Transformer temperature control method, device, equipment and storage medium

Abstract

The present application discloses a transformer temperature control method, device, equipment, and storage medium. The method includes: obtaining the cooling oil inlet temperature and cooling oil outlet temperature of the transformer at the current moment; instructing a cooling device to perform a temperature control operation based on the cooling oil inlet temperature and cooling oil outlet temperature; obtaining operating data of the transformer after the cooling device performs the temperature control operation; the operating data includes: hotspot temperature, top oil temperature, ambient temperature, load rate, and operating time; inputting the top oil temperature, ambient temperature, load rate, and operating time into a hotspot temperature prediction model to obtain a target hotspot temperature; obtaining multiple historical hotspot temperatures of the transformer; performing curve fitting on the multiple historical hotspot temperatures to obtain a hotspot temperature curve; and performing PID control on the hotspot temperature based on the hotspot temperature, target hotspot temperature, and hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature. The present application is conducive to improving the accuracy of temperature control.

Description

Technical Field

[0001] The present application relates to the technical field of transformers, and in particular to a transformer temperature control method, device, equipment, and storage medium. Background Art

[0002] In recent years, transformer temperature control technology has developed rapidly. Transformer temperature control involves controlling the temperature of multiple locations on the transformer, including the oil tank temperature, hot spot temperature, and more.

[0003] Existing transformer temperature control methods collect the temperature of the transformer's windings. When the temperature exceeds a preset threshold, a cooling device is used to cool the transformer down to below the threshold. However, simply lowering the transformer temperature to below the threshold does not ensure optimal operating conditions for the transformer windings, resulting in low temperature control accuracy. Summary of the Invention

[0004] To address the aforementioned problems existing in the prior art, embodiments of the present application provide a transformer temperature control method, device, equipment, and storage medium. Based on the cooling oil inlet and outlet temperatures, the cooling device is instructed to perform temperature control operations. Furthermore, by inputting the transformer's top oil temperature, ambient temperature, load factor, and operating time into a hotspot temperature prediction model, the transformer's target hotspot temperature can be predicted. Finally, based on a hotspot temperature curve constructed from the transformer's target hotspot temperature and historical hotspot temperatures, PID control can be performed on the hotspot temperature to adjust it to the target hotspot temperature. This improves the accuracy of temperature control.

[0005] In a first aspect, an embodiment of the present application provides a transformer temperature control method, comprising:

[0006] Obtaining temperature data of a transformer at a current moment; the transformer comprises: a high-voltage winding, a low-voltage winding, an oil tank, and a cooling device; the oil tank comprises cooling oil, the cooling oil being in contact with the high-voltage winding and the low-voltage winding; the oil tank is connected to the cooling device via a cooling oil inlet pipe and a cooling oil outlet pipe; the cooling device is configured to cool the cooling oil in the cooling oil outlet pipe and transport the cooled cooling oil to the oil tank via the cooling oil inlet pipe; the temperature data comprises a cooling oil inlet temperature of the cooling oil inlet pipe and a cooling oil outlet temperature of the cooling oil outlet pipe;

[0007] Instructing the cooling device to perform a temperature control operation based on the cooling oil inlet temperature and the cooling oil outlet temperature; the temperature control operation is used to make the difference between the cooling oil temperature difference between the cooling oil outlet temperature and the cooling oil inlet temperature and the minimum cooling oil temperature difference corresponding to the transformer greater than or equal to a preset difference;

[0008] Obtaining operating data of the transformer after the cooling device performs the temperature control operation; the operating data includes: hot spot temperature, top oil temperature, ambient temperature, load rate, and operating time; the hot spot temperature is the temperature of the surface of the low-voltage winding of the transformer; the top oil temperature is the temperature of the top of the oil tank; the ambient temperature is the temperature at a preset distance from the surface of the transformer; the load rate is the ratio of the load power of the transformer to the rated power; and the operating time is the time between the start-up time of the transformer and the time when the operating data is obtained;

[0009] Inputting the top oil temperature, the ambient temperature, the load rate, and the operating time into a hotspot temperature prediction model to obtain a target hotspot temperature;

[0010] Obtaining multiple historical hot spot temperatures of the transformer;

[0011] Performing curve fitting on the multiple historical hotspot temperatures to obtain a hotspot temperature curve;

[0012] The hotspot temperature is PID-controlled according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature.

[0013] In a second aspect, an embodiment of the present application provides a transformer temperature control device, comprising:

[0014] an acquisition unit, configured to acquire temperature data of a transformer at a current moment; the transformer comprising: a high-voltage winding, a low-voltage winding, an oil tank, and a cooling device; the oil tank comprising cooling oil, the cooling oil being in contact with the high-voltage winding and the low-voltage winding; the oil tank being connected to the cooling device via a cooling oil inlet pipe and a cooling oil outlet pipe; the cooling device being configured to cool the cooling oil in the cooling oil outlet pipe and transport the cooled cooling oil to the oil tank via the cooling oil inlet pipe; the temperature data comprising a cooling oil inlet temperature of the cooling oil inlet pipe and a cooling oil outlet temperature of the cooling oil outlet pipe;

[0015] a processing unit, configured to instruct the cooling device to perform a temperature control operation based on the cooling oil inlet temperature and the cooling oil outlet temperature; the temperature control operation is configured to ensure that a difference between a cooling oil temperature difference between the cooling oil outlet temperature and the cooling oil inlet temperature and a minimum cooling oil temperature difference corresponding to the transformer is greater than or equal to a preset difference;

[0016] The acquisition unit is configured to acquire operating data of the transformer after the cooling device performs the temperature control operation; the operating data includes: hot spot temperature, top oil temperature, load rate, and operating time; the hot spot temperature is the temperature of the surface of the low-voltage winding of the transformer; the top oil temperature is the temperature of the top of the oil tank; the ambient temperature is the temperature at a preset distance from the surface of the transformer; the load rate is the ratio of the load power of the transformer to the rated power; and the operating time is the time between the start-up time of the transformer and the acquisition time of the operating data;

[0017] The processing unit is configured to input the top oil temperature, the ambient temperature, the load rate, and the operating time into a hotspot temperature prediction model to obtain a target hotspot temperature;

[0018] The acquisition unit is used to acquire multiple historical hot spot temperatures of the transformer;

[0019] The processing unit is configured to perform curve fitting on the multiple historical hotspot temperatures to obtain a hotspot temperature curve;

[0020] The hotspot temperature is PID-controlled according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature.

[0021] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the method described in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in the first aspect.

[0023] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program product is operable to enable a computer to execute the method described in the first aspect.

[0024] The implementation of the embodiments of the present application has the following beneficial effects:

[0025] In an embodiment of the present application, the current temperature data of the transformer is first acquired. This temperature data includes the cooling oil inlet temperature of the cooling oil inlet pipe and the cooling oil outlet temperature of the cooling oil outlet pipe. Then, based on the cooling oil inlet and outlet temperatures, the cooling device is instructed to perform temperature control. Next, operational data of the transformer after the cooling device performs temperature control is acquired. This operational data includes the hotspot temperature, top oil temperature, ambient temperature, load factor, and operating time. The top oil temperature, ambient temperature, load factor, and operating time are input into a hotspot temperature prediction model to obtain a target hotspot temperature. Furthermore, multiple historical hotspot temperatures of the transformer are acquired and curve-fitted to obtain a hotspot temperature curve. Finally, based on the hotspot temperature, target hotspot temperature, and hotspot temperature curve, PID control is performed on the hotspot temperature to adjust it to the target hotspot temperature. Thus, by instructing the cooling device to perform temperature control, the difference between the cooling oil outlet temperature and the cooling oil inlet temperature and the transformer's corresponding minimum cooling oil temperature difference is ensured to be greater than or equal to a preset difference, thereby improving temperature control efficiency. In addition, the hotspot temperature prediction model can be used to predict the target hotspot temperature of the transformer. Combined with the hotspot temperature curve formed by the historical hotspot temperatures of the transformer, the hotspot temperature can be PID controlled, thereby adjusting the hotspot temperature of the low-voltage winding of the transformer to the target hotspot temperature, putting the transformer in the best operating state and improving the accuracy of temperature control. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 A schematic diagram of a transformer temperature control system provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of a transformer temperature control method provided in an embodiment of the present application;

[0029] Figure 3 A schematic diagram of a transformer temperature control device provided in an embodiment of the present application;

[0030] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0032] The terms "first," "second," "third," and "fourth," etc., in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, rather than to describe a specific order. In addition, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0033] References herein to "embodiments" mean that a particular feature, result, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0034] First, see Figure 1 , Figure 1 This is a schematic diagram of a transformer temperature control system provided in an embodiment of the present application. Figure 1 As shown, the transformer temperature control system includes: processing equipment, database and transformer.

