Transformer oil level monitoring method and system based on temperature compensation, medium, program product and terminal

Abstract

According to the transformer oil level monitoring method and system based on temperature compensation, the medium, the program product and the terminal, through combination of multi-sensor fusion and an intelligent algorithm, full-dimension sensing of the running state of the transformer is achieved. Compared with a traditional single-function monitoring device, the traditional device usually only monitors single parameters such as oil level or oil temperature and cannot comprehensively consider the incidence relation among the parameters, so that the recognition accuracy of oil level monitoring is low. According to the method, through fusion analysis of the multi-source data and in combination with learning and analysis capabilities of a machine learning algorithm, potential relationships and fault features behind the data can be mined, and the oil level monitoring and recognition accuracy is remarkably improved. According to the invention, fault hidden dangers can be found more timely and accurately, measures can be taken in a targeted manner for maintenance, and unnecessary inspection and maintenance are reduced, so that the operation and maintenance cost of the whole life cycle of the transformer is effectively reduced.

Description

Technical Field

[0001] The present application relates to the technical field of transformer condition monitoring, and in particular to a transformer oil level monitoring method, system, medium, program product, and terminal based on temperature compensation. Background Art

[0002] In modern power systems, transformers are core equipment for power transmission and distribution. The reliability of their operating status directly determines the safety and stability of the power grid. Real-time monitoring of the transformer's oil level and temperature is crucial for ensuring equipment safety and extending its lifespan. However, widely used traditional oil level monitoring technologies suffer from numerous significant drawbacks, making them unable to meet the high-precision, high-reliability, and real-time requirements for transformer monitoring in modern power systems.

[0003] Traditional technologies rely primarily on fixed threshold alarm mechanisms to monitor oil levels, triggering an alarm when the oil level falls below 90% of the rated value, for example. However, this monitoring method has significant shortcomings. Transformer oil significantly expands and contracts with temperature; for every 10°C change in oil temperature, the oil level fluctuates by approximately 2%-5%. In this scenario, fixed thresholds cannot accurately distinguish between true leaks and oil level deviations caused by temperature fluctuations, resulting in a high false alarm rate of 15%-20%. Furthermore, in extreme environmental conditions, such as temperatures as low as -30°C or high as 40°C, the nonlinear relationship between oil level and temperature is further exacerbated. Traditional monitoring methods are unable to achieve dynamic compensation and accurately reflect the true oil level fluctuations.

[0004] Furthermore, different types of fuel tanks, such as naturally cooled, forced-circulation, and composite fuel tanks, have varying structural characteristics that result in distinct responses to oil level and temperature. However, existing conventional technologies employ a unified model for monitoring and prediction, which inevitably leads to significant prediction errors exceeding ±10%, making it impossible to accurately monitor different tank types.

[0005] Traditional monitoring technologies also lack targeted anomaly detection rules. This makes it easy to miss critical faults, such as subtle oil level changes in the early stages of a slow leak, and prevent timely detection of potential safety hazards. Regarding temperature control, traditional methods rely primarily on manual intervention or simple on / off controls, such as starting and stopping cooling fans at full speed. This approach results in large temperature fluctuations, typically exceeding ±5°C. These large temperature fluctuations accelerate the aging of the insulating oil and shorten the transformer's service life.

[0006] Furthermore, traditional technologies exhibit a lag in responding to abnormalities, often exceeding five minutes, which falls far short of the real-time requirements of smart grids. According to the IEC 61850 standard, action delays should be less than one second, but traditional technologies clearly fall short in this regard, unable to promptly handle and regulate abnormal situations, posing significant safety risks. Summary of the Invention

[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides a transformer oil level monitoring method, system, medium, program product and terminal based on temperature compensation, which are used to solve the problems of traditional technology relying on a fixed threshold alarm mechanism to monitor the oil level, resulting in a high false alarm rate, inability to achieve dynamic compensation, inability to accurately monitor different oil tank types, temperature control method mainly relying on manual intervention or simple switch control, and hysteresis in abnormal response.

[0008] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides a transformer oil level monitoring method based on temperature compensation, including: collecting real-time operating condition data of the target transformer, and obtaining an oil level abnormality judgment model and an oil temperature prediction model corresponding to the oil tank type of the target transformer; inputting the real-time operating condition data into the oil level abnormality judgment model, and outputting the oil level abnormality judgment result of the target transformer; performing an early warning operation according to the oil level abnormality judgment result of the target transformer, or performing a temperature compensation control operation in combination with the oil temperature prediction model.

[0009] In some embodiments of the first aspect of the present application, the process of performing an early warning operation based on the oil level abnormality judgment result of the target transformer includes: when the oil level abnormality judgment result of the target transformer is an oil level abnormality, generating an early warning instruction, and issuing an early warning signal according to the early warning instruction.

[0010] In some embodiments of the first aspect of the present application, the process of performing temperature compensation control operations based on the oil level abnormality judgment result of the target transformer in combination with the oil temperature prediction model includes: when the oil level abnormality judgment result of the target transformer is that the oil level is normal, the real-time operating condition data is input into the oil temperature prediction model, and the predicted oil temperature value of the target transformer is output; the real-time oil temperature value in the real-time operating condition data is compared and analyzed with the predicted oil temperature value, and whether to generate a temperature control instruction is determined according to the comparison and analysis result; and the oil temperature of the target transformer is adjusted based on the temperature control instruction.

