CN113468762B

CN113468762B - Hot spot temperature calculation method, hot spot temperature calculation device, computer equipment and storage medium

Info

Publication number: CN113468762B
Application number: CN202110829389.0A
Authority: CN
Inventors: 刘继平; 周鑫; 陆汉东; 何洁明
Original assignee: Guangzhou Power Supply Bureau of Guangdong Power Grid Co Ltd
Current assignee: Guangzhou Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date: 2021-07-22
Filing date: 2021-07-22
Publication date: 2024-04-30
Anticipated expiration: 2041-07-22
Also published as: CN113468762A

Abstract

The application relates to a hot spot temperature calculation method, a hot spot temperature calculation device, computer equipment and a storage medium, which are suitable for the technical field of power systems. The method comprises the following steps: acquiring a temperature data matrix corresponding to a shell of a target transformer; constructing a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer; constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient state hot path model; and solving each temperature differential equation by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer. The method can accurately determine the hot spot temperature of the transformer, and further accurately determine whether the transformer has faults.

Description

Hot spot temperature calculation method, hot spot temperature calculation device, computer equipment and storage medium

Technical Field

The present application relates to the field of power systems, and in particular, to a method and apparatus for calculating a hotspot temperature, a computer device, and a storage medium.

Background

As the demand for energy by society continues to rise, transformers are also becoming increasingly important to power systems. The power transformer is used as power equipment widely applied to a power system, is a main component of safe transmission and economic distribution of electric energy, plays a vital role in safe and stable operation of the power system, and safe and reliable operation is an important guarantee of stable operation of the power system. However, during the use of the transformer, some faults usually occur, so that the content temperature of the transformer is increased, and if the content temperature of the transformer cannot be timely determined, the transformer is damaged, thereby affecting the whole power system.

In the conventional art, an infrared thermal imaging technology is generally used to acquire a temperature field of a transformer surface, and whether the transformer fails or not is determined according to the temperature field of the transformer surface.

However, in the above conventional techniques, the conventional infrared thermal imaging technique can only reflect the surface temperature field of the transformer, but cannot reflect the temperature distribution of the hot spot inside the transformer, and has certain limitations in use. Therefore, the transformer hot spot temperature cannot be accurately determined, and further, whether the transformer fails cannot be accurately determined.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a hot spot temperature calculating method, apparatus, computer device and storage medium, which are capable of accurately determining the hot spot temperature of a transformer, and further accurately determining whether the transformer fails.

In a first aspect, a hot spot temperature calculation method is provided, the method including: acquiring a temperature data matrix corresponding to a shell of a target transformer; constructing a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer; constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient state hot path model; and solving each temperature differential equation by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer.

In one embodiment, acquiring a temperature data matrix corresponding to a housing of a target transformer includes: acquiring an infrared thermal image corresponding to a shell of a target transformer; and preprocessing the infrared thermal image to obtain a temperature data matrix.

In one embodiment, preprocessing the infrared thermal image to obtain a temperature data matrix includes: carrying out gray scale treatment on the infrared thermal image by using a weighted average method to obtain a gray scale image after gray scale treatment; removing noise points in the gray image by using gray gradients in the neighborhood; performing edge detection on the gray level image with noise removed, and detecting the shell of the target transformer in the gray level image; calculating a temperature value corresponding to each pixel point according to a gray value corresponding to each pixel point in a gray image corresponding to the shell of the target transformer; and obtaining a temperature data matrix according to the temperature value corresponding to each pixel point.

In one embodiment, constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient thermal path model includes: calculating heat path parameters corresponding to the transient heat path model according to the internal connection structure and the heat flow direction of the transient heat path model; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the hot path parameters and the temperature data matrix.

In one embodiment, constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the hot path parameters and the temperature data matrix includes: determining whether a temperature data matrix is normal or not based on a preset temperature database; the preset temperature database comprises temperature data matrixes corresponding to the transformer in a normal state under various environments and load states; if the temperature data matrix is normal, acquiring center column data of the temperature data matrix; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters.

In one embodiment, solving each temperature differential equation by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer includes: and (3) carrying out iterative computation on each temperature differential equation by using a fourth-order Runge-Kutta algorithm with self-adaptive step length to obtain the temperature corresponding to each hot spot.

In one embodiment, performing iterative computation on each temperature differential equation by using a fourth-order finger-Kutta algorithm with an adaptive step length to obtain a temperature corresponding to each hot spot, including: setting an initialization step length of each temperature differential equation, and performing iterative computation for a plurality of times according to the initialization step length to obtain an initial result of each temperature differential equation; according to each initial result, adjusting the initialization step length until the iteration is preset for a preset number of times; and according to the adjusted initialization step length, calculating to obtain the temperature of the hot spot corresponding to the temperature differential equation.

In a second aspect, there is provided a hotspot temperature calculation apparatus, the apparatus comprising:

The acquisition module is used for acquiring a temperature data matrix corresponding to the shell of the target transformer;

The first construction module is used for constructing a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer;

The second construction module is used for constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient thermal path model;

And the solving module is used for solving each temperature differential equation by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer.

In a third aspect, there is provided a computer device comprising a memory storing a computer program and a processor implementing the hotspot temperature calculation method as described in any of the first aspects above when the computer program is executed by the processor.

In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a hotspot temperature calculation method as set forth in any of the first aspects above.

