Cooling method and device based on local heat source distribution in transformer and electronic equipment

Abstract

The invention discloses a cooling method and device based on local heat source distribution in a transformer and electronic equipment, and relates to the field of electrical engineering. The method comprises the following steps: acquiring temperature data at a plurality of preset positions in the transformer; based on the temperature data, a three-dimensional temperature field model reflecting distribution characteristics of a heat source in the transformer is established, and the three-dimensional temperature field model comprises temperature distribution and heat conduction characteristic parameters in the transformer; calculating a space coordinate and a thermal power parameter of a local heat source in the transformer by using the three-dimensional temperature field model; according to the space coordinates and the thermal power parameters, a target cooling area of the transformer cooling system and corresponding cooling strength parameters are determined, and the cooling strength parameters comprise the flow, the flow velocity and the temperature of a cooling medium; and the working state of the transformer cooling system is controlled according to the cooling intensity parameter, so that the transformer cooling system cools the target cooling area. By implementing the technical scheme provided by the invention, the cooling effect is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and particularly to a cooling method, device and electronic device based on the local heat source distribution inside a transformer. Background Art

[0002] With the continuous growth of industrial automation and power demand, as an indispensable device in the power system, the stability and efficiency of transformers have received extensive attention. During the operation of a transformer, its internal components will generate heat due to the passage of current. If the heat cannot be effectively controlled, it will have a serious impact on the performance and lifespan of the transformer. Therefore, maintaining an appropriate temperature inside the transformer is the key to ensuring the reliable operation of the power system.

[0003] Currently, the cooling technology of transformers mainly relies on traditional air cooling or oil-immersed cooling systems, which often adopt a unified cooling strategy to cool all heat sources to the same extent. However, this method cannot effectively distinguish and target-cool heat sources at different positions and with different intensities inside the transformer, resulting in a low cooling effect.

[0004] Therefore, there is an urgent need for a cooling method, device and electronic device based on the local heat source distribution inside a transformer. Summary of the Invention

[0005] The present application provides a cooling method, device and electronic device based on the local heat source distribution inside a transformer, which improves the cooling effect.

[0006] In a first aspect of the present application, a cooling method based on the local heat source distribution inside a transformer is provided. The method includes: obtaining temperature data at multiple preset positions inside the transformer; based on the temperature data, establishing a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer, where the three-dimensional temperature field model includes the temperature distribution and heat conduction characteristic parameters inside the transformer; using the three-dimensional temperature field model to calculate the spatial coordinates and thermal power parameters of the local heat sources inside the transformer; according to the spatial coordinates and the thermal power parameters, determining the target cooling area and the corresponding cooling intensity parameters of the transformer cooling system, where the cooling intensity parameters include the flow rate, flow velocity and temperature of the cooling medium; and controlling the working state of the transformer cooling system according to the cooling intensity parameters, so that the transformer cooling system cools the target cooling area.

[0007] By adopting the above technical solution, by obtaining the temperature data at multiple preset positions inside the transformer and establishing a three-dimensional temperature field model reflecting the distribution characteristics of heat sources inside the transformer, the temperature distribution and heat conduction characteristics inside the transformer can be accurately described. Using this model to calculate the spatial coordinates and thermal power parameters of local heat sources inside the transformer can accurately locate and quantify the heat generation and accumulation areas inside the transformer. According to the spatial coordinates and thermal power parameters of the local heat sources, the target cooling area and the corresponding cooling intensity parameters of the transformer cooling system can be determined, realizing targeted cooling of high-temperature areas. By controlling the working state of the transformer cooling system according to the cooling intensity parameters, precise cooling of the hot spot area inside the transformer can be achieved, improving the cooling efficiency and extending the service life of the transformer. This method fully considers the actual temperature distribution and heat distribution inside the transformer, and through mathematical modeling, calculation analysis, and precise control, realizes the intelligentization of transformer cooling, improves the cooling effect, and ensures the safe and stable operation of the transformer.

[0008] Optionally, the establishing a three-dimensional temperature field model reflecting the distribution characteristics of heat sources inside the transformer based on the temperature data specifically includes: dividing the inside of the transformer into multiple cube units; establishing a three-dimensional geometric model of the inside of the transformer based on the finite element analysis method, and setting nodes corresponding to each of the cube units in the three-dimensional geometric model; calculating the temperature values at each of the nodes based on the temperature data to obtain a three-dimensional temperature distribution matrix of the inside of the transformer; establishing a partial differential equation for the temperature field distribution inside the transformer based on the three-dimensional temperature distribution matrix; and solving the partial differential equation to obtain a three-dimensional temperature field model reflecting the distribution characteristics of heat sources inside the transformer.

[0009] By adopting the above technical solution, by dividing the inside of the transformer into multiple cube units and setting nodes corresponding to the cube units in the three-dimensional geometric model, the temperature distribution inside the transformer can be discretized, facilitating subsequent numerical calculation and analysis. Establishing a three-dimensional geometric model of the inside of the transformer based on the finite element analysis method can accurately describe the structural characteristics and boundary conditions of the transformer. By calculating the temperature values at each node to obtain a three-dimensional temperature distribution matrix of the inside of the transformer, the temperature distribution inside the transformer can be comprehensively reflected. Establishing a partial differential equation for the temperature field distribution inside the transformer based on the temperature distribution matrix and solving this equation can obtain a three-dimensional temperature field model reflecting the distribution characteristics of heat sources inside the transformer. This model comprehensively considers factors such as the geometric structure, material properties, and boundary conditions inside the transformer, and can accurately describe the heat conduction process and temperature distribution law inside the transformer.

[0010] Optionally, calculating the spatial coordinates and thermal power parameters of the local heat source inside the transformer by using the three-dimensional temperature field model specifically includes: representing the three-dimensional temperature field model as a temperature function with respect to spatial coordinates; taking the gradient of the temperature function to obtain a temperature gradient function; based on Fourier's law of heat conduction, calculating the heat flux density vector at each node inside the transformer according to the temperature gradient function; performing a divergence calculation on the heat flux density vector to obtain the heat source power density function at each node inside the transformer; according to the heat source power density function, determining target nodes greater than or equal to a preset power density threshold, determining the spatial coordinates corresponding to the target nodes as the spatial coordinates of the local heat source, and determining the thermal power parameters corresponding to the target nodes as the thermal power parameters of the local heat source.

[0011] By adopting the above technical solution, representing the three-dimensional temperature field model as a temperature function with respect to spatial coordinates and taking the gradient of the temperature function can obtain a temperature gradient function reflecting the temperature change rate. Based on Fourier's law of heat conduction, using the temperature gradient function to calculate the heat flux density vector at each node inside the transformer can reveal the direction and intensity of heat transfer inside the transformer. Performing a divergence calculation on the heat flux density vector can obtain the heat source power density function at each node inside the transformer, reflecting the generation and consumption of heat inside the transformer. By determining target nodes greater than or equal to a preset power density threshold and taking the spatial coordinates and thermal power parameters corresponding to the target nodes as the attributes of the local heat source, the high-temperature areas and heat accumulation areas inside the transformer can be accurately located and quantified. This method makes full use of the temperature distribution information provided by the three-dimensional temperature field model and realizes the accurate positioning and quantitative description of the heat source inside the transformer through operations such as mathematical derivation, heat flow calculation, and threshold judgment, providing an important basis for subsequent cooling control.

