Transformer operation control method, device, equipment, medium and program product

Abstract

The present invention relates to the technical field of transformers and discloses a transformer operation control method, device, equipment, medium and program product. The transformer operation control method comprises: obtaining oil temperature data of multiple positions in the transformer in a first preset time period, performing feature extraction and fusion on the oil temperature data of the multiple positions to obtain target oil temperature data for the first preset time period; analyzing the uniformity of the target oil temperature data to obtain a first target temperature entropy for the first preset time period; the first target temperature entropy is used to characterize the uniformity of the oil temperature distribution of the transformer; judging whether the first target temperature entropy for the first preset time period is less than a first preset value; if the first target temperature entropy for the first preset time period is less than the first preset value, controlling the transformer to operate normally. The present invention judges whether a transformer fault occurs based on the first target temperature entropy that characterizes the uniformity of the oil temperature distribution of the transformer, thereby improving the accuracy of transformer fault judgment.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and in particular to a method, device, equipment, medium and program product for controlling the operation of a transformer. Background Art

[0002] In power systems, transformers are critical equipment, and their safe and stable operation is crucial to ensuring power supply. Traditional transformer oil temperature protection methods often use the limit state method, which involves installing two upper and lower oil temperature sensors in the transformer body and using protection judgment logic to monitor and protect the transformer.

[0003] Specifically, the traditional transformer oil temperature protection method sets two warning temperature values. For example, the two warning temperature values ​​are 75°C and 105°C respectively. When at least one of the upper and lower oil temperatures of the transformer reaches 75°C, the "oil temperature warning" information is reported to the background; when the temperature reaches 105°C, the "oil temperature is too high" information is reported to the background, and the transformer line is directly tripped and cut off to protect the transformer body.

[0004] However, this traditional transformer oil temperature protection method cannot accurately set the temperature warning value. For example, in seasons with high ambient temperatures such as summer, when the transformer is operating at full load, the oil temperature can easily reach 75°C, resulting in frequent false alarms and low transformer operating stability. Summary of the Invention

[0005] In view of this, the present invention provides a transformer operation control method, device, equipment, medium and program product to solve the problem of low normal operation stability of the transformer caused by traditional transformer oil temperature protection methods.

[0006] In a first aspect, the present invention provides an operation control method for a transformer, comprising: obtaining oil temperature data of multiple positions in the transformer in a first preset time period, performing feature extraction and fusion on the oil temperature data of the multiple positions, and obtaining target oil temperature data for the first preset time period; wherein the target oil temperature data is used to reflect the oil temperature distribution characteristics of the transformer; analyzing the uniformity of the target oil temperature data to obtain a first target temperature entropy for the first preset time period; the first target temperature entropy is used to characterize the uniformity of the oil temperature distribution of the transformer; judging whether the first target temperature entropy for the first preset time period is less than a first preset value, and if the first target temperature entropy for the first preset time period is less than the first preset value, controlling the transformer to operate normally.

[0007] The present invention obtains oil temperature data of multiple positions of the transformer in the first preset time period, and can comprehensively and meticulously obtain oil temperature data of various positions inside the transformer, greatly improving the accuracy of transformer oil temperature monitoring and providing a reliable data basis for timely discovery of potential faults. The present invention performs feature extraction and fusion on the oil temperature data of multiple positions to obtain target oil temperature data for the first preset time period. The target oil temperature data can more accurately reflect the complex temperature distribution and changes inside the transformer. The present invention analyzes the uniformity of the target oil temperature data to obtain the first target temperature entropy of the first preset time period, and uses the first target temperature entropy to characterize the uniformity of the transformer oil temperature distribution. The transformer operation is controlled by judging the relationship between the first target temperature entropy and the first preset value. If the first target temperature entropy is less than the first preset value, it indicates that the uniformity of the oil temperature distribution is good, the transformer operation state is stable, and the transformer can be controlled to operate normally. Compared with related technologies, the first target temperature entropy of the present invention can comprehensively consider the dynamic fluctuations of oil temperature and the distribution of oil temperature in multiple directions, and can more accurately capture subtle changes in the operating status of the transformer and respond in a timely manner, effectively avoiding false alarms caused by a single temperature indicator, avoiding unnecessary shutdowns and maintenance, and improving the stability and reliability of transformer operation.

[0008] In an optional embodiment, feature extraction and fusion are performed on oil temperature data from multiple directions to obtain target oil temperature data for a first preset time period, including: dividing the oil temperature data from each direction according to a preset temperature interval to obtain multiple temperature intervals; determining the mean and standard deviation of the oil temperature data corresponding to each temperature interval, and converting the oil temperature data corresponding to each temperature interval to a standard normal distribution based on the mean and standard deviation to obtain multiple conversion results; performing nonlinear transformation on the multiple conversion results to obtain multiple transformation results, and summing the multiple transformation results to obtain a summation result; and normalizing the summation result to obtain the target oil temperature data for the first preset time period.

[0009] The present invention divides the oil temperature data of each direction according to a preset temperature interval to obtain multiple temperature intervals, determines the mean and standard deviation of the oil temperature data corresponding to each temperature interval, and can organize the original chaotic oil temperature data into a form with statistical regularity. The mean can reflect the central trend of the oil temperature data of each temperature interval, and the standard deviation can reflect the degree of dispersion of the oil temperature data of each temperature interval. According to the mean and standard deviation, the oil temperature data corresponding to each temperature interval is converted to a standard normal distribution to obtain multiple conversion results, unifying the oil temperature data of different temperature intervals under the same measurement standard, and eliminating the influence of the original data dimension and distribution differences. The present invention performs nonlinear transformation on multiple conversion results and adjusts the weight of the temperature data of each temperature interval. It can highlight the difference in the entropy calculation of the first target temperature of the oil temperature data of different temperature intervals, which is more in line with the characteristics of the influence of different temperature intervals on the transformer state in actual conditions. The present invention sums the nonlinear transformation results to achieve the fusion of oil temperature data in different directions, normalizes the summation results, maps the summation results to a specific range, and unifies the oil temperature data in different directions and temperature ranges in terms of dimension, which can more accurately reflect the importance of all oil temperature data of the transformer in the calculation of the first target temperature entropy.