The hot spot temperature calculation method, the hot spot temperature calculation device, the computer equipment and the storage medium acquire a temperature data matrix corresponding to the shell of the target transformer; constructing a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer; constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient state hot path model; and solving each temperature differential equation by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer. Instead of directly taking the acquired temperature data matrix corresponding to the shell of the target transformer as each hot spot temperature of the target transformer. Therefore, according to the method, based on the temperature data matrix corresponding to the shell of the target transformer and the transient state hot path model corresponding to the target transformer, the temperature differential equation corresponding to each hot spot in the target transformer is constructed, and the accuracy of the constructed temperature differential equation corresponding to each hot spot can be ensured. In addition, each temperature differential equation is solved by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer, so that the calculated preset algorithm can be guaranteed to solve each temperature differential equation, the accuracy of the temperature corresponding to each hot spot of the target transformer is obtained, and whether the target transformer fails or not can be further guaranteed to be accurately determined.

Drawings

FIG. 1 is a flow chart of a method for calculating a hot spot temperature in one embodiment;

FIG. 2 is a schematic diagram of a transient hot path model in a hot spot temperature calculation method according to an embodiment;

FIG. 3 is a flow chart of a hot spot temperature calculation step in one embodiment;

FIG. 4 is a flow chart of a method for calculating a hot spot temperature according to another embodiment;

FIG. 5 is a flow chart of a method for calculating a hot spot temperature according to another embodiment;

FIG. 6 is a flow chart of a method for calculating a hot spot temperature according to another embodiment;

FIG. 7 is a flow chart of a method for calculating a hot spot temperature according to another embodiment;

FIG. 8 is a schematic diagram of a hot spot temperature response curve in a hot spot temperature calculation method according to another embodiment;

FIG. 9 is a flow chart of a method for calculating a hot spot temperature according to another embodiment;

FIG. 10 is a block diagram of a hot spot temperature calculation device according to one embodiment;

FIG. 11 is a block diagram of a hot spot temperature calculation device in one embodiment;

FIG. 12 is a block diagram of a hot spot temperature calculation device in one embodiment;

FIG. 13 is an internal block diagram of a computer device in one embodiment as a server;

Fig. 14 is an internal configuration diagram of a computer device in one embodiment when the computer device is a terminal.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

It should be noted that, the execution body of the method for calculating the hot spot temperature provided by the embodiment of the present application may be a device for calculating the hot spot temperature, where the device for calculating the hot spot temperature may be implemented as part or all of a computer device in a manner of software, hardware or a combination of software and hardware, where the computer device may be a server or a terminal, where the server in the embodiment of the present application may be a server or a server cluster formed by multiple servers, and the terminal in the embodiment of the present application may be a smart phone, a personal computer, a tablet computer, a wearable device, a child story machine, an intelligent robot, and other intelligent hardware devices. In the following method embodiments, the execution subject is a computer device.

In one embodiment of the present application, as shown in fig. 1, a hot spot temperature calculating method is provided, and the method is applied to a computer device for illustration, and includes the following steps:

Step 101, a computer device acquires a temperature data matrix corresponding to a shell of a target transformer.

Optionally, the computer device may receive a temperature data matrix corresponding to the housing of the target transformer sent by the other device.

Optionally, the computer device may further acquire a temperature of the housing of the target transformer using the sensor, and then generate a temperature data matrix corresponding to the housing of the target transformer according to the acquired temperature of the housing of the target transformer.

Step 102, the computer equipment builds a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer.

In particular, the computer device may obtain an internal structure of the target transformer, wherein the target transformer internal structure comprises the geometry of the internal core and windings. After the computer equipment obtains the internal structure of the target transformer, a transient state hot path model of the local hot spot region gridding of the target transformer can be constructed by taking a single-turn coil of the target transformer as a calculation unit and taking the local hot spot region temperature distribution of the shell of the target transformer as a boundary condition according to the heat transfer mode of the internal structure. Fig. 2 is a schematic diagram of a transient thermal path model of a target transformer.

And 103, constructing a temperature differential equation corresponding to each hot spot in the target transformer by the computer equipment based on the temperature data matrix and the transient state hot path model.

Specifically, after the transient state thermal path model of the target transformer is built, the computer equipment can determine the position of each hot spot in the target transformer according to the heat flow mode in the transient state thermal path model, and build a temperature differential equation corresponding to each hot spot in the target transformer according to the thermoelectric analogy theory and a temperature data matrix corresponding to the shell of the target transformer.

And 104, solving each temperature differential equation by using a preset algorithm by the computer equipment to obtain the temperature corresponding to each hot spot of the target transformer.

Specifically, after the computer device builds the temperature differential equation corresponding to each hot spot in the target transformer, the computer device may solve each temperature differential equation using a preset algorithm. The preset algorithm may be a preset algorithm constructed based on a neural network, or may be a preset algorithm constructed based on an optimization theory, and the preset algorithm is not specifically limited in the embodiment of the present application.

After the computer equipment builds a preset algorithm, each differential equation can be solved by using the preset algorithm, so as to obtain the temperature corresponding to each hot spot of the target transformer.

In the hot spot temperature calculation method, a temperature data matrix corresponding to the shell of the target transformer is obtained; constructing a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer; constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient state hot path model; and solving each temperature differential equation by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer. Instead of directly taking the acquired temperature data matrix corresponding to the shell of the target transformer as each hot spot temperature of the target transformer. Therefore, according to the method, based on the temperature data matrix corresponding to the shell of the target transformer and the transient state hot path model corresponding to the target transformer, the temperature differential equation corresponding to each hot spot in the target transformer is constructed, and the accuracy of the constructed temperature differential equation corresponding to each hot spot can be ensured. In addition, each temperature differential equation is solved by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer, so that the calculated preset algorithm can be guaranteed to solve each temperature differential equation, the accuracy of the temperature corresponding to each hot spot of the target transformer is obtained, and whether the target transformer fails or not can be further guaranteed to be accurately determined.

