A transformer oil tank wall infrared temperature measurement image correction method and system

Abstract

The present application relates to the technical fields of power equipment online monitoring and fault diagnosis, in particular to a transformer oil tank wall infrared temperature measurement image correction method and system, comprising the steps of: collecting the infrared temperature measurement image of the transformer oil tank wall surface and transforming; obtaining the temperature of different positions of the transformer oil tank wall surface; constructing a temperature difference matrix; interpolating the temperature difference matrix; and summing the transformed infrared temperature measurement image and the interpolated temperature difference matrix to obtain the corrected infrared temperature measurement image. The present application constructs a temperature difference matrix by the temperature sensor and the infrared temperature measurement image of the transformer oil tank wall, linearly interpolates the temperature difference value of the corresponding position of the temperature sensor to obtain the temperature difference value of the corresponding position of each pixel point of the infrared temperature measurement image of the transformer oil tank wall for the other areas of the transformer oil tank wall without arranging the temperature sensor, and corrects the obtained infrared temperature measurement image, thereby improving the temperature precision of the infrared temperature measurement image.

Description

Technical Field

[0001] This invention relates to the field of online monitoring and fault diagnosis technology for power equipment, and in particular to a method and system for correcting infrared temperature measurement images of transformer tank walls. Background Technology

[0002] As a crucial operational hub in power transmission and distribution, transformers are one of the most vital components of the power system. Failures in transformers pose a significant threat to the stable operation of the power system and to societal production. Therefore, the safe and stable operation of transformers is of profound importance to ensuring power grid security. Real-time online sensing and diagnosis of transformer operating status can make power system operation safer, more reliable, more efficient, and more intelligent, laying a solid foundation for the digital transformation of the power grid.

[0003] Transformer overheat diagnosis is a crucial component of transformer fault diagnosis. Currently, online methods for diagnosing transformer overheating mainly fall into two categories: the first uses infrared image detection technology to monitor the temperature of the transformer and other equipment in the substation; the second, for oil-immersed power transformers, detects dissolved gases in the oil to estimate the likelihood of internal overheating. The accuracy of infrared temperature measurement is affected by factors such as ambient temperature and the distance between the measuring device and the measured equipment. Changes in ambient temperature and measuring distance significantly impact the accuracy of the system's temperature measurement. Currently, software algorithms are commonly used to correct infrared temperature images, which is computationally cumbersome and lacks effectiveness. Therefore, developing a simple and effective infrared temperature image correction method is essential.

[0004] Therefore, a method and system for correcting infrared temperature measurement images of transformer tank walls are needed. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method and system for correcting infrared temperature measurement images of transformer tank walls. The method utilizes temperature sensors arranged on the surface of the transformer tank to correct the infrared images, thus solving the problem of infrared images being easily affected by ambient temperature and shooting angle. The specific technical solution is as follows:

[0006] A method for correcting infrared thermography images of transformer tank walls includes the following steps:

[0007] Step S1: Acquire infrared thermography images of the transformer tank wall surface;

[0008] Step S2: Transform the acquired infrared temperature measurement image by adjusting the angle of the infrared temperature measurement image so that the four corners of the infrared temperature measurement image are aligned with the four vertices of the transformer, thus obtaining the transformed infrared temperature measurement image.

[0009] Step S3: Arrange several temperature sensors on the surface of the transformer tank wall to obtain the temperature at different locations on the surface of the transformer tank wall; Step S4: Extract the temperature corresponding to the location of the temperature sensor in the infrared temperature measurement image, and calculate the difference between the temperature sensor and the temperature at the corresponding location obtained by the temperature sensor to construct a temperature difference matrix.

[0010] Step S5: Interpolate the temperature difference matrix to obtain the interpolated temperature difference matrix of each pixel in the transformed infrared thermography image.

[0011] Step S6: Summing the transformed infrared temperature measurement image and the interpolated temperature difference matrix yields the corrected infrared temperature measurement image.

[0012] Preferably, step S2 specifically includes: identifying the four vertices of the infrared temperature measurement image, stretching and rotating the image so that the four corners of the infrared temperature measurement image are aligned with the four vertices of the transformer.