[0035] The transformer includes a high-voltage winding, a low-voltage winding, an oil tank, and a cooling device. The oil tank contains cooling oil, which contacts the high-voltage and low-voltage windings. The oil tank is connected to the cooling device via a cooling oil inlet pipe and a cooling oil outlet pipe. The cooling device cools the cooling oil in the cooling oil outlet pipe and delivers the cooled cooling oil to the oil tank via the cooling oil inlet pipe. The high-voltage and low-voltage windings are used to step up or down the voltage. For example, in a step-up transformer, the low-voltage winding is connected to the input voltage and the high-voltage winding is connected to the output voltage. In a step-down transformer, the high-voltage winding is connected to the input voltage and the low-voltage winding is connected to the output voltage. During transformer operation, both the high-voltage and low-voltage windings generate a significant amount of heat, causing their temperatures to rise. The cooling oil, which circulates between the high-voltage and low-voltage windings, transfers heat from the high-voltage and low-voltage windings to the cooling oil, thereby cooling the high-voltage and low-voltage windings. The cooling oil that has absorbed heat flows into the cooling device through the cooling oil outlet pipe. The cooling device can cool the cooling oil flowing into the cooling device, for example, by cooling the cooling oil through a fan, or by absorbing the heat of the cooling oil through other media to cool the cooling oil. The cooling device can transport the cooled cooling oil to the oil tank through the cooling oil inlet pipe, so that the cooling oil in the oil tank can circulate to cool the high-voltage winding and the low-voltage winding.

[0036] In an embodiment of the present application, a hot spot temperature sensor is provided on the surface of the low-voltage winding for detecting the hot spot temperature on the surface of the low-voltage winding. A temperature sensor is provided on the top of the oil tank for detecting the top oil temperature on the top of the oil tank. In addition, temperature sensors are provided on both the cooling oil inlet pipe and the cooling oil outlet pipe for detecting the cooling oil inlet temperature of the cooling oil inlet pipe and the cooling oil outlet temperature of the cooling oil outlet pipe, respectively. An ambient temperature sensor is also provided at a preset distance from the surface of the transformer for detecting the ambient temperature. The temperatures collected by all temperature sensors and the time of collection of each temperature are stored in a database. Among them, the load rate, operating time, and other operating data of the transformer are also stored in the database.

[0037] Among them, the database can be a server composed of one or more computers running in a local area network and a database management system, which is mainly used to provide functions such as data query, data update, data maintenance, caching, secure access and data recovery, including: file servers, cloud servers, etc. The database can also be a memory that supports data storage, reading and writing functions, such as random access memory (RAM), read-only memory (ROM), flash memory, disk storage, optical storage, etc., which is not specifically limited in this application. In an embodiment of the present application, the database can continuously obtain the temperature data and operating data of the transformer from the sensor of the transformer. In addition, the database can communicate data with the processing device to transmit the temperature data and operating data of the transformer to the processing device.

[0038] In an embodiment of the present application, the processing device may be a processor and controller of the transformer, including: a digital signal processor (DSP), a single-chip microcontroller unit (MCU), a field programmable gate array (FPGA), and the like. The processing device may also be a server with data processing and data communication functions, including: an application server, a virtual private server (VPS), a cloud server, and the like. This application does not specifically limit this. In an embodiment of the present application, the processing device is mainly used to control the temperature of the transformer based on the temperature data and operating data of the transformer.

[0039] It should be noted that existing transformer temperature control methods typically directly obtain the temperature of the transformer windings. Only after the winding temperature exceeds a threshold value is the transformer cooled by a cooling device to reduce the transformer temperature to below a preset threshold. However, cooling the transformer only after the winding temperature exceeds the threshold value results in low timeliness of temperature control, resulting in lower transformer safety. Furthermore, simply lowering the temperature to below the threshold does not ensure that the transformer windings are in optimal operating condition, resulting in low temperature control accuracy.

[0040] To this end, the above transformer temperature control system is applied, and the processing device obtains the temperature data of the transformer at the current moment; the temperature data includes the cooling oil inlet temperature of the cooling oil inlet pipe and the cooling oil outlet temperature of the cooling oil outlet pipe;

[0041] The processing equipment instructs the cooling device to perform temperature control operations according to the cooling oil inlet temperature and the cooling oil outlet temperature;

[0042] The processing device obtains the operating data of the transformer after the cooling device performs the temperature control operation; the operating data includes: hot spot temperature, top oil temperature, ambient temperature, load rate and operating time;

[0043] The processing equipment inputs the top oil temperature, ambient temperature, load rate and operating time into the hotspot temperature prediction model to obtain the target hotspot temperature;

[0044] The processing device obtains multiple historical hot spot temperatures of the transformer;

[0045] The processing equipment performs curve fitting on multiple historical hot spot temperatures to obtain a hot spot temperature curve;

[0046] The processing device performs PID control on the hotspot temperature according to the hotspot temperature, the target hotspot temperature and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature.

[0047] As can be seen, when applied to the above-mentioned transformer temperature control system, the processing device can instruct the cooling device to perform temperature control operations based on the cooling oil inlet temperature of the cooling oil inlet pipe and the cooling oil outlet temperature of the cooling oil outlet pipe, thereby improving the efficiency of the cooling oil in controlling the temperature of the low-voltage winding. Furthermore, the processing device can use a hotspot temperature prediction model to predict the target hotspot temperature of the low-voltage winding based on the transformer's operating data. Based on the hotspot temperature curve composed of the target hotspot temperature and the transformer's historical hotspot temperatures, PID control can be performed on the hotspot temperature to adjust the hotspot temperature to the target hotspot temperature, thereby maintaining the transformer in an optimal operating state and improving the accuracy of temperature control.

[0048] See Figure 2 , Figure 2 This is a schematic diagram of a transformer temperature control method provided in an embodiment of the present application. This method is applied to the processing equipment in the above-mentioned transformer temperature control system. This method includes but is not limited to the following steps:

[0049] 201: Obtain the temperature data of the transformer at the current moment.

[0050] In an embodiment of the present application, the temperature data includes the cooling oil inlet temperature of the cooling oil inlet pipe and the cooling oil outlet temperature of the cooling oil outlet pipe. Both the cooling oil inlet pipe and the cooling oil outlet pipe are provided with temperature sensors. The temperature sensor of the cooling oil inlet pipe can periodically collect the cooling oil inlet temperature, and the temperature sensor on the cooling oil outlet pipe can periodically collect the cooling oil outlet temperature. The temperature sensors can be pre-set based on the accuracy requirements for data collection. The collected data is stored in a database, and the processing device can obtain the current temperature data from the database. Optionally, the processing device can also obtain the current temperature data directly from the above-mentioned temperature sensors.

[0051] 202: Instruct the cooling device to perform temperature control operation according to the cooling oil inlet temperature and the cooling oil outlet temperature.

[0052] In this embodiment of the present application, the temperature control operation is used to ensure that the difference between the cooling oil outlet temperature and the cooling oil inlet temperature and the minimum cooling oil temperature difference corresponding to the transformer is greater than or equal to a preset difference. It will be understood that the cooling oil temperature difference between the cooling oil outlet temperature and the cooling oil inlet temperature is the temperature difference of the cooling oil provided by the cooling device. Based on this cooling oil temperature difference, the processing device can determine the cooling efficiency of the cooling device at the current moment and, based on this cooling efficiency, instruct the cooling device to perform the temperature control operation.