In one embodiment of the present application, as shown in fig. 3, the "obtaining the temperature data matrix corresponding to the housing of the target transformer" in the step 101 may include the following steps:

In step 301, a computer device obtains an infrared thermal image corresponding to a housing of a target transformer.

Specifically, the computer device may collect an infrared thermal image corresponding to the target transformer housing through a thermal infrared imager. The infrared thermal imager is arranged at the center of the shell opposite to the target transformer, and the distance between the infrared thermal imager and the left and right boundaries of the target transformer is equal to that between the infrared thermal imager and the upper and lower boundaries of the target transformer, so that the infrared thermal imager can completely shoot infrared thermal images of the shell of the target transformer opposite to the infrared thermal imager. The thermal infrared imager then transmits the thermal infrared image to the computer device via a network connection or a wired connection with the computer device.

In step 302, the computer device performs preprocessing on the infrared thermal image to obtain a temperature data matrix.

Specifically, the computer device may pre-process the infrared thermal image after the infrared thermal image is acquired. The preprocessing may include, but is not limited to, gray scale processing of the infrared thermal image, denoising of the infrared thermal image, region of interest identification of the infrared thermal image, and the like.

After the computer equipment preprocesses the infrared thermal image, a temperature data matrix is obtained according to the preprocessed infrared thermal image.

In the embodiment of the application, the infrared thermal image corresponding to the shell of the target transformer is obtained; the infrared thermal image is preprocessed to obtain a temperature data matrix, so that the obtained temperature data matrix can be ensured to be accurate, and the temperature of the target transformer shell can be represented.

In one embodiment of the present application, as shown in fig. 4, the step of preprocessing the ir thermal image to obtain a temperature data matrix in step 302 may include the following steps:

In step 401, the computer device performs gray-scale processing on the infrared thermal image by using a weighted average method, so as to obtain a gray-scale image after gray-scale processing.

Specifically, the computer device may perform gray scale processing on the obtained infrared thermal image, and convert the infrared thermal image into a gray scale image by using a weighted average method. The computer device may weight the red, green, and blue component values of each pixel of the infrared thermal image to calculate the pixel gray value using the following formula:

I(G_ij)＝a₁R(F_ij)+a₂G(F_ij)+a₃B(F_ij)；

a₁+a₂+a₃＝1；

Wherein G _ij is the I th row of the gray image, the j th column of the pixel, F _ij is the I th row of the infrared thermal image, the j th column of the pixel, I is the gray value of the pixel, R, G, B is the red, green and blue component values of the pixel, and a ₁、a₂、a₃ is the weighting weight, wherein, optionally, a ₁＝0.3,a₂＝0.6,a₃ =0.1. The value of a ₁、a₂、a₃ may be determined according to practical situations, and the value of a ₁、a₂、a₃ is not specifically limited in the embodiment of the present application.

In step 402, the computer device removes noise points in the gray image using the gray gradient in the neighborhood.

Specifically, the computer device may calculate the gray gradient GardI _k in each direction within the neighborhood of each pixel point G _ij in the gray image:

where n _k is the direction vector in the vicinity of the pixel point G _ij.

The computer device may compare the calculated gray gradient GardI _k with the first set threshold epsilon ₁, and determine whether each pixel point in the gray image is noise according to the comparison result.

Specifically, if the gray gradient GardI _k in each direction in the vicinity of the pixel point G _ij in the gray image is greater than the first set threshold epsilon ₁, namely:

GardI_k>ε₁，k＝1,2,…,8；

Then the pixel is determined to be a noise point, and the arithmetic mean of gray values of other pixels in the neighborhood is used to replace I (G _ij) with I (G' _ij): wherein epsilon ₁ can be set according to the actual situation, and the first preset threshold is not particularly limited in the embodiment of the present application.

In the formula, I (G ^k _ij) is a gray value of each direction in the vicinity of the pixel point G _ij.

In step 403, the computer device performs edge detection on the gray scale image after removing the noise point, and detects the shell of the target transformer in the gray scale image.

Specifically, after removing noise in the gray-scale image, the computer device may perform edge detection on the gray-scale image from which the noise points are removed using a preset detection algorithm. The preset algorithm may be an edge detection algorithm or other algorithms. The edge detection algorithm can comprise an edge operator method, a curved surface fitting method, a template matching method, a thresholding method, an edge detection method based on mathematical morphology, a wavelet transformation and wavelet packet transformation, an edge detection method based on fuzzy theory, an edge detection method based on a neural network, an edge detection algorithm based on fractal geometry and the like. The present application does not specifically limit the preset algorithm.

After the computer device performs edge detection on the gray image to obtain the outline of the target transformer shell in the gray image, the computer device can form a gray matrix G of the target transformer shell by using pixel points G _ij of the gray image in the outline of the target transformer shell, wherein the gray value of the pixel points G _ij is G _ij, namely the value corresponding to the matrix element:

in step 404, the computer device calculates a temperature value corresponding to each pixel according to the gray value corresponding to each pixel in the gray image corresponding to the housing of the target transformer.

Specifically, after the computer device obtains the gray value corresponding to each pixel point in the gray image corresponding to the shell of the target transformer, the computer device may set the highest temperature T _max corresponding to the maximum gray value and the lowest temperature T _min corresponding to the minimum gray value g _min according to the maximum gray value g _max.

After the computer device obtains the highest temperature T _max corresponding to the maximum gray value G _max and the minimum temperature T _min corresponding to the minimum gray value G _min, the computer device obtains a temperature value T _ij corresponding to a gray value G _ij of each pixel point G _ij in the gray image, where the temperature value T _ij is:

In step 405, the computer device obtains a temperature data matrix according to the temperature value corresponding to each pixel point.