[0013] Preferably, the arrangement of several temperature sensors on the surface of the transformer tank wall in step S3 specifically involves:

[0014] A square temperature sensor array of n columns and m rows is arranged on the outer wall of the transformer tank. The distance between two adjacent columns of temperature sensors is the same, and the distance between two adjacent rows of temperature sensors is the same.

[0015] Preferably, the square temperature sensor array is arranged in 3 columns and 5 rows according to the positions of the three windings of the transformer, i.e., n=3, m=5. The 5 temperature sensors in each column are respectively arranged at the positions of 1 / 6, 1 / 3, 1 / 2, 2 / 3 and 5 / 6 from top to bottom on the outer wall of the transformer tank.

[0016] Preferably, in step S4, the square temperature sensor array acquires the temperature at different locations on the surface of the transformer tank wall to form a first temperature matrix T, as detailed below:

[0017]

[0018] T i,j The temperature value obtained by the temperature sensor in the i-th row and j-th column, i = 1, ..., m, j = 1, 2, ..., n;

[0019] The temperature corresponding to the location of the temperature sensor in the infrared thermometry image is extracted to form a second temperature matrix T', as follows:

[0020] T i,j 'This represents the temperature value in the infrared thermography image corresponding to the location of the temperature sensor in the i-th row and j-th column;

[0021] Temperature difference matrix

[0022] Preferably, step S5 includes dividing the infrared temperature measurement image of the transformer tank wall surface into regions, wherein the area surrounded by the square temperature sensor array is divided into the central region, the area directly surrounded by the horizontal extension lines of the straight lines where the temperature sensors on both sides are located and the area directly surrounded by the vertical extension lines of the straight lines where the temperature sensors on both sides are located are divided into the edge regions, and the remaining four corner regions of the infrared temperature measurement image of the transformer tank wall surface are divided into the four corner regions.

[0023] Preferably, the temperature difference at each position in the central region of the infrared thermography image corresponding to the temperature difference matrix is ​​calculated using a four-point linear interpolation method, as follows:

[0024] (1) Let the numbers and corresponding temperature difference values ​​of the four end temperature sensors of any rectangle within the central interval be (1, ΔT1) to (4, ΔT4), where ΔT k The temperature difference value is the value at the location of temperature sensor k in the central interval. ΔT1 and ΔT2 are in the same row of the temperature difference matrix, and ΔT1 and ΔT4 are in the same column of the temperature difference matrix; ΔT3 and ΔT2 are in the same column of the temperature difference matrix, and ΔT3 and ΔT4 are in the same row of the temperature difference matrix; temperature sensors 1 to 4 respectively constitute the four vertices of the corresponding rectangle in the central interval.

[0025] (2) Using the temperature differences ΔT1 and ΔT2 corresponding to temperature sensor 1 and temperature sensor 2 as the standard, linear interpolation calculation of the temperature difference at each point in the central interval is performed to obtain ΔT. 1-2 ;

[0026] (3) Using the temperature differences ΔT1 and ΔT2 corresponding to temperature sensors 1 and 3 as standards, linear interpolation is performed on the temperature differences at each point within the central interval to obtain ΔT. 1-3 ;

[0027] (4) Using the temperature differences ΔT1 and ΔT4 corresponding to temperature sensors 1 and 4 as standards, linear interpolation is performed on the temperature differences at each point within the central interval to obtain ΔT. 1-4 ;

[0028] (5) Using the temperature differences ΔT2 and ΔT3 corresponding to temperature sensors 2 and 3 as standards, linear interpolation calculations are performed on the temperature differences at each point within the central interval to obtain ΔT. 2-3 ;

[0029] (6) Using the temperature differences ΔT2 and ΔT3 corresponding to temperature sensors 2 and 4 as standards, linear interpolation calculations are performed on the temperature differences at each point within the central interval to obtain ΔT. 2-4 ;

[0030] (7) Using the temperature differences ΔT3 and ΔT4 corresponding to temperature sensors 3 and 4 as standards, linear interpolation calculations are performed on the temperature differences at each point within the central interval to obtain ΔT. 3-4 ;

[0031] (8) After completing steps (2) to (7), each point in the central interval, except for the four endpoints ΔT1 to ΔT4, can obtain six temperature difference values. Therefore, the temperature difference ΔT at each point is ΔT = (ΔT... 1-2 +ΔT 1-3 +ΔT 1-4 +ΔT 2-3 +ΔT 2-4 +ΔT 3-4 ) / 6.

