Power detection method, data processing method, and power detection device

Abstract

The application provides a power detection method, a data processing method and a power detection device. The method comprises the following steps: obtaining an operating parameter of a power equipment under a current working condition; inputting a target model, so that the target model outputs a first temperature of a power component of the power equipment; determining a correction coefficient based on the first temperature and a second temperature of the power component under a preset working condition; and correcting a first temperature field of the power component under the preset working condition by using the correction coefficient, to obtain a second temperature field of the power component under the current working condition.

Description

Technical Field

[0001] This application relates to the field of power detection, and more particularly to a power detection method, a data processing method, and a power detection device. Background Technology

[0002] The temperature of electrical components (such as windings, radiators, and casings) in power equipment (e.g., transformers, generators, turbines) is often a key indicator for assessing the degree of insulation aging and load capacity of the equipment. However, current technologies struggle to rapidly predict the temperature field of electrical components in power equipment such as transformers and engines. This is especially true for components with upper temperature limits; the inability to obtain temperature data quickly and promptly can lead to significant errors in subsequent diagnosis and testing, and even pose safety hazards. Summary of the Invention

[0003] In view of this, embodiments of this application provide at least one power detection method, a data processing method, and a power detection device.

[0004] The technical solution of this application embodiment is implemented as follows: This application provides a power detection method, including: obtaining the operating parameters of the power equipment under the current operating condition, inputting them into a target model, so that the target model outputs the first temperature of the power components of the power equipment; determining a correction coefficient based on the first temperature and the second temperature of the power components under a preset operating condition; and using the correction coefficient to correct the first temperature field of the power components under the preset operating condition to obtain the second temperature field of the power components under the current operating condition.

[0005] This application provides a data processing method, including: sampling within a range corresponding to the operating parameters of a power device to obtain at least one operating condition corresponding to the power device; at least one sampled value of the operating parameters corresponding to each operating condition, wherein the at least one operating condition includes a preset operating condition; simulating sample data corresponding to the at least one operating condition based on the physical model of the power device and the at least one operating condition; the sample data includes the operating parameters of the power device under the at least one operating condition, the temperature of the power components of the power device, and the correlation between the operating parameters and the temperature of the power components, wherein the sample data is used to train a target model, and the target model is used to output the first temperature of the power components according to the operating parameters of the power device under the current operating condition.

[0006] This application provides a power detection device, including: an output module for obtaining operating parameters of a power device under current operating conditions, inputting them into a target model, and causing the model to output a first temperature of the power components of the power device; a determination module for determining a correction coefficient based on the first temperature and a second temperature of the power components under preset operating conditions; and a correction module for using the correction coefficient to correct the first temperature field of the power components under preset operating conditions to obtain a second temperature field of the power components under current operating conditions.

[0007] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of this application. Attached Figure Description

[0008] Figure 1 This is a schematic diagram illustrating the implementation process of a power detection method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the implementation flow of a data processing method provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating the implementation process of a method for rapid prediction of the thermal state of transformer windings based on Gaussian process regression and temperature field mapping correction, provided in an embodiment of this application. Figure 4 This is a schematic diagram of the composition structure of a power detection device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the composition structure of a data processing device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of this application.

[0009] It should be noted that the terms "first" and "second" mentioned above are only used to distinguish between different options and do not represent the degree of superiority or inferiority of the options or their priority in the implementation process. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] In the following description, the terms "first / second / third" are used merely to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that "first / second / third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for descriptive purposes only and is not intended to limit the scope of this application. It should also be noted that, for ease of description, only the parts relevant to the application are shown in the accompanying drawings.

[0012] This application provides a power detection method applicable to electronic devices. The electronic device refers to a device with data processing capabilities, such as a server, laptop, tablet, desktop computer, smart TV, set-top box, or mobile device (e.g., mobile phone, portable video player, personal digital assistant, dedicated messaging device, portable gaming device). In implementation, the electronic device may also include a power device whose temperature field needs to be determined. Figure 1 As shown, the method includes the following steps S101 to S103: Step S101: Obtain the operating parameters of the power equipment under the current operating conditions, input them into the target model, and make the target model output the first temperature of the power components of the power equipment.

[0013] Here, electrical equipment is a core component of the power system, mainly including power generation equipment and power supply equipment. For example, it may include, but is not limited to, at least one of the following: power plant boilers, turbines (such as steam turbines, gas turbines, water turbines, etc.), generators, transformers, transmission lines, instrument transformers, etc.

[0014] Electrical components are equipment parts installed in electrical equipment. For example, in the case of a transformer, electrical components may include, but are not limited to, at least one of windings, iron core, radiator, and casing. Similarly, in the case of a generator, electrical components may include, but are not limited to, at least one of windings, iron core, fan, shaft, and casing.

[0015] The current operating condition refers to the operating condition of the power equipment at the current moment, reflecting the environmental and working conditions of the power equipment at that moment. In practice, the types and values ​​of operating parameters (such as ambient temperature, ambient humidity, equipment load, electromagnetic intensity, etc.) corresponding to different operating conditions can be the same or different.

[0016] The first temperature is the characteristic temperature of the electrical component to be measured. In practice, the first temperature may include, but is not limited to, the extreme and / or average temperature values ​​of the electrical component. For example, the first temperature may be the average temperature of a heat sink. Alternatively, the first temperature may be the minimum and maximum temperatures of the windings. Yet another example is that the first temperature may be the extreme and average temperatures of the casing.

[0017] It is understandable that for different electrical components of the same electrical equipment, the initial temperature of the electrical component under the same operating parameters may be different.

[0018] During implementation, the initial temperature of multiple electrical devices and / or multiple electrical components can be predicted using a target model.

[0019] Operating parameters are the working parameters of electrical equipment under operating conditions, used to reflect the workload and / or temperature characteristics of the equipment. It is understood that by obtaining the operating parameters of electrical equipment, the operating status of the equipment can be controlled or adjusted in a timely manner to improve work efficiency or safety.

[0020] The target model is a processing model with data processing capabilities, used to calculate the first temperature of the power equipment based on its operating parameters. For example, the target model may include, but is not limited to, at least one of regression models, neural network models, and deep learning models.