Specifically, after obtaining the temperature value corresponding to each pixel point, the computer device obtains the transformer shell temperature data matrix T according to the temperature value corresponding to each pixel point.

In the implementation of the application, the computer equipment carries out gray scale processing on the infrared thermal image by using a weighted average method to obtain a gray scale image after gray scale processing; removing noise points in the gray image by using gray gradients in the neighborhood; performing edge detection on the gray level image with noise removed, and detecting the shell of the target transformer in the gray level image; calculating a temperature value corresponding to each pixel point according to a gray value corresponding to each pixel point in a gray image corresponding to the shell of the target transformer; and obtaining a temperature data matrix according to the temperature value corresponding to each pixel point. Therefore, the calculated temperature data matrix does not comprise temperature data except the target transformer shell, and noise is less, so that the accuracy of the calculated temperature data matrix is ensured.

In one embodiment of the present application, as shown in fig. 5, the "constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient thermal path model" in the step 103 may include the following steps:

In step 501, the computer device calculates a thermal path parameter corresponding to the transient thermal path model according to the internal connection structure and the heat flow direction of the transient thermal path model.

Specifically, the computer equipment takes a single-turn coil in the transient thermal circuit model as a calculation unit to calculate the temperatures of the parts such as each turn coil, the peripheral turn-to-turn insulation, the iron core and the like. According to the thermoelectric analogy theory, the load loss of the single-turn coil is equivalent to a direct current source with the output current of q1, the transmission of the load loss in the winding is equivalent through solid conduction thermal resistance Rs and solid heat capacity Cs, the heat transmitted to the surface of the winding is continuously transmitted in a convection heat transmission mode, and the heat is equivalent through external fluid convection thermal resistance Rl. The iron core is divided into hot-path grids with the same size as the coil, no-load loss of the iron core unit is equivalent to a direct current source with the output current of q2, the transmission of no-load loss in the iron core is equivalent through solid conduction thermal resistance Rs and solid heat capacity Cs, heat transmitted to the surface of the iron core is continuously transmitted in a convection heat transmission mode, and the heat is equivalent through external fluid convection thermal resistance Rl. The boundary node temperature of the transient thermal circuit model is determined by a transformer shell boundary temperature data matrix, and the transient thermal circuit model is equivalent to a direct current voltage source with the output voltage equal to the node temperature value.

The computer equipment calculates heat path parameters corresponding to the transient heat path model of the transformer by considering the nonlinear thermal resistance and heat capacity of the materials such as the coil and the insulation. Wherein, the solid conduction thermal resistance R _s is deduced from fourier law:

where δ is the coil thickness, a is the effective heat transfer area, and λ is the thermal conductivity.

The convective resistance of air, R _l, is derived from the Newton's cooling equation:

wherein A is an effective heat transfer area, h is a convective heat transfer coefficient, and h applies a similar principle and is calculated by means of dimensionless quantities:

wherein L is a characteristic size, nu is a Nu-Saint number, the movement state of the fluid is judged through a Rayleigh criterion R _a, and a calculation formula of the Rayleigh number is as follows.

Where G _r ^* is the modified Gellan number, P _r is the Planet number, G is the gravitational acceleration, β is the gas expansion coefficient, q _w is the winding heat flux density, ν is the air kinematic viscosity, and α is the thermal diffusivity.

Calculation formula of horizontal fluid-solid boundary knoop number:

Calculation formula of vertical solid boundary knoop number:

Heat capacity characterizes the performance of a dielectric material to store heat and charge and discharge heat:

C_th＝mc_p＝ρVc_p；

wherein c _p is specific heat capacity, and heat flow q is loss generated by the coil or the iron core unit:

Wherein Q is total loss, n represents n turns of coil, and m represents m segments of coil.

In step 502, the computer device constructs a temperature differential equation corresponding to each hot spot of the target transformer according to the hot path parameters and the temperature data matrix.

Specifically, after the thermal path parameters and the temperature data matrix are calculated, the computer device may construct a temperature differential equation corresponding to each hot spot of the target transformer according to the relationship between each thermal path parameter and the temperature data matrix.

In the embodiment of the application, the computer equipment calculates the heat path parameters corresponding to the transient heat path model according to the internal connection structure and the heat flow direction of the transient heat path model; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the hot path parameters and the temperature data matrix. Therefore, the accuracy of the temperature differential equation corresponding to each hot spot of the target transformer obtained through calculation can be ensured.

In one embodiment of the present application, as shown in fig. 6, the "constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the hot-path parameters and the temperature data matrix" in the step 502 may include the following steps:

In step 601, the computer device determines whether the temperature data matrix is normal based on a preset temperature database.

The preset temperature database comprises a plurality of temperature data matrixes corresponding to the transformer in a normal state under various environments and load states.

Specifically, the computer device may determine that the factors having the greatest influence on the temperature of each hot spot of the target transformer are the ambient temperature and the load factor, and the computer device obtains the temperature data matrix T' of the target transformer under different ambient temperatures and different load factors during normal operation, and establishes a corresponding preset temperature database.

The computer equipment can acquire an infrared thermal image of the target transformer running at the ambient temperature of 20 ℃ and under the rated load, obtain a corresponding temperature data matrix T at the ambient temperature of 20 ℃ and under the rated load after preprocessing, and compare the temperature data matrix T with the temperature data matrix T' when the target transformer runs normally at the ambient temperature of 20 ℃ and under the rated load, so as to determine whether the temperature data matrix is normal.

Optionally, the computer device may make a difference between the temperature value of each element in the temperature data matrix T and the temperature value of each element at the position corresponding to the temperature data matrix T', and calculate a modulus |Δgij| of the temperature difference between each element, where |Δgij| is smaller than the second set threshold epsilon ₂, that is:

The computer device determines that the temperature data matrix is normal. Wherein epsilon ₂ can be set according to the actual situation, and the second preset threshold is not particularly limited in the embodiment of the present application.