[0032] A method and system for correcting infrared thermography images of transformer tank walls, applied to the method described, including:

[0033] The infrared image acquisition module is used to acquire infrared temperature measurement images of the transformer tank wall surface;

[0034] The infrared image transformation module is used to transform the acquired infrared temperature measurement image and adjust the angle of the infrared temperature measurement image so that the four corners of the infrared temperature measurement image are aligned with the four vertices of the transformer, thus obtaining the transformed infrared temperature measurement image.

[0035] The temperature sensor module is used to obtain the temperature at different locations on the surface of the transformer tank wall through a temperature sensor.

[0036] The temperature difference matrix construction module is used to calculate and construct a temperature difference matrix based on the temperature at different locations on the surface of the transformer tank wall obtained from the transformed infrared thermogram and the temperature sensor.

[0037] The temperature difference matrix interpolation module is used to perform linear interpolation on the temperature difference matrix, corresponding to the interpolated temperature difference matrix of each pixel in the transformed infrared thermography image.

[0038] The infrared image correction module is used to sum the transformed infrared temperature measurement image and the interpolated temperature difference matrix to obtain the corrected infrared temperature measurement image.

[0039] The infrared image acquisition module is connected to the infrared image transformation module; the infrared image transformation module and the temperature sensor module are respectively connected to the temperature difference matrix construction module.

[0040] The temperature difference matrix construction module, temperature difference matrix interpolation module, and infrared image correction module are connected in sequence.

[0041] Preferably, the infrared image acquisition module includes an infrared thermal imager.

[0042] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0043] This invention provides a method and system for correcting infrared temperature measurement images of transformer tank walls. The invention constructs a temperature difference matrix using a temperature sensor and the acquired infrared temperature measurement image of the transformer tank wall. For other areas of the transformer tank wall without temperature sensors, the temperature difference values ​​at the corresponding locations of the temperature sensors are linearly interpolated to obtain the temperature difference values ​​at each pixel location in the infrared temperature measurement image of the transformer tank wall. This allows for the correction of the acquired infrared temperature measurement image, improving its temperature accuracy. Attached Figure Description

[0044] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0045] Figure 1 This is a flowchart of the method of the present invention;

[0046] Figure 2 This is a schematic diagram of the layout of a square temperature sensor array;

[0047] Figure 3 This is a flowchart of the temperature difference interpolation process of the present invention;

[0048] Figure 4 This is a system schematic diagram of the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0051] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0052] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0053] Example 1:

[0054] like Figure 1 As shown, this embodiment provides a method for correcting infrared temperature measurement images of transformer tank walls, including the following steps:

[0055] Step S1: Acquire infrared temperature images of the transformer tank wall surface; specifically, these can be obtained using an infrared thermal imager.

[0056] Step S2: Transform the acquired infrared temperature measurement image by adjusting the angle of the infrared temperature measurement image so that the four corners of the infrared temperature measurement image are aligned with the four vertices of the transformer, thus obtaining the transformed infrared temperature measurement image; specifically, identify the four vertices of the infrared temperature measurement image, stretch and rotate the image so that the four corners of the infrared temperature measurement image are aligned with the four vertices of the transformer.

[0057] Step S3: Arrange several temperature sensors on the surface of the transformer tank wall to obtain the temperature at different locations on the surface of the transformer tank wall.