[0010] In an optional embodiment, the uniformity of the target oil temperature data is analyzed to obtain the first target temperature entropy of the first preset time period, including: performing logarithmic processing on the target oil temperature data to obtain a first processing result; determining a second processing result based on the product of the first processing result and a preset value; and integrating the second processing result to obtain the first target temperature entropy of the first preset time period.

[0011] The oil temperature data of the present invention may fluctuate greatly. Logarithmic processing can convert exponential changes into linear changes, avoid the excessive influence of individual extreme values ​​on the overall calculation, and make the differences between different temperature ranges more balanced in the calculation results. The second processing result is determined based on the product of the first processing result and the preset value, which can unify the calculation benchmarks for different transformers or different operating conditions. The second processing result is integrated to obtain the first target temperature entropy for the first preset time period, which can make short-term fluctuations smoother and make the first target temperature entropy more stably reflect the uniformity of the oil temperature data distribution.

[0012] In an optional embodiment, after analyzing the uniformity of the target oil temperature data and obtaining the first target temperature entropy of the first preset time period, the method also includes: correcting the first target temperature entropy using a first compensation function and a second compensation function; the first compensation function is a function that increases the degree of compensation as the temperature increases, and the second compensation function is a function that increases the degree of compensation as the load increases.

[0013] The first compensation function of the present invention more accurately reflects the nonlinear effect of temperature on the transformer state. The first compensation function is used to correct the first target temperature entropy, making the corrected first target temperature entropy more consistent with the actual operation of the transformer under different temperature conditions. Because high loads increase the operating pressure of the transformer, a greater degree of compensation is required in the calculation of the first target temperature entropy to accurately reflect the impact of load on the transformer state. The present invention uses a second compensation function to adjust the first target temperature entropy, incorporating load factors into the calculation of the first target temperature entropy, so that the corrected first target temperature entropy better reflects the actual operation of the transformer under different load conditions.

[0014] In an optional embodiment, the operation control method of the transformer further includes: if the first target temperature entropy of the first preset time period is greater than or equal to the first preset value, and the first target temperature entropy of the first preset time period is less than the second preset value, sending an early warning message to the control background, and respectively obtaining the oil temperature data of multiple positions in the transformer in the second preset time period, the third preset time period and the fourth preset time period; the second preset value is greater than the first preset value, the first preset time period is less than the second preset time period, the second preset time period is less than the third preset time period, and the third preset time period is less than the fourth preset time period; using the oil temperature data of the second preset time period, the third preset time period and the third preset time period respectively to update the oil temperature data of the first preset time period, and returning the oil temperature data of the multiple positions. The steps of feature extraction and fusion of the oil temperature data of the second preset time period, until the second target temperature entropy of the second preset time period, the third target temperature entropy of the third preset time period and the fourth target temperature entropy of the fourth preset time period are obtained; if the second target temperature entropy, the third target temperature entropy and the fourth target temperature entropy are all within the preset range, the transformer is controlled to be disconnected; the preset range is the range between the first preset value and the second preset value; if there is a temperature entropy less than the first preset value among the second target temperature entropy, the third target temperature entropy and the fourth target temperature entropy, a cancellation warning message is sent to the control background, and the transformer is controlled to operate normally; if there is a temperature entropy greater than or equal to the second preset value among the second target temperature entropy, the third target temperature entropy and the fourth target temperature entropy, the transformer is controlled to be disconnected.

[0015] When the first target temperature entropy falls between the first and second preset values, the present invention sends an early warning message to identify abnormal trends in the transformer's oil temperature distribution, buying time for troubleshooting. Simultaneously, by continuously updating and analyzing oil temperature data from the second, third, and fourth preset time periods, the system dynamically tracks the oil temperature distribution, avoiding misjudgments based on data from a single time period and improving the accuracy and reliability of abnormality detection.

[0016] In an optional embodiment, the transformer operation control method further includes: if the first target temperature entropy in the first preset time period is greater than or equal to a second preset value, controlling the transformer to disconnect.

[0017] In a second aspect, the present invention provides an operation control device for a transformer, comprising: a feature fusion module for acquiring oil temperature data of multiple positions in the transformer in a first preset time period, performing feature extraction and fusion on the oil temperature data of multiple positions, and obtaining target oil temperature data for the first preset time period; wherein the target oil temperature data is used to reflect the oil temperature distribution characteristics of the transformer; a uniformity analysis module for analyzing the uniformity of the target oil temperature data to obtain a first target temperature entropy for the first preset time period; the first target temperature entropy is used to characterize the uniformity of the oil temperature distribution of the transformer; a transformer control module for determining whether the first target temperature entropy for the first preset time period is less than a first preset value, and if the first target temperature entropy for the first preset time period is less than the first preset value, controlling the normal operation of the transformer.

[0018] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the transformer operation control method of the first aspect or any corresponding embodiment thereof.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the transformer operation control method of the first aspect or any corresponding embodiment thereof.

[0020] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, which are used to enable a computer to execute the transformer operation control method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in related technologies, the following briefly introduces the drawings required for use in the specific embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 4 is a flow chart of a transformer operation control method according to an embodiment of the present invention.

[0023] Figure 2 2 is a flow chart of oil temperature data acquisition according to an embodiment of the present invention.

[0024] Figure 3 2 is a schematic diagram of the logic relationship of the tripping circuit according to an embodiment of the present invention.

[0025] Figure 4 1 is a schematic diagram of the logic relationship of the closing circuit according to an embodiment of the present invention.

[0026] Figure 5 2 is a schematic diagram of the opening and closing control process according to an embodiment of the present invention.

[0027] Figure 6 2 is a schematic diagram of transformer control judgment logic according to an embodiment of the present invention.

[0028] Figure 7 4 is a flow chart of another operation control method of a transformer according to an embodiment of the present invention.

[0029] Figure 8 4 is a structural block diagram of a transformer operation control device according to an embodiment of the present invention.