[0011] In some embodiments of the first aspect of the present application, the real-time oil temperature value in the real-time operating condition data is compared and analyzed with the predicted oil temperature value, and the process of determining whether to generate a temperature control instruction based on the comparison and analysis results includes: calculating the absolute value of the difference between the real-time oil temperature value in the real-time operating condition data and the predicted oil temperature value; if the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is within a preset tolerance range, no temperature control instruction is generated; if the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is not within the preset tolerance range, a temperature reduction instruction or a temperature increase instruction is generated.

[0012] In some embodiments of the first aspect of the present application, if the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is not within a preset tolerance range, the process of generating a temperature reduction instruction or a temperature increase instruction includes: if the real-time oil temperature value is greater than the predicted oil temperature value, a temperature reduction instruction is generated; if the real-time oil temperature value is less than the predicted oil temperature value, a temperature increase instruction is generated.

[0013] In some embodiments of the first aspect of the present application, the process of constructing the oil level abnormality judgment model includes: obtaining historical operating condition data of the transformer, labeling the historical operating condition data with status labels, and obtaining a training data set; using the training data set to train the oil level abnormality judgment model constructed based on the machine learning method until convergence, and obtaining the final oil level abnormality judgment model.

[0014] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides a transformer oil level monitoring system based on temperature compensation, including: a data acquisition and model selection module, used to collect real-time operating condition data of the target transformer, and obtain an oil level abnormality judgment model and an oil temperature prediction model corresponding to the oil tank type of the target transformer; an oil level abnormality judgment module, used to input the real-time operating condition data into the oil level abnormality judgment model, and output the oil level abnormality judgment result of the target transformer; an early warning or temperature compensation module, used to perform an early warning operation according to the oil level abnormality judgment result of the target transformer, or perform a temperature compensation control operation in combination with the oil temperature prediction model.

[0015] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the transformer oil level monitoring method based on temperature compensation when the computer program is executed by a processor.

[0016] To achieve the above-mentioned objectives and other related objectives, the fourth aspect of the present application provides a computer program product, which includes computer program code. When the computer program code is run on a computer, the computer implements the transformer oil level monitoring method based on temperature compensation.

[0017] To achieve the above-mentioned purpose and other related purposes, the fifth aspect of the present application provides an electronic terminal, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the transformer oil level monitoring method based on temperature compensation.

[0018] As described above, the temperature-compensated transformer oil level monitoring method, system, medium, program product, and terminal provided in this application have the following beneficial effects:

[0019] This application achieves full-dimensional perception of the transformer's operating status through the combination of multi-sensor fusion and intelligent algorithms. Compared with traditional single-function monitoring devices, traditional devices often only monitor single parameters such as oil level or oil temperature, and are unable to comprehensively consider the correlation between various parameters, resulting in low recognition accuracy of oil level monitoring. However, this application, through the fusion analysis of multi-source data, combined with the learning and analysis capabilities of machine learning algorithms, can explore the potential relationships and fault characteristics behind the data, significantly improving the recognition accuracy of oil level monitoring. This application can detect hidden faults more promptly and accurately, take targeted measures for maintenance, reduce unnecessary inspections and repairs, and thus effectively reduce the operation and maintenance costs of the transformer throughout its life cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Shown is a flow chart of a transformer oil level monitoring method based on temperature compensation in one embodiment of the present application.

[0021] Figure 2 Shown is a structural schematic diagram of a transformer oil level monitoring system based on temperature compensation in one embodiment of the present application.

[0022] Figure 3 Shown is a structural schematic diagram of an electronic terminal in one embodiment of the present application. DETAILED DESCRIPTION

[0023] The following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand the other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0024] Before further explaining the present invention in detail, the nouns and terms involved in the embodiments of the present invention are explained. The nouns and terms involved in the embodiments of the present invention are subject to the following interpretations:

[0025] <1> Random Forest (RF): An ensemble learning method that builds multiple decision trees and combines their results to improve prediction accuracy and stability. Like decision trees, random forests can be used for both classification and regression tasks. Its core idea is to use the predictions of multiple decision trees to reduce the model's variance, thereby improving overall generalization.

[0026] <2> Long Short-Term Memory (LSTM) is a special type of recurrent neural network designed to process sequential data and effectively address long-term dependencies. Compared to traditional recurrent neural networks, LSTMs incorporate memory cells and gating mechanisms, enabling the network to better capture long-term dependencies. Leveraging these memory cells and gating mechanisms, LSTM models successfully overcome the vanishing and exploding gradient problems common in traditional RNNs, while also enhancing their ability to model long-term dependencies. This results in significant performance improvements for LSTMs on a variety of sequence-related tasks.

[0027] <3> Mean Absolute Error (MAE) is the average of the absolute differences between actual observations and model predictions. It is a measure of forecast accuracy and is used to assess the accuracy of model predictions.

[0028] <4> Mean Squared Error (MSE): A commonly used loss function, often used to evaluate the difference between a model's predicted values ​​and the true values. It measures a model's predictive performance by calculating the average of the squared errors between the predicted and true values. A smaller MSE indicates a more accurate model's predictions; a larger MSE indicates a greater prediction error.