[0053] For example, instructing the cooling device to perform a temperature control operation according to the cooling oil inlet temperature and the cooling oil outlet temperature may include:

[0054] determining a difference between a cooling oil outlet temperature and a cooling oil inlet temperature to obtain a first cooling oil temperature difference;

[0055] determining a difference between the first cooling oil temperature difference and the minimum cooling oil temperature difference to obtain a first difference;

[0056] When the first difference is less than the preset difference, if at least one of the cooling oil inlet pipe and the cooling oil outlet pipe is blocked, the cooling device is instructed to perform a cleaning operation on the blocked pipe so that both the cooling oil inlet pipe and the cooling oil outlet pipe are unblocked; if both the cooling oil inlet pipe and the cooling oil outlet pipe are unblocked, the cooling device is instructed to add cooling oil to the cooling oil inlet pipe, and obtain the cooling oil outlet temperature after adding the cooling oil and the cooling oil inlet temperature after adding the cooling oil; determine the difference between the cooling oil outlet temperature after adding the cooling oil and the cooling oil inlet temperature after adding the cooling oil to obtain a second cooling oil temperature difference; determine the difference between the second cooling oil temperature difference and the minimum cooling oil temperature difference to obtain a second difference; and use the second difference as the first difference until the first difference is greater than or equal to the preset difference.

[0057] In the embodiment of the present application, the temperature control operation includes a cleaning operation and a cooling oil adding operation. The processing device can instruct the cooling device to perform the corresponding temperature control operation according to the cooling oil temperature difference between the cooling oil outlet temperature and the cooling oil inlet temperature.

[0058] Specifically, the processing device first determines the difference between the cooling oil outlet temperature and the cooling oil inlet temperature to obtain a first cooling oil temperature difference. The first cooling oil temperature difference represents the cooling temperature of the cooling oil by the cooling device at the current moment, and this cooling temperature also represents the cooling temperature of the cooling oil on the transformer windings at the current moment. The processing device then obtains the minimum cooling oil temperature difference corresponding to the transformer. The difference between the first cooling oil temperature difference and the minimum cooling oil temperature difference is determined to obtain a first difference. The first difference represents the difference between the cooling temperature of the cooling oil by the cooling device at the current moment and the minimum cooling temperature of the cooling oil by the cooling device.

[0059] When the first difference is less than the preset difference, it indicates that the cooling temperature of the cooling oil provided by the cooling device at the current moment cannot meet the cooling requirements of the transformer windings. In this case, the processing device will first determine the blockage status of the cooling oil inlet and outlet pipes. It should be noted that when the cooling oil inlet and / or outlet pipes are blocked, the cooling oil circulation rate, cooling oil inlet flow rate, and cooling oil outlet flow rate will all decrease, resulting in a decrease in the first cooling oil temperature difference. Therefore, the processing device needs to determine the blockage status of the cooling oil inlet and outlet pipes. Both the cooling oil inlet and outlet pipes are equipped with flow meters for measuring the cooling oil flow rates there and out, respectively. Based on the cooling oil flow rate in the cooling oil inlet pipe, it can be determined whether the cooling oil inlet pipe is blocked. Based on the cooling oil flow rate in the cooling oil outlet pipe, it can be determined whether the cooling oil outlet pipe is blocked.

[0060] If at least one of the cooling oil inlet pipe and the cooling oil outlet pipe is clogged, the processing device will instruct the cooling device to perform a cleaning operation on the clogged pipe to clear both the cooling oil inlet pipe and the cooling oil outlet pipe. Optionally, the cooling device may be provided with a cleaning brush. During the cleaning operation, the cooling device inserts the cleaning brush into the clogged pipe and controls the rotation of the cleaning brush to clean the clogged pipe until both the cooling oil inlet pipe and the cooling oil outlet pipe are cleared.

[0061] If neither the cooling oil inlet pipe nor the cooling oil outlet pipe is blocked, the cooling device is instructed to add cooling oil to the cooling oil inlet pipe. The cooling device may be connected to a reserve oil tank and can draw cooling oil from the reserve oil tank and add the added cooling oil to the cooling oil inlet pipe. The added cooling oil flows through the cooling oil inlet pipe into the transformer's oil tank. Simultaneously, the cooling oil in the transformer's oil tank continuously flows into the cooling oil outlet pipe and enters the cooling device through the cooling oil outlet pipe for cooling. The cooling device continuously delivers the cooled cooling oil to the cooling oil inlet pipe, thereby circulating the cooling oil. After adding cooling oil, both the cooling oil outlet temperature and the cooling oil inlet temperature change. At this point, the processing device obtains the cooling oil outlet temperature and the cooling oil inlet temperature after adding cooling oil. The difference between the cooling oil outlet temperature and the cooling oil inlet temperature after adding cooling oil is determined to obtain a second cooling oil temperature difference. Next, the difference between the second cooling oil temperature difference and the minimum cooling oil temperature difference is determined to obtain a second difference. The second difference is used as the first difference until the first difference is greater than or equal to the preset difference, instructing the cooling device to stop performing the temperature control operation.

[0062] As can be seen, by using the difference between the first cooling oil temperature difference between the cooling oil outlet temperature and the cooling oil inlet temperature and the minimum cooling oil temperature difference as the first difference, if the first difference is less than a preset difference, and if at least one of the cooling oil inlet and outlet pipes is blocked, the cooling device is instructed to clear the blocked pipe. If neither the cooling oil inlet nor the cooling oil outlet pipe is blocked, the cooling device is instructed to add cooling oil to the cooling oil inlet pipe until the first difference is greater than or equal to the preset difference. This allows the cooling oil to maintain a relatively high temperature for the transformer windings, improving transformer safety.

[0063] 203: Acquire operating data of the transformer after the cooling device performs the temperature control operation.

[0064] In this embodiment of the present application, operating data includes: hotspot temperature, top oil temperature, ambient temperature, load factor, and operating time. The hotspot temperature is the surface temperature of the transformer's low-voltage winding. The top oil temperature is the temperature at the top of the oil tank. The ambient temperature is the temperature at a predetermined distance from the transformer surface. The load factor is the ratio of the transformer's load power to its rated power. The operating time is the duration between the transformer's startup and the acquisition of the operating data.

[0065] Temperature sensors are installed on the surface of the transformer's low-voltage winding, the top of the oil tank, and at a preset distance from the transformer's surface. Data collected by these temperature sensors can be stored in a database. The processing device can obtain the hotspot temperature, top oil temperature, and ambient temperature from the database. Alternatively, the processing device can directly obtain these hotspot temperature, top oil temperature, and ambient temperature from the temperature sensors. The transformer's load rate and operating time can be monitored in real time by an operating data monitoring device within the transformer. The processing device can obtain the transformer's load rate and operating time from the operating data monitoring device.

[0066] 204: Input the top oil temperature, ambient temperature, load rate, and operating time into the hotspot temperature prediction model to obtain a target hotspot temperature.

[0067] In an embodiment of the present application, the hotspot temperature prediction model can be obtained by pre-training a preset hotspot temperature prediction model. The hotspot temperature prediction model can be used to predict the target hotspot temperature of the transformer under optimal operating conditions based on the transformer's top oil temperature, ambient temperature, load factor, and operating time. This means that the transformer's low-voltage winding has the highest transformation efficiency at all temperatures at the target hotspot temperature.

[0068] Exemplarily, the method further includes the following steps:

[0069] Obtain a preset hotspot temperature prediction model;

[0070] Get the training run dataset and the test run dataset;

[0071] Taking the training top oil temperature, training ambient temperature, training load rate and training running time of each set of training running data in the multiple sets of training running data as input and the training hotspot temperature as output, a preset hotspot temperature prediction model is trained to obtain a candidate hotspot temperature prediction model;

[0072] Inputting the actual top oil temperature, actual ambient temperature, actual load rate, and actual operating time of each set of test operation data into a candidate hotspot temperature prediction model to obtain multiple expected hotspot temperatures;

[0073] determining a loss compensation value based on a plurality of expected hot spot temperatures and an actual hot spot temperature corresponding to each set of test operation data in the plurality of sets of test operation data;

[0074] According to the loss compensation value, the model parameters of the candidate hotspot temperature prediction model are adjusted to obtain the hotspot temperature prediction model.

[0075] In the embodiment of the present application, the training operation data set includes multiple sets of training operation data, each set of training operation data includes: training hotspot temperature, training top oil temperature, training ambient temperature, training load rate, and training operation time. The test operation data set includes multiple sets of test operation data, each set of test operation data includes: actual hotspot temperature, actual top oil temperature, actual ambient temperature, actual load rate, and actual operation time.