If |Δgij| is not less than the second set threshold ε ₂, the computer device determines that the temperature data matrix is abnormal.

In step 602, if the temperature data matrix is normal, the computer device obtains center column data of the temperature data matrix.

Specifically, under the condition that the temperature data matrix is normal, the temperature corresponding to the central column data is highest, and the temperature of the shell of the target transformer can be most reversely and positively set, so that the computer equipment acquires the temperature data of the central column of the temperature data matrix, and takes the temperature data of the central column of the temperature data matrix as a column matrix alpha, and takes the extracted column matrix alpha as a temperature boundary condition of the transient thermal path model.

Optionally, in the case of an anomaly of the temperature data matrix, the computer device acquires data of a central column and an anomaly column of the temperature data matrix, respectively. And taking the data of the central column as a temperature boundary condition of the transient state thermal path model, and taking the data of the abnormal column as a temperature abnormal condition of the transient state thermal path model.

In step 603, the computer device constructs a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters.

Specifically, under the condition that the temperature data matrix is normal, the computer equipment constructs a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters. And substituting the thermal resistance, the heat capacity and the heat flow in the calculated heat path parameters into a transient heat path model corresponding to a target transformer local hot spot area by the computer equipment, and if the target transformer hot spot is positioned on a winding ith row and jth column coil, expressing differential equations of the turn coil and peripheral turn-to-turn insulation temperature nodes thereof as follows by kirchhoff's law:

Wherein T _i,j is the coil temperature, T _i,j,1/2/3/4 is the turn-to-turn insulation temperature, R _{s,i,j,1/2/3/4} is the conduction thermal resistance, R _l,j,t/b、R_l,i,l/r is the convection thermal resistance, C _cu,i,j is the coil heat capacity, and C _{s,i,j,1/2/3/4} is the insulation heat capacity; and i=1, 2, …, m is the number of coil segments, j=1, 2, …, n is the number of coil turns, 1/2/3/4 is expressed as four directions, t/b is the top/bottom of the coil, and l/r is the left/right side of the coil. And (5) writing a differential equation set of each temperature node of the coil, the inter-turn insulation and the iron core according to a thermoelectric analogy theory.

Wherein T _i,j is coil temperature data, which is the data of the central column of the temperature data matrix, and the computer device brings the data of the central column of the temperature data matrix into each differential equation set, so as to calculate and obtain the temperature of each hot spot in the target transformer.

Specifically, under the condition that the temperature data matrix is normal, the computer equipment respectively substitutes the data of the central column and the abnormal column of the temperature data matrix into each differential equation set, calculates to obtain the temperature of each hot spot in the target transformer corresponding to the central column data and the temperature of each hot spot in the target transformer corresponding to the abnormal column, compares the temperature of each hot spot in the target transformer corresponding to the central column data with the temperature of each hot spot in the target transformer corresponding to the abnormal column, and determines the reason for the abnormality of the temperature data matrix of the target transformer.

In the embodiment of the application, the computer equipment determines whether a temperature data matrix is normal or not based on a preset temperature database; the preset temperature database comprises temperature data matrixes corresponding to the transformer in a normal state under various environments and load states; if the temperature data matrix is normal, acquiring center column data of the temperature data matrix; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters. Therefore, the accuracy of the temperature differential equation corresponding to each hot spot of the constructed target transformer is achieved.

In the embodiment of the present application, the "solving the temperature differential equation by using the preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer" in the step 104 may include the following:

the computer equipment carries out iterative computation on each temperature differential equation by utilizing a fourth-order Runge-Kutta algorithm with self-adaptive step length to obtain the temperature corresponding to each hot spot.

Specifically, the computer equipment performs iterative computation on each temperature differential equation by using a fourth-order Dragon-Kutta (Runge-Kutta) algorithm with self-adaptive step length to obtain the temperature corresponding to each hot spot. The Longer-Kutta (Runge-Kutta) method is a high-precision single-step algorithm widely applied in engineering. Because the algorithm has high precision, measures are taken to inhibit errors, and therefore, the implementation principle is also complex. The algorithm is built on the basis of mathematical support. The Longge-Kutta method has the advantages of high precision, convergence, stability (under certain conditions), step length change in the calculation process, no need of calculating high-order derivative and the like.

Therefore, in the embodiment of the application, the computer equipment calculates the temperature corresponding to each hot spot by changing the step length in the calculation process by using a fourth-order Runge-Kutta algorithm of the self-adaptive step length.

In the embodiment of the application, the temperature differential equations are subjected to iterative computation by using a fourth-order Runge-Kutta algorithm with self-adaptive step length, so as to obtain the temperature corresponding to each hot spot. The accuracy of the calculated temperatures of the hot spots is ensured.

In one embodiment of the present application, as shown in fig. 7, the above-mentioned "using the fourth-order range-Kutta algorithm of the adaptive step length to perform iterative calculation on each temperature differential equation to obtain the temperature corresponding to each hot spot" may include the following steps:

Step 701, setting an initialization step length of the temperature differential equation by the computer equipment according to each temperature differential equation, and performing iterative computation for a plurality of times according to the initialization step length to obtain an initial result of each temperature differential equation.

Specifically, for each temperature differential equation, the computer device may set an initialization step of the temperature differential equation according to an actual requirement, where the initialization step may be 0.5 or 0.2, and the embodiment of the present application does not specifically limit the initialization step.

