it also includes regional extreme value analysis: obtaining temperature extreme value points in a two-dimensional temperature matrix, the temperature extreme value points include the highest temperature point and the lowest temperature point; obtaining the position and temperature value of the pixel points in the grayscale image corresponding to the highest temperature point and the lowest temperature point in the two-dimensional temperature matrix; comparing and analyzing the temperature extreme value points of multiple frames; if the position of the extreme value point continues to move in a certain direction in several consecutive frames, that is, the temperature abnormal area physically moves; if the temperature of the extreme value point continues to rise or fall, that is, the temperature of the temperature abnormal area increases or decreases.

[0020] As a preferred solution of the transformer winding temperature monitoring method of the present invention, the temperature change amount, temperature change rate, discrete degree of temperature distribution and change trend of extreme points are normalized and expressed as:

[0021]

[0022] Among them, X is the original data, X max is the maximum value in the data set, X min is the minimum value in the data set.

[0023] In a second aspect, the present invention provides a transformer winding temperature monitoring system, comprising an acquisition module for acquiring grayscale images of two adjacent frames or different frames of the transformer winding; a transmission module electrically connected to the acquisition module, the transmission module being used to receive and transmit the grayscale image; a processing module electrically connected to the transmission module, being used to receive the grayscale image transmitted by the transmission module, and calculating the temperature transfer result between two adjacent frames or different frames; and converting the grayscale image into a two-dimensional pseudo-color thermal image through RGB color mapping.

[0024] In a third aspect, the present invention provides a computing device comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the transformer winding temperature monitoring method.

[0025] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the transformer winding temperature monitoring method.

[0026] The beneficial effects of the present invention are: by obtaining a grayscale image of a transformer winding, obtaining temperature transfer data between two adjacent frames or different frames of the transformer winding, and normalizing the feature quantity, real-time monitoring of the transformer winding is achieved through data. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0028] Figure 1 A step diagram of a transformer winding temperature monitoring method.

[0029] Figure 2 This is the transformer winding heating model diagram of the transformer winding temperature monitoring system. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0032] Secondly, the present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0033] Furthermore, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0034] Example 1

[0035] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a transformer winding temperature monitoring method.

[0036] S100: Use infrared thermal imager to obtain images of transformer windings;

[0037] S200: extracting the temperature data of the image through infrared weak target detection and constructing a grayscale image; extracting the temperature data of the image through infrared weak target detection is a prior art. For example, there is a linear relationship between the grayscale value of a pixel and the temperature. Drawing a 3D temperature cloud map through software such as MATLAB can better show the temperature distribution of the analyzed object. Therefore, it will not be elaborated here.

[0038] It is worth noting that in infrared thermal imaging, the grayscale value of each pixel in the image is usually proportional to the temperature of the point, that is, the temperature is represented by the grayscale value. The grayscale value can range from an integer of 0 (black, representing the lowest temperature) to 255 (white, representing the highest temperature), depending on the number of bits of the image. This embodiment uses a 16-bit image, which can provide a wider temperature range and finer temperature distinction.

[0039] S300: Calculating temperature change data between two adjacent frames or different frames of the transformer winding through the grayscale image; the temperature change data includes temperature change amount, temperature change rate, temperature curve, spatial temperature distribution and regional extreme value, etc.

[0040] S400: Calculate edge wheel eigenvalues ​​and compensatory metrics. In image processing, an edge is where the pixel intensity changes most significantly in an image, usually marking the outline or boundary of an object. Edge detection is a method of identifying these changes. Edge wheel eigenvalues ​​refer to some key parameters calculated during the edge detection process, such as the strength, direction, and continuity of the edge. These eigenvalues ​​help describe and identify edge features in an image. Compensatory metrics refer to metrics used to adjust or compensate for errors and variability during the analysis process. For example, in temperature analysis, it is necessary to compensate for the effects of environmental factors (such as humidity and wind speed) on temperature readings. These indicators help improve the accuracy of measurements and ensure the reliability of analysis results. Calculating edge wheel eigenvalues ​​and compensatory metrics is also a prior art and will not be described in detail here.