[0058] Specifically, several temperature sensors are arranged on the surface of the transformer tank wall:

[0059] An array of n columns and m rows of square temperature sensors is arranged on the outer wall of the transformer tank. The distance between adjacent columns and rows of temperature sensors is the same. For example... Figure 2 As shown, the square temperature sensor array is arranged in 3 columns and 5 rows according to the positions of the three windings of the transformer, that is, n=3, m=5. The 5 temperature sensors in each column are respectively arranged at the positions of 1 / 6, 1 / 3, 1 / 2, 2 / 3 and 5 / 6 from top to bottom on the outer wall of the transformer tank.

[0060] Step S4: Extract the temperature from the infrared temperature measurement image at the location of the temperature sensor, and calculate the difference between the temperature at the corresponding location obtained by the temperature sensor to construct a temperature difference matrix.

[0061] A square temperature sensor array acquires the temperature at different locations on the surface of the transformer tank wall to form a first temperature matrix T, as detailed below:

[0062]

[0063] T i,j The temperature value obtained by the temperature sensor in the i-th row and j-th column, i = 1, ..., m, j = 1, 2, ..., n;

[0064] The temperature corresponding to the location of the temperature sensor in the infrared thermometry image is extracted to form a second temperature matrix T', as follows:

[0065] T i,j 'This represents the temperature value of the pixel in the infrared temperature measurement image corresponding to the location of the temperature sensor in the i-th row and j-th column;

[0066] Temperature difference matrix Step S5: Interpolate the temperature difference matrix to obtain the interpolated temperature difference matrix for each pixel of the transformed infrared thermography image. Specific steps are as follows: Figure 3 As shown.

[0067] like Figure 2 As shown, the infrared temperature measurement image of the transformer tank wall surface is first divided into regions. The area surrounded by the square temperature sensor array is divided into the central region. The areas directly surrounded by the horizontal extension lines of the straight lines where the temperature sensors are located on both sides and the areas directly surrounded by the vertical extension lines of the straight lines where the temperature sensors are located on both sides are divided into the edge regions. The remaining four corner regions of the infrared temperature measurement image of the transformer tank wall surface are divided into the four corner regions.

[0068] The temperature difference matrix corresponds to the temperature differences at various locations within the central region of the infrared thermography image, calculated using a four-point linear interpolation method, as follows:

[0069] (1) Let the numbers and corresponding temperature difference values ​​of the four end temperature sensors of any rectangle within the central interval be (1, ΔT1) to (4, ΔT4), where ΔT k The temperature difference value is the value at the location of temperature sensor k in the central interval. ΔT1 and ΔT2 are in the same row of the temperature difference matrix, and ΔT1 and ΔT4 are in the same column of the temperature difference matrix; ΔT3 and ΔT2 are in the same column of the temperature difference matrix, and ΔT3 and ΔT4 are in the same row of the temperature difference matrix; temperature sensors 1 to 4 respectively constitute the four vertices of the corresponding rectangle in the central interval.

[0070] (2) Using the temperature differences ΔT1 and ΔT2 corresponding to temperature sensor 1 and temperature sensor 2 as the standard, linear interpolation calculation of the temperature difference at each point in the central interval is performed to obtain ΔT. 1-2 For example, the temperature difference at a point a distance r from the location of temperature sensor 1 is: ΔT 1-2 (r)=(ΔT2-ΔT1)*r / L, where L is the distance between temperature sensor 1 and temperature sensor 2, and the same applies below.

[0071] (3) Using the temperature differences ΔT1 and ΔT2 corresponding to temperature sensors 1 and 3 as standards, linear interpolation is performed on the temperature differences at each point within the central interval to obtain ΔT. 1-3 ;

[0072] (4) Using the temperature differences ΔT1 and ΔT4 corresponding to temperature sensors 1 and 4 as standards, linear interpolation is performed on the temperature differences at each point within the central interval to obtain ΔT. 1-4 ;

[0073] (5) Using the temperature differences ΔT2 and ΔT3 corresponding to temperature sensors 2 and 3 as standards, linear interpolation calculations are performed on the temperature differences at each point within the central interval to obtain ΔT. 2-3 ;

[0074] (6) Using the temperature differences ΔT2 and ΔT3 corresponding to temperature sensors 2 and 4 as standards, linear interpolation calculations are performed on the temperature differences at each point within the central interval to obtain ΔT. 2-4 ;