[0029] To facilitate understanding of the embodiments of this application, first Figure 1 Detailed description. Figure 1 The following is a flow chart showing a method for monitoring transformer oil level based on temperature compensation according to an embodiment of the present invention. The method in this embodiment includes:

[0030] Step S11: collecting real-time operating data of the target transformer, and obtaining an oil level abnormality judgment model and an oil temperature prediction model corresponding to the oil tank type of the target transformer.

[0031] It is important to note that real-time operating data on the target transformer is collected, including oil level, oil temperature, transformer load factor, and ambient temperature. Oil level data is collected using a high-precision laser ranging sensor with an accuracy of ±1mm and a sampling frequency of 1Hz. This sensor accurately captures oil level changes within the transformer tank in real time. Continuous monitoring of oil level data allows for timely detection of abnormal oil level fluctuations. For example, excessively high oil levels can lead to increased pressure within the transformer, posing the risk of oil injection or even explosion. Low oil levels may indicate a leak in the transformer tank, requiring prompt maintenance.

[0032] Oil temperature is measured using a PT100 platinum resistor, a highly accurate and stable sensor with an accuracy of ±0.5°C. To ensure comprehensive and accurate measurement of the oil temperature within the tank, temperature sensors are embedded at three key locations: the top, middle, and bottom. Oil temperature data at these locations can reveal the temperature distribution within the tank. For example, an abnormally high oil temperature at the bottom of the tank may indicate a localized overheating fault at the bottom of the transformer. Comprehensive analysis of oil temperature data from these three locations allows for a more accurate assessment of the transformer's internal heating conditions, providing crucial insight for transformer fault diagnosis.

[0033] Transformer load factor data is acquired through a Supervisory Control and Data Acquisition (SCADA) system. This system collects transformer operating parameters in real time and calculates the load factor, which is set between 0 and 150%. The load factor directly reflects the transformer's workload. Excessive load factors can increase heating in the transformer windings and core, accelerate insulation aging, and affect the transformer's service life and safe operation. By monitoring and analyzing load factor data, the transformer's operating mode can be rationally adjusted to avoid long-term overload operation.

[0034] Ambient temperature data is collected by a digital temperature and humidity sensor with a measurement range of -40°C to 85°C, adapting to temperature measurement requirements in diverse environmental conditions. Ambient temperature has a direct and significant impact on transformer oil temperature. When ambient temperature rises, transformer heat dissipation deteriorates, leading to a corresponding increase in oil temperature. By collecting ambient temperature data and comparing and analyzing it with oil temperature data, the cause of the oil temperature increase can be accurately determined, distinguishing between normal temperature rises due to elevated ambient temperature and abnormal temperature rises caused by internal transformer faults (such as winding short circuits or localized core overheating), thereby improving the accuracy and reliability of transformer fault diagnosis.

[0035] Through comprehensive monitoring of multi-dimensional data, the operating status of the transformer can be fully analyzed, and oil level anomalies can be promptly identified, providing a more comprehensive data foundation for transformer operation and maintenance. Furthermore, through multi-dimensional data correlation analysis, the accuracy and reliability of transformer oil level anomaly diagnosis are significantly improved, reducing the occurrence of misjudgments and missed judgments, and providing stronger guarantees for the safe and stable operation of the transformer.

[0036] It should be understood that different types of oil tanks have different oil level change characteristics and oil temperature heat dissipation characteristics. Therefore, establishing corresponding models for different oil tank types can more accurately judge oil level abnormalities and predict oil temperature change trends, significantly improving the accuracy and reliability of transformer operating status assessment and prediction, and can promptly detect transformer oil level abnormalities, providing strong support for transformer preventive maintenance and effectively reducing the occurrence rate of transformer failures.

[0037] In this embodiment, a corresponding oil level anomaly determination model and oil temperature prediction model are constructed for each type of oil tank. For example, oil tank types include, but are not limited to, naturally cooled oil tanks, forced oil circulation oil tanks, and composite oil tanks. An oil level anomaly determination model and oil temperature prediction model are established for naturally cooled oil tanks, forced oil circulation oil tanks, and composite oil tanks. The corresponding models are established based on the transformer's oil tank type, which is not limited in this embodiment. During actual transformer oil level monitoring, the corresponding oil level anomaly determination model and oil temperature prediction model are selected based on the transformer's oil tank type.

[0038] Furthermore, a machine learning approach is employed to construct an oil level anomaly determination model and an oil temperature prediction model. Such machine learning approaches include random forests, naive Bayesian methods, support vector machines, convolutional neural networks, long short-term memory networks, extreme gradient boosting, recursive neural networks, and multilayer perceptrons, and are selected based on practical needs and are not limited in this embodiment.

[0039] In one embodiment, the process of constructing the oil level abnormality judgment model includes:

[0040] Obtain historical operating condition data of the transformer, annotate the historical operating condition data with state labels, and obtain a training data set;

[0041] The oil level anomaly judgment model constructed based on the machine learning method is trained using the training data set until convergence to obtain the final oil level anomaly judgment model.

[0042] Preferably, the oil level anomaly judgment model of the present invention is established using a random forest algorithm. By constructing multiple decision trees and aggregating their prediction results, the random forest algorithm effectively improves the model's generalization ability and anti-interference capabilities, and can accurately identify oil level anomaly patterns in complex transformer operating condition data. Multiple sets of historical transformer operating condition data collected are used as input to the oil level anomaly judgment model. The historical operating condition data includes oil level, oil temperature, transformer load factor, and ambient temperature data. Each set of historical operating condition data corresponds to an oil level anomaly probability value as output, and the prediction accuracy is calculated based on the model's predicted oil level anomaly probability value and the actual oil level anomaly probability value.