[0041] The characteristic quantities are normalized. The characteristic quantities of this embodiment are temperature change data, including temperature change, temperature change rate, statistical characteristics of temperature distribution (such as maximum value, minimum value, average value, standard deviation), etc. These characteristic quantities are key information extracted from temperature data, which are used to describe and analyze temperature distribution and changes. In temperature change analysis, temperature change rate analysis, temperature curve analysis, spatial temperature distribution analysis, and regional extreme value analysis, the normalized characteristic quantities can more accurately reflect the relative importance of temperature changes rather than absolute size. For example, a temperature change of 10 degrees may have different meanings in different temperature ranges. Through normalization, this change can be compared more fairly with other temperature changes. That is, the normalized data is easier to interpret because they are all on the same scale, which helps to understand the relationship between the data.

[0042] In addition, although grayscale images can provide temperature information, the human eye is more sensitive to color than grayscale, so grayscale images are often converted into pseudo-color images to facilitate more intuitive identification of temperature differences. Pseudo-color processing is a process that converts a single-channel grayscale image into a three-channel color image, so that different temperature areas are displayed in different colors, thereby enhancing the visual effect of the image. Pseudo-color processing is a prior art and will not be described here. By performing pseudo-color processing on grayscale images, it is easier for the human eye to understand the overheating of the transformer winding more intuitively.

[0043] The present invention obtains the image of the transformer winding through an infrared thermal imager, extracts the temperature data of the image through infrared weak target detection and constructs a grayscale image, and calculates the temperature change data between different frames or two adjacent frames, such as the temperature change amount, temperature change rate, temperature curve, spatial temperature distribution and regional extreme value, etc., so that the overheating of the transformer winding can be monitored more accurately, so that the temperature measurement results are not only visualized, but also can be analyzed through precise data.

[0044] Example 2

[0045] This embodiment is the second embodiment of the present invention, and is based on embodiment 1.

[0046] S301: Temperature variation analysis: select any area in the grayscale image; obtain multiple frames and extract the average temperature value of all pixels in the selected area; it is worth noting that the areas selected by multiple frames are all the same area; calculate the temperature difference between two or more adjacent frames, expressed as

[0047] ΔT=T new -T old

[0048] Among them, T new is the average temperature value of all pixels in the selected area of ​​the next frame, T old is the average temperature value of all pixels in the selected area of ​​the previous frame. This embodiment calculates the temperature difference between two adjacent frames.

[0049] S302: Temperature change rate analysis: select any area in the grayscale image; obtain multiple frames and extract temperature data in the selected area; it is worth noting that the areas selected by multiple frames are all the same area; calculate the average temperature value T(t) in the selected area of ​​each frame in the obtained multiple frames, and record the timestamp t of each frame image; calculate the temperature change rate between two consecutive frames, expressed as:

[0050]

[0051] Among them, t2 and t1 are the timestamps of adjacent frames respectively.

[0052] S303: Temperature curve analysis: select any area or single pixel in the grayscale image; obtain multiple frames and extract the average temperature or single-point temperature value of the selected area; it is worth noting that the areas selected by multiple frames are the same area; establish a two-dimensional coordinate of the temperature change over time and construct a temperature curve; analyze the temperature change trend over time through linear regression.

[0053] Linear regression analysis is as follows: collect temperature data and corresponding time points through grayscale images of different frames, ensure that the data is arranged in chronological order, use time as the independent variable (x-axis) and temperature as the dependent variable (y-axis), and plot all data points on the graph. Observe whether the data points show a linear relationship, that is, whether the data points are arranged roughly along a straight line. Use the least squares method to calculate the best fit line, which will minimize the sum of the squares of the vertical distances from all data points to the line. The slope represents the rate at which the temperature changes over time. Use the linear regression equation to predict temperature. Given a time point, the corresponding temperature can be predicted. Linear regression analysis is a prior art and will not be described in detail here.