[0030] Figure 9 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0032] In power systems, transformers are critical equipment, and their safe and stable operation is crucial to ensuring power supply. Traditional transformer oil temperature protection methods often use the limit state method, which involves installing two oil temperature sensors, one above the other, in the transformer body, using the same protection logic to monitor and protect the transformer.

[0033] Traditional transformer oil temperature protection methods typically set two warning temperature values: 75°C and 105°C. When either of the upper and lower oil temperatures reaches 75°C, an "Oil Temperature Warning" message is sent to the backend. When either of the upper and lower oil temperatures reaches 105°C, an "Oil Temperature Excessive" message is sent to the backend, and the circuit breaker is immediately tripped to protect the transformer. However, this traditional transformer oil temperature protection method has many drawbacks.

[0034] First, it was impossible to accurately set the warning temperature. In high-temperature seasons like summer, when the transformer was operating at full load, the oil temperature could easily reach 75°C, resulting in frequent false alarms. This not only interfered with technicians' assessment of the transformer's actual operating status but also affected its stable operation.

[0035] Secondly, the layout and judgment logic of the transformer's oil temperature sensors are flawed. Typically, the upper oil temperature sensor is located close to the transformer's upper radiator, providing better heat dissipation, while the lower oil temperature sensor is located near the copper windings, which generate more heat. This causes the upper oil temperature to be significantly lower than the lower oil temperature, with the temperature difference reaching over 10 degrees Celsius. In this situation, traditional transformer oil temperature protection methods cannot accurately reflect the actual temperature changes within the transformer, easily leading to misjudgments.

[0036] Furthermore, traditional transformer oil temperature protection methods have a slow response speed. When a fault such as a short circuit occurs within the transformer, the oil temperature rises rapidly, potentially rising from a normal temperature to 75°C in a short period of time, and quickly exceeding 105°C. Due to the limited response speed of traditional transformer oil temperature protection methods, they are unable to respond in time, resulting in serious transformer failures and even damage to the transformer itself, causing losses to the power system.

[0037] An embodiment of the present invention provides a transformer operation control method, which determines whether the transformer has a fault by using a first target temperature entropy that characterizes the uniformity of the transformer's oil temperature distribution, thereby achieving the effect of improving the accuracy of transformer fault judgment.

[0038] According to an embodiment of the present invention, an embodiment of a transformer operation control method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] In this embodiment, a transformer operation control method is provided, which can be used in computer equipment. Figure 1 FIG. 1 is a flow chart of a method for controlling the operation of a transformer according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0040] Step S101, obtaining oil temperature data of multiple positions in the transformer in a first preset time period, performing feature extraction and fusion on the oil temperature data of multiple positions, and obtaining target oil temperature data of the first preset time period; wherein the target oil temperature data is used to reflect the oil temperature distribution characteristics of the transformer.

[0041] The first preset time period can be set according to actual conditions. The first preset time period is set as small as possible to obtain oil temperature data in a short period of time. For example, the first preset time period can be 1 second.

[0042] In some optional embodiments, six oil temperature sensors are provided on the transformer, namely, top, bottom, left, right, front, and rear. These sensors are placed at the center of the six surfaces inside the transformer respectively. Through the sensors in six directions, the oil temperature data of the six directions in the transformer within 1 second are obtained.

[0043] For example, Figure 2 As shown, this is a schematic diagram of the oil temperature data acquisition process. The upper oil temperature sensor located at the center of the upper surface of the transformer collects the oil temperature data of the upper surface of the transformer, the lower oil temperature sensor located at the center of the lower surface of the transformer collects the oil temperature data of the lower surface of the transformer, the left oil temperature sensor located at the center of the left surface of the transformer collects the oil temperature data of the left surface of the transformer, the right oil temperature sensor located at the center of the right surface of the transformer collects the oil temperature data of the right surface of the transformer, the front oil temperature sensor located at the center of the front surface of the transformer collects the oil temperature data of the front surface of the transformer, and the rear oil temperature sensor located at the center of the rear surface of the transformer collects the oil temperature data of the rear surface of the transformer. The oil temperature data of the upper surface, the lower surface, the left surface, the right surface, the front surface and the rear surface constitute the oil temperature data of the transformer.

[0044] Step S102 : Analyze the uniformity of the target oil temperature data to obtain a first target temperature entropy for a first preset time period; the first target temperature entropy is used to characterize the uniformity of the oil temperature distribution of the transformer.

[0045] The first target temperature entropy characterizes the uniformity of the transformer's oil temperature distribution. When the ambient temperature is high or the transformer load is high, the overall oil temperature rises. Due to the relative stability of heat transfer within the transformer, the temperature changes detected by the six oil temperature sensors are consistent. Therefore, the first target temperature entropy remains stable and low. When a fault occurs within the transformer, the local oil temperature gradually rises, and the temperature changes detected by the six oil temperature sensors are inconsistent, causing the overall oil temperature state to become chaotic. The more chaotic the transformer's internal oil temperature data, the greater the first target temperature entropy. Therefore, by monitoring changes in the first target temperature entropy, internal transformer faults can be detected.

[0046] In some optional embodiments, feature extraction and fusion are performed on oil temperature data from multiple directions to obtain target oil temperature data for a first preset time period, including: dividing the oil temperature data from each direction according to a preset temperature interval to obtain multiple temperature intervals; determining the mean and standard deviation of the oil temperature data corresponding to each temperature interval, and converting the oil temperature data corresponding to each temperature interval to a standard normal distribution based on the mean and standard deviation to obtain multiple conversion results; performing nonlinear transformation on the multiple conversion results to obtain multiple transformation results, summing the multiple transformation results to obtain a summation result; and normalizing the summation result to obtain the target oil temperature data for the first preset time period.

[0047] Step S103 , determining whether the first target temperature entropy in the first preset time period is less than a first preset value; if the first target temperature entropy in the first preset time period is less than the first preset value, controlling the transformer to operate normally.

[0048] The first preset value may be set according to actual conditions. For example, the first preset value may be 0.3.

[0049] In some optional implementations, if the first target temperature entropy in the first preset time period is greater than or equal to a second preset value, the transformer is controlled to be disconnected.