[0021] In some implementations, the target model can be obtained by training the processing model.

[0022] In some implementations, the target model can calculate the first temperature corresponding to the power component based on operating parameters.

[0023] In some implementations, the target model can be based on a mapping table between operating parameters and power component temperatures under different operating conditions. By looking up the table, the power component temperature corresponding to the operating parameters under the current operating condition can be used as the first temperature.

[0024] Step S102: Determine the correction coefficient based on the first temperature and the second temperature of the power component under the preset operating conditions.

[0025] Here, the preset operating condition is a pre-set benchmark operating condition used for comparison.

[0026] In some implementations, the preset operating conditions may be related to or unrelated to the current operating conditions.

[0027] Understandably, preset operating conditions serve as the basis for temperature conversion, providing a reference temperature for electrical components (a second temperature), and can be independent of the current operating conditions. For example, preset operating conditions could be the operating conditions under which the electrical equipment is in a suitable working environment. Alternatively, preset operating conditions could be the operating conditions under representative extreme conditions (such as cold environments, hot environments, light load environments, overload environments, etc.).

[0028] The preset operating condition can also be a condition that is similar to or the same as the current operating condition. In this way, by using the second temperature of the preset operating condition combined with the correction coefficient determined by the first temperature, it is more suitable for the scenario of correcting the temperature of the power components under the current operating condition.

[0029] The second temperature is a characteristic temperature of the power component obtained under preset operating conditions, and the power component corresponding to the second temperature is the same as that corresponding to the first temperature. There is a correlation between the second temperature and the operating parameters of the power equipment under preset operating conditions. In implementation, the second temperature can be obtained through sampling, empirical values, or simulation; this application does not limit this method.

[0030] The correction factor can be understood as the conversion factor between the temperature of the power component under the preset operating conditions and the temperature of the power component under the current operating conditions.

[0031] In some implementations, the correction factor is determined by scaling the second temperature and / or compensating for the second temperature.

[0032] For example, the difference between the second temperature and the first temperature can be determined as a correction factor.

[0033] For example, the scaling factor of the first temperature obtained by scaling the second temperature can be determined as the correction factor.

[0034] Step S103: Using a correction coefficient, the first temperature field of the power component under the preset operating conditions is corrected to obtain the second temperature field of the power component under the current operating conditions.

[0035] Here, the first temperature field represents the temperature distribution at various points on the power component under preset operating conditions, and the second temperature field represents the temperature distribution at various points on the power component under the current operating conditions. The temperatures in the first temperature field include the second temperature, and the temperatures in the second temperature field include the first temperature.

[0036] It is understandable that, since the first temperature and the second temperature represent the characteristic temperatures of the power components (the same local area or the whole) under the current operating conditions and the preset operating conditions, respectively, the correction coefficients obtained based on the first temperature and the second temperature can be used to convert the temperature distribution of the power components under the current operating conditions and the preset operating conditions, except for the more typical characteristic temperatures.

[0037] In this embodiment, a first temperature of the power component is obtained based on the operating parameters of the power equipment under the current operating condition using a target model. Further, a correction coefficient is obtained to convert the second temperature of the power component under a preset operating condition into the first temperature. Finally, the correction coefficient is used to correct the first temperature field of the power component under the preset operating condition to obtain the second temperature field of the power component under the current operating condition. In this way, by determining the conversion information (correction coefficient) between the characteristic temperature of the power component under the current operating condition (corresponding to the first temperature) and the preset operating condition (corresponding to the second temperature), and further utilizing the correction coefficient in conjunction with the temperature distribution of the power component under the preset operating condition, the temperature field conversion can be quickly achieved from a numerical perspective. This allows for the rapid acquisition of the temperature field information of the power component under the current operating condition, providing a timely and effective basis for subsequent equipment control and equipment diagnosis.

[0038] In some embodiments, step S102 may include step S111: Step S111: Map the second temperature to the first temperature through a linear transformation, and determine the first correction coefficient and the second correction coefficient.

[0039] Here, the first correction factor can be a factor used to scale the second temperature in the linear transformation, and the second correction factor can be a factor used to compensate for the second temperature in the linear transformation, and the first correction factor is not zero. For example, the first temperature can be the product of the second temperature and the first correction factor, plus the second correction factor.

[0040] In practice, when the first temperature (and the corresponding second temperature) includes multiple temperature values, the first correction factor and the second correction factor are common correction factors that enable the conversion of all multiple temperature values. For example, the first correction factor and the second correction factor that convert the multiple temperature values ​​corresponding to the second temperature to the multiple temperature values ​​corresponding to the first temperature can be obtained by solving a system of simultaneous equations.

[0041] Step S103 above may include the following step S112: Step S112: Using the first correction coefficient and the second correction coefficient, perform a linear transformation on the first temperature field to determine the second temperature field.

[0042] Here, the method for performing a linear transformation on the first temperature field is the same as the method for mapping the second temperature to the first temperature. This ensures that the second temperature field obtained based on the first and second correction coefficients has data consistency.

[0043] For example, for the first temperature field The second temperature field is obtained by performing a linear transformation. The process can be seen in the following formula (1): (1); in, and These represent the first correction factor and the second correction factor, respectively.

[0044] In this embodiment, a first temperature is obtained by linearly transforming a second temperature, and a second temperature field is obtained by linearly transforming the first temperature field using the corresponding first and second correction coefficients. This allows for the rapid acquisition of correction coefficients for temperature conversion between a preset operating condition and the current operating condition through a linear transformation with low computational complexity. Furthermore, this reduces computational costs while improving the speed and efficiency of converting the temperature field using correction coefficients to obtain the second temperature field.

[0045] In some embodiments, the first temperature includes a first temperature extreme value, and the second temperature includes a second temperature extreme value. Step S103 above may include the following step S121: Step S121: Using the correction coefficient, correct each temperature in the first temperature field except for the second temperature extreme value, and obtain each temperature in the second temperature field except for the first temperature extreme value.

[0046] Here, the first temperature field includes the second temperature extremum, and the second temperature field includes the first temperature extremum. After determining the correction coefficient, considering that the temperature extremum (first temperature extremum) of the power component under the current operating conditions has already been obtained, it is only necessary to correct the temperatures in the first temperature field excluding the temperature extremum (second temperature extremum). Finally, the temperature distribution formed by the corrected temperature and the first temperature extremum is determined as the second temperature field.