[0054] S304: Spatial temperature distribution analysis: Obtain the temperature value of each pixel from the grayscale image and form a two-dimensional temperature matrix, where the number of rows and columns of the two-dimensional temperature matrix corresponds to the number of rows and columns of the grayscale image pixels; the two-dimensional temperature matrix is ​​usually a two-dimensional array, where the number of rows and columns corresponds to the number of pixels in the image.

[0055] For example, if the resolution of an image is 320x240 pixels, then the corresponding two-dimensional temperature matrix will be an array of 320 rows and 240 columns. The value of each element in the matrix represents the temperature of the corresponding pixel, and these values ​​are obtained by the correspondence between the grayscale and temperature of the grayscale image.

[0056] The statistical characteristics of temperature distribution are calculated through a two-dimensional temperature matrix, including the maximum temperature, minimum temperature, average temperature, standard deviation of temperature and the degree of dispersion of temperature distribution; or the temperature contour lines of different regions are displayed through a contour map. The distance between the lines on the contour map can reflect the gradient of temperature change. The smaller the line spacing, the more drastic the temperature change.

[0057] S304: Regional extreme value analysis: obtain the temperature extreme value points in the two-dimensional temperature matrix, the temperature extreme value points include the highest temperature point and the lowest temperature point; obtain the position and temperature value of the pixel points in the grayscale image corresponding to the highest temperature point and the lowest temperature point in the two-dimensional temperature matrix; compare and analyze the temperature extreme value points of multiple frames; if the position of the extreme value point continues to move in a certain direction in several consecutive frames, the temperature anomaly area physically moves; if the temperature of the extreme value point continues to rise or fall, the temperature of the temperature anomaly area increases or decreases.

[0058] S401: normalize the temperature change, temperature change rate, discrete degree of temperature distribution and change trend of extreme points, and express it as:

[0059]

[0060] Among them, X is the original data, X max is the maximum value in the data set, X min is the minimum value in the data set.

[0061] For example, X is the temperature change, which is expressed as X = [10, 20, 30, 40, 50]. min =10,X max =50; when X=10, X norm =0; Similarly, the normalized data X norm =[0, 0.25, 0.5, 0.75, 1]. Through this process, the original temperature change data is normalized to the range of 0 to 1.

[0062] The present invention reflects the temperature value through the grayscale of the grayscale image, and calculates the temperature change data between different frames or two adjacent frames, such as temperature change analysis, temperature change rate analysis, temperature curve analysis, spatial temperature distribution and regional extreme value analysis, to judge and monitor the temperature of the transformer winding in the form of data.

[0063] Example 3

[0064] See also Figure 1 and Figure 2 , which is the third embodiment of the present invention, is based on Embodiment 1 and Embodiment 2.

[0065] The acquisition module is used to acquire grayscale images of two adjacent frames or different frames of the transformer winding; infrared image data collected by the infrared camera. The data format is usually a 16-bit grayscale image, representing the temperature information of each pixel. The transmission module is electrically connected to the acquisition module, and the transmission module is used to receive and transmit the grayscale image; the processing module is electrically connected to the transmission module, and is used to receive the grayscale image transmitted by the transmission module, calculate the temperature transfer result between two adjacent frames or different frames; and convert the grayscale image into a two-dimensional pseudo-color thermal image through RGB color mapping.

[0066] This embodiment further provides a computing device, which is applicable to the case of online monitoring of the integrity of the casing casing on the converter transformer valve side, and includes:

[0067] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the online monitoring method for the integrity of the casing of the converter valve side as proposed in the above embodiment.

[0068] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for online monitoring the integrity of the casing of the converter transformer valve side proposed in the above embodiment is implemented.

[0069] The storage medium proposed in this embodiment and the online monitoring method for realizing the integrity of the bushing housing on the converter transformer valve side proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0070] The present invention forms a transformer winding temperature monitoring system through a collection module, a transmission module and a processing module. The transformer winding temperature is collected and calculated through the system, and the transformer winding temperature is more intuitively displayed.