[0012] Optionally, determining the target cooling area and the corresponding cooling intensity parameter of the transformer cooling system according to the spatial coordinates and the thermal power parameters specifically includes: based on the spatial coordinates and the thermal power parameters, performing a clustering analysis on the local heat source to obtain multiple heat source clustering centers and the heat load corresponding to each heat source clustering center; according to the spatial coordinates of each heat source clustering center, determining the cooling node closest to each heat source clustering center in the transformer cooling system and taking the cooling node as the cooling action point of the heat source clustering center; calculating the average heat load within a spherical area with each cooling action point as the center and a preset radius as the radius; determining the spherical area with the average heat load greater than the preset heat load threshold as the target cooling area of the transformer cooling system; for each target cooling area, calculating the cooling intensity parameter corresponding to the target cooling area according to the corresponding average heat load.

[0013] By adopting the above technical solution, clustering analysis is carried out based on the spatial coordinates and thermal power parameters of the local heat sources, so that the heat source distribution inside the transformer can be divided into several typical high-temperature regions, and each region is represented by a heat source clustering center. By calculating the heat loads of each heat source clustering center, the heat dissipation requirements of each high-temperature region can be quantitatively evaluated. According to the spatial coordinates of the heat source clustering center, the cooling node with the shortest distance is determined as the cooling action point in the transformer cooling system, and the spatial mapping relationship between the high-temperature region and the cooling system can be established. By calculating the average heat load within the spherical region centered on the cooling action point, the overall heat dissipation requirements of this region can be evaluated. The spherical region with an average heat load greater than the preset threshold is determined as the target cooling region of the transformer cooling system, and the regions that need to be cooled with emphasis inside the transformer can be identified. For each target cooling region, the corresponding cooling intensity parameter is calculated according to its average heat load, and the precise regulation of the cooling system for the high-temperature region can be realized. Through a series of operations such as clustering analysis, spatial mapping, and heat load calculation, this method transforms the complex heat source distribution into several typical high-temperature regions, determines the cooling requirements and cooling strategies for each region, and realizes the regional and refined control of transformer cooling.

[0014] Optionally, the clustering analysis of the local heat sources based on the spatial coordinates and the thermal power parameters to obtain a plurality of heat source clustering centers and the heat loads corresponding to each of the heat source clustering centers specifically includes: using the spatial coordinates of the local heat sources as the clustering feature vectors and the thermal power parameters as the clustering weights to construct a clustering sample set; clustering the clustering sample set to obtain a preset number of target clustering clusters; for each of the target clustering clusters, calculating the weighted average of the thermal power parameters of each sample point, and using the weighted average as the heat source clustering center of the target clustering cluster; for each of the target clustering clusters, calculating the sum of the thermal power parameters corresponding to each sample point to obtain the heat load.

[0015] By adopting the above technical solution, taking the spatial coordinates of the local heat source as the clustering feature vector and the thermal power parameter as the clustering weight to construct a clustering sample set, the position information and thermal power information of the heat source can be comprehensively considered, providing a complete data basis for clustering analysis. Clustering the clustering sample set to obtain a preset number of target clustering clusters can divide the heat source distribution inside the transformer into several representative high-temperature regions. For each target clustering cluster, calculating the weighted average of the thermal power parameters of the sample points as the heat source clustering center of the clustering cluster can obtain a central point that comprehensively reflects the heat source distribution characteristics of this region. By calculating the sum of the thermal power parameters of the sample points within each target clustering cluster, the total heat load of the clustering cluster can be obtained, quantitatively evaluating the heat dissipation requirement of this region. By constructing a clustering sample set, using a clustering algorithm to group the heat sources, and calculating the central points and total heat loads of each clustering cluster, the method realizes the extraction of regional characteristics and quantitative description of the heat source distribution inside the transformer, providing an important reference for the subsequent formulation of cooling strategies.

[0016] Optionally, the step of clustering the clustering sample set to obtain a preset number of target clustering clusters specifically includes: randomly extracting a preset number of sample points from the clustering sample set as the initial clustering centers; calculating the Euclidean distance between each sample point and each of the initial clustering centers, and dividing each of the sample points into the clustering cluster corresponding to the nearest initial clustering center; for each of the clustering clusters, calculating the weighted average of the thermal power of the sample points in the clustering cluster, and updating the weighted average of the thermal power as the new clustering center of the corresponding clustering cluster; performing iterative calculation on the new clustering centers to obtain a preset number of clustering clusters.

[0017] By adopting the above technical solution, by randomly extracting a preset number of sample points from the clustering sample set as the initial clustering centers, the clustering starting points can be evenly selected in the sample space, providing a reasonable initial value for the subsequent iterative optimization. Calculating the Euclidean distance between each sample point and the initial clustering center and dividing the sample points into the clustering cluster where the nearest clustering center is located can realize the preliminary grouping of the sample points. For each clustering cluster, calculating the weighted average of the thermal power of the sample points as the new clustering center can more accurately reflect the overall characteristics of the clustering cluster. By iteratively calculating the new clustering centers and continuously updating the belonging relationship of the sample points until a preset number of stable clustering clusters are obtained, the optimization and convergence of the clustering results can be realized. This method uses a clustering algorithm method to perform clustering analysis on the heat source sample set through iterative optimization, can effectively process large-scale and high-dimensional temperature data, obtain the typical regional division of the heat source distribution inside the transformer, and provide a regional decision-making basis for the subsequent cooling control.

[0018] Optionally, controlling the operating state of the transformer cooling system according to the cooling intensity parameter so that the transformer cooling system cools the target cooling area specifically includes: generating a control strategy for the transformer cooling system according to the cooling intensity parameters corresponding to each target cooling area, where the control strategy includes the start-stop states of each cooling unit, and control instructions for the flow rate, flow velocity, and temperature of the cooling medium; sending the control strategy to the transformer cooling system so that the transformer cooling system controls the start-stop states of each cooling unit according to the control strategy, and adjusts the flow rate, flow velocity, and temperature of the cooling medium.

[0019] By adopting the above technical solution, generating a control strategy for the transformer cooling system according to the cooling intensity parameters corresponding to each target cooling area can formulate a control plan for the cooling requirements of different areas. The control strategy includes key control instructions such as the start-stop states of each cooling unit, the flow rate, flow velocity, and temperature of the cooling medium, and can comprehensively guide the operation of the transformer cooling system. Sending the control strategy to the transformer cooling system can realize the remote transmission and execution of control instructions. The transformer cooling system controls the start-stop states of each cooling unit according to the received control strategy, and adjusts the flow rate, flow velocity, and temperature of the cooling medium, and can achieve precise control of the target cooling area. By dynamically adjusting the operating parameters of the cooling system, it can adapt to the change of the internal heat source distribution of the transformer and realize the optimization of the cooling effect. This method realizes the intelligent control of the transformer cooling system by generating and sending the control strategy, can flexibly adjust the cooling strategy according to the actual heat source distribution of the transformer, improves the cooling efficiency and energy utilization rate, and ensures the safe and stable operation of the transformer.

