Transformer operation monitoring system based on Internet of Things

Abstract

The invention discloses a transformer operation monitoring system based on the Internet of Things, and relates to the technical field of transformer operation monitoring, and the system can accurately evaluate the criticality and urgency of various types of data through calculating the importance index, the real-time index and the data size index of each type of transformer operation data. And different transmission channels can be adjusted and selected in a way of obtaining a comprehensive score based on data driving, so that the discovery and solving speed of key problems in the operation data can be effectively improved, namely the response speed and accuracy of the key problems are effectively improved, and the stability and safety of a power system are effectively enhanced. Meanwhile, by setting the threshold value and selecting the transmission channel according to the comprehensive score, higher flexibility is provided, the transmission strategy can be rapidly adjusted under different conditions so as to cope with the emergency situation, and therefore the stability and reliability of the electric power system are further ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer operation monitoring, and in particular to a transformer operation monitoring system based on the Internet of Things. Background Art

[0002] The transformer operation monitoring method based on the Internet of Things is a method that uses technical means such as sensor networks, data communication technology and cloud computing to monitor and analyze the operating status of power transformers in real time. This method can effectively improve the safety and reliability of transformers, optimize maintenance work, and reduce the occurrence of unplanned power outages. The following are the specific implementation steps of the existing transformer operation monitoring method based on the Internet of Things:

[0003] First, various types of intelligent sensors are installed at key parts of the transformer. These sensors include but are not limited to temperature, humidity, oil level, gas pressure, partial discharge and vibration. They are used to collect data reflecting the health status of the transformer in real time, such as temperature changes, oil quality and other physical parameters; then the collected data is preprocessed to remove noise and outliers to ensure the data quality of subsequent analysis; then the preprocessed data is transmitted in the form of a data communication network, including but not limited to wireless or wired methods, mainly to a remote data center; then, the pre-trained prediction model is used at the remote data center to perform trend prediction or fault diagnosis prediction tasks on the preprocessed data, and finally, the corresponding transformer operation monitoring strategy is formulated based on the prediction results.

[0004] Although the existing transformer operation monitoring methods based on the Internet of Things have achieved certain results, there are still some challenges in practical application, especially in terms of data transmission efficiency:

[0005] Specifically, different types of operating data have different degrees of importance for the operation of the power system. For example, partial discharge data is directly related to the aging degree of the insulation material inside the transformer and potential safety hazards. Therefore, the timeliness and accuracy of such data are crucial. Although data such as ambient temperature is also important, its fluctuation will not immediately affect the safe operation of the transformer. Therefore, a slightly delayed data update cycle can be accepted. Therefore, the existing transmission method for transformer operating data is only to classify the data based on its characteristics and then select different transmission methods for transmission. Although this simple classification transmission method can distinguish key data from auxiliary data to a certain extent, it does not fully consider the actual importance and urgency of each data, resulting in the following problems:

[0006] First, the transmission method cannot be adjusted according to the importance and real-time requirements of the data, which can easily lead to delays in the discovery and resolution of key issues, thus affecting the stability and security of the power system. Second, fixed transmission strategies cannot adapt to dynamically changing needs. For example, in emergencies such as extreme weather or equipment aging, some originally non-critical data becomes more important and requires a higher priority transmission method than before. However, the current system is unable to quickly adjust the transmission strategy to deal with this situation, which makes the stability and security of the power system vulnerable to being affected.