[0047] In this embodiment, extreme temperatures are used as characteristic temperatures for determining correction coefficients. This is because the measurement of extreme temperatures is less affected by data fluctuations, resulting in higher accuracy and reliability. Therefore, determining correction coefficients based on extreme temperatures, and then using these coefficients to correct other temperature values ​​to obtain a complete temperature field, improves the reliability and reference value of the correction coefficients, further enhancing the accuracy and reliability of the resulting second temperature field. It is understood that for power components with temperature limitations (such as upper and / or lower temperature limits), the solution in this embodiment can provide more reliable real-time temperature field information.

[0048] In some embodiments, the above-described power detection method may further include the following steps S131 to S133: Step S131: Obtain the first working condition parameter group corresponding to the current working condition.

[0049] Here, a working condition parameter group is a set of working condition parameters corresponding to a working condition, and each working condition parameter group includes at least one working condition parameter. The type of the working condition parameter in the first working condition parameter group corresponding to the current working condition is the same as the type of the working condition parameter in the second working condition parameter group corresponding to the preset working condition.

[0050] For example, the first set of operating condition parameters may include at least one of the following operating condition parameters: equipment load of the power equipment, ambient temperature, ambient humidity, electromagnetic intensity, electromagnetic interference, etc.

[0051] In implementation, typical operating condition parameters that affect the efficiency or safety of power equipment can be included as parameters in the operating condition parameter group. For example, ambient temperature can be used as an operating condition parameter for power equipment equipped with heat sinks. Similarly, electromagnetic interference can be used as an operating condition parameter for power equipment with transmission components.

[0052] Step S132: Determine the parameter range of at least one working condition parameter in the first working condition parameter group.

[0053] Here, the parameter range of some or all operating condition parameters in the operating condition parameter group can be determined.

[0054] In some implementations, the parameter ranges corresponding to different types of operating parameters in the operating parameter group can be pre-divided into multiple sub-ranges, and then, after obtaining the first operating parameter group, the sub-ranges in which each operating parameter is located can be determined.

[0055] For example, the load rate of electrical equipment can be divided into sub-ranges of 0.2 (i.e., 20%) to 1 (i.e., 100%), with each range being 0.2, and into sub-ranges of 0.1 (i.e., 1 to 1.5).

[0056] For example, the ambient temperature of the environment where the electrical equipment is located can be adjusted from -20 degrees Celsius ( ) to 40 degrees Celsius divided into 10 A subrange of a range.

[0057] Step S133: Determine the working condition corresponding to the second working condition parameter group that matches the parameter range as the preset working condition.

[0058] Here, the parameter range of the second working condition parameter group matches that of at least one working condition parameter in the first working condition parameter group, indicating that the preset working condition is similar to the current working condition, so the value of the working condition parameter in the second working condition parameter group is the same as or similar to the value of the working condition parameter in the first working condition parameter group.

[0059] For example, if there is at least one working condition parameter in the working condition parameter group to be determined, and the parameter range of the working condition parameter is the same as that of the corresponding working condition parameter in the first working condition parameter group, then the working condition parameter group can be considered as the second working condition parameter group, and the corresponding working condition is the preset working condition.

[0060] For example, if in the set of working condition parameters to be determined, there is at least one working condition parameter whose parameter range is adjacent to or overlaps with the parameter range of the corresponding working condition parameter in the first working condition parameter set, then the working condition parameter set can be considered as the second working condition parameter set, and the corresponding working condition is the preset working condition.

[0061] For example, if the parameter range of each working condition parameter in the working condition parameter group to be determined is the same as the parameter range of the corresponding working condition parameter in the first working condition parameter group, then the working condition parameter group can be considered as the second working condition parameter group, and the corresponding working condition is the preset working condition.

[0062] Understandably, when the operating condition parameter group includes multiple operating condition parameters, the higher the overlap between the parameter range of the operating condition parameters in the second operating condition parameter group and the parameter range of the operating condition parameters in the first operating condition parameter group, the closer the preset operating condition is to the current operating condition, and the higher the accuracy and reference value of the second temperature field obtained based on the second temperature corresponding to the preset operating condition and the first temperature field.

[0063] In this embodiment, by comparing the parameter ranges of the operating condition parameters in the operating condition parameter group, the operating condition corresponding to the second operating condition parameter group with a more matching parameter range is determined as the preset operating condition. This improves the correlation between the preset operating condition and the current operating condition based on the range of the operating condition parameters, thereby improving the accuracy of the second temperature field obtained by correcting the temperature of the power components under the preset operating condition and its adaptability to the current operating condition.

[0064] In some embodiments, each set of operating parameters includes a first operating parameter characterizing the load characteristics of the power equipment and a second operating parameter characterizing the thermal convection conditions in the environment where the power equipment is located. Step S132 may include the following step S141: Step S141: Determine the parameter range of the first working condition parameter in the first working condition parameter group.

[0065] Here, the first operating condition parameter characterizing the load characteristics of power equipment can be, but is not limited to, at least one of the following: equipment load rate, operating efficiency (such as the ratio between output power and input power), and response time. For example, a higher load rate indicates a larger load on the power equipment. Similarly, higher operating efficiency indicates higher energy conversion efficiency, suggesting a potentially smaller load. Furthermore, a shorter response time indicates a smaller scale of tasks to be executed or currently being executed, enabling timely responses to signals or instructions, and thus a potentially smaller load.

[0066] The second operating condition parameter characterizing the thermal convection conditions in the environment where the power equipment is located may include, but is not limited to, at least one of the following: ambient temperature, ambient convective heat transfer coefficient, fluid velocity (such as the speed of air, water, oil, etc. during thermal convection), and fluid parameters (such as fluid density, specific heat capacity, thermal conductivity, kinematic viscosity, etc.). For example, the higher the temperature of the environment where the power equipment is located, the more likely it is to overheat the power equipment or its electrical components. Similarly, the greater the fluid velocity in the environment where the power equipment is located, the more intense the heat exchange between the fluid and the surface of solids (such as air-cooled radiators, equipment casings), which also easily leads to overheating of the power equipment or its electrical components.