[0020] In the second aspect of the present application, a cooling device based on the local heat source distribution inside the transformer is provided. The device includes: an acquisition module and a processing module, where: the acquisition module is used to acquire temperature data at multiple preset positions inside the transformer; the processing module is used to establish a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer based on the temperature data, and the three-dimensional temperature field model includes the temperature distribution and heat conduction characteristic parameters inside the transformer; the processing module is further used to calculate the spatial coordinates and thermal power parameters of the local heat sources inside the transformer by using the three-dimensional temperature field model; the processing module is further used to determine the target cooling area and the corresponding cooling intensity parameters of the transformer cooling system according to the spatial coordinates and the thermal power parameters, where the cooling intensity parameters include the flow rate, flow velocity, and temperature of the cooling medium; the processing module is further used to control the operating state of the transformer cooling system according to the cooling intensity parameters so that the transformer cooling system cools the target cooling area.

[0021] In a third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, both the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the above method.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions, and when the instructions are executed, the above method is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By obtaining temperature data at multiple preset positions inside the transformer and establishing a three-dimensional temperature field model reflecting the internal heat source distribution characteristics of the transformer, the temperature distribution and heat conduction characteristics inside the transformer can be accurately described. Using this model to calculate the spatial coordinates and thermal power parameters of local heat sources inside the transformer can accurately locate and quantify the heat generation and accumulation areas inside the transformer. According to the spatial coordinates and thermal power parameters of the local heat sources, the target cooling area and corresponding cooling intensity parameters of the transformer cooling system can be determined, realizing targeted cooling of high-temperature areas. By controlling the working state of the transformer cooling system according to the cooling intensity parameters, precise cooling of the hot spot area inside the transformer can be achieved, improving the cooling efficiency and extending the service life of the transformer. This method fully considers the actual temperature distribution and heat distribution inside the transformer, and through mathematical modeling, calculation analysis, and precise control, realizes the intelligentization of transformer cooling, improves the cooling effect, and ensures the safe and stable operation of the transformer. Description of the Drawings

[0024] Figure 1 is a schematic flowchart of a cooling method based on the distribution of local heat sources inside a transformer disclosed in an embodiment of the present application; Figure 2 is a schematic block diagram of a cooling device based on the distribution of local heat sources inside a transformer disclosed in an embodiment of the present application; Figure 3 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

[0025] Description of the reference numerals: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Embodiments

[0026] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments.

[0027] In the description of the embodiments of this application, words such as "for example" or "for illustration" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for illustration" is intended to present the relevant concepts in a specific manner.

[0028] In the description of the embodiments of this application, the meaning of the term "a plurality of" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] This application provides a cooling method based on the local heat source distribution inside a transformer. Refer to Figure 1 , Figure 1 is a schematic flow chart of the cooling method based on the local heat source distribution inside a transformer provided by an embodiment of this application. This method is applied to a controller, and the controller is a controller that executes a cooling program based on the local heat source distribution inside a transformer. This method includes steps S101 to S105, and the above steps are as follows: Step S101: Obtain temperature data at multiple preset positions inside the transformer.

[0030] In step S101, the controller obtains the temperature data at multiple preset positions inside the transformer by communicating with the temperature sensors inside the transformer. Specifically, the controller first determines the preset positions inside the transformer, which are preset according to the structural characteristics and heat distribution characteristics of the transformer and cover key parts inside the transformer, such as the iron core, winding, oil tank, etc.

[0031] After determining the preset positions, the controller establishes a communication connection with the temperature sensors installed at these preset positions. The temperature sensors can be thermocouples, thermal resistors or other types of temperature measurement devices, capable of measuring the temperature values at their respective positions in real time. The controller collects temperature data from each temperature sensor at regular intervals according to a preset collection frequency through wired or wireless communication means. The preset collection frequency can be set according to actual needs. For example, it can be collected once every 1 minute, and this application does not limit this. After receiving the temperature data sent by the temperature sensors, the controller analyzes and stores the temperature data to obtain the temperature values at multiple preset positions inside the transformer at different times.

[0032] Step S102: Based on the temperature data, establish a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer. The three-dimensional temperature field model includes the temperature distribution and heat conduction characteristic parameters inside the transformer.

[0033] In step S102, based on the temperature data, establishing a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer specifically includes: dividing the inside of the transformer into multiple cubic units; based on the finite element analysis method, establishing a three-dimensional geometric model of the inside of the transformer and setting nodes corresponding to each cubic unit in the three-dimensional geometric model; based on the temperature data, calculating the temperature values at each node to obtain a three-dimensional temperature distribution matrix inside the transformer; based on the three-dimensional temperature distribution matrix, establishing a partial differential equation for the temperature field distribution inside the transformer; and solving the partial differential equation to obtain a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer.

[0034] Specifically, the controller divides the space inside the transformer and discretizes it into multiple cubic units. The sizes of these cubic units can be determined according to the size of the transformer and the required modeling accuracy. For example, the inside of the transformer can be divided into 10*10*10 cubic units, and the side length of each unit is 10 cm.

[0035] Then, the controller establishes a three-dimensional geometric model of the inside of the transformer based on the finite element analysis method. In the embodiments of this application, the finite element analysis can be understood as a numerical calculation method that transforms a complex continuous problem into a simple discrete problem for solution. The controller constructs a three-dimensional geometric model of the transformer according to the structural parameters of the transformer, such as the sizes and positions of the iron core, winding, oil tank, etc. In the three-dimensional geometric model, each cubic unit corresponds to a node, and the position coordinates of the node are the center coordinates of the cubic unit.

[0036] Next, the controller maps the collected temperature data to the nodes in the three-dimensional geometric model. Specifically, based on the position information of the temperature sensors, the controller assigns the measured temperature values to the corresponding nodes. For the nodes without temperature sensors, the controller estimates their temperature values using interpolation algorithms (such as linear interpolation, spline interpolation, etc.). Through this step, the controller obtains a three-dimensional temperature distribution matrix inside the transformer, and each element of the three-dimensional temperature distribution matrix corresponds to the temperature value of a node.

[0037] After obtaining the three-dimensional temperature distribution matrix, the controller establishes a partial differential equation for the temperature field distribution inside the transformer based on the heat conduction equation. The heat conduction equation describes the heat transfer process inside an object and takes into account thermal physical parameters such as the thermal conductivity, density, and specific heat capacity of the material. The controller substitutes these parameters into the heat conduction equation to obtain a partial differential equation for temperature, where the independent variable is the spatial coordinates of the nodes and the dependent variable is the temperature value of the nodes. The partial differential equation is: ; where T represents temperature, t represents time, (x, y, z) are the spatial coordinates of each node, α represents the thermal diffusivity of the material (thermal conductivity divided by density and specific heat capacity), Q represents the power density of the internal heat source, ρ represents the density of the material, and c represents the specific heat capacity of the material.