[0007] Therefore, the prior art urgently needs a technical solution for a transformer operation monitoring system based on the Internet of Things. Summary of the invention

[0008] In order to solve the above technical problems, the present invention provides a transformer operation monitoring system based on the Internet of Things, which specifically includes the following modules:

[0009] Data acquisition and preprocessing module: used to deploy at least two types of sensors at key parts of the transformer, collect transformer operation data through the sensors, and perform preprocessing on the collected transformer operation data;

[0010] Transmission channel selection module: connected to the data acquisition and preprocessing module, used to classify the preprocessed transformer operation data according to data characteristics, and calculate the comprehensive score of each type of transformer operation data, and select different transmission channels according to the comprehensive score to upload the transformer operation data to the remote data center, the transmission channels include the first channel and the second channel;

[0011] Importance index calculation unit: used to calculate the importance index of the operating data of each type of transformer;

[0012] Fault probability value acquisition subunit: used to obtain the fault probability value of the operation data of each type of transformer through the historical fault records of each type of transformer;

[0013] Potential loss value calculation subunit: used to collect the direct loss value and indirect loss value caused by the abnormal operation data of each type of transformer in the historical data, and calculate the potential loss value of the operation data of each type of transformer based on the direct loss value and the indirect loss value;

[0014] Importance index calculation subunit: used to calculate the importance index of the operating data of each type of transformer based on the fault probability value and potential loss value of the operating data of each type of transformer;

[0015] Among them, the calculation formula for the importance index of the operating data of each type of transformer is:

[0016] CIi =P i ·w P +(L dir,i +L ind,i )·w L ;

[0017] In the formula, CI i represents the importance index of the operating data of the i-th type transformer; P i represents the fault probability value of the operating data of the i-th type transformer; (L dir,i +L ind,i ) represents the potential loss value of the operating data of the i-th type transformer; L dir,i Represents the direct loss value of the operating data of the i-th type transformer; L ind,i represents the indirect loss value of the operating data of the i-th type transformer; w P and L The weight coefficients representing the failure probability value and the potential loss value respectively;

[0018] Real-time index calculation unit: used to calculate the real-time index of the operating data of each type of transformer;

[0019] Minimum response time acquisition subunit: for the operation data of each type of transformer, using experimental testing to determine the shortest time required for the system to respond from the detection of an abnormality to the response of the system, and obtain the minimum response time of the operation data of each type of transformer;

[0020] Average response time calculation subunit: for the operation data of each type of transformer, to count the time required to complete a complete response cycle under normal operating conditions at least twice, and perform averaging processing on the statistical results to obtain the average response time of the operation data of each type of transformer;

[0021] Maximum tolerable delay acquisition subunit: used to determine the maximum tolerable delay of the operation data of each type of transformer based on historical data;

[0022] A real-time index calculation subunit: used to calculate the real-time index of the operating data of each type of transformer according to the minimum response time, average response time and maximum tolerable delay of the operating data of each type of transformer;

[0023] Among them, the calculation formula for the real-time index of the operating data of each type of transformer is:

[0024]

[0025] Where TRI i Represents the real-time index of the operating data of the i-th type transformer; T min,irepresents the minimum response time of the operating data of the i-th type transformer; T avg,i represents the average response time of the operating data of the i-th type transformer; D max,i represents the maximum tolerable delay of the operating data of the i-th type transformer;

[0026] Data volume index calculation unit: used to calculate the data volume index of the operating data of each type of transformer;

[0027] Average data packet size calculation subunit: for the operation data of each type of transformer, using a network traffic monitoring tool to continuously monitor and record the size of the data packet generated per second, and taking the average value to obtain the average data packet size of the operation data of each type of transformer;

[0028] Maximum data transmission volume calculation subunit: used for summing up the data packet sizes continuously monitored and recorded by the network traffic monitoring tool within each second, obtaining the data transmission volume of the operation data of each type of transformer in a specific time period, and determining the maximum data transmission volume of the operation data of each type of transformer based on the data transmission volume of the operation data of each type of transformer in the specific time period;

[0029] A data volume index calculation subunit: used to calculate the data volume index of the operating data of each type of transformer according to the average data packet size and the maximum data transmission volume of the operating data of each type of transformer;

[0030] Among them, the calculation formula for the data volume index of the operating data of each type of transformer is:

[0031]

[0032] In the formula, DVI i represents the data volume index of the operating data of the i-th type transformer; V avg,i represents the average data packet size of the operating data of the i-th type transformer; V peak,i represents the maximum data transmission volume of the operating data of the i-th type transformer; β represents the adjustment coefficient, which is used to adjust the importance ratio of the average data packet size to the maximum data transmission volume;