After the initial step length is set, the computer equipment can utilize a fourth-order Runge-Kutta algorithm to carry out iterative computation for preset times according to the set initial step length, so as to obtain the initial result of each temperature differential equation. The preset times can be set according to actual demands, and can be tens or hundreds, and the implementation of the application does not limit the preset times specifically.

For example, the computer device sets an initial iteration step h=0.2, and calculates m=25 steps for the differential equation by a fourth-order ringe-Kutta method, so as to obtain a calculation result of 25 steps before iteration: y (1), y (2), …, y (25).

In step 702, the computer device adjusts the initialization step according to each initial result until after the preset iteration preset times.

Specifically, the computer device performs differential calculation on each initial result, determines the change rate of each initial result, and then adjusts the initialization step according to the change rate of each initial result.

Illustratively, the preset number of times is 25, and the computer device calculates the change rate of the derivative of the result of the previous 25 steps of iteration, namely the second derivative:

Defining a threshold epsilon ₃、ε₄ of the function differential change rate respectively, wherein 0< epsilon ₃<ε₄, and performing self-adaptive adjustment on the initial iteration step h:

After updating the iteration step h', continuing to calculate 25 steps, obtaining the results of the 26 th to 50 th steps of iteration by calculation, and calculating the differential change rate of the results of the 26 th to 50 th steps of iteration. And similarly, each calculation step is 25, the differential change rate of the calculation result is solved, the step length of iterative calculation is continuously updated, the self-adaptive change of the linearity of the iterative step length h with the function is satisfied, and the optimal step length of iterative calculation is continuously searched.

The threshold epsilon ₃、ε₄ of the change rate can be determined according to practical situations, and the threshold epsilon ₃、ε₄ of the change rate is not particularly limited in the embodiment of the application.

In step 703, the computer device calculates the temperature of the hot spot corresponding to the temperature differential equation according to the adjusted initialization step.

Specifically, after finishing the adjustment of the initialization step length, calculating according to the adjusted initialization step length to obtain the temperature of the hot spot corresponding to the temperature differential equation. And the computer equipment compares the transient temperature change trend of each node and acquires the position of the hot spot of the target transformer.

For example, the computer device may compare transient temperature change trends of the nodes, and obtain the location of the hot spot of the target transformer as the 4 th copper foil set at the center of the low-voltage winding of the target transformer, and the location is 87% from the bottom of the low-voltage winding.

As shown in fig. 8, the current hot spot temperature is 91.7 ℃ in the target transformer hot spot temperature response curve, and as shown in fig. 8, if the current operation condition is kept unchanged, it is estimated that the target transformer hot spot temperature will rise to 122.3 ℃.

In the embodiment of the application, aiming at each temperature differential equation, the computer equipment sets the initialization step length of the temperature differential equation, and performs iterative computation for a plurality of times according to the initialization step length to obtain the initial result of each temperature differential equation; according to each initial result, adjusting the initialization step length until the iteration is preset for a preset number of times; and according to the adjusted initialization step length, calculating to obtain the temperature of the hot spot corresponding to the temperature differential equation. Therefore, the temperature of each hot spot of the target transformer can be accurately calculated, the internal heating defect of the target transformer can be found in advance according to the temperature of each hot spot, transformer state maintenance is better realized, and the working performance of the target transformer is improved.

In order to better illustrate the hot spot temperature calculation method provided by the application, the embodiment of the application provides an overall flow chart of the hot spot temperature calculation method, which comprises the following steps:

In step 901, a computer device obtains an infrared thermal image corresponding to a housing of a target transformer.

In step 902, the computer device performs gray-scale processing on the infrared thermal image by using a weighted average method, so as to obtain a gray-scale image after gray-scale processing.

In step 903, the computer device removes noise points in the gray image using the gray gradient in the neighborhood.

In step 904, the computer device performs edge detection on the gray scale image after removing the noise points, and detects the shell of the target transformer in the gray scale image.

In step 905, the computer device calculates a temperature value corresponding to each pixel according to the gray value corresponding to each pixel in the gray image corresponding to the housing of the target transformer.

In step 906, the computer device obtains a temperature data matrix according to the temperature values corresponding to the pixel points.

In step 907, the computer device constructs a transient thermal path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer.

In step 908, the computer device calculates a thermal path parameter corresponding to the transient thermal path model according to the internal connection structure of the transient thermal path model and the heat flow direction.

In step 909, the computer device determines whether the temperature data matrix is normal based on the preset temperature database.

In step 910, if the temperature data matrix is normal, the computer device obtains center column data of the temperature data matrix.

In step 911, the computer device constructs a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters.

Step 912, for each temperature differential equation, the computer device sets an initialization step length of the temperature differential equation, and performs multiple iterative computations according to the initialization step length to obtain an initial result of each temperature differential equation.

Step 913, the computer device adjusts the initialization step according to each initial result until after the preset iteration preset times.

In step 914, the computer device calculates the temperature of the hot spot corresponding to the temperature differential equation according to the adjusted initialization step.

It should be understood that, although the steps in the flowcharts of fig. 1, 3-7, and 9 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps of fig. 1, 3-7, and 9 may include steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the steps or stages in other steps.

In one embodiment of the present application, as shown in fig. 10, there is provided a hot spot temperature calculating apparatus 1000, including: an acquisition module 1010, a first construction module 1020, a second construction module 1030, and a solution module 1040, wherein:

And an acquisition module 1010, configured to acquire a temperature data matrix corresponding to the housing of the target transformer.

The first construction module 1020 is configured to construct a transient thermal path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer.

The second construction module 1030 is configured to construct a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient thermal path model.

And the solving module 1040 is configured to solve each temperature differential equation by using a preset algorithm, so as to obtain temperatures corresponding to each hot spot of the target transformer.