[0043] Specifically, the random forest model for the oil level anomaly detection model consists of 100 decision trees. Experimental verification shows that this number of decision trees ensures the model fully exploits data features while avoiding overfitting caused by too many decision trees. Furthermore, the maximum depth of each decision tree is set to 10. This ensures the model effectively models complex data relationships while reducing computational complexity and improving training and prediction efficiency.

[0044] In this embodiment, labeling the historical operating condition data of n groups of transformers with status labels is a key step in model training. Labeling the status labels means assigning a numerical value based on the analysis results of the historical operating condition data of each group of transformers. This numerical value is the actual oil level abnormality probability value. Specifically, based on the oil level fluctuation range, oil temperature and load correlation, the historical operating condition data is analyzed to obtain the actual oil level abnormality probability value corresponding to the historical operating condition data of each group of transformers. For example, when the oil level fluctuates abnormally by a large margin in a short period of time, and the oil temperature and load show an abnormal nonlinear relationship, it indicates that the oil level state corresponding to the group of operating condition data may be an oil level abnormality, and the actual oil level abnormality probability value will be assigned a higher numerical value. By collecting a large amount of historical operating condition data of transformers and labeling them with status labels, a training sample set corresponding to each type of oil tank is formed, which is used for subsequent model training of each type of oil tank.

[0045] In this embodiment, the oil level abnormality probability value is set between 0 and 1, and the oil level abnormality probability threshold is set to 0.9. When the oil level abnormality probability value is greater than 0.9, the transformer tank oil level status is abnormal. When the oil level abnormality probability value is less than or equal to 0.9, the transformer tank oil level status is normal.

[0046] For each set of input transformer historical operating condition information, the model will output a predicted oil level abnormality probability value. The goal of model training is to make the predicted oil level abnormality probability value of any set of transformer historical operating condition data as close as possible to the actual oil level abnormality probability value of the set of transformer historical operating condition information, that is, to optimize the model performance by minimizing the sum of the prediction accuracies.

[0047] The calculation formula for prediction accuracy is:

[0048] Z n =(A n -W n ) 2 ; (Formula 1)

[0049] Among them, n is the group number of the historical operating condition data of multiple transformers, Z n is the prediction accuracy, A n is the predicted oil level abnormality probability value corresponding to the historical operating data of the nth group of transformers, W n is the actual oil level abnormality probability value corresponding to the historical operating condition data of the nth group of transformers.

[0050] During the training process of the oil level anomaly judgment model, the training objective is to minimize the sum of the prediction accuracies of the historical operating condition data of all groups of transformers. The model is trained by adjusting the model parameters through multiple iterations until the sum of the prediction accuracies reaches convergence. The training is then stopped to obtain the final oil level anomaly judgment model.

[0051] Preferably, the oil temperature prediction model adopts a long short-term memory network (LSTM). The LSTM network can model and learn the law of oil temperature changes over time, thereby realizing the prediction of oil temperature at future moments. The hidden layer of the LSTM network in this embodiment is set to 64 units. This number of hidden units has been determined through a large number of experiments and parameter debugging. While ensuring that the model fully learns the complex characteristics of oil temperature changes, it can avoid overfitting of the model due to too many hidden units, or inability to effectively extract data features due to too few hidden units. At the same time, the time window is set to 60 seconds, that is, when the model predicts oil temperature, it will analyze based on historical data within the past 60 seconds. The length of this time window comprehensively considers the dynamic characteristics of transformer oil temperature changes and the consumption of computing resources. It can not only cover the key historical information of oil temperature changes, but also ensure the computing efficiency of the model, so that the model can quickly respond to real-time changes in oil temperature.

[0052] Data marked as normal from multiple sets of historical transformer operating condition data, including historical oil temperature series, oil level, and ambient temperature feature vectors, is used as input for the LSTM network. Historical oil temperature series refer to the changing trends of oil temperature values ​​over time, as well as the oil level and ambient temperature within the corresponding time interval. By analyzing these feature vectors, the model can learn patterns in oil temperature variation, such as whether the oil temperature gradually rises, falls, or remains stable within certain time periods. This provides an important basis for predicting future oil temperatures.

[0053] The LSTM network outputs the predicted oil temperature for the next 30 seconds. Based on this predicted oil temperature, appropriate measures can be taken in advance, such as adjusting the transformer load and improving heat dissipation, to prevent faults caused by excessively high or low oil temperatures and ensure safe transformer operation. The training objective of the model is to minimize the LSTM network's loss function. Training stops when the LSTM network's loss function is less than or equal to the preset target loss function value, resulting in an oil temperature prediction model.

[0054] Among them, the calculation formula of the loss function is:

[0055]

[0056] Among them, MSE is the loss function, x is the group number of the feature vector, m is the number of groups of the feature vector, y x is the predicted oil temperature value corresponding to the xth group of eigenvectors, is the actual oil temperature corresponding to the xth group of eigenvectors. During model training, the loss function changes as the model parameters are adjusted. The goal of model training is to minimize the loss function by adjusting the model parameters.