[0033] Comprehensive score calculation unit: used to comprehensively calculate the importance index, real-time index and data volume index of the operating data of each type of transformer, and calculate the comprehensive score of the operating data of each type of transformer;

[0034] Among them, the calculation formula for obtaining the comprehensive score of the operating data of each type of transformer is:

[0035] CS i =w1·CI i +w2 TRIi +w3·DVI i ;

[0036] In the formula, CS i Represents the comprehensive score of the operating data of the i-th type transformer; CI i Represents the importance index of the operating data of the i-th type transformer; TRI i Represents the real-time index of the operating data of the i-th type transformer; DVI i represents the data volume index of the operation data of the i-th type transformer; w1, w2 and w3 represent the weight coefficients of the importance index, the real-time index and the data volume index respectively, and w1+w2+w3=1;

[0037] Transmission channel selection unit: used to set a threshold for the comprehensive score of the operating data of each type of transformer. If the comprehensive score of the operating data of the transformer of the current type is greater than or equal to the threshold, the operating data of the transformer is uploaded to the remote data center through the first channel; if the comprehensive score of the operating data of the transformer of the current type is less than the threshold, the operating data of the transformer is uploaded to the remote data center through the second channel;

[0038] Prediction module: connected to the transmission channel selection module, used to predict the transformer operation data that has been preprocessed and uploaded to the data center using a pre-trained machine learning model to obtain a prediction result;

[0039] Strategy formulation module: connected to the prediction module, used to formulate transformer operation monitoring strategies based on the prediction results.

[0040] The embodiments of the present invention have the following technical effects:

[0041] The present invention can accurately evaluate the criticality and urgency of various types of data by calculating the importance index, real-time index and data volume index of each type of transformer operating data, and can adjust and select different transmission channels based on the comprehensive score obtained by data drive, so as to effectively improve the speed of discovering and solving key problems in the operating data, that is, effectively improve the response speed and accuracy to key problems, and thus effectively enhance the stability and safety of the power system. At the same time, by setting thresholds and selecting transmission channels according to comprehensive scores, the present invention provides higher flexibility and can quickly adjust the transmission strategy in different situations to cope with emergencies, thereby further ensuring the stability and reliability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 This is a flow chart of a transformer operation monitoring system based on the Internet of Things provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0045] Embodiment 1: Figure 1 As shown, the present invention provides a transformer operation monitoring system based on the Internet of Things, including the following modules:

[0046] Data acquisition and preprocessing module: used to deploy at least two types of sensors at key parts of the transformer, collect transformer operation data through the sensors, and perform preprocessing on the collected transformer operation data;

[0047] Types of sensors include:

[0048] Temperature sensor: used to monitor the temperature changes inside and outside the transformer in real time. High temperature may be an indication of transformer overload or internal fault.

[0049] Humidity sensor: monitors humidity levels around the transformer, as high humidity may cause insulation degradation, increasing the risk of failure.

[0050] Oil level and oil quality sensor: used to detect the liquid level of transformer cooling oil and the status of oil quality (such as moisture content, acid value, etc.), which is crucial to ensure the normal operation of the transformer.

[0051] Gas Pressure Sensors: Particularly in sealed transformers, monitoring changes in internal gas pressure can provide early warning of potential problems, such as leaks or internal shorts.

[0052] Partial discharge sensor: This sensor can capture the tiny discharge signals generated by the aging of the insulation material inside the transformer and is an effective means of evaluating the insulation status of the transformer.

[0053] Vibration sensors: By detecting abnormal vibrations in the transformer's mechanical components, they can help identify problems such as mechanical failure or unbalanced loads.

[0054] Preprocessing includes:

[0055] Noise removal: Since the sensor may be affected by electromagnetic interference or other external factors, the raw data often contains noise. Using filtering technology (such as low-pass filter) can effectively reduce these unnecessary interference signals.