[0038] This equation indicates that the rate of temperature change inside the transformer is related to the temperature gradient at that point and the internal heat source (Q). Among them, the temperature gradient describes the rate of temperature change in space and reflects the direction and intensity of heat transfer inside the object.

[0039] Finally, the controller solves the above partial differential equation to obtain a three-dimensional temperature field model reflecting the distribution characteristics of the internal heat source of the transformer. Numerical methods such as the finite difference method and the finite element method can be used to solve the partial differential equation.

[0040] For example, assume that the thermal conductivity of the insulating oil inside the transformer is 0.15 W / (m·K), the density is 900 kg / m³, and the specific heat capacity is 2000 J / (kg·K). At a certain moment, the temperature distribution matrix inside the transformer is: T(x, y, z) = 80 + 0.01·x + 0.02·y + 0.03·z; where the units of x, y, and z are cm and the unit of T is °C.

[0041] Substituting these data into the heat conduction equation, we can get: =(0.15 / 900 / 2000)·(0.01² + 0.02² + 0.03²)+Q / 900 / 2000; After simplification: =1.17×10 -9+Q / 1800000 This partial differential equation describes the temperature change of the insulating oil inside the transformer. Among them, the temperature change rate is affected by the temperature gradient (1 + 4 + 9) and the internal heat source (Q). If the power density distribution of the internal heat source is known, this equation can be solved to obtain the law of temperature change over time.

[0042] Step S103: Use the three-dimensional temperature field model to calculate the spatial coordinates and thermal power parameters of the local heat source inside the transformer.

[0043] In step S103, using the three-dimensional temperature field model to calculate the spatial coordinates and thermal power parameters of the local heat source inside the transformer specifically includes: representing the three-dimensional temperature field model as a temperature function with respect to spatial coordinates; taking the gradient of the temperature function to obtain the temperature gradient function; based on Fourier's law of heat conduction, calculating the heat flux density vector at each node inside the transformer according to the temperature gradient function; performing divergence calculation on the heat flux density vector to obtain the heat source power density function at each node inside the transformer; according to the heat source power density function, determining the target nodes greater than or equal to the preset power density threshold, determining the spatial coordinates corresponding to the target nodes as the spatial coordinates of the local heat source, and determining the thermal power parameters corresponding to the target nodes as the thermal power parameters of the local heat source.

[0044] Specifically, the controller represents the three-dimensional temperature field model as a temperature function T(x, y, z) with respect to spatial coordinates (x, y, z), where x, y, and z are the three-dimensional spatial coordinates of each node inside the transformer; taking the gradient of the temperature function T(x, y, z) to obtain the temperature gradient function , expressed as: ; where , , are the partial derivatives of the temperature function T(x, y, z) in the x, y, and z directions respectively; then the controller calculates the heat flux density vector q(x, y, z) at each node inside the transformer according to Fourier's law of heat conduction, and the calculation formula is: ; where k is the thermal conductivity of the transformer insulation material; then the controller performs divergence calculation on the heat flux density vector q(x, y, z) to obtain the heat source power density function Q(x, y, z) at each node inside the transformer, and the calculation formula is: ; where is the Laplacian operator of the temperature function T(x, y, z); then, based on the heat source power density function Q(x, y, z), the controller locates the nodes where Q(x, y, z) is greater than the preset power density threshold Q 0 , determines the spatial coordinates (x, y, z) of these nodes as the spatial coordinates of the local heat source, and determines the corresponding Q(x, y, z) value as the thermal power parameter of the local heat source.

[0045] Specifically, the controller represents the three-dimensional temperature field model as a temperature function T(x, y, z) with respect to the spatial coordinates (x, y, z). This function describes the relationship between the temperature values of each node inside the transformer and their spatial positions. Then, the controller calculates the gradient of the temperature function T(x, y, z) to obtain the temperature gradient function . The temperature gradient represents the rate of change of temperature in space and reflects the direction and intensity of heat transfer. The gradient calculation can be achieved through the definition of partial derivatives, that is, by calculating the partial derivatives of the temperature function in the x, y, and z directions respectively , , .

[0046] Next, based on Fourier's law of heat conduction, the controller calculates the heat flux density vector q(x, y, z) at each node inside the transformer. Fourier's law of heat conduction describes the relationship between the heat flux density and the temperature gradient, that is, the direction of the heat flux density is opposite to the temperature gradient, and its magnitude is proportional to the product of the temperature gradient and the material's thermal conductivity. By substituting the temperature gradient function into Fourier's law of heat conduction, the controller obtains the spatial distribution of the heat flux density vector. After obtaining the heat flux density vector, the controller calculates its divergence to obtain the heat source power density function Q(x, y, z) at each node inside the transformer. Divergence calculation is used to measure the degree of convergence or divergence of a vector field in space and reflects the generation or consumption of heat in space. By taking the divergence of the heat flux density vector, the controller obtains the heat source power density function, which represents the rate of heat generation per unit volume.

[0047] Finally, based on the heat source power density function Q(x, y, z), the controller locates the nodes whose values are greater than the preset power density threshold Q 0 , determines the spatial coordinates of these nodes as the spatial coordinates of the local heat source, and determines the corresponding Q value as the thermal power parameter of the local heat source. The preset power density threshold Q 0 is set according to the design and operation requirements of the transformer and represents the abnormal level of the heat source power density. Through this step, the controller determines the local areas inside the transformer where significant heat is generated, that is, the location and intensity information of the local heat source.

[0048] For example, assume that the temperature function inside the transformer is T(x, y, z) = 50 + 0.01x² + 0.02y² + 0.03z², where the units of x, y, and z are cm and the unit of T is °C. The controller calculates the gradient of this function to obtain the temperature gradient function , and then according to Fourier's law of heat conduction, calculates the heat flux density vector q(x, y, z) = (-0.003x, -0.006y, -0.009z), where the thermal conductivity of the insulating material is 0.15 W / (m·K). Next, the controller calculates the divergence of the heat flux density vector to obtain the heat source power density function Q(x, y, z) = -0.00018, with the unit of W / cm³. Assume that the preset power density threshold is 0.0001 W / cm³. The controller finds the nodes where the Q value is greater than this threshold and discovers that the Q value at the node (10, 20, 30) is 0.00036 W / cm³, exceeding the threshold. Therefore, the controller determines the coordinates of this node as the spatial coordinates of the local heat source and determines its Q value as the thermal power parameter, obtaining a local heat source located at (10 cm, 20 cm, 30 cm) with a thermal power of 0.00036 W.

[0049] Step S104: Determine the target cooling area and the corresponding cooling intensity parameters of the transformer cooling system according to the spatial coordinates and the thermal power parameters. The cooling intensity parameters include the flow rate, flow velocity, and temperature of the cooling medium.