[0057] Furthermore, this embodiment also uses MAE calculation to assess whether the model's predictive performance meets practical application requirements, thereby measuring the predictive performance of the oil temperature prediction model. For example, if MAE is set to ≤ 1.2°C, after model training, if the calculated MAE value during the actual prediction process is greater than 1.2°C, the model structure or training parameters may need to be readjusted to improve the model's prediction accuracy. If the MAE value is 1.2°C or less, it indicates that the model's prediction results are relatively close to the actual situation and the model's predictive performance is good.

[0058] Step S12: inputting the real-time operating condition data into an oil level abnormality judgment model, and outputting an oil level abnormality judgment result of the target transformer.

[0059] After selecting the oil level anomaly judgment model corresponding to the target transformer's tank type, the target transformer's real-time operating data is input into the corresponding oil level anomaly judgment model. This real-time operating data includes oil level, oil temperature, transformer load factor, and ambient temperature data. This multi-dimensional data reflects the transformer's operating status from different perspectives, providing a comprehensive analysis basis for the model. After receiving the real-time operating data, the oil level anomaly judgment model outputs an oil level anomaly probability value, which is the oil level anomaly judgment result for the target transformer. The oil level anomaly probability value quantifies the probability that the current oil level is abnormal. If the oil level anomaly probability value is greater than the oil level anomaly probability threshold, the oil level anomaly judgment result is an oil level anomaly. If the oil level anomaly probability value is less than or equal to the oil level anomaly probability threshold, the oil level anomaly judgment result is a normal oil level.

[0060] Specifically, the present invention uses an abnormal probability threshold comparison method to determine the oil level status. The range of the oil level abnormal probability value is set between 0 and 1, and the oil level abnormal probability threshold is set to 0.9. When the output oil level abnormal probability value is greater than 0.9, the oil level abnormality judgment result is determined to be an oil level abnormality, which indicates that the oil level of the transformer tank is very likely to have a real fault such as a tank leak; when the oil level abnormal probability value is less than or equal to 0.9, the oil level abnormality judgment result is determined to be a normal oil level. The normal oil level here includes two situations: one is that the oil level itself is within the normal fluctuation range; the other is that even if the oil level has shifted, this shift is a normal phenomenon caused by temperature changes, and is not caused by a fault such as a tank leak. In this case, the oil level is considered to be in a normal state, and the oil level can be restored to a normal level through measures such as temperature compensation.

[0061] The present invention uses an oil level anomaly judgment model to judge the true and false abnormality of the oil level, which has significant advantages over traditional oil level monitoring methods. Traditional methods often only judge whether the oil level is abnormal based on a single oil level value or a simple threshold comparison. It cannot distinguish between oil level fluctuations caused by normal factors such as temperature changes and oil level anomalies caused by real faults, and is prone to misjudgment. The oil level anomaly judgment model constructed by the present invention using the random forest algorithm can comprehensively analyze a variety of operating data, explore the potential relationships between data, accurately identify the essential causes of oil level anomalies, effectively avoid the occurrence of misjudgments, greatly improve the accuracy and reliability of oil level anomaly judgment, and provide a more powerful guarantee for the safe and stable operation of the transformer. It also provides a more scientific and accurate basis for fault diagnosis and processing by operation and maintenance personnel.

[0062] Step S13: performing an early warning operation according to the result of the oil level abnormality judgment of the target transformer, or performing a temperature compensation control operation in combination with the oil temperature prediction model.

[0063] In one embodiment, the process of performing a warning operation according to the oil level abnormality judgment result of the target transformer includes: when the oil level abnormality judgment result of the target transformer is oil level abnormality, generating a warning instruction, and issuing a warning signal according to the warning instruction.

[0064] Specifically, when the oil level abnormality judgment result of the target transformer is an oil level abnormality, that is, when the oil level abnormality probability value is greater than 0.9, an early warning instruction is generated, and an early warning signal is issued according to the early warning instruction. The early warning signal includes but is not limited to sound and light alarms, text messages or email notifications, platform pop-up reminders and the like. Among them, the sound and light alarm is to sound a buzzer or speaker, flash a warning light or display a specific color, which can attract the attention of nearby staff at the first time; the text message or email notification is to send text messages or emails to maintenance personnel or management personnel to ensure that even if the staff is not on site, they can quickly obtain abnormal conditions; the platform pop-up reminder refers to the intuitive display of early warning information on the operation and maintenance management platform, which is convenient for operation and maintenance personnel to uniformly view and manage the operating status of multiple transformers. The present invention can ensure that the operation and maintenance personnel are informed of the oil level abnormality in a timely manner by executing the early warning operation, so that measures can be taken quickly to troubleshoot and handle the fault, avoid damage to the transformer or even cause safety accidents due to faults such as oil level leakage, thereby improving the reliability and safety of transformer operation.

[0065] In one embodiment, the process of performing temperature compensation control operation based on the oil level abnormality judgment result of the target transformer in combination with the oil temperature prediction model includes:

[0066] When the oil level abnormality judgment result of the target transformer is that the oil level is normal, the real-time operating condition data is input into the oil temperature prediction model, and the predicted oil temperature value of the target transformer is output;

[0067] Comparing and analyzing the real-time oil temperature value in the real-time operating condition data with the predicted oil temperature value, and determining whether to generate a temperature control instruction based on the comparison and analysis result;

[0068] The oil temperature of the target transformer is adjusted based on the temperature control instruction.