[0076] Specifically, the processing device first obtains a preset hotspot temperature prediction model. This preset hotspot temperature prediction model can be a deep learning network model, such as a recurrent neural network (RNN) model. The preset hotspot temperature prediction model includes an input layer, multiple hidden layers, and an output layer. The input layer is used to input feature quantities corresponding to the operating data, and the hidden layers are used to transmit the input feature quantities until they are transmitted to the output layer. The output layer is used to output the feature quantities of the expected hotspot temperature corresponding to the operating data.

[0077] The processing device then obtains a training run data set and a test run data set. The processing device uses the training top oil temperature, training ambient temperature, training load rate, and training run time of each set of training run data in the training run data set as input, and the training hotspot temperature as output. The processing device then trains the preset hotspot temperature prediction model until the training reaches a preset number of iterations, thereby obtaining a candidate hotspot temperature prediction model.

[0078] Next, the processing device inputs the actual top oil temperature, actual ambient temperature, actual load rate, and actual operating time for each set of test data in the test data set into the candidate hotspot temperature prediction model to obtain multiple expected hotspot temperatures. Each set of test data corresponds to an expected hotspot temperature. The processing device can determine a loss compensation value based on the multiple expected hotspot temperatures and the actual hotspot temperature corresponding to each set of test data.

[0079] Exemplarily, determining the loss compensation value based on the multiple expected hotspot temperatures and the actual hotspot temperature corresponding to each set of test operation data in the multiple sets of test operation data may include:

[0080] The loss compensation value is expressed by the following formula (1):

[0081]

[0082] Where L represents the loss compensation value, D represents the number of groups of test run data, and Y i1 represents the actual hotspot temperature corresponding to the i-th group of test running data in multiple groups of test running data, Y i0 represents the expected hotspot temperature corresponding to the i-th set of test run data.

[0083] As can be seen from formula (1), the processing device can determine the square of the difference between each expected hotspot temperature and the actual hotspot temperature corresponding to the expected hotspot temperature, obtaining multiple square values. These multiple square values ​​are then summed to obtain a total square value. Finally, the ratio of the total square value to the number of test run data groups is used as the loss compensation value to obtain the loss compensation value corresponding to the candidate hotspot temperature prediction model.

[0084] Therefore, by determining the loss compensation value of the candidate hotspot temperature prediction model, the deviation value between the expected hotspot temperature predicted by the candidate hotspot temperature prediction model and the actual hotspot temperature can be determined, so as to adjust the model parameters of the candidate hotspot temperature prediction model to improve the prediction accuracy of the hotspot temperature prediction model, and thus improve the accuracy of temperature control.

[0085] Finally, when the loss compensation value is greater than the preset loss compensation value, the processing device adjusts the model parameters of the candidate hotspot temperature prediction model to obtain a new candidate hotspot temperature prediction model, and tests the new candidate hotspot temperature prediction model through a test run data set to obtain a new loss compensation value until the loss compensation value is less than or equal to the preset loss compensation value to obtain the hotspot temperature prediction model.

[0086] It can be seen that by training the preset hotspot temperature prediction model with the training operation data set, a candidate hotspot temperature prediction model can be obtained, which can predict the expected hotspot temperature based on the top oil temperature, ambient temperature, load factor, and operating time. By testing the candidate hotspot temperature prediction model with the test operation data set, the loss compensation value between the expected hotspot temperature and the actual hotspot temperature can be obtained. The model parameters of the candidate hotspot temperature prediction model are adjusted based on this loss compensation value, and the hotspot temperature prediction model is obtained. The hotspot temperature prediction model can then be used to predict the target hotspot temperature of the transformer under optimal operating conditions, thereby improving the accuracy of temperature control.

[0087] 205: Obtain multiple historical hot spot temperatures of the transformer.

[0088] In an embodiment of the present application, the processing device may obtain multiple historical hot spot temperatures of the transformer, and obtain a collection time corresponding to each of the multiple historical hot spot temperatures.

[0089] 206: Perform curve fitting on multiple historical hotspot temperatures to obtain a hotspot temperature curve.

[0090] In an embodiment of the present application, the processing device can perform curve fitting on multiple historical hotspot temperatures by the point tracing method to draw a hotspot temperature curve. The horizontal axis of the hotspot temperature curve represents the collection time of the historical hotspot temperature, and the vertical axis of the hotspot temperature curve represents the historical hotspot temperature.

[0091] 207: Performing proportional-integral-differentiation (PID) control on the hotspot temperature according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature.

[0092] In an embodiment of the present application, PID control may adopt fuzzy PID control to adjust the hotspot temperature corresponding to the low-voltage winding of the transformer to the target hotspot temperature.

[0093] Exemplarily, performing PID control on the hotspot temperature according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature may include:

[0094] Determine the difference between the target hot spot temperature and the hot spot temperature to obtain the target hot spot temperature difference;

[0095] determining a difference between a plurality of adjacent hot spot temperatures on the hot spot temperature curve to obtain a plurality of hot spot temperature difference values;

[0096] Determining a change rate corresponding to each of the multiple hotspot temperature differences according to the multiple hotspot temperature differences to obtain multiple hotspot temperature difference change rates;

[0097] Determining a target temperature difference change rate corresponding to a target hotspot temperature difference based on a plurality of hotspot temperature difference change rates;

[0098] Determine the control coefficient based on the target hot spot temperature difference and the target temperature difference change rate;

[0099] The hotspot temperature is PID controlled according to the control coefficient to adjust the hotspot temperature to the target hotspot temperature.

[0100] In the embodiments of the present application, the control coefficients include: a proportional coefficient, an integral coefficient, and a differential coefficient. PID control primarily includes: proportional control, integral control, and differential control. The processing device can perform PID control on the hotspot temperature by determining the proportional coefficient corresponding to the proportional control, the integral coefficient corresponding to the integral control, and the differential coefficient corresponding to the differential control, thereby adjusting the hotspot temperature to the target hotspot temperature.

[0101] Specifically, the processing device first determines the difference between the target hotspot temperature and the hotspot temperature to obtain a target hotspot temperature difference. Then, according to a preset period, multiple hotspot temperatures are selected from the hotspot temperature curve and the hotspot temperature difference between any two of the multiple hotspot temperatures is determined to obtain multiple hotspot temperature difference values. Based on the multiple hotspot temperature difference values, a rate of change corresponding to each of the multiple hotspot temperature difference values ​​can be determined. Specifically, the rate of change of each hotspot temperature difference value is obtained by calculating the ratio of each hotspot temperature difference value to the difference between the two hotspot temperatures corresponding to the hotspot temperature difference value at the time of collection.

[0102] Then, the processing device can determine the target temperature difference change rate corresponding to the target hotspot temperature difference based on the multiple hotspot temperature difference change rates. For example, the processing device can perform curve fitting on the multiple hotspot temperature difference change rates to obtain a hotspot temperature difference change rate curve, and then obtain the target temperature difference change rate corresponding to the target hotspot temperature difference from the hotspot temperature difference change rate curve. It should be noted that since the target hotspot temperature is a predicted hotspot temperature, the hotspot temperature difference change rate corresponding to the target hotspot temperature cannot be directly obtained. Therefore, the processing device predicts the target temperature difference change rate corresponding to the target hotspot temperature difference based on the multiple hotspot temperature difference change rates, and uses the target temperature difference change rate as the hotspot temperature difference change rate corresponding to the target hotspot temperature.

[0103] Then, the control coefficient is determined according to the target hotspot temperature difference and the target temperature difference change rate. Exemplarily, the control coefficient is determined according to the target hotspot temperature difference and the target temperature difference change rate, which may include:

[0104] determining a target hotspot temperature difference as a first fuzzy value, and determining a target temperature difference change rate as a second fuzzy value;

[0105] Obtaining the fuzzy domain and membership function corresponding to the first fuzzy value and the second fuzzy value;

[0106] Divide the fuzzy domain into multiple fuzzy subsets;

[0107] determining the membership of the first fuzzy value in each of the plurality of fuzzy subsets according to the membership function, and obtaining a plurality of first memberships;

[0108] determining the membership of each fuzzy subset of the second fuzzy value in the plurality of fuzzy subsets according to the membership function, to obtain a plurality of second memberships;

[0109] Get the control coefficient rule table;

[0110] Determining the degree of membership of each fuzzy subset of the control coefficient in the plurality of fuzzy subsets according to the plurality of first degrees of membership, the plurality of second degrees of membership, and the control coefficient rule table, to obtain a plurality of third degrees of membership;

[0111] A control coefficient is determined according to the plurality of third membership degrees.