[0075] (7) Using the temperature differences ΔT3 and ΔT4 corresponding to temperature sensors 3 and 4 as standards, linear interpolation calculations are performed on the temperature differences at each point within the central interval to obtain ΔT. 3-4 ;

[0076] (8) After completing steps (2) to (7), each point in the central interval, except for the four endpoints ΔT1 to ΔT4, can obtain six temperature difference values. Therefore, the temperature difference ΔT at each point is ΔT = (ΔT... 1-2 +ΔT 1-3 +ΔT 1-4 +ΔT 2-3 +ΔT 2-4 +ΔT 3-4 ) / 6.

[0077] The temperature difference at each location within the edge region of the infrared thermography image corresponding to the temperature difference matrix is ​​calculated using the following steps:

[0078] 1) Based on the temperature difference value of the central interval, the temperature difference value of two vertices on the edge of the central interval is known. Based on the other temperature difference values ​​on the straight line where the temperature difference values ​​of these two vertices are located, the temperature difference values ​​of the other two vertices that form a rectangle with these two vertices are obtained by linear interpolation.

[0079] 2) Use the four-point linear interpolation method to perform linear interpolation on the remaining points in the edge interval, as detailed in steps (1) to (8) above.

[0080] The temperature difference matrix corresponds to the temperature difference at each position in the four corner intervals of the infrared thermography image, calculated using the following steps: After interpolation calculation of the temperature difference in the edge intervals, the temperature difference values ​​of the three adjacent vertices in the four corner intervals can be obtained. Then, the three-point linear interpolation method is used for interpolation calculation, as detailed in steps (2) to (5) above. The corresponding temperature difference ΔT = (ΔT 1-2 +ΔT 1-3 +ΔT 1-4 +ΔT 2-3 ) / 4.

[0081] By combining the temperature interpolations of each interval, the interpolated temperature difference matrix of each pixel in the corresponding infrared temperature measurement image can be obtained. Step S6: Summing the transformed infrared temperature measurement image and the interpolated temperature difference matrix yields the corrected infrared temperature measurement image.

[0082] Since the positions of each sensor in the square temperature sensor array are known, corresponding pixels in the infrared temperature measurement image correspond to their positions. Linear interpolation of the pixel positions in the corresponding infrared temperature measurement image based on the positions of two temperature sensors and their temperature difference is feasible. The interpolation between points is performed using a linear interpolation method, and the resulting temperature interpolations are averaged to reduce error and improve accuracy. For the four-point linear interpolation method, six different temperature interpolations can be obtained for each point within the interval, and the final temperature interpolation value for that point is the average of these six different temperature interpolations. For the three-point linear interpolation method, four different temperature interpolations can be obtained for each point within the interval, and the final temperature interpolation value for that point is the average of these four different temperature interpolations. Different fitting algorithms are used for different locations on the transformer tank wall to make the fitting results more reasonable and improve the diagnostic accuracy.

[0083] Example 2:

[0084] A method and system for correcting infrared thermography images of transformer tank walls, applied to the method described, including:

[0085] The infrared image acquisition module is used to acquire infrared temperature measurement images of the transformer tank wall surface; the specific principle is described in step S1 above. The infrared image transformation module is used to transform the acquired infrared temperature measurement images, adjusting the angle of the infrared temperature measurement images so that the four corners of the infrared temperature measurement images are aligned with the four vertices of the transformer, thus obtaining the transformed infrared temperature measurement images; the specific principle is described in step S2 above.

[0086] The temperature sensor module is used to obtain the temperature at different locations on the surface of the transformer tank wall through a temperature sensor; the specific principle is explained in step S3 above.

[0087] The temperature difference matrix construction module is used to calculate and construct a temperature difference matrix based on the transformed infrared temperature measurement image and the temperature obtained from the temperature sensor at different locations on the surface of the transformer tank wall; the principle is described in step S4 above.

[0088] The temperature difference matrix interpolation module is used to perform linear interpolation on the temperature difference matrix, corresponding to the interpolated temperature difference matrix of each pixel in the transformed infrared temperature measurement image; the principle is described in step S5 above.