[0050] In step S104, according to the spatial coordinates and the thermal power parameters, determining the target cooling area and the corresponding cooling intensity parameters of the transformer cooling system specifically includes: performing clustering analysis on the local heat sources based on the spatial coordinates and the thermal power parameters to obtain multiple heat source clustering centers and the heat loads corresponding to each heat source clustering center; determining the cooling nodes in the transformer cooling system that are closest to each heat source clustering center according to the spatial coordinates of each heat source clustering center, and using the cooling nodes as the cooling action points of the heat source clustering center; calculating the average heat load within the spherical region with each cooling action point as the center and a preset radius; determining the spherical regions with an average heat load greater than the preset heat load threshold as the target cooling areas of the transformer cooling system; and calculating the cooling intensity parameters corresponding to the target cooling areas according to the corresponding average heat loads.

[0051] Specifically, the controller performs clustering analysis on the local heat sources using a clustering algorithm based on the spatial coordinates and the thermal power parameters of the local heat sources. The purpose of the clustering analysis is to group the local heat sources with similar spatial positions and similar thermal powers into one category to form heat source clustering centers. Through the clustering analysis, the controller can obtain multiple heat source clustering centers, and each heat source clustering center represents a high-temperature region. At the same time, the controller also calculates the total thermal power of the local heat sources included in each clustering center as the heat load of this clustering center.

[0052] Then, based on the spatial coordinates of each heat source clustering center, the controller locates the cooling node in the transformer cooling system that is closest to it. A cooling node refers to a key component in the cooling system responsible for heat transfer and exchange, such as coolers, fans, etc. By calculating the Euclidean distance between the heat source clustering center and the cooling node, the controller finds the cooling node closest to each clustering center and uses it as the cooling action point for that heat source clustering center. This step establishes the spatial mapping relationship between the high-temperature area and the cooling system.

[0053] Next, with each cooling action point as the center and a preset radius, the controller demarcates multiple spherical regions. These spherical regions represent the influence range of the cooling action points. The controller calculates the average heat load within each spherical region, that is, by summing the thermal powers of all local heat sources within the region and then dividing by the volume of the region. The average heat load reflects the heat density level within the region.

[0054] The controller determines the spherical regions with an average heat load greater than the preset heat load threshold as the target cooling regions of the transformer cooling system. The preset heat load threshold is set according to the design and operation requirements of the transformer, representing the demarcation standard for the high-temperature regions that need to be cooled intensively. Through this step, the controller identifies the regions inside the transformer that need to be cooled intensively, that is, the regions with a relatively high heat load level.

[0055] Finally, for each target cooling region, the controller calculates the required cooling intensity parameters according to its corresponding average heat load. The cooling intensity parameters include the flow rate, flow velocity, and temperature of the cooling medium. The controller establishes a quantitative relationship between the average heat load and the cooling intensity parameters through thermal engineering calculation formulas, such as Newton's law of cooling, Fourier's law of heat conduction, etc. By solving these formulas, the controller obtains the specific values of the flow rate, flow velocity, and temperature of the cooling medium required for each target cooling region. For each of the said target cooling regions, according to the corresponding average heat load Q 1 , calculate the cooling intensity parameters of this target cooling region, including the flow rate f of the cooling medium, the flow velocity v, and the temperature t. The calculation formulas are: f = α × Q 1 × V / c; v = β × Q 1 / (c × ρ); t = T - Q 1 / (h × A); where α and β are preset proportionality coefficients, c is the specific heat capacity of the cooling medium, V is the volume of the target cooling region, ρ is the density of the cooling medium, T is the initial oil temperature of the transformer tank, h is the heat transfer coefficient between the cooling medium and the tank, and A is the contact area between the target cooling region and the tank.

[0056] For example, assume that through cluster analysis, the controller obtains 3 heat source cluster centers inside the transformer, and their spatial coordinates are (10, 20, 30), (40, 50, 60), (70, 80, 90) respectively, with the unit being cm; the corresponding heat loads are 50W, 80W, and 120W respectively. The controller finds the cooling nodes closest to these cluster centers in the cooling system, which are located at (15, 25, 35), (45, 55, 65), (75, 85, 95) respectively, and uses them as the cooling action points. Then, the controller takes these cooling action points as the centers and a radius of 20 cm to delimit 3 spherical regions. After calculation, the average heat loads of these 3 spherical regions are 0.002 W / cm³, 0.003 W / cm³, and 0.005 W / cm³ respectively. Assume that the preset heat load threshold is 0.0025 W / cm³, then the controller determines the latter two spherical regions as the target cooling regions. For these two target cooling regions, the controller obtains the required cooling intensity parameters according to the thermal calculation formula: the first region requires a cooling medium flow rate of 2 m³ / h, a flow velocity of 1 m / s, and a temperature of 20 °C; the second region requires a cooling medium flow rate of 3 m³ / h, a flow velocity of 1.5 m / s, and a temperature of 15 °C.

[0057] In a possible implementation manner, based on the spatial coordinates and thermal power parameters, cluster analysis is performed on local heat sources to obtain multiple heat source cluster centers and the heat loads corresponding to each heat source cluster center, specifically including: using the spatial coordinates of the local heat sources as the cluster feature vectors and the thermal power parameters as the cluster weights to construct a cluster sample set; performing clustering on the cluster sample set to obtain a preset number of target clusters; for each target cluster, calculating the weighted average of the thermal power parameters of each sample point, and using the weighted average as the heat source cluster center of the target cluster; for each target cluster, calculating the sum of the thermal power parameters corresponding to each sample point to obtain the heat load.

[0058] Specifically, the controller uses the spatial coordinates of the local heat sources as the cluster feature vectors and the thermal power parameters as the cluster weights to construct a cluster sample set. The cluster feature vectors represent the positions of each local heat source in three-dimensional space and are the basic basis for performing cluster analysis. The cluster weights represent the magnitudes of the thermal powers of each local heat source and reflect their importance in the clustering process. By combining the spatial coordinates and thermal power parameters, the controller constructs a complete cluster sample set, providing a data basis for subsequent cluster analysis.

[0059] Then, the controller clusters the clustered sample set to obtain a preset number of target clustering clusters. The purpose of clustering is to group similar data points in the sample set into one category to form several clustering clusters. The controller can select an appropriate clustering algorithm according to actual needs and set the number of target clustering clusters. Through clustering analysis, the controller divides the local heat sources into several regions, and the heat sources within each region are relatively close in spatial position and thermal power.

[0060] Next, for each target clustering cluster, the controller calculates the weighted average of the thermal power parameters of each sample point and uses the weighted average as the heat source clustering center of the clustering cluster. The heat source clustering center represents the central position and average thermal intensity of the heat source distribution within each clustering cluster. By calculating the weighted average of the thermal power parameters of all sample points within the clustering cluster, the controller obtains a clustering center that comprehensively considers the spatial position and thermal power magnitude. This clustering center can represent the overall characteristics of the clustering cluster and is an important reference for subsequent analysis and decision-making.

[0061] Finally, for each target clustering cluster, the controller sums up the thermal power parameters corresponding to each sample point to obtain the heat load of the clustering cluster. The heat load represents the total heat generation level within each clustering cluster and reflects the overall heat dissipation demand of the region. By adding up the thermal powers of all local heat sources within the clustering cluster, the controller obtains the total heat load of the clustering cluster, providing a quantitative index for the subsequent design and optimization of the cooling system.