[0112] In the embodiment of the present application, the fuzzy domain is the value range corresponding to the first fuzzy value and the second fuzzy value. The control coefficient rule table is used to indicate the mapping rules between the first membership degree, the second membership degree, and the control coefficient membership degree of each fuzzy subset in multiple fuzzy subsets. The control coefficient rule table includes: a proportional coefficient rule table, an integral coefficient rule table, and a differential coefficient rule table.

[0113] Specifically, the processing device first determines the target hotspot temperature difference as a first fuzzy value and determines the target temperature difference change rate as a second fuzzy value. It will be appreciated that in fuzzy PID control, the first fuzzy value input is the difference between the target value and the actual value, and the second fuzzy value input is the change rate of the difference between the target value and the actual value. Therefore, the processing device uses the target hotspot temperature difference as the first fuzzy value and the target temperature difference change rate as the second fuzzy value.

[0114] Then, the processing device obtains the fuzzy domain and membership function corresponding to the first fuzzy value and the second fuzzy value. The fuzzy domain is used to limit the value range of the first fuzzy value and the second fuzzy value. The membership function is used to represent the membership mapping relationship between the first fuzzy value or the second fuzzy value and each fuzzy subset in the fuzzy domain. The fuzzy domain and membership function can be pre-set based on actual test results. The membership function can adopt a normal membership function or a Cauchy membership function, which is not limited in this application.

[0115] Furthermore, the processing device divides the fuzzy domain into multiple fuzzy subsets. For example, when the fuzzy domain is [-3, 3], the fuzzy domain can be divided into five fuzzy subsets, namely: [-3, -2], [-2, -1], [-1, 0], [0, 1], [1, 2], and [2, 3]. Each fuzzy subset corresponds to a level, with -3 corresponding to negative large, -2 corresponding to negative medium, -1 corresponding to negative small, 0 corresponding to zero, 1 corresponding to positive small, 2 corresponding to positive medium, and 3 corresponding to positive large. Based on the membership function, the membership of the first fuzzy value in each fuzzy subset in the multiple fuzzy subsets can be determined to obtain multiple first memberships, where the first membership represents the probability that the first fuzzy value belongs to an endpoint of each fuzzy subset in the multiple fuzzy subsets. Similarly, the processing device determines the membership of the second fuzzy value in each fuzzy subset in the multiple fuzzy subsets based on the membership function to obtain multiple second memberships.

[0116] Then, the processing device obtains a control coefficient rule table, including a proportional coefficient rule table, an integral coefficient rule table, and a differential coefficient rule table. The control coefficient rule table is used to indicate the mapping rules between the first and second memberships and the membership of the control coefficient in each of the multiple fuzzy subsets. For example, in the proportional coefficient rule table, one first and one second membership may correspond to a third membership corresponding to one proportional coefficient. Based on the multiple first and second memberships, the processing device can determine the membership of the proportional coefficient in each of the multiple fuzzy subsets from the proportional coefficient rule table to obtain multiple third memberships. Similarly, based on the multiple first and second memberships, the processing device can determine the membership of the integral coefficient in each of the multiple fuzzy subsets from the integral coefficient rule table to obtain multiple third memberships. Based on the multiple first and second memberships, the processing device can determine the membership of the differential coefficient in each of the multiple fuzzy subsets from the differential coefficient rule table to obtain multiple third memberships.

[0117] Finally, the processing device defuzzifies the control coefficient based on the multiple third degrees of membership to determine the control coefficient. For example, the proportional coefficient is determined based on the multiple third degrees of membership corresponding to the proportional coefficient. The integral coefficient is determined based on the multiple third degrees of membership corresponding to the integral coefficient. The differential coefficient is determined based on the multiple third degrees of membership corresponding to the differential coefficient. The mapping relationship between the multiple third degrees of membership and the control coefficient can be pre-set based on actual test results.

[0118] Thus, by using the target hotspot temperature difference as the first fuzzy value and the target temperature difference change rate as the second fuzzy value, the membership of the first fuzzy value in each of the multiple fuzzy subsets can be determined based on the membership function of the first fuzzy value and the second fuzzy value, thereby obtaining multiple first memberships, and the membership of the second fuzzy value in each of the multiple fuzzy subsets can be determined based on the membership function of the first fuzzy value and the second fuzzy value, thereby obtaining multiple second memberships. Then, based on the multiple first memberships and the multiple second memberships, the membership of the control coefficient in each of the multiple fuzzy subsets is determined from a control coefficient rule table, thereby obtaining multiple third memberships, and then the control coefficient is determined based on the multiple third memberships. Thus, PID control of the hotspot temperature can be performed using the control coefficient, thereby improving the accuracy of temperature control.

[0119] Finally, the processing device inputs the control coefficient into the PID controller to perform PID control on the hotspot temperature, including proportional control, integral control and differential control, so as to adjust the hotspot temperature corresponding to the low-voltage winding of the transformer to the target hotspot temperature.

[0120] Thus, by determining the difference between the target hotspot temperature and the hotspot temperature, a target hotspot temperature difference is obtained, and the difference between multiple adjacent hotspot temperatures on the hotspot temperature curve is determined to obtain multiple hotspot temperature differences. Then, based on the multiple hotspot temperature differences, the rate of change corresponding to each of the multiple hotspot temperature differences is determined to obtain multiple hotspot temperature difference change rates. Based on the multiple hotspot temperature difference change rates, the target temperature difference change rate corresponding to the target hotspot temperature difference can be determined. Furthermore, based on the target hotspot temperature difference and the target temperature difference change rate, a control coefficient can be determined. Based on the control coefficient, the hotspot temperature can be PID controlled to adjust the hotspot temperature to the target hotspot temperature, so that the low-voltage winding of the transformer is in the optimal operating state, thereby improving the accuracy of temperature control.

[0121] For example, before performing PID control on the hotspot temperature according to the control coefficient, the following steps may also be included:

[0122] Get the initial population particle number, acceleration coefficient and inertia weight;

[0123] Generate multiple swarm particles according to the number of initial swarm particles;

[0124] The position and velocity of each particle in the plurality of population particles are used as inputs of PID control, and the fitness evaluation value of each particle in the plurality of population particles is determined to obtain a plurality of fitness evaluation values;

[0125] If the maximum fitness evaluation value among multiple fitness evaluation values ​​is less than the preset fitness evaluation value, the position of the population particle corresponding to the maximum fitness evaluation value is taken as the optimal position;

[0126] Determine a target position and a target velocity of each of the plurality of swarm particles according to the optimal position, the acceleration coefficient, the inertia weight, and the position and velocity of each of the plurality of swarm particles;

[0127] Obtaining a target control coefficient according to a target position and a target velocity of each particle in the plurality of population particles;

[0128] The target position of each swarm particle is used as the position of the swarm particle, the target speed of each swarm particle is used as the speed of the swarm particle, and the target control coefficient is used as the control coefficient until the maximum fitness evaluation value among the multiple fitness evaluation values ​​corresponding to the multiple swarm particles is greater than or equal to the preset fitness evaluation value; the target control coefficient when the maximum fitness evaluation value is greater than or equal to the preset fitness evaluation value is used as the control coefficient.

[0129] In the embodiment of the present application, each of the plurality of population particles includes a position and a velocity. It should be noted that the control coefficient may change during the operation of the transformer, and the control coefficient needs to be updated by a particle swarm optimization (PSO).

[0130] Specifically, the processing device first obtains the initial population particle count, acceleration coefficient, and inertia weight of the particle swarm. These initial population particle count, acceleration coefficient, and inertia weight can be pre-set based on actual test results. Based on the initial population particle count, multiple population particles are generated, where the position and velocity of each population particle corresponds to a random solution for PID control.

[0131] Then, the processing device uses the position and velocity of each of the multiple population particles as input for PID control, determines the fitness evaluation value of each of the multiple population particles, and obtains multiple fitness evaluation values. The fitness evaluation value represents the probability of obtaining an optimal solution when the control coefficient performs PID control on the population particle corresponding to the fitness evaluation value.

[0132] If the maximum fitness evaluation value among the multiple fitness evaluation values ​​is less than the preset fitness evaluation value, it means that the control effect of the PID control through the current control coefficient is poor. The processing device will take the position of the population particle corresponding to the maximum fitness evaluation value as the optimal position, and determine the target position and target speed of each population particle in the multiple population particles based on the optimal position, acceleration coefficient, inertia weight, and the position and speed of each population particle in the multiple population particles.