[0071] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure of performing the function described herein, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0072] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0073] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0074] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A transformer winding temperature monitoring method, characterized in that: include: Acquire an image of the transformer windings; Extract the temperature data of the image and construct a grayscale image through infrared weak target detection; Calculate the temperature variation data between two adjacent frames or different frames of the transformer winding through the grayscale image; Calculate the edge wheel eigenvalues ​​and compensatory metrics, and normalize the feature quantities.

2. The transformer winding temperature monitoring method according to claim 1, characterized in that: Also includes temperature variation analysis: Select any area in the grayscale image; Acquire multiple frames and extract the average temperature value of all pixels in the selected area; Calculate the temperature difference between two or more adjacent frames, expressed as: ΔT=T new -T old Among them, T new is the average temperature value of all pixels in the selected area of ​​the next frame, T old The average temperature value of all pixels in the selected area of ​​the previous frame.

3. The transformer winding temperature monitoring method according to claim 1 or 2, characterized in that: Also includes temperature rate of change analysis: Select any area in the grayscale image; Acquire multiple frames and extract temperature data within a selected area; Calculate the average temperature value T(t) in the selected area of ​​each frame in the acquired multiple frames, and record the timestamp t of each frame image; Calculate the temperature change rate between two consecutive frames, expressed as: Among them, t2 and t1 are the timestamps of adjacent frames respectively.

4. The transformer winding temperature monitoring method according to claim 1 or 2, characterized in that: Also includes temperature profile analysis: Select any area or single pixel in the grayscale image; Get multiple frames and extract the average temperature of the selected area or the temperature value of a single point; Establish two-dimensional coordinates of temperature variation over time and construct a temperature curve; The temperature variation trend over time was analyzed by linear regression.

5. The transformer winding temperature monitoring method according to claim 1 or 2, characterized in that: Also includes spatial temperature distribution analysis: Obtain the temperature value of each pixel from the grayscale image and form a two-dimensional temperature matrix, where the number of rows and columns of the two-dimensional temperature matrix corresponds to the number of rows and columns of the grayscale image pixels; The statistical characteristics of temperature distribution are calculated through a two-dimensional temperature matrix, and the statistical characteristics include the maximum temperature, the minimum temperature, the average temperature, the standard deviation of temperature and the degree of dispersion of temperature distribution; Or use a contour map to show the temperature contours in different areas.

6. The transformer winding temperature monitoring method according to claim 5, characterized in that: Also includes regional extreme value analysis: Obtaining the temperature extreme points in the two-dimensional temperature matrix, the temperature extreme points include the highest temperature point and the lowest temperature point; Obtain the positions and temperature values ​​of the pixels in the grayscale image corresponding to the highest temperature point and the lowest temperature point in the two-dimensional temperature matrix; Compare and analyze the temperature extreme points of multiple frames; If the position of the extreme point continues to move in a certain direction in several consecutive frames, the temperature anomaly area is physically moving; If the temperature of the extreme point continues to rise or fall, the temperature of the temperature anomaly area increases or decreases.

7. The transformer winding temperature monitoring method according to claim 1, characterized in that: The temperature change, temperature change rate, discrete degree of temperature distribution and change trend of extreme points are normalized and expressed as: Among them, X is the original data, X max is the maximum value in the data set, X min is the minimum value in the data set.

8. A transformer winding temperature monitoring system, characterized in that: include: An acquisition module, used for acquiring grayscale images of two adjacent frames or different frames of the transformer winding; A transmission module, electrically connected to the acquisition module, and configured to receive and transmit the grayscale image; The processing module is electrically connected to the transmission module, and is used to receive the grayscale image transmitted by the transmission module, calculate the temperature transfer result between two adjacent frames or different frames; and convert the grayscale image into a two-dimensional pseudo-color thermal image through RGB color mapping.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the transformer winding temperature monitoring method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the transformer winding temperature monitoring method according to any one of claims 1 to 7.

Images