[0069] It should be noted that when the oil level abnormality judgment result of the target transformer is normal, that is, when the oil level abnormality probability value is less than or equal to 0.9, the temperature compensation control operation is performed. Specifically, the real-time collected operating data, including oil level, oil temperature, transformer load rate and ambient temperature data, are input into the oil temperature prediction model. After the model receives the data, it calculates through the internal network and outputs the predicted oil temperature value of the target transformer in the next 30 seconds, providing an important reference basis for subsequent temperature control. After obtaining the predicted oil temperature value, the real-time oil temperature value in the real-time operating condition data is compared and analyzed with the predicted oil temperature value to determine whether the transformer oil temperature needs to be regulated. If necessary, a temperature control instruction is generated.

[0070] If a temperature control instruction is generated, the oil temperature of the target transformer is adjusted based on the instruction. Specific oil temperature adjustment methods include: starting the transformer oil circulation pump to accelerate oil flow and improve heat exchange efficiency; activating the built-in electric heater to raise the oil temperature to a set range; starting the forced oil circulation cooling system and adjusting the cooling device power, such as increasing fan speed and speeding up the radiator fan; and injecting spare cooling oil. These precise oil temperature adjustments effectively control oil temperature fluctuations, preventing adverse effects on transformer operation caused by oil level deviations due to abnormal oil temperature fluctuations, thereby ensuring the stability of the transformer's operating conditions.

[0071] In one embodiment, the process of comparing and analyzing the real-time oil temperature value in the real-time operating condition data with the predicted oil temperature value and determining whether to generate a temperature control instruction based on the comparison and analysis result includes:

[0072] Calculating the absolute value of the difference between the real-time oil temperature value in the real-time operating condition data and the predicted oil temperature value;

[0073] If the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is within a preset tolerance range, no temperature control instruction is generated;

[0074] If the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is not within a preset tolerance range, a temperature reduction instruction or a temperature increase instruction is generated.

[0075] It's important to note that the oil temperature prediction model is based on an LSTM network. As input, the model receives the feature vector of the current moment in real-time operating data. These feature vectors contain multi-dimensional data such as historical oil temperature sequences, oil levels, and ambient temperatures. Based on this input data, the model calculates and learns through internal network calculations to output the predicted oil temperature value for the next moment, that is, the predicted oil temperature value for the next 30 seconds.

[0076] The real-time operating condition data in this embodiment is updated and collected in real time to ensure the timeliness and accuracy of the model input data. After collecting the actual oil temperature value at the next moment, it is compared with the predicted oil temperature value at the next moment output by the model, that is, the actual oil temperature value and the predicted oil temperature value at the same moment are compared. Through this real-time comparison mechanism, the deviation between the model prediction result and the actual situation can be discovered in time, and the latest judgment basis for the generation of temperature control instructions can be provided based on the comparison results. In addition, the real-time updated operating condition data can also promptly reflect various changes in the transformer operation process, such as sudden load changes, sudden changes in ambient temperature, etc., which can improve the timeliness and effectiveness of temperature compensation control operations and ensure that the transformer is always in a stable and safe operating state.

[0077] Furthermore, the absolute value of the difference between the actual oil temperature value and the predicted oil temperature value at the same time is calculated, and the absolute value of the difference is compared to see whether it is within a preset tolerance range. The preset tolerance range is the tolerance range of the difference between the real-time oil temperature value and the predicted oil temperature value, for example, the preset tolerance range is set to 4°C-5°C.

[0078] If the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is within the preset tolerance range, it means that the actual change of the oil temperature in the transformer tank at the current moment is consistent with the predicted trend and is in a normal fluctuation state. At this time, there is no need to perform additional control on the transformer oil temperature, so no temperature control instruction is generated.

[0079] If the absolute difference between the real-time oil temperature and the predicted oil temperature falls outside the preset tolerance range, it indicates that the oil temperature in the transformer tank is showing an abnormal trend, which may affect the safe and stable operation of the transformer. Therefore, a temperature reduction or increase instruction is generated based on the specific situation of the difference.

[0080] In some examples, if the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is not within a preset tolerance range, the process of generating a temperature reduction instruction or a temperature increase instruction includes:

[0081] If the real-time oil temperature value is greater than the predicted oil temperature value, a temperature reduction instruction is generated;

[0082] If the real-time oil temperature value is less than the predicted oil temperature value, a temperature increase instruction is generated.

[0083] Specifically, when the real-time oil temperature is greater than the predicted value, indicating an upward trend in the oil temperature within the transformer tank, a temperature reduction instruction is generated to take measures to lower the oil temperature. When the real-time oil temperature is less than the predicted value, indicating a downward trend in the oil temperature within the transformer tank, a temperature increase instruction is generated to prevent excessively low oil temperature from impacting transformer performance. This precise instruction generation logic, based on the direction of the difference, enables timely and accurate regulation of the transformer's oil temperature based on the actual temperature trend within the transformer tank, effectively ensuring the stability of the transformer's operating conditions.

[0084] Furthermore, the target transformer's oil temperature is adjusted based on a temperature reduction command or a temperature increase command, adjusting the target transformer's oil temperature to a value where the absolute difference between the real-time oil temperature and the predicted oil temperature is within a preset tolerance range. Specific methods for adjusting the oil temperature include: activating the forced oil circulation cooling system based on the temperature reduction command, adjusting the cooling device's power, such as increasing the fan speed to 120% of the rated speed; injecting spare cooling oil if the oil temperature remains above 95°C; activating the transformer's oil circulation pump based on the temperature increase command to accelerate oil flow and improve heat exchange efficiency, activating the built-in electric heater, and raising the oil temperature to a set range through PID control. The oil temperature adjustment method in this embodiment is selected based on the oil tank type and the actual transformer conditions, and is not limited here.