[0133] The target position and target velocity of each particle in the population can be expressed by the following formula (2):

[0134]

[0135] Among them, v represents the target velocity of the swarm particles, x represents the target position of the swarm particles, v0 represents the target velocity of the swarm particles, x0 represents the position of the swarm particles, rand represents a random number between [0, 1], ω represents the inertia weight, c1 and c2 represent the acceleration coefficients, and x best Indicates the optimal position.

[0136] Thus, according to the optimal position, acceleration coefficient, inertia weight, position and velocity of each population particle in the plurality of population particles, the processing device can determine the target position and target velocity of each population particle in the plurality of population particles by formula (2).

[0137] Furthermore, a target control coefficient can be obtained based on the target position and target velocity of each particle in the multiple population particles. The mapping relationship between the target position and target velocity and the target control coefficient can be pre-set based on actual test results. The processing device will use the target position of each population particle as the position of the population particle, the target velocity of each population particle as the velocity of the population particle, and the target control coefficient as the control coefficient, and continue to determine multiple fitness evaluation values ​​corresponding to the multiple population particles until the maximum fitness evaluation value among the multiple fitness evaluation values ​​corresponding to the multiple population particles is greater than or equal to the preset fitness evaluation value. The target control coefficient when the maximum fitness evaluation value is greater than or equal to the preset fitness evaluation value is used as the control coefficient. PID control of the hotspot temperature using the control coefficient at this time can better improve the temperature control effect and thus improve the accuracy of temperature control.

[0138] In summary, in this embodiment of the present application, the current temperature data of the transformer is first acquired. This temperature data includes the cooling oil inlet temperature of the cooling oil inlet pipe and the cooling oil outlet temperature of the cooling oil outlet pipe. Then, based on the cooling oil inlet and outlet temperatures, the cooling device is instructed to perform temperature control. Next, operational data of the transformer after the cooling device performs temperature control is acquired. This operational data includes the hotspot temperature, top oil temperature, ambient temperature, load factor, and operating time. The top oil temperature, ambient temperature, load factor, and operating time are input into a hotspot temperature prediction model to obtain a target hotspot temperature. Furthermore, multiple historical hotspot temperatures of the transformer are acquired and curve-fitted to obtain a hotspot temperature curve. Finally, based on the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve, PID control is performed on the hotspot temperature to adjust it to the target hotspot temperature. Thus, by instructing the cooling device to perform temperature control, the difference between the cooling oil outlet temperature and the cooling oil inlet temperature and the transformer's corresponding minimum cooling oil temperature difference is ensured to be greater than or equal to a preset difference, thereby improving temperature control efficiency. In addition, the hotspot temperature prediction model can be used to predict the target hotspot temperature of the transformer. Combined with the hotspot temperature curve formed by the historical hotspot temperatures of the transformer, the hotspot temperature can be PID controlled, thereby adjusting the hotspot temperature of the low-voltage winding of the transformer to the target hotspot temperature, putting the transformer in the best operating state and improving the accuracy of temperature control.

[0139] See Figure 3 , Figure 3 Schematic diagram of a transformer temperature control device provided in an embodiment of the present application. The transformer temperature control device 300 can be the processing device of any of the above embodiments. The transformer temperature control device 300 includes an acquisition unit 301 and a processing unit 302.

[0140] An acquisition unit 301 is configured to acquire temperature data of the transformer at the current moment. The transformer includes a high-voltage winding, a low-voltage winding, an oil tank, and a cooling device. The oil tank contains cooling oil, which contacts the high-voltage winding and the low-voltage winding. The oil tank is connected to the cooling device via a cooling oil inlet pipe and a cooling oil outlet pipe. The cooling device is configured to cool the cooling oil in the cooling oil outlet pipe and transport the cooled cooling oil to the oil tank via the cooling oil inlet pipe. The temperature data includes a cooling oil inlet temperature of the cooling oil inlet pipe and a cooling oil outlet temperature of the cooling oil outlet pipe.

[0141] The processing unit 302 is configured to instruct the cooling device to perform a temperature control operation based on the cooling oil inlet temperature and the cooling oil outlet temperature; the temperature control operation is configured to ensure that the difference between the cooling oil outlet temperature and the cooling oil inlet temperature and the minimum cooling oil temperature difference corresponding to the transformer is greater than or equal to a preset difference;

[0142] The acquisition unit 301 is configured to acquire operating data of the transformer after the cooling device performs a temperature control operation; the operating data includes: hot spot temperature, top oil temperature, load rate, and operating time; the hot spot temperature is the temperature of the surface of the low-voltage winding of the transformer; the top oil temperature is the temperature of the top of the oil tank; the ambient temperature is the temperature at a preset distance from the surface of the transformer; the load rate is the ratio of the load power of the transformer to the rated power; and the operating time is the time between the start-up time of the transformer and the acquisition time of the operating data.

[0143] The processing unit 302 is used to input the top oil temperature, ambient temperature, load rate and operating time into the hot spot temperature prediction model to obtain the target hot spot temperature;

[0144] An acquisition unit 301 is configured to acquire multiple historical hot spot temperatures of the transformer;

[0145] The processing unit 302 is used to perform curve fitting on multiple historical hotspot temperatures to obtain a hotspot temperature curve;

[0146] The hotspot temperature is PID-controlled according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature.

[0147] In a possible embodiment, in terms of instructing the cooling device to perform a temperature control operation according to the cooling oil inlet temperature and the cooling oil outlet temperature, the processing unit 302 is specifically configured to:

[0148] determining a difference between a cooling oil outlet temperature and a cooling oil inlet temperature to obtain a first cooling oil temperature difference;

[0149] determining a difference between the first cooling oil temperature difference and the minimum cooling oil temperature difference to obtain a first difference;

[0150] When the first difference is less than the preset difference, if at least one of the cooling oil inlet pipe and the cooling oil outlet pipe is blocked, the cooling device is instructed to perform a cleaning operation on the blocked pipe so that both the cooling oil inlet pipe and the cooling oil outlet pipe are unblocked; if both the cooling oil inlet pipe and the cooling oil outlet pipe are unblocked, the cooling device is instructed to add cooling oil to the cooling oil inlet pipe, and obtain the cooling oil outlet temperature after adding the cooling oil and the cooling oil inlet temperature after adding the cooling oil; determine the difference between the cooling oil outlet temperature after adding the cooling oil and the cooling oil inlet temperature after adding the cooling oil to obtain a second cooling oil temperature difference; determine the difference between the second cooling oil temperature difference and the minimum cooling oil temperature difference to obtain a second difference; and use the second difference as the first difference until the first difference is greater than or equal to the preset difference.

[0151] In one possible embodiment, in performing PID control on the hotspot temperature according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature, the processing unit 302 is specifically configured to:

[0152] Determine the difference between the target hot spot temperature and the hot spot temperature to obtain the target hot spot temperature difference;

[0153] determining a difference between a plurality of adjacent hot spot temperatures on the hot spot temperature curve to obtain a plurality of hot spot temperature difference values;

[0154] Determining a change rate corresponding to each of the multiple hotspot temperature differences according to the multiple hotspot temperature differences to obtain multiple hotspot temperature difference change rates;

[0155] Determining a target temperature difference change rate corresponding to a target hotspot temperature difference based on a plurality of hotspot temperature difference change rates;

[0156] Determine the control coefficient based on the target hotspot temperature difference and the target temperature difference change rate; the control coefficient includes: proportional coefficient, integral coefficient and differential coefficient;

[0157] The hotspot temperature is PID controlled according to the control coefficient to adjust the hotspot temperature to the target hotspot temperature.