[0067] Understandably, by obtaining the first and second operating condition parameters, it is possible to better understand the load conditions and temperature change trends of the power equipment under its current operating conditions.

[0068] Step S133 above may include the following step S142: Step S142: Determine the working condition corresponding to the second working condition parameter group whose first working condition parameter is within the parameter range as the preset working condition.

[0069] Here, since the load condition of power equipment has a significant impact on the equipment's working efficiency and safety, when determining the preset operating conditions, priority can be given to whether the range of the first operating condition parameter in the second operating condition parameter group is closer to the current operating condition.

[0070] During implementation, the operating conditions corresponding to the second operating condition parameter group where the first and second operating condition parameters are within their respective parameter ranges can be defined as preset operating conditions. This can further improve the correlation between preset operating conditions and current operating conditions.

[0071] In this embodiment, the preset operating condition is determined by matching the parameter range of the first operating condition parameter characterizing the load characteristics of the power equipment with the operating condition corresponding to the first operating condition parameter in the first operating condition parameter group. This allows for the rapid determination of a preset operating condition close to the current operating condition based on the operating condition parameter characterizing the load characteristics of the power equipment. For example, when the data scale is limited and the changes in environmental thermal convection conditions are small, a preset operating condition more suitable for the current operating condition can be obtained based on the load condition of the power equipment.

[0072] This application provides a data processing method applicable to electronic devices. The electronic device refers to a device with data processing capabilities, such as a server, laptop, tablet, desktop computer, smart TV, set-top box, or mobile device (e.g., mobile phone, portable video player, personal digital assistant, dedicated messaging device, portable gaming device). In implementation, the electronic device may also include an electrical device with a temperature field to be determined. Figure 2 As shown, the method includes the following steps S201 to S202: Step S201: Sample within the range of the operating parameters of the power equipment to obtain at least one operating condition corresponding to the power equipment; each operating condition corresponds to at least one sampled value of the operating parameters, and the at least one operating condition includes a preset operating condition.

[0073] Here, the range of operating parameters can be preset values ​​determined based on the type of power equipment or equipment parameters, or empirical values.

[0074] During implementation, the methods for sampling operating parameters within the range may include, but are not limited to, random sampling, systematic sampling, and Latin Hypercube Sampling (LHS).

[0075] For example, random sampling can be performed within the overall range of operating parameters.

[0076] For example, the overall range of operating parameters can be divided into multiple sub-ranges, and sampling can be performed in each sub-range.

[0077] Step S202: Based on the physical model of the power equipment, simulate and obtain sample data corresponding to at least one operating condition; the sample data includes the operating parameters of the power equipment under at least one operating condition, the temperature of the power components of the power equipment, and the correlation between the operating parameters and the temperature of the power components. The sample data is used to train and obtain the target model. The target model is used to output the first temperature of the power components according to the operating parameters of the power equipment under the current operating condition.

[0078] Here, the physical model of the power equipment refers to its physical three-dimensional geometric model, including the structure of each power component. By constructing the physical model, the temperature of the power components can be simulated based on the operating parameters of the power equipment under different operating conditions.

[0079] For example, the finite volume method can be used to perform fluid-thermal coupled multiphysics calculations to solve the energy, momentum, and mass conservation equations, thereby obtaining temperature field information of power components under various operating conditions.

[0080] During implementation, the types and number of operating parameters can be dynamically adjusted or selected as needed, and this application embodiment does not limit this.

[0081] For example, based on the ease of obtaining the parameters, the parameters that are easier to obtain can be selected as the running parameters from a variety of parameters.

[0082] For example, parameters related to the monitoring, condition assessment, and / or operation and maintenance of power equipment can be used as operating parameters.

[0083] Understandably, when the operating conditions determined by sampling parameter values ​​include preset operating conditions, the target model can be trained using sample data under the preset operating conditions as a correction benchmark, which can further improve the accuracy of correcting the temperature field under the preset operating conditions to obtain the temperature field under the current operating conditions.

[0084] During implementation, for each operating condition, the sample data can be a set of operating parameters of the power equipment corresponding to that operating condition, as well as the temperature of the power components.

[0085] In this embodiment, by sampling within the range corresponding to the operating parameters of the power equipment, at least one operating condition corresponding to the sampled value is obtained. Furthermore, combined with the physical model of the power equipment, simulation is performed to obtain sample data for training the target model, which reflects the correlation between operating parameters and the temperature of power components under each operating condition. Thus, on the one hand, by sampling the operating parameters to determine one operating condition including preset operating conditions, the sampling method can be flexibly selected according to the usage scenario of the power equipment (at least including the usage scenario corresponding to the preset operating condition), improving the practicality of the sample data and thus improving the usability of the target model trained based on the sample data. On the other hand, simulation based on the physical model of the power equipment can improve the reliability of the simulation results (sample data), thereby improving the reliability of the target model trained based on the sample data.

[0086] In some embodiments, the operating parameters include a first operating parameter characterizing the load characteristics of the power equipment and a second operating parameter characterizing the temperature characteristics of at least one sampling feature point during the operation of the power equipment.

[0087] Here, the first operating parameter may include the equipment load status of the power equipment, such as the load rate, operating efficiency, whether it is overloaded, whether it is lightly loaded, etc.

[0088] The sampling feature points are those that can reflect the temperature characteristics of the power equipment during operation. In implementation, the location and number of sampling feature points can be dynamically adjusted and selected according to needs, and this application embodiment does not limit this.

[0089] For example, the second operating parameter may include the casing temperature of the electrical equipment, which is readily available.

[0090] For example, the second operating parameter may include characteristic temperatures related to insulation indicators, such as the top layer oil temperature of the insulating fluid (insulating oil) for electrical equipment.

[0091] In some implementations, the number of sampling feature points of the same type can be multiple, thereby reducing the impact of data fluctuations or sampling errors. For example, when the second operating parameter is the temperature of the power equipment casing, multiple locations can be selected for temperature measurement to obtain multiple temperature values ​​at multiple measurement points (sampling feature points). Alternatively, multiple samples can be taken from the same measurement point to obtain multiple temperature values.