[0050] In some optional implementations, if the first target temperature entropy of the first preset time period is greater than or equal to the first preset value, and the first target temperature entropy of the first preset time period is less than the second preset value, an early warning message is sent to the control background, and the oil temperature data of multiple positions in the transformer in the second preset time period, the third preset time period and the fourth preset time period are obtained respectively; the second preset value is greater than the first preset value, the first preset time period is less than the second preset time period, the second preset time period is less than the third preset time period, and the third preset time period is less than the fourth preset time period; the oil temperature data of the second preset time period, the third preset time period and the third preset time period are used to update the oil temperature data of the first preset time period respectively, and the oil temperature data of multiple positions are returned. Perform feature extraction and fusion steps until a second target temperature entropy of a second preset time period, a third target temperature entropy of a third preset time period, and a fourth target temperature entropy of a fourth preset time period are obtained; if the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy are all within a preset range, the transformer is controlled to disconnect; the preset range is a range between a first preset value and a second preset value; if any of the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy is less than the first preset value, a warning cancellation message is sent to the control background, and the transformer is controlled to operate normally; if any of the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy is greater than or equal to the second preset value, the transformer is controlled to disconnect.

[0051] Among them, the second preset value can be set according to actual conditions. For example, the second preset value can be 0.7. The second preset time period, the third preset time period and the third preset time period can be set according to actual conditions. For example, the second preset time period can be 15 seconds, the third preset time period can be 30 seconds, and the fourth preset time period can be 60 seconds.

[0052] In some optional embodiments, the normal operation of the transformer is controlled by a closing circuit. When the closing circuit is turned on, the transformer operates normally. The disconnection of the transformer is controlled by an opening circuit. When the opening circuit is turned on, the transformer is disconnected.

[0053] Among them, the opening circuit is controlled by two control circuits, and the closing circuit is controlled by two control circuits; for example, Figure 3 As shown in the figure, it is a schematic diagram of the logic relationship of the opening circuit. The first control circuit, the second control circuit and the opening circuit are arranged in series. Only when the first control circuit and the second control circuit are closed, the opening circuit is turned on. When the opening circuit is turned on, the transformer performs the opening operation and the transformer is disconnected. Figure 4 As shown in the figure, it is a schematic diagram of the logical relationship of the closing circuit. The third control circuit, the fourth control circuit and the closing circuit are arranged in series. Only when the third control circuit and the fourth control circuit are closed, the closing circuit is turned on. When the closing circuit is turned on, the transformer performs the closing operation and the transformer operates normally.

[0054] In some optional embodiments, the computer device that controls the operation control method of the transformer is provided with a transformer body control opening and closing module, such as Figure 5 The figure shows a schematic diagram of the opening and closing control process. When the first control loop and the second control loop are both closed, the transformer body controls the opening and closing module to send an opening signal to the transformer to perform the transformer opening operation. When the third control loop and the fourth control loop are both closed, the transformer body controls the opening and closing module to send a closing signal to the transformer to perform the transformer closing operation.

[0055] For example, Figure 6As shown, it is a schematic diagram of transformer control judgment logic, which judges whether the first target temperature entropy of 1 second is less than 0.3. When the first target temperature entropy is less than 0.3, it is judged that the transformer is in normal state, and the first control loop and the second control loop are controlled to be disconnected, and the third control loop and the fourth control loop are controlled to be closed to make the transformer operate normally; when the first target temperature entropy is greater than or equal to 0.3, it is judged whether the first target temperature entropy is greater than or equal to 0.7. When the first target temperature entropy is greater than or equal to 0.7, it is judged that the transformer is in fault state, and the first control loop and the second control loop are controlled to be closed, and the third control loop and the fourth control loop are controlled to be disconnected, so that the tripping loop is turned on, and a tripping instruction is sent to the transformer to control the transformer to disconnect; when the first target temperature entropy is greater than or equal to 0.3, and the first target temperature entropy is less than 0.7, it is judged that the transformer is in early warning state, and the first control loop is controlled to be closed, the second control loop is disconnected, and the third control loop and the fourth control loop are controlled to be closed, and an early warning message is sent to the control background, and it lasts Calculate the second target temperature entropy at 15 seconds, the third target temperature entropy at 30 seconds, and the fourth target temperature entropy at 60 seconds. When the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy are all less than 0.7, and the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy are all greater than or equal to 0.3, control the second control loop to close, control the third control loop and the fourth control loop to disconnect, so that the tripping loop is turned on, and send a tripping instruction to the transformer to control the transformer to disconnect; when any target temperature entropy of the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy is less than 0.3, control the first control loop to disconnect, cancel the early warning state, and control the normal operation of the transformer; when any target temperature entropy of the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy is greater than or equal to 0.7, control the second control loop to close, control the third control loop and the fourth control loop to disconnect, so that the tripping loop is turned on, and send a tripping instruction to the transformer to control the transformer to disconnect.

[0056] In the embodiment of the present invention, when the first target temperature entropy is less than 0.3, it means that the transformer oil temperature distribution is relatively uniform and orderly, and the transformer is controlled to operate normally; when the first target temperature entropy is greater than or equal to 0.7, it means that under the combined influence of temperature and load, the temperature abnormality in multiple areas of the transformer has spread, and the oil temperature distribution is in a highly chaotic state, and the transformer is controlled to be disconnected so that technicians can conduct a comprehensive inspection and maintenance of the transformer; when the first target temperature entropy is greater than or equal to 0.3, and the first target temperature entropy is less than 0.7, it means that after considering the temperature and load factors, the transformer may have signs of local overheating, and the oil temperature distribution begins to become chaotic to a certain extent. Therefore, the transformer is first controlled to operate normally, and an early warning message is sent to the control background. The second target temperature entropy at 15 seconds, the third target temperature entropy at 30 seconds, and the fourth target temperature entropy at 60 seconds are continuously calculated. In the early warning state In the state, when the second target temperature entropy, the third target temperature entropy and the fourth target temperature entropy are all less than 0.7, and the second target temperature entropy, the third target temperature entropy and the fourth target temperature entropy are all greater than or equal to 0.3, it means that the oil temperature distribution of the transformer is still relatively chaotic during continuous monitoring, and therefore, the transformer is controlled to be disconnected for maintenance; in the early warning state, when any one of the second target temperature entropy, the third target temperature entropy and the fourth target temperature entropy is less than 0.3, it means that the oil temperature distribution of the transformer tends to be uniform during continuous monitoring, and then the early warning state is canceled and the transformer is controlled to operate normally; in the early warning state, when any one of the second target temperature entropy, the third target temperature entropy and the fourth target temperature entropy is greater than or equal to 0.7, it means that the oil temperature distribution of the transformer is becoming more and more chaotic during continuous monitoring, and then the transformer is controlled to be disconnected for maintenance.