[0062] For example, assume that through heat source localization, the controller obtains 10 local heat sources inside the transformer, and their spatial coordinates and thermal power parameters are as follows: (10, 20, 30), 50W; (15, 25, 35), 60W; (20, 30, 40), 55W; (40, 50, 60), 80W; (45, 55, 65), 85W; (50, 60, 70), 90W; (70, 80, 90), 120W; (75, 85, 95), 110W; (80, 90, 100), 130W; (85, 95, 105), 125W.

[0063] The controller constructed a clustering sample set using the spatial coordinates of these 10 local heat sources as the clustering feature vectors and the thermal power parameters as the clustering weights. Then, the controller used the k-means algorithm to cluster the sample set into 3 target clustering clusters. After calculation, the controller obtained 3 heat source clustering centers, which were (17, 27, 37), (47, 57, 67), and (80, 90, 100) respectively, and their weighted average thermal powers were 58W, 88W, and 124W respectively. For each clustering cluster, the controller summed up the thermal power parameters of the internal sample points to obtain the heat loads of the 3 clustering clusters, which were 165W, 255W, and 385W respectively.

[0064] In a possible implementation manner, clustering the clustering sample set to obtain a preset number of target clustering clusters specifically includes: randomly extracting a preset number of sample points from the clustering sample set as the initial clustering centers; calculating the Euclidean distance between each sample point and each initial clustering center, and dividing each sample point into the clustering cluster corresponding to the nearest initial clustering center; for each clustering cluster, calculating the weighted average thermal power of the sample points in the clustering cluster, and updating the weighted average thermal power as the new clustering center of the corresponding clustering cluster; performing iterative calculation on the new clustering centers to obtain a preset number of clustering clusters.

[0065] Specifically, the controller randomly extracts a preset number of sample points from the clustering sample set as the initial clustering centers. The number of initial clustering centers is the number of target clustering clusters, which needs to be set according to the complexity of the internal heat source distribution of the transformer and the design requirements of the cooling system. Through the random extraction method, the controller evenly selects the initial clustering centers in the sample space, providing a starting point for subsequent clustering iteration.

[0066] Then, the controller calculates the Euclidean distance between each sample point and each initial clustering center. The Euclidean distance is a commonly used distance metric, which represents the straight-line distance between two points in a multi-dimensional space. By calculating the Euclidean distance between the sample point and the clustering center, the controller can measure the similarity between each sample point and each clustering cluster. The smaller the distance, the closer the sample point is to the clustering center, and the more likely it belongs to the same clustering cluster.

[0067] Next, the controller divides each sample point into the clustering cluster corresponding to the nearest initial clustering center. This step assigns the sample points to the most similar clustering cluster according to the calculation result of the Euclidean distance. In this way, the controller completes the preliminary division of the sample set and obtains several clustering clusters with the initial clustering centers as the core.

[0068] After obtaining the preliminarily divided clustering clusters, the controller calculates the weighted average of the thermal powers of all sample points in each clustering cluster. The weighted average of the thermal powers takes into account the thermal power differences of the sample points within the clustering cluster, and a comprehensive thermal power value of the clustering center is obtained through weighted calculation. Then, the controller updates this weighted average of the thermal powers as the new clustering center of the corresponding clustering cluster. Compared with the initial clustering center, the new clustering center can more accurately reflect the overall characteristics of the clustering cluster.

[0069] Finally, the controller performs iterative calculations on the new clustering centers, continuously repeating the above steps until a preset number of stable clustering clusters are obtained. In each iteration, the controller recalculates the Euclidean distance between the sample points and the new clustering centers, and re-divides the clustering clusters according to the distance. Then, the controller calculates the weighted average of the thermal powers of each clustering cluster again and updates it as the new clustering center. As the number of iterations increases, the clustering centers are continuously optimized, and the sample points within the clustering clusters become more and more compact, and finally converge to the target clustering clusters of the preset number.

[0070] For example, assume that the controller randomly selects 3 sample points as the initial clustering centers from a clustering sample set containing 100 local heat sources, which are (10, 20, 30), (40, 50, 60), and (70, 80, 90) respectively. Then, the controller calculates the Euclidean distance between each sample point and these 3 initial clustering centers, and divides the sample points into the clustering clusters where the nearest clustering center is located.

[0071] In the first iteration, the controller calculates the weighted average of the thermal powers of the sample points for each clustering cluster, and obtains new clustering centers, such as (15, 25, 35), (45, 55, 65), and (75, 85, 95). Then, the controller recalculates the Euclidean distance between the sample points and the new clustering centers, and re-divides the clustering clusters according to the distance.

[0072] The controller continuously repeats this process. After multiple iterations, 3 stable target clustering clusters are finally obtained, and their clustering centers are (18, 27, 38), (47, 58, 69), and (79, 88, 98) respectively. The sample points within these 3 clustering clusters are highly similar in spatial position and thermal power, representing 3 typical high-temperature regions inside the transformer.

[0073] In this way, the controller uses the k-means clustering algorithm to divide the complex local heat source sample set into the target clustering clusters of the preset number through iterative optimization. The sample points within each clustering cluster have similar spatial position and thermal power characteristics, representing a high-temperature region inside the transformer.

[0074] Step S105: Control the operating state of the transformer cooling system according to the cooling intensity parameter, so that the transformer cooling system cools the target cooling area.

[0075] In step S105, controlling the operating state of the transformer cooling system according to the cooling intensity parameter so that the transformer cooling system cools the target cooling area specifically includes: generating a control strategy for the transformer cooling system according to the cooling intensity parameters corresponding to each target cooling area, where the control strategy includes start-stop states of each cooling unit, control instructions for the flow rate, flow velocity, and temperature of the cooling medium; sending the control strategy to the transformer cooling system so that the transformer cooling system controls the start-stop states of each cooling unit according to the control strategy and adjusts the flow rate, flow velocity, and temperature of the cooling medium.

[0076] Specifically, the controller generates a control strategy for the transformer cooling system according to the cooling intensity parameters corresponding to each target cooling area. The controller takes these parameters as inputs and generates a complete control strategy for the cooling system through preset control algorithms and logics. The control strategy contains specific control instructions for each cooling unit of the cooling system, such as the start-stop state of the cooling unit, the set values of the flow rate, flow velocity, and temperature of the cooling medium, etc. Each cooling unit may be an independent cooling loop, including components such as coolers, pumps, valves, and fans, and is responsible for cooling a specific area. The controller determines the corresponding cooling unit according to the positions and cooling requirements of each target area and generates targeted control instructions.

[0077] For example, for a target area with a high heat load, the controller may instruct the corresponding cooling unit to increase the flow rate and flow velocity of the cooling medium to enhance the cooling effect; for a target area with a low heat load, the controller may reduce the working intensity of the corresponding cooling unit to save energy. At the same time, the controller also adjusts the temperature of the cooling medium according to the type of the cooling medium and the heat exchange efficiency to optimize the cooling process.