[0092] In this embodiment, the operating parameters include a first operating parameter characterizing the load characteristics of the power equipment and a second operating parameter characterizing the temperature characteristics of at least one sampled feature point during the operation of the power equipment. This allows the sample data to correlate the load condition of the power equipment and the temperature characteristics of the sampled feature points during operation with the temperature of the power components. Consequently, the target model trained using the sample data can predict the temperature of the power components based on the load condition of the power equipment and the temperature characteristics of the sampled feature points during operation.

[0093] In some embodiments, the number of at least one operating condition is a target number, and each operating condition corresponds to the sampled values ​​of multiple operating condition parameters. The above step S201 may include the following steps S211 to S213: Step S211: Divide the value range corresponding to each working condition parameter into the range interval of the target quantity.

[0094] In implementation, the target quantity can be determined based on at least one of the following: the range of values ​​corresponding to the operating condition parameters, the model size, and the preset number of samples.

[0095] For example, when the range of values ​​corresponding to the operating parameters is small, the number of targets can be reduced to make the difference between each sampled value larger, or the number of targets can be increased to make each sampled value more accurate.

[0096] For example, after setting the total number of samples to 100, you can use 100 as the target number.

[0097] During implementation, the value range corresponding to each working condition parameter can be evenly divided into a range interval of the target number. Step S212: For each working condition parameter, randomly and uniquely select a parameter value from each range interval corresponding to the working condition parameter to obtain the target number of sampled values ​​corresponding to the working condition parameter.

[0098] It is understandable that by randomly selecting parameter values ​​within each range of the operating condition parameters and dividing the value range of each operating condition parameter into multiple equally probable intervals, the randomness of the distribution of the target number of sampled values ​​can be improved.

[0099] Step S213: Randomly combine the sampled values ​​of various working condition parameters to obtain a target number of working conditions; each working condition corresponds to a working condition parameter group, and each working condition parameter group includes a sampled value of each working condition parameter.

[0100] During implementation, after obtaining the target number of operating conditions, simulation can be performed on each set of operating condition parameters based on the physical model of the power equipment to obtain the operating parameters of the power equipment and the temperature of the power components under each set of operating condition parameters.

[0101] It is understandable that the sampling method described in steps S211 to S213 can be referred to as Latin hypercube sampling.

[0102] In this embodiment, the value range corresponding to each working condition parameter is divided into a target number of range intervals, and the sampled values ​​uniquely selected in each interval are randomly combined to obtain the working conditions corresponding to the target number of working condition parameter groups. In this way, the sample data can be evenly distributed in the multidimensional parameter space, and more representative sample data can be obtained with fewer simulations.

[0103] In some embodiments, the above data processing method may further include the following step S221: Step S221: Take the operating parameters of the power equipment under at least one operating condition in the sample data as the first input of the target model, and take the temperature of the power component corresponding to the operating parameters in the sample data as the model output of the target model to train the model parameters; the model output is determined based on the mean of the probability distribution of the power component temperature, and the probability distribution is taken as the second input of the target model, which is determined based on the first input.

[0104] Here, the first input is the initial input of the target model, which can be imported from external input or imported by the target model itself.

[0105] The second input is an intermediate input to the target model, which can be obtained by processing the target model from the initial input. The final result (the temperature of the power components corresponding to the operating parameters) is then obtained based on the second input as the final output.

[0106] In some implementations, the temperature of the electrical component output by the target model can be a typical characteristic temperature, such as a temperature extreme or a temperature average.

[0107] In some implementations, the target model can be a processing model capable of probabilistic prediction. The target model can predict the probability distribution of the temperature of electrical components based on the operating parameters of the power equipment under at least one operating condition, using this probability distribution as a second input. Further, the target model can determine the mean of the predicted temperature values ​​of the electrical components and the confidence level corresponding to the mean based on the probability distribution. If the confidence level corresponding to the mean is greater than a preset confidence level threshold, the mean of the predicted values ​​is used as the model output. For example, the target model can be a processing model capable of performing Gaussian regression calculations.

[0108] In some implementations, during the training of the target model based on sample data, the sample data can be divided into training samples and test samples; the training samples are used for model training, and the test samples are used for model validation. This allows for verification of the rationality of the uncertainty estimation while ensuring that the error of the mean predicted value is closer to a preset range.

[0109] In this embodiment, during the training of the target model using sample data, the target model predicts the probability distribution of the temperature of the power components corresponding to the operating parameters, and further determines the final model output based on the predicted probability distribution. This transforms complex calculations into simple mappings, improving prediction speed and efficiency while quantifying the uncertainty of the predicted values, thus providing a basis for risk assessment during training.

[0110] In related technologies, transformers, as core equipment in power systems, have their winding hot spot temperature as a key indicator for assessing insulation aging life and load capacity. Methods for obtaining winding temperature typically include the following: 1. Direct measurement method: This method measures directly using built-in sensors. It has high accuracy but is costly and difficult to popularize.

[0111] 2. Thermal model calculation method: Based on empirical formula estimation, this method is simple and fast but has limited accuracy and cannot provide a complete temperature field distribution.

[0112] 3. Numerical simulation method: such as the finite volume method. This method can obtain an accurate three-dimensional temperature field, but it consumes a lot of computational resources, takes a long time, and cannot be used for online monitoring.

[0113] Therefore, there is a need in this field for a technical solution that can maintain the accuracy of numerical simulation while enabling rapid prediction of winding temperature field.

[0114] To address the above issues, this application proposes a rapid prediction method for the thermal state of transformer windings based on Gaussian process regression and temperature field mapping correction. This method combines the high accuracy of numerical simulation with the high efficiency of machine learning, and provides crucial information on prediction uncertainties. This offers an effective solution for achieving online, real-time, and accurate assessment and risk management of the thermal state of transformer windings. Figure 3 As shown, the method may include the following steps S301 to S305: Step S301: Construct a high-precision finite volume method multiphysics model.

[0115] Here, the transformer can be considered as the electrical equipment in the above embodiments. The multiphysics model can be considered as the physical model of the electrical equipment in the above embodiments.

[0116] During implementation, a refined three-dimensional geometric model of the transformer, including windings, core, insulating oil, radiator, and casing, can be established. After meshing, the finite volume method can be used to calculate the temperature and fluid field based on this three-dimensional ensemble model, thereby obtaining sample data corresponding to different operating conditions.