[0057] This embodiment of the present invention sends an early warning when the first target temperature entropy falls between the first and second preset values, providing early notification of abnormal trends in the transformer's oil temperature distribution and buying time for troubleshooting. Furthermore, by continuously updating and analyzing oil temperature data from the second, third, and fourth preset time periods, dynamic tracking of the oil temperature distribution is achieved, avoiding misjudgments based on data from a single time period and improving the accuracy and reliability of abnormality detection.

[0058] The transformer operation control method provided by this embodiment obtains the oil temperature data of multiple positions of the transformer in the first preset time period, and can comprehensively and meticulously obtain the oil temperature data of each position inside the transformer, which greatly improves the accuracy of transformer oil temperature monitoring and provides a reliable data basis for timely discovery of potential faults. The embodiment of the present invention performs feature extraction and fusion on the oil temperature data of multiple positions to obtain the target oil temperature data of the first preset time period. The target oil temperature data can more accurately reflect the complex temperature distribution and changes inside the transformer. The embodiment of the present invention analyzes the uniformity of the target oil temperature data to obtain the first target temperature entropy of the first preset time period, and uses the first target temperature entropy to characterize the uniformity of the transformer oil temperature distribution. The operation of the transformer is controlled by judging the relationship between the first target temperature entropy and the first preset value. If the first target temperature entropy is less than the first preset value, it indicates that the uniformity of the oil temperature distribution is good, the transformer operation state is stable, and the transformer can be controlled to operate normally. Compared with the related art, the first target temperature entropy of the embodiment of the present invention can comprehensively consider the dynamic fluctuations of oil temperature and the distribution of oil temperature in multiple directions, and can more accurately capture subtle changes in the operating status of the transformer and respond in a timely manner, effectively avoiding false alarms caused by a single temperature indicator, avoiding unnecessary shutdowns and maintenance, and improving the stability and reliability of transformer operation.

[0059] In this embodiment, a transformer operation control method is provided, which can be used in computer equipment. Figure 7 FIG. 1 is a flow chart of another operation control method of a transformer according to an embodiment of the present invention. Figure 7 As shown, the process includes the following steps:

[0060] Step S701, obtaining oil temperature data of multiple positions in the transformer in a first preset time period, performing feature extraction and fusion on the oil temperature data of multiple positions, and obtaining target oil temperature data of the first preset time period; wherein the target oil temperature data is used to reflect the oil temperature distribution characteristics of the transformer.

[0061] Specifically, the above step S701 includes:

[0062] Step S7011: Divide the oil temperature data of each direction into preset temperature intervals to obtain multiple temperature intervals.

[0063] The preset temperature interval can be set according to actual conditions. For example, the preset temperature interval can be 0.05°C. Then the oil temperature data of each direction is divided by 0.05°C. The obtained multiple temperature intervals may include (20, 20.05), (20.05, 20.10), etc. The number of the obtained multiple temperature intervals can be expressed as ,in, =1, 2, 3, 4, 5, 6, which correspond to the numbers of the six oil temperature sensors. For example, in a certain collection cycle, the data collected by the upper oil temperature sensor are divided into Temperature intervals, and at the same time, count the number of oil temperature data in each temperature interval , for example, in the number (Upper oil temperature sensor) In the temperature range Temperature data.

[0064] Step S7012: determining the mean and standard deviation of the oil temperature data corresponding to each temperature interval, and transforming the oil temperature data corresponding to each temperature interval into a standard normal distribution according to the mean and standard deviation, to obtain a plurality of transformation results.

[0065] Among them, when the number is (Upper oil temperature sensor) In the temperature range When the three temperature data are 40.1, 40.12, and 40.08 respectively, the average , the standard deviation is calculated as:

[0066]

[0067] in, For the number Oil temperature sensor The standard deviation of the oil temperature data within a temperature range is For the number The oil temperature sensor The number of oil temperature data in each temperature range, is the location of the oil temperature data, For the number Oil temperature sensor The mean of the oil temperature data in the temperature range, For the The temperature range of Temperature data.

[0068] In some optional implementations, the formula for converting the oil temperature data corresponding to each temperature interval into a standard normal distribution is:

[0069]

[0070] in, For the number Oil temperature sensor The conversion results within the temperature range are For the The temperature range of Temperature data, For the number Oil temperature sensor The standard deviation of the oil temperature data within a temperature range is For the number Oil temperature sensor The mean of the oil temperature data in a temperature range.

[0071] Step S7013: Perform nonlinear transformation on the multiple transformation results to obtain multiple transformation results, and sum the multiple transformation results to obtain a summation result.

[0072] Among them, the use of The function performs nonlinear transformation on multiple transformation results to obtain multiple transformation results. The function relationship is:

[0073]

[0074] in, For pairs numbered Oil temperature sensor A function that performs nonlinear transformation on the conversion results within a temperature range, For the number Oil temperature sensor The conversion results in a temperature range.

[0075] in, The function has special nonlinear properties and can map data to The oil temperature data closer to the mean is weighted higher, while the oil temperature data farther from the mean is weighted lower. This weight distribution method is based on the physical characteristics of transformer operation. Generally, the temperature range close to the mean oil temperature is more representative of the normal operation of the transformer and should contribute more to the first target temperature entropy.