[0158] In a possible embodiment, in determining the control coefficient according to the target hotspot temperature difference and the target temperature difference change rate, the processing unit 302 is specifically configured to:

[0159] determining a target hotspot temperature difference as a first fuzzy value, and determining a target temperature difference change rate as a second fuzzy value;

[0160] Obtaining a fuzzy domain and a membership function corresponding to the first fuzzy value and the second fuzzy value; the fuzzy domain is a value interval corresponding to the first fuzzy value and the second fuzzy value;

[0161] Divide the fuzzy domain into multiple fuzzy subsets;

[0162] determining the membership of the first fuzzy value in each of the plurality of fuzzy subsets according to the membership function, and obtaining a plurality of first memberships;

[0163] determining the membership of each fuzzy subset of the second fuzzy value in the plurality of fuzzy subsets according to the membership function, to obtain a plurality of second memberships;

[0164] Obtaining a control coefficient rule table; the control coefficient rule table is used to indicate a mapping rule between the first membership degree, the second membership degree, and the membership degree of each fuzzy subset of the control coefficient in the plurality of fuzzy subsets; the control coefficient rule table includes: a proportional coefficient rule table, an integral coefficient rule table, and a differential coefficient rule table;

[0165] Determining the degree of membership of each fuzzy subset of the control coefficient in the plurality of fuzzy subsets according to the plurality of first degrees of membership, the plurality of second degrees of membership, and the control coefficient rule table, to obtain a plurality of third degrees of membership;

[0166] A control coefficient is determined according to the plurality of third membership degrees.

[0167] In a possible embodiment, before performing PID control on the hotspot temperature according to the control coefficient, the processing unit 302 is further configured to:

[0168] Get the initial population particle number, acceleration coefficient and inertia weight;

[0169] Generate multiple swarm particles according to the number of initial swarm particles; each of the multiple swarm particles includes a position and a velocity;

[0170] The position and velocity of each particle in the plurality of population particles are used as inputs of PID control, and the fitness evaluation value of each particle in the plurality of population particles is determined to obtain a plurality of fitness evaluation values;

[0171] If the maximum fitness evaluation value among multiple fitness evaluation values ​​is less than the preset fitness evaluation value, the position of the population particle corresponding to the maximum fitness evaluation value is taken as the optimal position;

[0172] Determine a target position and a target velocity of each of the plurality of swarm particles according to the optimal position, the acceleration coefficient, the inertia weight, and the position and velocity of each of the plurality of swarm particles;

[0173] Obtaining a target control coefficient according to a target position and a target velocity of each particle in the plurality of population particles;

[0174] The target position of each swarm particle is used as the position of the swarm particle, the target speed of each swarm particle is used as the speed of the swarm particle, and the target control coefficient is used as the control coefficient until the maximum fitness evaluation value among the multiple fitness evaluation values ​​corresponding to the multiple swarm particles is greater than or equal to the preset fitness evaluation value; the target control coefficient when the maximum fitness evaluation value is greater than or equal to the preset fitness evaluation value is used as the control coefficient.

[0175] In a possible embodiment, the processing unit 302 is further configured to:

[0176] Obtain a preset hotspot temperature prediction model;

[0177] Obtain a training run data set and a test run data set; the training run data set includes multiple sets of training run data, each set of training run data includes: training hotspot temperature, training top oil temperature, training ambient temperature, training load rate, and training run time; the test run data set includes multiple sets of test run data, each set of test run data includes: actual hotspot temperature, actual top oil temperature, actual ambient temperature, actual load rate, and actual run time;

[0178] Taking the training top oil temperature, training ambient temperature, training load rate and training running time of each set of training running data in the multiple sets of training running data as input and the training hotspot temperature as output, a preset hotspot temperature prediction model is trained to obtain a candidate hotspot temperature prediction model;

[0179] Inputting the actual top oil temperature, actual ambient temperature, actual load rate, and actual operating time of each set of test operation data into a candidate hotspot temperature prediction model to obtain multiple expected hotspot temperatures;

[0180] determining a loss compensation value based on a plurality of expected hot spot temperatures and an actual hot spot temperature corresponding to each set of test operation data in the plurality of sets of test operation data;

[0181] According to the loss compensation value, the model parameters of the candidate hotspot temperature prediction model are adjusted to obtain the hotspot temperature prediction model.

[0182] In a possible embodiment, determining the loss compensation value according to the plurality of expected hotspot temperatures and the actual hotspot temperature corresponding to each set of test operation data in the plurality of sets of test operation data includes:

[0183] The loss compensation value is expressed by the following formula (1):

[0184]

[0185] Where L represents the loss compensation value, D represents the number of groups of test run data, and Y i1represents the actual hotspot temperature corresponding to the i-th group of test running data in multiple groups of test running data, Y i0 represents the expected hotspot temperature corresponding to the i-th set of test run data.

[0186] See Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown, electronic device 400 includes a transceiver 401, a processor 402, and a memory 403. These are connected via a bus 404. Memory 403 is used to store computer programs and data and can transmit data stored in memory 403 to processor 402. Electronic device 400 may be transformer temperature control device 300. Electronic device 400 may also be the processing device of any of the above embodiments.

[0187] The processor 402 is configured to read the computer program in the memory 403 and perform the following operations:

[0188] Obtaining temperature data of the transformer at the current moment; the temperature data includes the cooling oil inlet temperature of the cooling oil inlet pipe and the cooling oil outlet temperature of the cooling oil outlet pipe;

[0189] Instruct the cooling device to perform temperature control operations according to the cooling oil inlet temperature and the cooling oil outlet temperature;

[0190] Obtaining transformer operating data after the cooling device performs temperature control operations; operating data includes: hot spot temperature, top oil temperature, ambient temperature, load rate, and operating time;

[0191] The top oil temperature, ambient temperature, load rate and operating time are input into the hotspot temperature prediction model to obtain the target hotspot temperature;

[0192] Obtain multiple historical hot spot temperatures of the transformer;

[0193] Perform curve fitting on multiple historical hotspot temperatures to obtain hotspot temperature curves;

[0194] The hotspot temperature is PID-controlled according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature.

[0195] The above mainly introduces the solution of the embodiment of the present application from the perspective of the execution process of the method side. It is understandable that, in order to realize the above functions, the electronic device 400 includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0196] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement part or all of the steps of any one of the methods described in the above method embodiments.

[0197] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the methods described in the above method embodiments.

[0198] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required for this application.

[0199] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0200] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. 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. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0201] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0202] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0203] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling 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 method described in each embodiment of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0204] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0205] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A transformer temperature control method, characterized in that: include: Obtaining temperature data of a transformer at a current moment; the transformer comprises: a high-voltage winding, a low-voltage winding, an oil tank, and a cooling device; the oil tank comprises cooling oil, the cooling oil being in contact with the high-voltage winding and the low-voltage winding; the oil tank is connected to the cooling device via a cooling oil inlet pipe and a cooling oil outlet pipe; the cooling device is configured to cool the cooling oil in the cooling oil outlet pipe and transport the cooled cooling oil to the oil tank via the cooling oil inlet pipe; the temperature data comprises a cooling oil inlet temperature of the cooling oil inlet pipe and a cooling oil outlet temperature of the cooling oil outlet pipe; Instructing the cooling device to perform a temperature control operation based on the cooling oil inlet temperature and the cooling oil outlet temperature; the temperature control operation is used to make the difference between the cooling oil temperature difference between the cooling oil outlet temperature and the cooling oil inlet temperature and the minimum cooling oil temperature difference corresponding to the transformer greater than or equal to a preset difference; Obtaining operating data of the transformer after the cooling device performs the temperature control operation; the operating data includes: hot spot temperature, top oil temperature, ambient temperature, load rate, and operating time; the hot spot temperature is the temperature of the surface of the low-voltage winding of the transformer; the top oil temperature is the temperature of the top of the oil tank; the ambient temperature is the temperature at a preset distance from the surface of the transformer; the load rate is the ratio of the load power of the transformer to the rated power; and the operating time is the time between the start-up time of the transformer and the time when the operating data is obtained; Inputting the top oil temperature, the ambient temperature, the load rate, and the operating time into a hotspot temperature prediction model to obtain a target hotspot temperature; Obtaining multiple historical hot spot temperatures of the transformer; Performing curve fitting on the multiple historical hotspot temperatures to obtain a hotspot temperature curve; The hotspot temperature is PID-controlled according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature.