[0089] The infrared image correction module is used to sum the transformed infrared temperature measurement image and the interpolated temperature difference matrix to obtain the corrected infrared temperature measurement image; the principle is described in step S6 above.

[0090] The infrared image acquisition module is connected to the infrared image transformation module; the infrared image transformation module and the temperature sensor module are respectively connected to the temperature difference matrix construction module.

[0091] The temperature difference matrix construction module, temperature difference matrix interpolation module, and infrared image correction module are connected in sequence. The infrared image acquisition module includes an infrared thermal imager.

[0092] Those skilled in the art will recognize that the modules of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0093] In the embodiments provided by this invention, it should be understood that the division of modules is only a logical functional division. In actual implementation, there may be other division methods, such as multiple modules can be combined into one module, one module can be split into multiple modules, or some features can be ignored.

[0094] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0095] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for correcting infrared thermographic images of a transformer tank wall, characterized in that, Includes the following steps: Step S1: Acquire infrared thermography images of the transformer tank wall surface; Step S2: Transform the acquired infrared temperature measurement image by adjusting the angle of the infrared temperature measurement image so that the four corners of the infrared temperature measurement image are aligned with the four vertices of the transformer, thus obtaining the transformed infrared temperature measurement image. Step S3: Arrange several temperature sensors on the surface of the transformer tank wall to obtain the temperature at different locations on the surface of the transformer tank wall; Step S4: Extract the temperature corresponding to the location of the temperature sensor in the infrared temperature measurement image, and calculate the difference between the temperature at the corresponding location obtained by the temperature sensor to construct a temperature difference matrix; Step S5 involves interpolating the temperature difference matrix to obtain the interpolated temperature difference matrix for each pixel of the transformed infrared temperature measurement image. This includes dividing the infrared temperature measurement image of the transformer tank wall surface into regions. The region enclosed by the square temperature sensor array is designated as the central region. The regions enclosed by the horizontal extensions of the straight lines containing the edge row temperature sensors and the vertical extensions of the straight lines containing the edge column temperature sensors are designated as edge regions. The remaining four corner regions of the infrared temperature measurement image of the transformer tank wall surface are designated as corner regions. The temperature difference at each position in the central region of the infrared temperature measurement image is calculated using a four-point linear interpolation method, as detailed below: (1) Let the numbering and corresponding temperature difference values ​​of the four end temperature sensors of any rectangle within the central interval be (1, ΔT1) ~ (4, ΔT4), where ΔT k Let ΔT1 and ΔT2 be the temperature difference values ​​at the location of temperature sensor k in the central interval. ΔT1 and ΔT2 are in the same row of the temperature difference matrix, and ΔT1 and ΔT4 are in the same column of the temperature difference matrix. ΔT3 and ΔT2 are in the same column of the temperature difference matrix, and ΔT3 and ΔT4 are in the same row of the temperature difference matrix. Temperature sensors 1 to 4 respectively constitute the four vertices of the corresponding rectangle in the central interval. (2) Using the temperature differences ΔT1 and ΔT2 corresponding to temperature sensor 1 and temperature sensor 2 as the standard, linear interpolation calculation of the temperature difference at each point in the central interval is performed to obtain ΔT. 1-2 ; (3) Using the temperature differences ΔT1 and ΔT2 corresponding to temperature sensor 1 and temperature sensor 3 as the standard, linear interpolation calculation of the temperature difference at each point in the central interval is performed to obtain ΔT. 1-3 ; (4) Using the temperature differences ΔT1 and ΔT4 corresponding to temperature sensors 1 and 4 as standards, linear interpolation is performed on the temperature differences at each point in the central interval to obtain ΔT. 1-4 ; (5) Using the temperature differences ΔT2 and ΔT3 corresponding to temperature sensors 2 and 3 as standards, linear interpolation is performed on the temperature differences at each point in the central interval to obtain ΔT. 2-3 ; (6) Using the temperature differences ΔT2 and ΔT3 corresponding to temperature sensors 2 and 4 as standards, linear interpolation is performed on the temperature differences at each point in the central interval to obtain ΔT. 2-4 ; (7) Using the temperature differences ΔT3 and ΔT4 corresponding to temperature sensors 3 and 4 as standards, linear interpolation is performed on the temperature differences at each point in the central interval to obtain ΔT. 3-4 ; (8) After completing steps (2) to (7), each point in the central interval except for the four endpoints ΔT1 to ΔT4 can obtain six temperature difference values. Then, the temperature difference ΔT at each point is equal to (ΔT). 1-2 +ΔT 1-3 + ΔT 1-4 +ΔT 2-3 +ΔT 2-4 +ΔT 3-4 ) / 6; Step S6: Summing the transformed infrared temperature measurement image and the interpolated temperature difference matrix yields the corrected infrared temperature measurement image.