[0056] Outlier detection and processing: Some extreme values ​​may be caused by measurement errors or unusual events. Statistical methods (such as standard deviation method) are used to identify and correct these outliers to avoid them affecting subsequent data analysis.

[0057] Data standardization / normalization: Converting data from different sources to the same scale for easy comparison and comprehensive analysis. This usually involves a linear or nonlinear transformation process so that all features have similar ranges and distributions.

[0058] Missing value filling: In some cases, data may be missing due to sensor failure or other reasons. Based on the data of adjacent time points or other information of related variables, these missing values ​​can be estimated and filled by interpolation or other prediction models.

[0059] Transmission channel selection module: connected to the data acquisition and preprocessing module, used to classify the preprocessed transformer operation data according to data characteristics, and calculate the comprehensive score of each type of transformer operation data, and select different transmission channels according to the comprehensive score to upload the transformer operation data to the remote data center, the transmission channels include the first channel and the second channel;

[0060] It is worth noting that the first channel has a higher priority than the second channel, and the first channel should be selected using dedicated optical fiber or a low-latency wireless network. The second channel is usually selected based on cost considerations, that is, a transmission cost lower than the public Internet or standard wireless protocol of the first channel.

[0061] Importance index calculation unit: used to calculate the importance index of the operating data of each type of transformer;

[0062] Fault probability value acquisition subunit: used to obtain the fault probability value of the operation data of each type of transformer through the historical fault records of each type of transformer;

[0063] Potential loss value calculation subunit: used to collect the direct loss value and indirect loss value caused by the abnormal operation data of each type of transformer in the historical data, and calculate the potential loss value of the operation data of each type of transformer based on the direct loss value and the indirect loss value;

[0064] It is worth noting that the direct loss value refers to the economic loss that can be clearly quantified due to the abnormal operation data of the transformer, including but not limited to the cost of equipment maintenance or replacement, material loss, etc.; the indirect loss value refers to the economic loss that is indirectly caused by the abnormal operation data of the transformer and is difficult to quantify immediately, including but not limited to the decline in production efficiency, environmental impact costs, etc.; the direct loss value and the indirect loss value quantify the economic losses caused by the abnormal operation data of the transformer from the short-term and long-term dimensions respectively. Adding the sum can provide a more comprehensive risk assessment perspective, ensuring that no important economic factors are ignored when calculating potential losses.

[0065] Importance index calculation subunit: used to calculate the importance index of the operating data of each type of transformer based on the fault probability value and potential loss value of the operating data of each type of transformer;

[0066] Among them, the calculation formula for the importance index of the operating data of each type of transformer is:

[0067] CI i =P i ·w P +(L dir,i +L ind,i )·w L ;

[0068] In the formula, CI i represents the importance index of the operating data of the i-th type transformer; P i represents the fault probability value of the operating data of the i-th type transformer; (L dir,i +L ind,i ) represents the potential loss value of the operating data of the i-th type transformer; L dir,i Represents the direct loss value of the operating data of the i-th type transformer; L ind,i represents the indirect loss value of the operating data of the i-th type transformer; w P and L The weight coefficients representing the failure probability value and the potential loss value respectively;

[0069] Real-time index calculation unit: used to calculate the real-time index of the operating data of each type of transformer;

[0070] Minimum response time acquisition subunit: for the operation data of each type of transformer, using experimental testing to determine the shortest time required for the system to respond from the detection of an abnormality to the response of the system, and obtain the minimum response time of the operation data of each type of transformer;

[0071] It is worth noting that the following are specific examples of the experimental test methods:

[0072] First, a test platform containing a transformer of the same model is built, and all necessary sensors and communication equipment are installed. Then, partial discharge is selected as the fault mode, and the trigger condition is set to a discharge intensity exceeding 100pC. Then, the discharge intensity is gradually increased until the trigger condition is reached, and the detection timestamp is recorded. During the process, after waiting for the system to issue an alarm, the reaction timestamp is recorded, and the response time is calculated. If the detection timestamp t1 = 10:00:00 and the reaction timestamp t2 = 10:00:05, the minimum response time is 5 seconds, and then at least five tests under the same conditions are performed to ensure the consistency and reliability of the results. Through the above-mentioned system test method, the minimum response time of each type of transformer operation data can be accurately determined, thereby providing solid data support for the subsequent real-time index calculation.