[0117] Step S302: Systematically construct a sample library based on Latin hypercube sampling.

[0118] Here, the sample library is the set of sample data constructed from the sample data in the above embodiments.

[0119] During implementation, the type and range of values ​​for the operating parameters should be determined first.

[0120] For example, operating parameters may include transformer load rate, ambient convective heat transfer coefficient, and ambient temperature; wherein: Transformer load factor can be expressed as The value ranges from 0.2 to 1.5, covering light load to overload. For example, a load factor of 0.2 can be considered as the transformer being under light load; a load factor exceeding 1 (such as 1.5) can be considered as the transformer being under overload.

[0121] The environmental convective heat transfer coefficient can be expressed as The value ranges from 5 to 25 watts per square meter (°C). This ranges from natural convection to forced air cooling. For example, the convective heat transfer coefficient in a natural scenario might be relatively small, around 5. Conversely, the convective heat transfer coefficient in a forced air cooling scenario might be relatively large, around 25.

[0122] Ambient temperature can be expressed as The value range is -20 to 40 ( This covers typical environmental conditions. For example, the ambient temperature in a cold environment is approximately -20°C. In a hot environment, the ambient temperature is approximately 40°C.

[0123] Furthermore, Latin hypercube sampling is performed based on the parameter range corresponding to each operating condition parameter.

[0124] For example, the total number of samples can be set. The value is 200, corresponding to the target quantity in the above embodiments. The value range of each operating condition parameter is evenly divided into 200 intervals. A value is randomly and uniquely selected within each interval. The selected values ​​of the three parameters (i.e., the sampled values ​​of each operating condition parameter in the above embodiments) are randomly combined to generate 200 sets of input parameter combinations (i.e., the operating condition parameter sets in the above embodiments), such as... This ensures that the sample data is uniformly distributed within the three-dimensional parameter space.

[0125] Finally, sample data is generated and the dataset is divided: For each of the 200 sets of operating parameters, the transformer temperature and fluid field were calculated using the finite volume method, and the corresponding simulated observation samples were recorded to construct a sample library. The inputs during the calculation process included the transformer casing convective heat transfer coefficient (i.e., ...) as boundary conditions under the corresponding operating conditions. ), and as a heat source, the transformer at the corresponding load rate (i.e. The calculation calculates the winding losses, core losses, and eddy current losses of the transformer under various operating conditions. The output is the winding temperature field distribution of the transformer under the corresponding operating conditions. This calculation yields the detailed temperature field distribution of the transformer under various operating conditions, i.e., the temperature distribution of different electrical components (such as windings, core, and casing) under various operating conditions, and extracts the lowest temperature of the winding temperature field. and highest temperature Simultaneously record the top oil temperature Temperature of the characteristic temperature measuring point on the outer casing (i.e., the point on the top of the transformer casing) It should be noted that the number of temperature measurement points on the outer casing can be selected based on the specific transformer type; for example, 3 to 5 temperature measurement points can be selected.

[0126] In practice, after obtaining the sample data, the sample library can be divided into 160 training samples for model training and 40 test samples for model validation at a ratio of 4:1.

[0127] Step S303: Probabilistic prediction model for key temperature parameters based on Gaussian process regression.

[0128] Here, the key temperature parameters can correspond to the characteristic temperatures in the above embodiments, namely, the extreme temperatures and / or the average temperatures. This step is the core step for achieving fast and reliable prediction.

[0129] During implementation, it can be based on the easily measurable top oil temperature. Temperature of characteristic temperature measurement points on the outer casing and load rate As model input (i.e., the operating parameters in the above embodiments), the lowest winding temperature is used. and highest temperature As model output. And for and Independent Gaussian Process Regression (GPR) models were established.

[0130] During the model definition phase, a Gaussian process can be defined by a mean function and a covariance function (i.e., a kernel function). The kernel function can be, but is not limited to, one of the following: a quadratic exponential kernel function, a linear kernel function, or a radial basis function.

[0131] For example, the squared exponential kernel function of the model can be defined by the following formula (2): (2); in, and The input vector represents the two sets of top oil temperature, shell feature temperature measurement point temperature, and load rate in the sample data, respectively. For signal variance, The length scale is used. Understandably, this kernel function effectively captures the smooth, non-linear relationship between input and output.

[0132] During the model training phase, 160 training samples can be used to optimize the hyperparameter set of each GPR model by maximizing the marginal likelihood function. For example, the composition of the super-generated set can be seen in the following formula (3): (3); in, This represents the variance of the observation noise.

[0133] During the model validation phase, 40 test samples can be used to validate the model, bringing the error of the prediction mean (such as the mean absolute error) close to the preset range (such as being within the acceptable range of less than 5%), and verifying the rationality of its uncertainty estimation.

[0134] In the model prediction phase, for a new operating condition input That is, the given set of operating parameters The trained GPR model outputs a Gaussian distribution. For example, a Gaussian distribution. The form can be seen in the following formula (4): (4); in, Represents a functional relationship. corresponding input vector The output is for the working condition. The predicted values ​​of the highest or lowest temperatures of the lower winding are based on the predicted average. and prediction variance Sure.

[0135] For example, the following is the predicted mean. and prediction variance The possible values ​​of: The average of the predicted highest winding temperature The final predicted value determined as the key temperature parameter (maximum temperature, i.e., temperature extreme value). That is, the first temperature in the above embodiments.

[0136] Variance of the predicted maximum winding temperature This can characterize the predicted value. The uncertainty. A 95% confidence interval can be calculated based on this; for example, see the following formula (5): (5).

[0137] The average of the predicted highest winding temperature The final predicted value of the key temperature parameter (the lowest temperature, i.e., the temperature extreme value) is determined. That is, the first temperature in the above embodiments.

[0138] Variance of the predicted maximum winding temperature This can characterize the predicted value. The uncertainty. A 95% confidence interval can be calculated based on this; for example, see the following formula (6): (6).

[0139] Step S304: Correction of winding temperature field based on reference temperature field.

[0140] This step is used to quickly reconstruct the complete temperature field (corresponding to the second temperature field in the above embodiments). The reference temperature field can correspond to the first temperature field in the above embodiments.