[0078] After generating the control strategy, the controller sends it to the transformer cooling system. Through communication interfaces and protocols, the controller establishes a connection with the cooling system and transmits the control strategy to the execution unit of the cooling system. The execution unit may be an integrated control module or distributed control nodes and is responsible for parsing and executing each instruction in the control strategy.

[0079] After receiving the control strategy, the transformer cooling system controls the working states of each cooling unit according to the content of the strategy. For the cooling units that need to be started, the cooling system sends start commands and monitors their operating states; for the cooling units that need to be stopped, the cooling system sends stop commands and ensures their safe shutdown. At the same time, the cooling system also adjusts the flow rate, flow velocity, and temperature of the cooling medium in each cooling unit according to the set values in the control strategy to meet the cooling requirements of different target areas.

[0080] For example, assume that the controller generates the following control strategy according to the cooling intensity parameters: Target area 1: Start cooling unit 1, set the cooling medium flow rate to 2 m³ / h, the flow velocity to 1 m / s, and the temperature to 20 °C. Target area 2: Start cooling unit 2, set the cooling medium flow rate to 3 m³ / h, the flow velocity to 1.5 m / s, and the temperature to 15 °C. Target area 3: Stop cooling unit 3. After the controller sends this control strategy to the transformer cooling system, the cooling system performs the following operations according to the content of the strategy: Start cooling unit 1 and adjust its cooling medium flow rate to 2 m³ / h, the flow velocity to 1 m / s, and the temperature to 20 °C. Start cooling unit 2 and adjust its cooling medium flow rate to 3 m³ / h, the flow velocity to 1.5 m / s, and the temperature to 15 °C. Stop the operation of cooling unit 3 and ensure its safe shutdown.

[0081] Referring to Figure 2 , the present application also provides a cooling device based on the local heat source distribution inside the transformer. This device is a controller, and the controller includes an acquisition module 201 and a processing module 202. The acquisition module 201 is used to acquire temperature data at multiple preset positions inside the transformer; the processing module 202 is used to establish a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer based on the temperature data. The three-dimensional temperature field model includes the temperature distribution and heat conduction characteristic parameters inside the transformer; the processing module 202 is also used to calculate the spatial coordinates and heat power parameters of the local heat sources inside the transformer using the three-dimensional temperature field model; the processing module 202 is also used to determine the target cooling area and the corresponding cooling intensity parameters of the transformer cooling system according to the spatial coordinates and heat power parameters. The cooling intensity parameters include the flow rate, flow velocity, and temperature of the cooling medium; the processing module 202 is also used to control the working state of the transformer cooling system according to the cooling intensity parameters so that the transformer cooling system cools the target cooling area.

[0082] In a possible implementation, the processing module 202 establishes a three-dimensional temperature field model reflecting the internal heat source distribution characteristics of the transformer based on the temperature data, specifically including: the processing module 202 divides the interior of the transformer into multiple cubic units; the processing module 202 establishes a three-dimensional geometric model of the interior of the transformer based on the finite element analysis method, and sets nodes corresponding to each cubic unit in the three-dimensional geometric model; the processing module 202 calculates the temperature values at each node based on the temperature data to obtain a three-dimensional temperature distribution matrix of the interior of the transformer; the processing module 202 establishes a partial differential equation for the temperature field distribution inside the transformer based on the three-dimensional temperature distribution matrix; the processing module 202 solves the partial differential equation to obtain a three-dimensional temperature field model reflecting the internal heat source distribution characteristics of the transformer.

[0083] Optionally, the processing module 202 uses the three-dimensional temperature field model to calculate the spatial coordinates and thermal power parameters of local heat sources inside the transformer, specifically including: the processing module 202 represents the three-dimensional temperature field model as a temperature function with respect to spatial coordinates; the processing module 202 takes the gradient of the temperature function to obtain a temperature gradient function; the processing module 202 calculates the heat flux density vector at each node inside the transformer based on Fourier's law of heat conduction according to the temperature gradient function; the processing module 202 calculates the divergence of the heat flux density vector to obtain the heat source power density function at each node inside the transformer; the processing module 202 determines the target nodes with a power density greater than or equal to the preset power density threshold according to the heat source power density function, determines the spatial coordinates corresponding to the target nodes as the spatial coordinates of the local heat source, and determines the thermal power parameters corresponding to the target nodes as the thermal power parameters of the local heat source.

[0084] Optionally, the processing module 202 determines the target cooling area and the corresponding cooling intensity parameters of the transformer cooling system according to the spatial coordinates and thermal power parameters, specifically including: the processing module 202 performs cluster analysis on the local heat sources based on the spatial coordinates and thermal power parameters to obtain multiple heat source cluster centers and the heat loads corresponding to each heat source cluster center; the processing module 202 determines the cooling node closest to each heat source cluster center in the transformer cooling system according to the spatial coordinates of each heat source cluster center, and uses the cooling node as the cooling action point of the heat source cluster center; the processing module 202 calculates the average heat load within a spherical area with each cooling action point as the center and a preset radius as the radius; the processing module 202 determines the spherical area with an average heat load greater than the preset heat load threshold as the target cooling area of the transformer cooling system; the processing module 202 calculates the cooling intensity parameters corresponding to the target cooling area according to the corresponding average heat load for each target cooling area.

[0085] Optionally, the processing module 202 performs clustering analysis on the local heat sources based on the spatial coordinates and heat power parameters to obtain multiple heat source clustering centers and the heat loads corresponding to each heat source clustering center. Specifically, the processing module 202 uses the spatial coordinates of the local heat sources as the clustering feature vectors and the heat power parameters as the clustering weights to construct a clustering sample set; the processing module 202 performs clustering on the clustering sample set to obtain a preset number of target clustering clusters; for each target clustering cluster, the processing module 202 calculates the weighted average of the heat power parameters of each sample point and uses the weighted average as the heat source clustering center of the target clustering cluster; for each target clustering cluster, the processing module 202 calculates the sum of the heat power parameters corresponding to each sample point to obtain the heat load.

[0086] Optionally, the processing module 202 performs clustering on the clustering sample set to obtain a preset number of target clustering clusters. Specifically, the processing module 202 randomly extracts a preset number of sample points from the clustering sample set as the initial clustering centers; the processing module 202 calculates the Euclidean distance between each sample point and each initial clustering center and divides each sample point into the clustering cluster corresponding to the nearest initial clustering center; for each clustering cluster, the processing module 202 calculates the weighted average of the heat power of the sample points in the clustering cluster and updates the weighted average of the heat power as the new clustering center of the corresponding clustering cluster; the processing module 202 performs iterative calculation on the new clustering centers to obtain a preset number of clustering clusters.

[0087] Optionally, the processing module 202 controls the working state of the transformer cooling system according to the cooling intensity parameters, so that the transformer cooling system cools the target cooling area. Specifically, the processing module 202 generates a control strategy for the transformer cooling system according to the cooling intensity parameters corresponding to each target cooling area. The control strategy includes the start-stop states of each cooling unit, the control instructions for the flow rate, flow velocity, and temperature of the cooling medium; the processing module 202 sends the control strategy to the transformer cooling system, so that the transformer cooling system controls the start-stop states of each cooling unit according to the control strategy and adjusts the flow rate, flow velocity, and temperature of the cooling medium.