[0076] In some optional embodiments, the oil temperature data of all temperature intervals of the six oil temperature sensors are processed. The multiple transformation results after function adjustment are summed to obtain the summation result, namely:

[0077]

[0078] in, To sum the results, is the number of the oil temperature sensor, Indicates the temperature range, Indicates the number of the same oil temperature sensor temperature range, is the number of temperature intervals, For the number The oil temperature sensor The number of oil temperature data in each temperature range, For the number The oil temperature sensor The number of oil temperature data in each temperature range, For the The temperature range of Temperature data, For the number Oil temperature sensor The standard deviation of the oil temperature data within a temperature range is For the number Oil temperature sensor The mean of the oil temperature data in a temperature range.

[0079] Step S7014: normalize the summation result to obtain target oil temperature data in the first preset time period.

[0080] Among them, the use of The function normalizes the summation result. The expression of the function is:

[0081]

[0082] in, Indicates the The sum of the temperature intervals is is the total number of temperature intervals.

[0083] in, The function converts the sum of the input results into a probability distribution vector, amplifies the elements with larger values ​​through exponential operation, and suppresses the elements with smaller values, so that the sum of the results of all temperature intervals is 1. After the function is processed, the data of different temperature ranges of different oil temperature sensors are unified in dimension. For example, if a temperature range passes through The value after function processing is relatively large. After the function is normalized, the proportion of the probability distribution with a total of 1 will be correspondingly larger, indicating that this temperature range has a higher importance in the overall temperature distribution.

[0084] Step S702 : Analyze the uniformity of the target oil temperature data to obtain a first target temperature entropy for a first preset time period; the first target temperature entropy is used to characterize the uniformity of the oil temperature distribution of the transformer.

[0085] Specifically, the above step S702 includes:

[0086] Step S7021: perform logarithmic processing on the target oil temperature data to obtain a first processing result.

[0087] Step S7022: Determine a second processing result based on the product of the first processing result and a preset value.

[0088] The preset value may be -1.

[0089] Step S7023: Integrate the second processing result to obtain a first target temperature entropy for a first preset time period.

[0090] In some optional implementations, the calculation formula for the first target temperature entropy is:

[0091]

[0092] in, is the first target temperature entropy, is the minimum value of the collected oil temperature data, is the maximum value of the collected oil temperature data, is the number of the oil temperature sensor, Indicates the temperature range, Indicates the number of the same oil temperature sensor temperature range, is the number of temperature intervals, For the number The oil temperature sensor The number of oil temperature data in each temperature range, For the number The oil temperature sensor The number of oil temperature data in each temperature range, For the The temperature range of Temperature data, For the number Oil temperature sensor The standard deviation of the oil temperature data within a temperature range is For the number Oil temperature sensor The mean of the oil temperature data in a temperature range.

[0093] In some optional embodiments, after analyzing the uniformity of the target oil temperature data and obtaining the first target temperature entropy of the first preset time period, the method further includes: correcting the first target temperature entropy using a first compensation function and a second compensation function; the first compensation function is a function that increases the degree of compensation as the temperature increases, and the second compensation function is a function that increases the degree of compensation as the load increases.

[0094] In an embodiment of the present invention, the first target temperature entropy is corrected using the first compensation function and the second compensation function, and it is determined whether the corrected first target temperature entropy of the first preset time period is less than the first preset value. If the corrected first target temperature entropy of the first preset time period is less than the first preset value, the transformer is controlled to operate normally.

[0095] The first compensation function may be a temperature compensation function, and the expression of the first compensation function is:

[0096]

[0097] in, is the first compensation function, is the first adjustment parameter, is the second adjustment parameter, For the The temperature range of Temperature data, is the reference temperature, which is determined based on multiple factors such as the transformer's design parameters, historical operating data, and industry standards. For example, It can be 50.

[0098] in, and The temperature compensation function is obtained through a large number of experiments and actual operation data fitting, and is used to adjust the shape and compensation degree of the temperature compensation function to adapt to the characteristics of different transformers. For example, , .

[0099] In some optional embodiments, as the temperature Above reference temperature , exponential term will increase, leading to The value of decreases, that is, the higher the temperature, the more obvious the compensation effect. This is because the operating state of the transformer is more unstable at high temperature, and a larger compensation needs to be given in the calculation of the first target temperature entropy to more accurately reflect its impact on the overall state of the transformer.

[0100] The second compensation function may be a load compensation function, and the expression of the second compensation function is:

[0101]

[0102] in, is the real-time load of the transformer, is the rated load of the transformer, is the third adjustment parameter, is the fourth adjustment parameter, and The sensitivity and compensation strength of the load compensation function can be adjusted based on the load-temperature characteristic curve of the transformer and actual operating experience. For example, , .

[0103] in, It indicates the ratio of real-time load to rated load, reflecting the current load level of the transformer. Close to or exceeding the rated load hour, The value of will increase, resulting in The value of decreases, that is, the higher the load, the more significant the compensation effect. This is because high load will increase the operating pressure of the transformer and have a more serious impact on its status. Therefore, a greater degree of compensation is required in the calculation of the first target temperature entropy to accurately reflect the impact of the load on the transformer status.

[0104] In some optional implementations, after the calculation formula of the first target temperature entropy is updated using the first compensation function and the second compensation function, the resulting relationship is:

[0105]

[0106] in, is the first target temperature entropy, is the minimum value of the collected oil temperature data, is the maximum value of the collected oil temperature data, is the number of the oil temperature sensor, Indicates the temperature range, Indicates the number of the same oil temperature sensor temperature range, is the number of temperature intervals, For the number The oil temperature sensor The number of oil temperature data in each temperature range, For the number The oil temperature sensor The number of oil temperature data in each temperature range, For the The temperature range of Temperature data, For the number Oil temperature sensor The standard deviation of the oil temperature data within a temperature range is For the number Oil temperature sensor The mean of the oil temperature data in the temperature range, is the first compensation function, is the second compensation function.