[0141] During implementation, the reference temperature field under rated operating conditions can first be obtained, that is, the transformer under rated load and typical environmental conditions (such as...) can be pre-calculated and stored. The value is 1.0. The value is 10. The detailed winding temperature field distribution (with a value of 20) can be used as a reference temperature field and can be expressed as follows: (i.e., the field temperature dataset), which includes the minimum and maximum values ​​corresponding to the winding temperature. and The rated operating condition can correspond to the preset operating condition in the above embodiments. and This can correspond to the second temperature in the above embodiments.

[0142] Further, the correction coefficients for the temperature field are calculated. For any operating condition, the corresponding correction coefficients are obtained from the model trained in step S303. and .

[0143] In implementation, in conjunction with formula (1) in the above embodiments, according to and ,as well as and Determine the correction factor and The process can be found in the following formulas (7) and (8): (7); (8); In this way, this scheme can quickly generate a physically reasonable complete temperature field by making its temperature extreme values ​​match the current working conditions through linear transformation, while maintaining the internal heat distribution pattern of the reference temperature field.

[0144] Step S305: Online rapid prediction and application.

[0145] During implementation, the trained GPR model and reference temperature field can be integrated into the online monitoring system. The top oil temperature is then collected in real time through the online monitoring system. Temperature of characteristic temperature measurement points on the outer casing and load rate Complete the task in real time and The prediction of its confidence interval is performed, and the complete winding temperature field is reconstructed. The results can be used for real-time visualization, hotspot temperature alarms, insulation life assessment, and optimized control of cooling systems.

[0146] In this embodiment, firstly, an accurate sample library is constructed using the finite volume method. This involves sampling 200 times within the specified range of operating parameters using a Latin hypercube, and dividing the resulting simulation samples into 160 training samples and 40 test samples. Secondly, a Gaussian process regression model is trained, using easily measurable parameters as input and winding extreme temperatures as output, thereby providing probabilistic predictions of the highest and lowest transformer winding temperatures under complex operating conditions with quantified uncertainty. Finally, a linear correction method is used to quickly map the rated operating condition reference temperature field to the current predicted operating condition, obtaining a complete winding temperature field distribution. In this way, on the one hand, using the simulation results of the finite volume method multiphysics field as the true data can improve the reliability of the multiphysics field simulation results of transformers based on high precision; on the other hand, by using the Gaussian process regression model, complex numerical calculations are transformed into fast mapping, achieving high efficiency and probabilistic prediction at the second level, providing quantification of the uncertainty of the predicted values, and providing a basis for risk assessment; furthermore, by using the linear correction method, the reference temperature field under rated operating conditions is "transformed" into the temperature field under the current operating conditions, realizing the leap from "point prediction" to "field reconstruction", and enabling complete temperature field reconstruction based on a small amount of temperature data; and finally, the input parameters are easy to obtain through existing monitoring systems, and the output results are relatively comprehensive, which can be directly used for online monitoring, thermal status assessment, and intelligent operation and maintenance, improving the engineering practicality of this solution.

[0147] This application provides a power detection model that can be applied to electronic devices or power equipment under test. For example... Figure 4 As shown, the power monitoring model 400 may include: Output module 410 is used to obtain the operating parameters of the power equipment under the current operating conditions, input them into the target model, and make the target model output the first temperature of the power components of the power equipment; The determination module 420 is used to determine the correction coefficient based on the first temperature and the second temperature of the power component under preset operating conditions. The correction module 430 is used to correct the first temperature field of the power component under the preset operating conditions using a correction coefficient, so as to obtain the second temperature field of the power component under the current operating conditions.

[0148] In some embodiments, the determining module may further be used to: map the second temperature to the first temperature through a linear transformation, and determine the first correction coefficient and the second correction coefficient; the correction module may further be used to: perform a linear transformation on the first temperature field using the first correction coefficient and the second correction coefficient, and determine the second temperature field.

[0149] In some embodiments, the first temperature includes a first temperature extreme value, and the second temperature includes a second temperature extreme value; the correction module can also be used to: use a correction coefficient to correct each temperature in the first temperature field except for the second temperature extreme value, so as to obtain each temperature in the second temperature field except for the first temperature extreme value.

[0150] In some embodiments, the power monitoring model may further include an operating condition determination module, configured to: obtain a first operating condition parameter group corresponding to the current operating condition; determine the parameter range of at least one operating condition parameter in the first operating condition parameter group; and determine the operating condition corresponding to a second operating condition parameter group that matches the parameter range as a preset operating condition.

[0151] In some embodiments, each operating condition parameter group includes a first operating condition parameter characterizing the load characteristics of the power equipment and a second operating condition parameter characterizing the thermal convection conditions in the environment where the power equipment is located; the operating condition determination module can also be used to: determine the parameter range in which the first operating condition parameter is located in the first operating condition parameter group; and determine the operating condition corresponding to the second operating condition parameter group in which the first operating condition parameter is within the parameter range as the preset operating condition.

[0152] This application provides a data processing model that can be applied to electronic devices or power equipment under test. For example... Figure 5 As shown, the data processing model 500 may include: The sampling module 510 is used to sample within the range of the operating parameters of the power equipment to obtain at least one operating condition corresponding to the power equipment; each operating condition corresponds to at least one sampled value of the operating parameter, and the at least one operating condition includes a preset operating condition. Simulation module 520, based on the physical model of the power equipment, simulates and obtains sample data corresponding to at least one operating condition. The sample data includes the operating parameters of the power equipment under at least one operating condition, the temperature of the power components of the power equipment, and the correlation between the operating parameters and the temperature of the power components. The sample data is used to train the target model, and the target model is used to output the first temperature of the power components based on the operating parameters of the power equipment under the current operating condition.

[0153] In some embodiments, the number of at least one working condition is the target number, and each working condition corresponds to the sampled values ​​of multiple working condition parameters; the sampling module can also be used to: divide the value range corresponding to each working condition parameter into a range interval of the target number; for each working condition parameter, randomly and uniquely select a parameter value from each range interval corresponding to the working condition parameter to obtain the sampled values ​​of the target number corresponding to the working condition parameter; randomly combine the sampled values ​​of multiple working condition parameters to obtain the target number of working conditions; each working condition corresponds to a working condition parameter group, and each working condition parameter group includes a sampled value of each working condition parameter.