[0088] It should be noted that when the device provided in the above embodiments realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be seen in the method embodiments, which will not be repeated here.

[0089] This application also provides an electronic device. Refer to Figure 3 , Figure 3It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0090] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0091] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0092] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface).

[0093] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one of the following hardware forms: Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0094] Among them, the memory 305 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , in the memory 305 as a computer storage medium, it may include an operating system, a network communication module, a user interface module, and an application program for the cooling method based on the local heat source distribution in the transformer.

[0095] In Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 301 can be used to call the application program for the cooling method based on the local heat source distribution in the transformer stored in the memory 305. When executed by one or more processors 301, the electronic device 300 is caused to execute the method as described in one or more of the above embodiments. It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0096] This application also provides a computer-readable storage medium, and the computer-readable storage medium stores instructions. When executed by one or more processors 301, the electronic device 300 is caused to execute the method as described in one or more of the above embodiments.

[0097] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] In several implementation manners provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0099] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of this application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0102] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth.

[0103] This application aims to cover any variations, uses, or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A cooling method based on local heat source distribution in a transformer, characterized in that: The method comprises: Obtain temperature data at multiple preset locations inside the transformer; Based on the temperature data, a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer is established, wherein the three-dimensional temperature field model includes temperature distribution and heat conduction characteristic parameters inside the transformer; Utilizing the three-dimensional temperature field model, calculating the spatial coordinates and thermal power parameters of the local heat source inside the transformer; Determine a target cooling area and a corresponding cooling intensity parameter of a transformer cooling system according to the spatial coordinates and the thermal power parameter, wherein the cooling intensity parameter includes a flow rate, a flow velocity and a temperature of a cooling medium; The working state of the transformer cooling system is controlled according to the cooling intensity parameter, so that the transformer cooling system can cool the target cooling area.

2. The method according to claim 1, characterized in that The three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer is established based on the temperature data, specifically including: Dividing the interior of the transformer into a plurality of cubic units; Based on the finite element analysis method, a three-dimensional geometric model inside the transformer is established, and nodes corresponding to each of the cubic units are set in the three-dimensional geometric model; Based on the temperature data, the temperature value at each of the nodes is calculated to obtain a three-dimensional temperature distribution matrix inside the transformer; Based on the three-dimensional temperature distribution matrix, a partial differential equation of the temperature field distribution inside the transformer is established; The partial differential equation is solved to obtain a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer.

3. The method according to claim 1, characterized in that The method of calculating the spatial coordinates and thermal power parameters of the local heat source inside the transformer by using the three-dimensional temperature field model specifically includes: Representing the three-dimensional temperature field model as a temperature function with respect to a spatial coordinate; Calculating the gradient of the temperature function to obtain a temperature gradient function; Based on Fourier's law of heat conduction, the heat flux density vector at each node inside the transformer is calculated according to the temperature gradient function; Performing divergence calculation on the heat flux density vector to obtain a heat source power density function at each node inside the transformer; According to the heat source power density function, a target node greater than or equal to a preset power density threshold is determined, the spatial coordinates corresponding to the target node are determined as the spatial coordinates of the local heat source, and the thermal power parameters corresponding to the target node are determined as the thermal power parameters of the local heat source.

4. The method according to claim 1, characterized in that: Determining the target cooling area and the corresponding cooling intensity parameter of the transformer cooling system according to the spatial coordinates and the thermal power parameter specifically includes: Based on the spatial coordinates and the thermal power parameters, cluster analysis is performed on the local heat source to obtain a plurality of heat source cluster centers and heat loads corresponding to each of the heat source cluster centers; According to the spatial coordinates of each of the heat source cluster centers, determining the cooling node in the transformer cooling system that is closest to each of the heat source cluster centers, and using the cooling node as the cooling action point of the heat source cluster center; Calculate the average heat load in a spherical area with each cooling action point as the center and a preset radius as the radius; Determine the spherical area where the average heat load is greater than a preset heat load threshold as the target cooling area of ​​the transformer cooling system; For each of the target cooling areas, a cooling intensity parameter corresponding to the target cooling area is calculated according to the corresponding average heat load.

5. The method according to claim 4, characterized in that The clustering analysis of the local heat source based on the spatial coordinates and the thermal power parameters to obtain a plurality of heat source cluster centers and the heat loads corresponding to each of the heat source cluster centers specifically includes: The spatial coordinates of the local heat source are used as clustering feature vectors, and the thermal power parameters are used as clustering weights to construct a clustering sample set; Clustering the clustering sample set to obtain a preset number of target clusters; For each of the target clusters, a weighted average value of the thermal power parameters of each sample point is calculated, and the weighted average value is used as the heat source cluster center of the target cluster; For each of the target clusters, the thermal power parameters corresponding to the sample points are calculated and summed to obtain the thermal load.

6. The method according to claim 5, characterized in that The clustering of the cluster sample set to obtain a preset number of target clusters specifically includes: Randomly selecting a preset number of sample points from the cluster sample set as initial cluster centers; Calculating the Euclidean distance between each sample point and each of the initial cluster centers, and dividing each of the sample points into a cluster corresponding to the initial cluster center closest to the sample point; For each of the clusters, calculating a weighted average value of thermal power of the sample points in the cluster, and updating the weighted average value of thermal power as a new cluster center of the corresponding cluster; The new cluster centers are iteratively calculated to obtain a preset number of clusters.

7. The method according to claim 1, characterized in that The controlling the working state of the transformer cooling system according to the cooling intensity parameter so that the transformer cooling system cools the target cooling area specifically includes: Generate a control strategy for the transformer cooling system according to the cooling intensity parameters corresponding to each target cooling area, wherein the control strategy includes control instructions for the start and stop status of each cooling unit, the flow rate, flow velocity and temperature of the cooling medium; The control strategy is sent to the transformer cooling system so that the transformer cooling system controls the start and stop states of each cooling unit according to the control strategy and adjusts the flow rate, flow velocity and temperature of the cooling medium.

8. A cooling device based on local heat source distribution in a transformer, characterized in that: The device comprises an acquisition module (201) and a processing module (202), wherein: The acquisition module (201) is used to acquire temperature data at multiple preset positions inside the transformer; The processing module (202) is used to establish a three-dimensional temperature field model reflecting the heat source distribution characteristics inside the transformer based on the temperature data, wherein the three-dimensional temperature field model includes the temperature distribution and heat conduction characteristic parameters inside the transformer; The processing module (202) is further used to calculate the spatial coordinates and thermal power parameters of the local heat source inside the transformer using the three-dimensional temperature field model; The processing module (202) is further used to determine a target cooling area and a corresponding cooling intensity parameter of the transformer cooling system according to the spatial coordinates and the thermal power parameter, wherein the cooling intensity parameter includes a flow rate, a flow velocity and a temperature of a cooling medium; The processing module (202) is further used to control the working state of the transformer cooling system according to the cooling intensity parameter, so that the transformer cooling system can cool the target cooling area.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images