2. The method according to claim 1, characterized in that The step of instructing the cooling device to perform a temperature control operation according to the cooling oil inlet temperature and the cooling oil outlet temperature includes: determining a difference between the cooling oil outlet temperature and the cooling oil inlet temperature to obtain a first cooling oil temperature difference; determining a difference between the first cooling oil temperature difference and the minimum cooling oil temperature difference to obtain a first difference; When the first difference is less than the preset difference, if at least one of the cooling oil inlet pipe and the cooling oil outlet pipe is blocked, the cooling device is instructed to perform a cleaning operation on the blocked pipe so that both the cooling oil inlet pipe and the cooling oil outlet pipe are unblocked; if both the cooling oil inlet pipe and the cooling oil outlet pipe are unblocked, the cooling device is instructed to add cooling oil to the cooling oil inlet pipe, and obtain the cooling oil outlet temperature and the cooling oil inlet temperature after adding the cooling oil; determine the difference between the cooling oil outlet temperature and the cooling oil inlet temperature after adding the cooling oil to obtain a second cooling oil temperature difference; determine the difference between the second cooling oil temperature difference and the minimum cooling oil temperature difference to obtain a second difference; and use the second difference as the first difference until the first difference is greater than or equal to the preset difference.

3. The method according to claim 1 or 2, characterized in that The performing PID control on the hotspot temperature according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature includes: Determining a difference between the target hotspot temperature and the hotspot temperature to obtain a target hotspot temperature difference; determining a difference between a plurality of adjacent hot spot temperatures on the hot spot temperature curve to obtain a plurality of hot spot temperature difference values; Determining, based on the multiple hotspot temperature differences, a change rate corresponding to each of the multiple hotspot temperature differences to obtain multiple hotspot temperature difference change rates; Determining a target temperature difference change rate corresponding to the target hotspot temperature difference according to the multiple hotspot temperature difference change rates; Determining a control coefficient based on the target hotspot temperature difference and the target temperature difference change rate; the control coefficient includes: a proportional coefficient, an integral coefficient, and a differential coefficient; The PID control is performed on the hotspot temperature according to the control coefficient to adjust the hotspot temperature to the target hotspot temperature.

4. The method according to claim 3, characterized in that The determining of the control coefficient according to the target hotspot temperature difference and the target temperature difference change rate includes: determining the target hotspot temperature difference as a first fuzzy value, and determining the target temperature difference change rate as a second fuzzy value; Obtaining a fuzzy domain and a membership function corresponding to the first fuzzy value and the second fuzzy value; the fuzzy domain is a value interval corresponding to the first fuzzy value and the second fuzzy value; dividing the fuzzy domain into a plurality of fuzzy subsets; determining, according to the membership function, the membership of the first fuzzy value in each of the plurality of fuzzy subsets to obtain a plurality of first memberships; determining the membership of the second fuzzy value in each of the plurality of fuzzy subsets according to the membership function, to obtain a plurality of second memberships; Obtaining a control coefficient rule table; the control coefficient rule table is used to indicate a mapping rule between the first membership degree, the second membership degree, and the membership degree of the control coefficient in each of the multiple fuzzy subsets; the control coefficient rule table includes: a proportional coefficient rule table, an integral coefficient rule table, and a differential coefficient rule table; Determining the degree of membership of the control coefficient in each of the plurality of fuzzy subsets according to the plurality of first degrees of membership, the plurality of second degrees of membership, and the control coefficient rule table, to obtain a plurality of third degrees of membership; The control coefficient is determined according to the plurality of third membership degrees.

5. The method according to claim 3, characterized in that Before performing the PID control on the hotspot temperature according to the control coefficient, the method further includes: Get the initial population particle number, acceleration coefficient and inertia weight; Generate a plurality of population particles according to the number of the initial population particles; each of the plurality of population particles includes a position and a velocity; Using the position and velocity of each of the plurality of population particles as inputs of the PID control, determining a fitness evaluation value of each of the plurality of population particles, and obtaining a plurality of fitness evaluation values; If the maximum fitness evaluation value among the multiple fitness evaluation values ​​is less than the preset fitness evaluation value, the position of the population particle corresponding to the maximum fitness evaluation value is used as the optimal position; Determining a target position and a target velocity of each of the plurality of population particles according to the optimal position, the acceleration coefficient, the inertia weight, and the position and velocity of each of the plurality of population particles; Obtaining a target control coefficient according to a target position and a target velocity of each of the plurality of population particles; The target position of each swarm particle is used as the position of the swarm particle, the target speed of each swarm particle is used as the speed of the swarm particle, and the target control coefficient is used as the control coefficient until the maximum fitness evaluation value among the multiple fitness evaluation values ​​corresponding to the multiple swarm particles is greater than or equal to the preset fitness evaluation value; and the target control coefficient when the maximum fitness evaluation value is greater than or equal to the preset fitness evaluation value is used as the control coefficient.

6. The method according to claim 1 or 2, characterized in that The method further comprises: Obtain a preset hotspot temperature prediction model; Obtaining a training run data set and a test run data set; the training run data set includes multiple sets of training run data, each set of training run data includes: training hotspot temperature, training top oil temperature, training ambient temperature, training load rate, and training run time; the test run data set includes multiple sets of test run data, each set of test run data includes: actual hotspot temperature, actual top oil temperature, actual ambient temperature, actual load rate, and actual run time; Taking the training top oil temperature, training ambient temperature, training load rate and training running time of each set of training running data in the multiple sets of training running data as input and the training hotspot temperature as output, the preset hotspot temperature prediction model is trained to obtain a candidate hotspot temperature prediction model; Inputting the actual top oil temperature, actual ambient temperature, actual load rate, and actual operating time of each set of test operation data into the candidate hotspot temperature prediction model to obtain a plurality of expected hotspot temperatures; determining a loss compensation value according to the plurality of expected hotspot temperatures and an actual hotspot temperature corresponding to each set of test operation data in the plurality of sets of test operation data; According to the loss compensation value, the model parameters of the candidate hotspot temperature prediction model are adjusted to obtain the hotspot temperature prediction model.

7. The method according to claim 6, characterized in that The determining of the loss compensation value according to the multiple expected hotspot temperatures and the actual hotspot temperature corresponding to each set of test operation data in the multiple sets of test operation data includes: The loss compensation value is expressed by the following formula: Where L represents the loss compensation value, D represents the number of groups of test run data, and Y i1 represents the actual hotspot temperature corresponding to the i-th group of test running data in multiple groups of test running data, Y i0 represents the expected hotspot temperature corresponding to the i-th set of test run data.

8. A transformer temperature control device, characterized in that: include: an acquisition unit, configured to acquire temperature data of a transformer at a current moment; the transformer comprising: a high-voltage winding, a low-voltage winding, an oil tank, and a cooling device; the oil tank comprising cooling oil, the cooling oil being in contact with the high-voltage winding and the low-voltage winding; the oil tank being connected to the cooling device via a cooling oil inlet pipe and a cooling oil outlet pipe; the cooling device being configured to cool the cooling oil in the cooling oil outlet pipe and transport the cooled cooling oil to the oil tank via the cooling oil inlet pipe; the temperature data comprising a cooling oil inlet temperature of the cooling oil inlet pipe and a cooling oil outlet temperature of the cooling oil outlet pipe; a processing unit, configured to instruct the cooling device to perform a temperature control operation based on the cooling oil inlet temperature and the cooling oil outlet temperature; the temperature control operation is configured to ensure that a difference between a cooling oil temperature difference between the cooling oil outlet temperature and the cooling oil inlet temperature and a minimum cooling oil temperature difference corresponding to the transformer is greater than or equal to a preset difference; The acquisition unit is configured to acquire operating data of the transformer after the cooling device performs the temperature control operation; the operating data includes: hot spot temperature, top oil temperature, ambient temperature, load rate, and operating time; the hot spot temperature is the temperature of the surface of the low-voltage winding of the transformer; the top oil temperature is the temperature of the top of the oil tank; the ambient temperature is the temperature at a preset distance from the surface of the transformer; the load rate is the ratio of the load power of the transformer to the rated power; and the operating time is the time between the start-up time of the transformer and the acquisition time of the operating data; The processing unit is configured to input the top oil temperature, the ambient temperature, the load rate, and the operating time into a hotspot temperature prediction model to obtain a target hotspot temperature; The acquisition unit is used to acquire multiple historical hot spot temperatures of the transformer; The processing unit is configured to perform curve fitting on the multiple historical hotspot temperatures to obtain a hotspot temperature curve; The hotspot temperature is PID-controlled according to the hotspot temperature, the target hotspot temperature, and the hotspot temperature curve to adjust the hotspot temperature to the target hotspot temperature.

9. An electronic device, characterized in that: include: A processor and a memory, the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs 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 a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images