In one embodiment of the present application, as shown in fig. 11, the obtaining module 1010 includes: an acquisition unit 1011 and a preprocessing unit 1012, wherein:

And an acquisition unit 1011 for acquiring an infrared thermal image corresponding to the case of the target transformer.

And the preprocessing unit 1012 is used for preprocessing the infrared thermal image to obtain a temperature data matrix.

In one embodiment of the present application, the preprocessing unit is specifically configured to perform gray-scale processing on the infrared thermal image by using a weighted average method, so as to obtain a gray-scale image after gray-scale processing; removing noise points in the gray image by using gray gradients in the neighborhood; performing edge detection on the gray level image with noise removed, and detecting the shell of the target transformer in the gray level image; calculating a temperature value corresponding to each pixel point according to a gray value corresponding to each pixel point in a gray image corresponding to the shell of the target transformer; and obtaining a temperature data matrix according to the temperature value corresponding to each pixel point.

In one embodiment of the present application, as shown in fig. 12, the second building block 1030 includes: a calculation unit 1031 and a construction unit 1032, wherein:

The calculating unit 1031 is configured to calculate a thermal path parameter corresponding to the transient thermal path model according to the internal connection structure of the transient thermal path model and the heat flow direction.

And the construction unit 1032 is used for constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the hot path parameters and the temperature data matrix.

In one embodiment of the present application, the construction unit 1032 is specifically configured to determine whether the temperature data matrix is normal based on a preset temperature database; the preset temperature database comprises temperature data matrixes corresponding to the transformer in a normal state under various environments and load states; if the temperature data matrix is normal, acquiring center column data of the temperature data matrix; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters.

In one embodiment of the present application, the solution module 1040 is specifically configured to perform iterative computation on each temperature differential equation by using a fourth-order range-Kutta algorithm with an adaptive step length, so as to obtain a temperature corresponding to each hot spot.

In one embodiment of the present application, the above-mentioned solving module 1040 is specifically configured to set an initialization step length of the temperature differential equation for each temperature differential equation, and perform multiple iterative computations according to the initialization step length to obtain an initial result of each temperature differential equation; according to each initial result, adjusting the initialization step length until the iteration is preset for a preset number of times; and according to the adjusted initialization step length, calculating to obtain the temperature of the hot spot corresponding to the temperature differential equation.

For specific limitation of the hot spot temperature calculation means, reference may be made to the limitation of the hot spot temperature calculation method hereinabove, and no further description is given here. The various modules in the hot spot temperature computing device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment of the present application, a computer device is provided, which may be a server, and when the computer device is a server, an internal structure diagram thereof may be as shown in fig. 13. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store hotspot temperature calculation data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a hot spot temperature calculation method.

In one embodiment of the present application, a computer device is provided, which may be a terminal, and when the computer device is a terminal, an internal structure diagram thereof may be as shown in fig. 14. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a hot spot temperature calculation method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structures shown in fig. 13 and 14 are merely block diagrams of portions of structures associated with aspects of the present application and are not intended to limit the computer device to which aspects of the present application may be applied, and that a particular computer device may include more or less components than those shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment of the application, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program: acquiring a temperature data matrix corresponding to a shell of a target transformer; constructing a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer; constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient state hot path model; and solving each temperature differential equation by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer.

In one embodiment of the application, the processor when executing the computer program further performs the steps of: acquiring an infrared thermal image corresponding to a shell of a target transformer; and preprocessing the infrared thermal image to obtain a temperature data matrix.

In one embodiment of the application, the processor when executing the computer program further performs the steps of: carrying out gray scale treatment on the infrared thermal image by using a weighted average method to obtain a gray scale image after gray scale treatment; removing noise points in the gray image by using gray gradients in the neighborhood; performing edge detection on the gray level image with noise removed, and detecting the shell of the target transformer in the gray level image; calculating a temperature value corresponding to each pixel point according to a gray value corresponding to each pixel point in a gray image corresponding to the shell of the target transformer; and obtaining a temperature data matrix according to the temperature value corresponding to each pixel point.

In one embodiment of the application, the processor when executing the computer program further performs the steps of: calculating heat path parameters corresponding to the transient heat path model according to the internal connection structure and the heat flow direction of the transient heat path model; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the hot path parameters and the temperature data matrix.

In one embodiment of the application, the processor when executing the computer program further performs the steps of: determining whether a temperature data matrix is normal or not based on a preset temperature database; the preset temperature database comprises temperature data matrixes corresponding to the transformer in a normal state under various environments and load states; if the temperature data matrix is normal, acquiring center column data of the temperature data matrix; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters.

In one embodiment of the application, the processor when executing the computer program further performs the steps of: and (3) carrying out iterative computation on each temperature differential equation by using a fourth-order Runge-Kutta algorithm with self-adaptive step length to obtain the temperature corresponding to each hot spot.

In one embodiment of the application, the processor when executing the computer program further performs the steps of: setting an initialization step length of each temperature differential equation, and performing iterative computation for a plurality of times according to the initialization step length to obtain an initial result of each temperature differential equation; according to each initial result, adjusting the initialization step length until the iteration is preset for a preset number of times; and according to the adjusted initialization step length, calculating to obtain the temperature of the hot spot corresponding to the temperature differential equation.

In one embodiment of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of: acquiring a temperature data matrix corresponding to a shell of a target transformer; constructing a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer; constructing a temperature differential equation corresponding to each hot spot in the target transformer based on the temperature data matrix and the transient state hot path model; and solving each temperature differential equation by using a preset algorithm to obtain the temperature corresponding to each hot spot of the target transformer.

In one embodiment of the application, the computer program when executed by the processor further implements the steps of: acquiring an infrared thermal image corresponding to a shell of a target transformer; and preprocessing the infrared thermal image to obtain a temperature data matrix.