[0107] The first compensation function in this embodiment of the present invention more accurately reflects the nonlinear effect of temperature on the transformer's state. The first compensation function is used to correct the first target temperature entropy, making the corrected first target temperature entropy more consistent with the transformer's actual operating conditions under different temperature conditions. Because high loads increase the transformer's operating pressure, greater compensation is required in the calculation of the first target temperature entropy to accurately reflect the load's effect on the transformer's state. This embodiment of the present invention uses a second compensation function to adjust the first target temperature entropy, incorporating load factors into the calculation of the first target temperature entropy. This allows the corrected first target temperature entropy to better reflect the transformer's actual operating conditions under different load conditions.

[0108] Step S703: determine whether the first target temperature entropy of the first preset time period is less than the first preset value. If the first target temperature entropy of the first preset time period is less than the first preset value, control the transformer to operate normally. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0109] The embodiment of the present invention divides the oil temperature data of each direction according to a preset temperature interval to obtain multiple temperature intervals, determines the mean and standard deviation of the oil temperature data corresponding to each temperature interval, and can organize the original chaotic oil temperature data into a form with statistical regularity. The mean can reflect the central trend of the oil temperature data of each temperature interval, and the standard deviation can reflect the degree of dispersion of the oil temperature data of each temperature interval. According to the mean and standard deviation, the oil temperature data corresponding to each temperature interval is converted to a standard normal distribution to obtain multiple conversion results, and the oil temperature data of different temperature intervals are unified under the same measurement standard, eliminating the influence of the original data dimension and distribution differences. The embodiment of the present invention performs nonlinear transformation on multiple conversion results and adjusts the weight of the temperature data of each temperature interval. It can highlight the difference in the entropy calculation of the first target temperature of the oil temperature data of different temperature intervals, which is more in line with the characteristics of the influence of different temperature intervals on the transformer state in actual conditions. The embodiment of the present invention sums the results of the nonlinear transformation to achieve the fusion of oil temperature data from different directions, normalizes the summation result, maps the summation result to a specific range, and unifies the dimensions of the oil temperature data from different directions and temperature ranges, thereby more accurately reflecting the importance of all oil temperature data of the transformer in the calculation of the first target temperature entropy. The oil temperature data in the embodiment of the present invention may fluctuate greatly. Logarithmic processing can convert exponential changes into linear changes, avoid the excessive impact of individual extreme values ​​on the overall calculation, and make the differences between different temperature ranges more evenly reflected in the calculation results. The second processing result is determined based on the product of the first processing result and the preset value, which can unify the calculation benchmarks for different transformers or different operating conditions. The second processing result is integrated to obtain the first target temperature entropy for the first preset time period, which can smooth short-term fluctuations and make the first target temperature entropy more stably reflect the uniformity of the oil temperature data distribution.

[0110] This embodiment also provides a transformer operation control device for implementing the above-mentioned embodiments and preferred implementations. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0111] This embodiment provides a transformer operation control device, such as Figure 8 Shown, including:

[0112] The feature fusion module 801 is used to obtain oil temperature data at multiple locations in the transformer in a first preset time period, perform feature extraction and fusion on the oil temperature data at multiple locations, and obtain target oil temperature data for the first preset time period; wherein the target oil temperature data is used to reflect the oil temperature distribution characteristics of the transformer.

[0113] The uniformity analysis module 802 is used to analyze the uniformity of the target oil temperature data to obtain a first target temperature entropy for a first preset time period; the first target temperature entropy is used to characterize the uniformity of the oil temperature distribution of the transformer.

[0114] The transformer control module 803 is used to determine whether the first target temperature entropy in the first preset time period is less than the first preset value, and if the first target temperature entropy in the first preset time period is less than the first preset value, control the transformer to operate normally.

[0115] In some optional implementations, the feature fusion module 801 includes:

[0116] The temperature division unit is used to divide the oil temperature data of each direction according to a preset temperature interval to obtain multiple temperature intervals.

[0117] The standard conversion unit is used to determine the mean and standard deviation of the oil temperature data corresponding to each temperature interval, and convert the oil temperature data corresponding to each temperature interval into a standard normal distribution according to the mean and standard deviation to obtain multiple conversion results.

[0118] The nonlinear transformation unit is used to perform nonlinear transformation on the multiple transformation results to obtain multiple transformation results, and to sum the multiple transformation results to obtain a summation result.

[0119] The normalization processing unit is used to perform normalization processing on the summation result to obtain target oil temperature data in a first preset time period.

[0120] In some optional implementations, the uniformity analysis module 802 includes:

[0121] The logarithmic processing unit is used to perform logarithmic processing on the target oil temperature data to obtain a first processing result.

[0122] The multiplication unit is used to determine the second processing result according to the product of the first processing result and the preset value.

[0123] The integral processing unit is used to perform integral processing on the second processing result to obtain a first target temperature entropy in a first preset time period.

[0124] In some optional embodiments, the operation control device of the transformer includes:

[0125] The correction module is used to correct the first target temperature entropy using a first compensation function and a second compensation function; the first compensation function is a function that increases the compensation degree as the temperature increases, and the second compensation function is a function that increases the compensation degree as the load increases.

[0126] In some optional embodiments, the transformer control module 803 is further used to send an early warning message to the control background according to the first target temperature entropy of the first preset time period being greater than or equal to the first preset value, and the first target temperature entropy of the first preset time period being less than the second preset value, and respectively obtain the oil temperature data of multiple positions in the transformer in the second preset time period, the third preset time period and the fourth preset time period; the second preset value is greater than the first preset value, the first preset time period is less than the second preset time period, the second preset time period is less than the third preset time period, and the third preset time period is less than the fourth preset time period; the oil temperature data of the first preset time period is updated using the oil temperature data of the second preset time period, the third preset time period and the third preset time period, respectively, and returns the oil temperature data of multiple positions. The steps of feature extraction and fusion of oil temperature data are performed until a second target temperature entropy of a second preset time period, a third target temperature entropy of a third preset time period, and a fourth target temperature entropy of a fourth preset time period are obtained; when the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy are all within a preset range, the transformer is controlled to be disconnected; the preset range is a range between a first preset value and a second preset value; when there is a temperature entropy less than the first preset value among the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy, a warning cancellation message is sent to the control background, and the transformer is controlled to operate normally; when there is a temperature entropy greater than or equal to the second preset value among the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy, the transformer is controlled to be disconnected.