[0085] It should be noted that the monitoring method of the present invention can be applied to the operation and maintenance of new energy stations. For example, it can be used to efficiently operate and maintain 35kV oil-immersed transformers in wind farms. By continuously analyzing the trend of transformer oil temperature changes, potential problems such as reduced cooling system efficiency can be discovered in a timely manner. For example, when the oil temperature rise trend exceeds the normal range, combined with data such as load rate and ambient temperature, it is determined whether the cooling system efficiency is reduced due to cooling fan failure, heat sink blockage, etc., and then arrangements for inspection and maintenance are made in advance to avoid overheating and damage to the transformer due to cooling system failure, ensure the stable output of electricity from new energy stations, and improve the reliability and economy of new energy power generation.

[0086] The monitoring method of the present invention can also be applied to the digital twin system of the power grid. The collected monitoring data is connected to the dispatching master station through protocols such as IEC61850. The data connected to the dispatching master station provides key real-time parameter support for the dynamic regulation of transformer load, enabling staff to make scientific and reasonable dynamic adjustments to the transformer load in the power grid based on accurate transformer operating status information, such as oil level, oil temperature, load rate, etc., optimize the power grid operation mode, improve the overall operation efficiency and stability of the power grid, and promote the intelligent development of the power grid.

[0087] It should be emphasized that the present invention realizes full-dimensional perception of the transformer's operating status through the combination of multi-sensor fusion and intelligent algorithms. Compared with traditional single-function monitoring devices, traditional devices often only monitor single parameters such as oil level or oil temperature, and are unable to comprehensively consider the correlation between various parameters, resulting in low recognition accuracy of oil level monitoring. However, the present invention, through the fusion analysis of multi-source data, combined with the learning and analysis capabilities of machine learning algorithms such as random forests and LSTM, can mine the potential relationships and fault characteristics behind the data, significantly improving the recognition accuracy of oil level monitoring. The present invention can discover hidden faults more promptly and accurately, take targeted measures for maintenance, reduce unnecessary inspections and repairs, and thus effectively reduce the operation and maintenance costs of the transformer throughout its life cycle.

[0088] In the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects, and do not limit their order. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity or execution order, and words such as "first" and "second" do not necessarily mean different.

[0089] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" represent examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0090] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0091] Figure 2 Schematic diagram of a transformer oil level monitoring system based on temperature compensation provided by an embodiment of the present application. Figure 2 As shown, the system 200 includes:

[0092] The data acquisition and model selection module 201 is used to collect the real-time operating data of the target transformer and obtain the oil level abnormality judgment model and oil temperature prediction model corresponding to the oil tank type of the target transformer;

[0093] The oil level abnormality judgment module 202 is configured to input the real-time operating condition data into an oil level abnormality judgment model and output an oil level abnormality judgment result of the target transformer;

[0094] The early warning or temperature compensation module 203 is used to perform an early warning operation according to the abnormal oil level judgment result of the target transformer, or perform a temperature compensation control operation in combination with the oil temperature prediction model.

[0095] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0096] It should also be understood that the division of modules in the embodiments of the present application is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the present application may be integrated into a single processor, or may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0097] Figure 3 : is a schematic block diagram of an electronic terminal provided in an embodiment of the present application. Figure 3 As shown, the electronic terminal includes: at least one processor 301, memory 302, at least one network interface 303 and a user interface 305. The various components in the device are coupled together through a bus system 304. It is understood that the bus system 304 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 304 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 3 Various buses are labeled as bus systems.

[0098] The user interface 305 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0099] It will be appreciated that the memory 302 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM) or a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0100] The memory 302 in the embodiment of the present invention is used to store various types of data to support the operation of the electronic terminal 300. Examples of such data include: any executable program used to operate on the electronic terminal 300, such as the operating system 3021 and the application 3022; the operating system 3021 includes various system programs, such as the framework layer, the core library layer, the driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 3022 can include various application programs, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The transformer oil level monitoring method based on temperature compensation provided in the embodiment of the present invention can be included in the application 3022.

[0101] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 301. Processor 301 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in processor 301 or by software instructions. The above processor 301 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 301 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor 301 can be a microprocessor or any conventional processor. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium located in a memory. The processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0102] In an exemplary embodiment, the electronic terminal 300 may be configured to execute the aforementioned method using one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs).

[0103] According to the method provided in the embodiments of the present application, the present application also provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute the transformer oil level monitoring method based on temperature compensation of any of the embodiments shown.

[0104] According to the method provided in the embodiments of the present application, the present application also provides a computer-readable storage medium, which stores program code. When the program code is run on a computer, the computer executes the transformer oil level monitoring method based on temperature compensation of any embodiment shown in the embodiments.

[0105] As used in this specification, the terms "component," "module," "system," and the like are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of illustration, both an application running on a computing device and a computing device can be a component. One or more components can reside in a process and / or an execution thread, and a component can be located on a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures stored thereon. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component on a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0106] Those skilled in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0107] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only 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, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0109] Units described as separate components may or may not be physically separate, and 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.