[0154] In some embodiments, the data processing model may further include a training module, configured to: use the operating parameters of the power equipment under at least one operating condition in the sample data as the first input of the target model, use the temperature of the power component corresponding to the operating parameters in the sample data as the model output of the target model, and train the model parameters of the target model; the model output is determined based on the mean of the probability distribution of the power component temperature, and the probability distribution is used as the second input of the target model, which is determined based on the first input.

[0155] In some embodiments, the operating parameters include a first operating parameter characterizing the load characteristics of the power equipment and a second operating parameter characterizing the temperature characteristics of at least one sampling feature point during the operation of the power equipment.

[0156] This application provides an electronic device. For example... Figure 6 As shown, the electronic device 600 may include a memory 610 and a processor 620. The memory 610 stores a data processing program that can run on the processor 620, and the processor 620, when executing the program, can implement any step of the above-described method.

[0157] This application also proposes a computer program including computer-readable code, which, when run in an electronic device, enables a processor in the electronic device to execute methods provided in this application.

[0158] This application provides a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, implement the method provided in this application.

[0159] This application provides a computer-readable storage medium storing a computer program or computer-executable instructions for implementing the method provided in this application when executed by a processor.

[0160] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and devices according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0161] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0162] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0163] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

[0164] The descriptions of the above device embodiments are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0165] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0166] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0167] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0168] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0169] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0170] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0171] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks. The above descriptions are merely embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A power detection method, comprising: Obtain the operating parameters of the power equipment under the current operating conditions, input them into the target model, and make the target model output the first temperature of the power components of the power equipment; Based on the first temperature and the second temperature of the power component under the preset operating conditions, a correction factor is determined; Using the correction coefficient, the first temperature field of the power component under the preset operating condition is corrected to obtain the second temperature field of the power component under the current operating condition.

2. The method according to claim 1, wherein determining the correction coefficient based on the first temperature and the second temperature of the power component under preset operating conditions includes: The second temperature is mapped to the first temperature through a linear transformation, and the first correction coefficient and the second correction coefficient are determined. The step of using the correction coefficient to correct the first temperature field of the power component under the preset operating condition to obtain the second temperature field of the power component under the current operating condition includes: The first temperature field is linearly transformed using the first correction coefficient and the second correction coefficient to determine the second temperature field.

3. The method according to claim 1, wherein the first temperature includes a first temperature extreme value, and the second temperature includes a second temperature extreme value; The step of using the correction coefficient to correct the first temperature field of the power component under the preset operating condition to obtain the second temperature field of the power component under the current operating condition includes: Using the correction coefficient, each temperature in the first temperature field except for the second temperature extreme value is corrected, thereby obtaining each temperature in the second temperature field except for the first temperature extreme value.

4. The method according to any one of claims 1 to 3, further comprising: Obtain the first set of operating parameters corresponding to the current operating condition; Determine the parameter range of at least one operating condition parameter in the first operating condition parameter group; The working condition corresponding to the second working condition parameter group that matches the parameter range is determined as the preset working condition.

5. The method according to claim 4, wherein each set of operating parameters includes a first operating parameter characterizing the load characteristics of the power equipment and a second operating parameter characterizing the thermal convection conditions in the environment where the power equipment is located; Determining the parameter range of at least one operating condition parameter in the first operating condition parameter group includes: Determine the parameter range of the first working condition parameter in the first working condition parameter group; The step of determining the working condition corresponding to the second working condition parameter group that matches the parameter range as the preset working condition includes: The working condition corresponding to the second working condition parameter group whose first working condition parameter is within the parameter range is determined as the preset working condition.

6. A data processing method, comprising: Sampling is performed within the range of operating parameters of the power equipment to obtain at least one operating condition corresponding to the power equipment. Each working condition corresponds to at least one sampled value of the working condition parameter, and the at least one working condition includes a preset working condition; Based on the physical model of the power equipment, simulations are performed to obtain sample data corresponding to the at least one operating condition. The sample data includes the operating parameters of the power equipment under at least one operating condition, the temperature of the power components of the power equipment, and the correlation between the operating parameters and the temperature of the power components. The sample data is used to train a target model, and the target model is used to output the first temperature of the power components based on the operating parameters of the power equipment under the current operating condition.

7. The method according to claim 6, wherein the number of the at least one working condition is a target number, and each working condition corresponds to the sampled values ​​of multiple working condition parameters; The step of sampling within the range corresponding to the operating parameters of the power equipment to obtain at least one operating condition corresponding to the power equipment includes: The value range corresponding to each working condition parameter is divided into a range interval for the target number; For each operating condition parameter, a parameter value is randomly and uniquely selected from each range interval corresponding to the operating condition parameter to obtain the target quantity of sampled values ​​corresponding to the operating condition parameter. The sampled values ​​of the various working condition parameters are randomly combined to obtain the target number of working conditions; each working condition corresponds to a working condition parameter group, and each working condition parameter group includes a sampled value of each working condition parameter.

8. The method according to claim 6, further comprising: The operating parameters of the power equipment under at least one operating condition in the sample data are used as the first input of the target model, and the temperature of the power component corresponding to the operating parameters in the sample data is used as the model output of the target model to train the model parameters; the model output is determined based on the mean of the probability distribution of the power component temperature, and the probability distribution is used as the second input of the target model, which is determined based on the first input.

9. The method according to any one of claims 6 to 8, wherein the operating parameters include a first operating parameter characterizing the load characteristics of the power equipment and a second operating parameter characterizing the temperature characteristics of at least one sampling feature point during the operation of the power equipment.

10. A power detection device, comprising: The output module is used to obtain the operating parameters of the power equipment under the current operating conditions, input them into the target model, and make the target model output the first temperature of the power components of the power equipment. The determination module is used to determine a correction coefficient based on the first temperature and the second temperature of the power component under preset operating conditions; The correction module is used to correct the first temperature field of the power component under the preset operating condition using the correction coefficient, so as to obtain the second temperature field of the power component under the current operating condition.

Images