In one embodiment of the application, the computer program when executed by the processor further implements the steps of: carrying out gray scale treatment on the infrared thermal image by using a weighted average method to obtain a gray scale image after gray scale treatment; removing noise points in the gray image by using gray gradients in the neighborhood; performing edge detection on the gray level image with noise removed, and detecting the shell of the target transformer in the gray level image; calculating a temperature value corresponding to each pixel point according to a gray value corresponding to each pixel point in a gray image corresponding to the shell of the target transformer; and obtaining a temperature data matrix according to the temperature value corresponding to each pixel point.

In one embodiment of the application, the computer program when executed by the processor further implements the steps of: calculating heat path parameters corresponding to the transient heat path model according to the internal connection structure and the heat flow direction of the transient heat path model; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the hot path parameters and the temperature data matrix.

In one embodiment of the application, the computer program when executed by the processor further implements the steps of: determining whether a temperature data matrix is normal or not based on a preset temperature database; the preset temperature database comprises temperature data matrixes corresponding to the transformer in a normal state under various environments and load states; if the temperature data matrix is normal, acquiring center column data of the temperature data matrix; and constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters.

In one embodiment of the application, the computer program when executed by the processor further implements the steps of: and (3) carrying out iterative computation on each temperature differential equation by using a fourth-order Runge-Kutta algorithm with self-adaptive step length to obtain the temperature corresponding to each hot spot.

In one embodiment of the application, the computer program when executed by the processor further implements the steps of: setting an initialization step length of each temperature differential equation, and performing iterative computation for a plurality of times according to the initialization step length to obtain an initial result of each temperature differential equation; according to each initial result, adjusting the initialization step length until the iteration is preset for a preset number of times; and according to the adjusted initialization step length, calculating to obtain the temperature of the hot spot corresponding to the temperature differential equation.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.

Claims

1. A method of hotspot temperature calculation, the method comprising:

acquiring a temperature data matrix corresponding to a shell of a target transformer;

constructing a transient state hot path model corresponding to the target transformer based on the internal structure and the heat transfer mode of the target transformer;

calculating heat path parameters corresponding to the transient heat path model according to the internal connection structure of the transient heat path model and the heat flow direction;

determining whether the temperature data matrix is normal or not based on a preset temperature database; the preset temperature database comprises temperature data matrixes corresponding to the transformer in a normal state under various environments and load states;

if the temperature data matrix is normal, acquiring center column data of the temperature data matrix;

Constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters; if the hot spot is located in the ith row and the jth column of coils of the windings in the target transformer, the temperature differential equation corresponding to the hot spot is expressed as follows by kirchhoff's law:

Wherein, T _i,j is the data of the central column of the temperature data matrix, T _i,j,1/2/3/4 is the turn-to-turn insulation temperature of the winding, R _{s,i,j,1/2/3/4} is the conduction thermal resistance, C _cu,i,j is the heat capacity of the coil, and C _{s,i,j,1/2/3/4} is the insulation heat capacity; and i=1, 2, …, m is the number of segments of the coil, j=1, 2, …, n is the number of turns of the coil, 1/2/3/4 is expressed as four directions, q is the loss generated by the coil;

and performing iterative computation on each temperature differential equation by using a fourth-order Runge-Kutta algorithm with self-adaptive step length to obtain the temperature corresponding to each hot spot.

2. The method of claim 1, wherein the obtaining a temperature data matrix corresponding to a housing of the target transformer comprises:

Acquiring an infrared thermal image corresponding to the shell of the target transformer;

And preprocessing the infrared thermal image to obtain the temperature data matrix.

3. The method of claim 2, wherein the preprocessing the infrared thermal image to obtain the temperature data matrix comprises:

carrying out gray scale processing on the infrared thermal image by using a weighted average method to obtain a gray scale image after gray scale processing;

removing noise points in the gray image by using gray gradients in the neighborhood;

Performing edge detection on the gray level image with noise removed, and detecting the shell of the target transformer in the gray level image;

calculating a temperature value corresponding to each pixel point according to a gray value corresponding to each pixel point in a gray image corresponding to the shell of the target transformer;

And obtaining the temperature data matrix according to the temperature value corresponding to each pixel point.

4. The method of claim 1, wherein the performing iterative computation on each temperature differential equation by using a fourth-order range-Kutta algorithm with an adaptive step length to obtain a temperature corresponding to each hot spot includes:

Setting an initialization step length of each temperature differential equation, and performing iterative computation for a plurality of times according to the initialization step length to obtain an initial result of each temperature differential equation;

according to each initial result, adjusting the initialization step length until the preset iteration preset times;

And according to the adjusted initialization step sizes, calculating to obtain the temperature of the hot spot corresponding to the temperature differential equation.

5. A hotspot temperature computing device, the device comprising:

The second construction module is used for calculating heat path parameters corresponding to the transient heat path model according to the internal connection structure of the transient heat path model and the heat flow direction; determining whether the temperature data matrix is normal or not based on a preset temperature database; the preset temperature database comprises temperature data matrixes corresponding to the transformer in a normal state under various environments and load states; if the temperature data matrix is normal, acquiring center column data of the temperature data matrix; constructing a temperature differential equation corresponding to each hot spot of the target transformer according to the central column data and the hot path parameters; if the hot spot is located in the ith row and the jth column of coils of the windings in the target transformer, the temperature differential equation corresponding to the hot spot is expressed as follows by kirchhoff's law:

And the solving module is used for carrying out iterative computation on each temperature differential equation by utilizing a fourth-order Runge-Kutta algorithm with self-adaptive step length to obtain the temperature corresponding to each hot spot.

6. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.

7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.