[0073] Average response time calculation subunit: for the operation data of each type of transformer, to count the time required to complete a complete response cycle under normal operating conditions at least twice, and perform averaging processing on the statistical results to obtain the average response time of the operation data of each type of transformer;

[0074] Maximum tolerable delay acquisition subunit: used to determine the maximum tolerable delay of the operation data of each type of transformer based on historical data;

[0075] A real-time index calculation subunit: used to calculate the real-time index of the operating data of each type of transformer according to the minimum response time, average response time and maximum tolerable delay of the operating data of each type of transformer;

[0076] Among them, the calculation formula for the real-time index of the operating data of each type of transformer is:

[0077]

[0078] Where TRI i Represents the real-time index of the operating data of the i-th type transformer; T min,i represents the minimum response time of the operating data of the i-th type transformer; T avg,i represents the average response time of the operating data of the i-th type transformer; D max,i represents the maximum tolerable delay of the operating data of the i-th type transformer;

[0079] Data volume index calculation unit: used to calculate the data volume index of the operating data of each type of transformer;

[0080] Average data packet size calculation subunit: for the operation data of each type of transformer, using a network traffic monitoring tool to continuously monitor and record the size of the data packet generated per second, and taking the average value to obtain the average data packet size of the operation data of each type of transformer;

[0081] Maximum data transmission volume calculation subunit: used for summing up the data packet sizes continuously monitored and recorded by the network traffic monitoring tool within each second, obtaining the data transmission volume of the operation data of each type of transformer in a specific time period, and determining the maximum data transmission volume of the operation data of each type of transformer based on the data transmission volume of the operation data of each type of transformer in the specific time period;

[0082] A data volume index calculation subunit: used to calculate the data volume index of the operating data of each type of transformer according to the average data packet size and the maximum data transmission volume of the operating data of each type of transformer;

[0083] Among them, the calculation formula for the data volume index of the operating data of each type of transformer is:

[0084]

[0085] In the formula, DVI i represents the data volume index of the operating data of the i-th type transformer; V avg,i represents the average data packet size of the operating data of the i-th type transformer; V peak,i represents the maximum data transmission volume of the operating data of the i-th type transformer; β represents the adjustment coefficient, which is used to adjust the importance ratio of the average data packet size to the maximum data transmission volume;

[0086] Comprehensive score calculation unit: used to comprehensively calculate the importance index, real-time index and data volume index of the operating data of each type of transformer, and calculate the comprehensive score of the operating data of each type of transformer;

[0087] Among them, the calculation formula for obtaining the comprehensive score of the operating data of each type of transformer is:

[0088] CS i =w1·CI i +w2 TRI i +w3·DVI i ;

[0089] In the formula, CS i Represents the comprehensive score of the operating data of the i-th type transformer; CIi Represents the importance index of the operating data of the i-th type transformer; TRI i Represents the real-time index of the operating data of the i-th type transformer; DVI i represents the data volume index of the operation data of the i-th type transformer; w1, w2 and w3 represent the weight coefficients of the importance index, the real-time index and the data volume index respectively, and w1+w2+w3=1;

[0090] Transmission channel selection unit: used to set a threshold for the comprehensive score of the operating data of each type of transformer. If the comprehensive score of the operating data of the transformer of the current type is greater than or equal to the threshold, the operating data of the transformer is uploaded to the remote data center through the first channel; if the comprehensive score of the operating data of the transformer of the current type is less than the threshold, the operating data of the transformer is uploaded to the remote data center through the second channel;

[0091] Prediction module: connected to the transmission channel selection module, used to predict the transformer operation data that has been preprocessed and uploaded to the data center using a pre-trained machine learning model to obtain a prediction result;