[0127] In some optional implementations, the transformer control module 803 is further configured to control the transformer to disconnect according to the first target temperature entropy in the first preset time period being greater than or equal to a second preset value.

[0128] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0129] The operation control device of the transformer in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0130] The embodiment of the present invention also provides a computer device having the above Figure 9 The operation control device of the transformer shown.

[0131] See also Figure 9 , Figure 9 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 9As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 9 A processor 10 is taken as an example.

[0132] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0133] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0134] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0135] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0136] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0137] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0138] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0139] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A transformer operation control method, characterized in that: The method comprises: Obtaining oil temperature data at multiple locations in the transformer during a first preset time period, performing feature extraction and fusion on the oil temperature data at multiple locations to obtain target oil temperature data for the first preset time period; wherein the target oil temperature data is used to reflect the oil temperature distribution characteristics of the transformer; Analyzing the uniformity of the target oil temperature data to obtain a first target temperature entropy for the first preset time period; the first target temperature entropy is used to characterize the uniformity of the oil temperature distribution of the transformer; determining whether the first target temperature entropy in the first preset time period is less than a first preset value, and if the first target temperature entropy in the first preset time period is less than the first preset value, controlling the transformer to operate normally; The feature extraction and fusion of the oil temperature data of multiple directions to obtain the target oil temperature data for the first preset time period includes: dividing the oil temperature data of each direction according to preset temperature intervals to obtain multiple temperature intervals; determining the mean and standard deviation of the oil temperature data corresponding to each temperature interval, and converting the oil temperature data corresponding to each temperature interval into a standard normal distribution based on the mean and the standard deviation to obtain multiple conversion results; performing nonlinear transformation on the multiple conversion results to obtain multiple transformation results, summing the multiple transformation results to obtain a summation result; and normalizing the summation result to obtain the target oil temperature data for the first preset time period. The analyzing the uniformity of the target oil temperature data to obtain the first target temperature entropy of the first preset time period includes: performing logarithmic processing on the target oil temperature data to obtain a first processing result; determining a second processing result based on the product of the first processing result and a preset value; and integrating the second processing result to obtain the first target temperature entropy of the first preset time period.

2. The method according to claim 1, characterized in that After analyzing the uniformity of the target oil temperature data to obtain the first target temperature entropy of the first preset time period, the method further includes: The first target temperature entropy is corrected using a first compensation function and a second compensation function; the first compensation function is a function that increases the degree of compensation as the temperature increases, and the second compensation function is a function that increases the degree of compensation as the load increases.

3. The method according to claim 1, characterized in that The method further comprises: If the first target temperature entropy in the first preset time period is greater than or equal to the first preset value, and the first target temperature entropy in the first preset time period is less than the second preset value, send an early warning message to the control background, and obtain the oil temperature data of multiple positions in the transformer in the second preset time period, the third preset time period, and the fourth preset time period respectively; the second preset value is greater than the first preset value, the first preset time period is less than the second preset time period, the second preset time period is less than the third preset time period, and the third preset time period is less than the fourth preset time period; updating the oil temperature data of the first preset time period using the second preset time period, the third preset time period, and the oil temperature data of the third preset time period, respectively, and returning to the step of extracting and fusing features of the oil temperature data of multiple directions until a second target temperature entropy of the second preset time period, a third target temperature entropy of the third preset time period, and a fourth target temperature entropy of the fourth preset time period are obtained; If the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy are all within a preset range, controlling the transformer to disconnect; the preset range is a range between the first preset value and the second preset value; If the temperature entropy among the second target temperature entropy, the third target temperature entropy and the fourth target temperature entropy is less than the first preset value, sending a warning cancellation message to the control background and controlling the normal operation of the transformer; If there is a temperature entropy greater than or equal to the second preset value among the second target temperature entropy, the third target temperature entropy, and the fourth target temperature entropy, the transformer is controlled to be disconnected.

4. The method according to claim 3, characterized in that The method further comprises: If the first target temperature entropy in the first preset time period is greater than or equal to the second preset value, the transformer is controlled to be disconnected.

5. A transformer operation control device, characterized in that: The device comprises: a feature fusion module, configured to obtain oil temperature data at multiple locations in the transformer during a first preset time period, perform feature extraction and fusion on the oil temperature data at multiple locations, and obtain target oil temperature data for the first preset time period; wherein the target oil temperature data is used to reflect the oil temperature distribution characteristics of the transformer; a uniformity analysis module, configured to analyze the uniformity of the target oil temperature data to obtain a first target temperature entropy for the first preset time period; the target temperature entropy is used to characterize the uniformity of the oil temperature distribution of the transformer; a transformer control module, configured to determine whether the first target temperature entropy during the first preset time period is less than a first preset value, and if the first target temperature entropy during the first preset time period is less than the first preset value, control the transformer to operate normally; The feature fusion module includes: a temperature division unit for dividing the oil temperature data of each direction according to a preset temperature interval to obtain multiple temperature intervals; a standard conversion unit for determining the mean and standard deviation of the oil temperature data corresponding to each temperature interval, and converting the oil temperature data corresponding to each temperature interval into a standard normal distribution based on the mean and standard deviation to obtain multiple conversion results; a nonlinear transformation unit for performing nonlinear transformation on the multiple conversion results to obtain multiple conversion results, and summing the multiple conversion results to obtain a summation result; a normalization processing unit for performing normalization processing on the summation result to obtain target oil temperature data in a first preset time period; The uniformity analysis module includes: a logarithmic processing unit for performing logarithmic processing on the target oil temperature data to obtain a first processing result; a multiplication unit for determining a second processing result based on the product of the first processing result and a preset value; and an integral processing unit for integrating the second processing result to obtain a first target temperature entropy for a first preset time period.

6. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the transformer operation control method according to any one of claims 1 to 4 by executing the computer instructions.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the transformer operation control method according to any one of claims 1 to 4.

8. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to cause a computer to execute the transformer operation control method according to any one of claims 1 to 4.

Images