[0110] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0111] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (program) are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs)).

[0112] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program codes.

[0113] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0114] In summary, the present application provides a transformer oil level monitoring method, system, medium, program product and terminal based on temperature compensation, including: collecting real-time operating data of the target transformer, and obtaining an oil level anomaly judgment model and an oil temperature prediction model corresponding to the oil tank type of the target transformer; inputting the real-time operating data into the oil level anomaly judgment model, and outputting the oil level anomaly judgment result of the target transformer; performing an early warning operation based on the oil level anomaly judgment result of the target transformer, or performing a temperature compensation control operation in combination with the oil temperature prediction model. The present application realizes full-dimensional perception of the transformer operating status through the combination of multi-sensor fusion and intelligent algorithms. Compared with traditional single-function monitoring devices, traditional devices often only monitor a single parameter such as oil level or oil temperature, and cannot comprehensively consider the correlation between the various parameters, resulting in a low recognition accuracy of oil level monitoring. However, the present application, through the fusion analysis of multi-source data, combined with the learning and analysis capabilities of the machine learning algorithm, can mine the potential relationships and fault characteristics behind the data, significantly improving the recognition accuracy of oil level monitoring. This application can more promptly and accurately detect potential faults, take targeted maintenance measures, and reduce unnecessary inspections and repairs, thereby effectively reducing the operation and maintenance costs of the transformer throughout its life cycle. Therefore, this application effectively overcomes the various shortcomings of the existing technology and has high industrial application value.

[0115] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A transformer oil level monitoring method based on temperature compensation, characterized in that: include: Collect the real-time operating data of the target transformer and obtain the oil level abnormality judgment model and oil temperature prediction model corresponding to the oil tank type of the target transformer; Inputting the real-time operating condition data into an oil level abnormality judgment model, and outputting an oil level abnormality judgment result of the target transformer; An early warning operation is performed according to the abnormal oil level judgment result of the target transformer, or a temperature compensation control operation is performed in combination with an oil temperature prediction model.

2. The transformer oil level monitoring method based on temperature compensation according to claim 1, characterized in that: The process of performing an early warning operation according to the abnormal oil level judgment result of the target transformer includes: When the oil level abnormality judgment result of the target transformer is that the oil level is abnormal, an early warning instruction is generated, and an early warning signal is issued according to the early warning instruction.

3. The transformer oil level monitoring method based on temperature compensation according to claim 1, characterized in that: The process of performing temperature compensation control operation based on the oil level abnormality judgment result of the target transformer and the oil temperature prediction model includes: When the oil level abnormality judgment result of the target transformer is that the oil level is normal, the real-time operating condition data is input into the oil temperature prediction model, and the predicted oil temperature value of the target transformer is output; Comparing and analyzing the real-time oil temperature value in the real-time operating condition data with the predicted oil temperature value, and determining whether to generate a temperature control instruction based on the comparison and analysis result; The oil temperature of the target transformer is adjusted based on the temperature control instruction.

4. The transformer oil level monitoring method based on temperature compensation according to claim 3 is characterized in that: The process of comparing and analyzing the real-time oil temperature value in the real-time operating condition data with the predicted oil temperature value, and determining whether to generate a temperature control instruction based on the comparison and analysis result includes: Calculating the absolute value of the difference between the real-time oil temperature value in the real-time operating condition data and the predicted oil temperature value; If the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is within a preset tolerance range, no temperature control instruction is generated; If the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is not within a preset tolerance range, a temperature reduction instruction or a temperature increase instruction is generated.

5. The transformer oil level monitoring method based on temperature compensation according to claim 4, characterized in that: If the absolute value of the difference between the real-time oil temperature value and the predicted oil temperature value is not within a preset tolerance range, the process of generating a temperature reduction instruction or a temperature increase instruction includes: If the real-time oil temperature value is greater than the predicted oil temperature value, a temperature reduction instruction is generated; If the real-time oil temperature value is less than the predicted oil temperature value, a temperature increase instruction is generated.

6. The transformer oil level monitoring method based on temperature compensation according to claim 1, characterized in that: The construction process of the oil level abnormality judgment model includes: Obtain historical operating condition data of the transformer, annotate the historical operating condition data with state labels, and obtain a training data set; The oil level anomaly judgment model constructed based on the machine learning method is trained using the training data set until convergence to obtain the final oil level anomaly judgment model.

7. A transformer oil level monitoring system based on temperature compensation, characterized in that: include: The data acquisition and model selection module is used to collect the real-time operating data of the target transformer and obtain the oil level abnormality judgment model and oil temperature prediction model corresponding to the oil tank type of the target transformer; An oil level abnormality judgment module is used to input the real-time operating condition data into an oil level abnormality judgment model and output an oil level abnormality judgment result of the target transformer; The early warning or temperature compensation module is used to perform an early warning operation according to the abnormal oil level judgment result of the target transformer, or to perform a temperature compensation control operation in combination with the oil temperature prediction model.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the transformer oil level monitoring method based on temperature compensation according to any one of claims 1 to 6 is implemented.

9. A computer program product, characterized in that The computer program product includes computer program code, and when the computer program code is run on a computer, the computer is enabled to implement the transformer oil level monitoring method based on temperature compensation according to any one of claims 1 to 6.

10. An electronic terminal comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the transformer oil level monitoring method based on temperature compensation according to any one of claims 1 to 6.

Images