[0092] It is worth noting that the training process of the machine learning model usually includes: collecting a large amount of operating data from historical transformer operation records, including multi-source sensor data such as temperature, humidity, oil level, gas pressure, partial discharge and vibration, labeling these data, marking normal operating conditions and different types of fault conditions such as partial discharge, overheating, etc., for supervised learning, and then extracting meaningful features from the original data based on domain knowledge, such as mean, variance, peak, frequency domain features, etc., to enhance the learning ability of the model, and then performing feature selection, that is, screening out the most representative and discriminative features through statistical analysis or machine learning methods, reducing redundant information, and improving Model efficiency. Then select a machine learning model suitable for time series data analysis, such as random forest, support vector machine (SVM), long short-term memory network (LSTM), etc., and then use the labeled historical data to train the selected model. During the training process, the model will continuously adjust its internal parameters to minimize the prediction error and maximize the accuracy. The model's hyperparameters are optimized through methods such as cross-validation to ensure the generalization ability of the model on different data sets. Finally, an independent test set is used to evaluate the model performance. Common evaluation indicators include accuracy, recall rate, F1 score, etc. The stability and reliability of the model are verified through multiple experiments to ensure its effectiveness in practical applications.

[0093] The prediction process of the machine learning model includes: obtaining real-time operating data from the smart sensors deployed on the transformer, performing preprocessing operations such as denoising and normalization on the collected data to ensure that the data quality meets the model input requirements, and then constructing the same feature vector as the training stage based on the preprocessed data for model input. The feature vector is then input into the pre-trained machine learning model, and the model outputs prediction results, such as trend predictions or fault diagnosis results for a period of time in the future;

[0094] The above-mentioned training and prediction process of machine learning models is existing technology and will not be elaborated here. Specifically, steps such as data collection and preprocessing, feature engineering, model selection and training, model evaluation and verification have been widely used in many fields and have mature tools and technical support. The real-time data collection, preprocessing, feature extraction, model reasoning and other links involved in the prediction process are also common practices. In particular, there is rich practical experience in industrial Internet of Things and intelligent operation and maintenance systems, so I will not go into details.

[0095] Strategy formulation module: connected with the prediction module, used to formulate transformer operation monitoring strategy based on the prediction results;

[0096] The prediction results may include partial discharge prediction, overheating prediction, oil quality deterioration prediction and load prediction, etc. The monitoring strategy based on the prediction results may include immediate response measures and temporary alternatives. The immediate response measures are: if the prediction results show that a serious fault is about to occur, such as partial discharge that may cause insulation breakdown, the protection mechanism should be activated immediately to cut off the power supply to prevent the accident from expanding, and a professional team should be arranged to go to the scene for inspection and repair immediately to ensure that the problem is handled in a timely manner; the temporary alternative is to switch to a backup transformer or other power supply path to ensure the continuity of power supply, and re-plan the power distribution in the power grid to reduce the burden on the faulty transformer.

[0097] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0098] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A transformer operation monitoring system based on the Internet of Things, characterized in that: Includes the following modules: Data acquisition and preprocessing module: used to deploy at least two types of sensors at key parts of the transformer, collect transformer operation data through the sensors, and perform preprocessing on the collected transformer operation data; Transmission channel selection module: connected to the data acquisition and preprocessing module, used to classify the preprocessed transformer operation data according to data characteristics, and calculate the comprehensive score of each type of transformer operation data, and select different transmission channels according to the comprehensive score to upload the transformer operation data to the remote data center, the transmission channels include the first channel and the second channel; Prediction module: connected to the transmission channel selection module, used to predict the transformer operation data that has been preprocessed and uploaded to the data center using a pre-trained machine learning model to obtain a prediction result; Strategy formulation module: connected to the prediction module, used to formulate transformer operation monitoring strategies based on the prediction results.