2. The method for correcting infrared thermography images of transformer tank walls according to claim 1, characterized in that, Step S2 specifically includes: identifying the four vertices of the infrared temperature measurement image, stretching and rotating the image so that the four corners of the infrared temperature measurement image are aligned with the four vertices of the transformer.

3. The method for correcting infrared thermography images of transformer tank walls according to claim 1, characterized in that, In step S3, arranging several temperature sensors on the surface of the transformer tank wall specifically involves: n columns are arranged on the outer wall of the transformer tank. A square temperature sensor array with m rows, where the distance between adjacent columns of temperature sensors is the same, and the distance between adjacent rows of temperature sensors is the same.

4. The method for correcting infrared thermography images of transformer tank walls according to claim 3, characterized in that, The square temperature sensor array is arranged in 3 columns and 5 rows according to the positions of the three windings of the transformer, i.e., n=3, m=5. The 5 temperature sensors in each column are respectively arranged at the positions of 1 / 6, 1 / 3, 1 / 2, 2 / 3 and 5 / 6 from top to bottom on the outer wall of the transformer tank.

5. The method for correcting infrared thermography images of transformer tank walls according to claim 3, characterized in that, In step S4, the square temperature sensor array acquires the temperature at different locations on the surface of the transformer tank wall to form a first temperature matrix. The details are as follows: ； The temperature value obtained by the temperature sensor in the i-th row and j-th column. , ; Extract the temperature corresponding to the location of the temperature sensor from the infrared thermography image to form a second temperature matrix. The details are as follows: ； This is the temperature value in the infrared temperature measurement image corresponding to the location of the temperature sensor in the i-th row and j-th column; Temperature difference matrix .

6. A method and system for correcting infrared thermography images of transformer tank walls, characterized in that, The method applied to any one of claims 1 to 5 includes: The infrared image acquisition module is used to acquire infrared temperature measurement images of the transformer tank wall surface; The infrared image transformation module is used to transform the acquired infrared temperature measurement image and adjust the angle of the infrared temperature measurement image so that the four corners of the infrared temperature measurement image are aligned with the four vertices of the transformer, thus obtaining the transformed infrared temperature measurement image. The temperature sensor module is used to obtain the temperature at different locations on the surface of the transformer tank wall through a temperature sensor. The temperature difference matrix construction module is used to calculate and construct a temperature difference matrix based on the temperature at different locations on the surface of the transformer tank wall obtained from the transformed infrared thermogram and the temperature sensor. The temperature difference matrix interpolation module is used to perform linear interpolation on the temperature difference matrix, corresponding to the interpolated temperature difference matrix of each pixel in the transformed infrared thermography image. The infrared image correction module is used to sum the transformed infrared temperature measurement image and the interpolated temperature difference matrix to obtain the corrected infrared temperature measurement image. The infrared image acquisition module is connected to the infrared image transformation module; the infrared image transformation module and the temperature sensor module are respectively connected to the temperature difference matrix construction module. The temperature difference matrix construction module, temperature difference matrix interpolation module, and infrared image correction module are connected in sequence.

7. The method and system for correcting infrared temperature measurement images of a transformer tank wall according to claim 6, characterized in that, The infrared image acquisition module includes an infrared thermal imager.

Images