2. A transformer operation monitoring system based on the Internet of Things according to claim 1, characterized in that: The transmission channel selection module includes the following units: Importance index calculation unit: used to calculate the importance index of the operating data of each type of transformer; Real-time index calculation unit: used to calculate the real-time index of the operating data of each type of transformer; Data volume index calculation unit: used to calculate the data volume index of the operating data of each type of transformer; Comprehensive score calculation unit: used to comprehensively calculate the importance index, real-time index and data volume index of the operating data of each type of transformer, and calculate the comprehensive score of the operating data of each type of transformer; Transmission channel selection unit: used to set a threshold for the comprehensive score of the operation data of each type of transformer. If the comprehensive score of the operation data of the current type of transformer is greater than or equal to the threshold, the first channel is used to upload the operation data of the transformer to the remote data center; If the comprehensive score of the operating data of the transformer of the current category is less than the threshold, the operating data of the transformer is uploaded to the remote data center through the second channel.

3. A transformer operation monitoring system based on the Internet of Things according to claim 2, characterized in that: The calculation of the importance index of the operating data of each type of transformer includes: Fault probability value acquisition subunit: used to obtain the fault probability value of the operation data of each type of transformer through the historical fault records of each type of transformer; Potential loss value calculation subunit: used to collect the direct loss value and indirect loss value caused by the abnormal operation data of each type of transformer in the historical data, and calculate the potential loss value of the operation data of each type of transformer based on the direct loss value and the indirect loss value; Importance index calculation subunit: used to calculate the importance index of the operating data of each type of transformer based on the fault probability value and potential loss value of the operating data of each type of transformer.

4. The transformer operation monitoring system based on the Internet of Things according to claim 3 is characterized in that: The calculation of the real-time index of the operation data of each type of transformer includes: Minimum response time acquisition subunit: for the operation data of each type of transformer, using experimental testing to determine the shortest time required for the system to respond from the detection of an abnormality to the response of the system, and obtain the minimum response time of the operation data of each type of transformer; Average response time calculation subunit: for the operation data of each type of transformer, to count the time required to complete a complete response cycle under normal operating conditions at least twice, and perform averaging processing on the statistical results to obtain the average response time of the operation data of each type of transformer; Maximum tolerable delay acquisition subunit: used to determine the maximum tolerable delay of the operation data of each type of transformer based on historical data; Real-time index calculation subunit: used to calculate the real-time index of the operating data of each type of transformer according to the minimum response time, average response time and maximum tolerable delay of the operating data of each type of transformer.

5. A transformer operation monitoring system based on the Internet of Things according to claim 4, characterized in that: The calculation of the data volume index of the operating data of each type of transformer includes: Average data packet size calculation subunit: for the operation data of each type of transformer, using a network traffic monitoring tool to continuously monitor and record the size of the data packet generated per second, and taking the average value to obtain the average data packet size of the operation data of each type of transformer; Maximum data transmission volume calculation subunit: used for summing up the data packet sizes continuously monitored and recorded by the network traffic monitoring tool within each second, obtaining the data transmission volume of the operation data of each type of transformer in a specific time period, and determining the maximum data transmission volume of the operation data of each type of transformer based on the data transmission volume of the operation data of each type of transformer in the specific time period; Data volume index calculation subunit: used to calculate the data volume index of the operating data of each type of transformer according to the average data packet size and maximum data transmission volume of the operating data of each type of transformer.

6. The transformer operation monitoring system based on the Internet of Things according to claim 5 is characterized in that: The calculation formula of the importance index of the operating data of each type of transformer is: CI i =P i ·In P +(L dir,i +L ind,i )·In L ; In the formula, CI i represents the importance index of the operating data of the i-th type transformer; P i represents the fault probability value of the operating data of the i-th type transformer; (L dir,i +L ind,i ) represents the potential loss value of the operating data of the i-th type transformer; L dir,i Represents the direct loss value of the operating data of the i-th type transformer; L ind,i represents the indirect loss value of the operating data of the i-th type transformer; w P and L The weight coefficients represent the failure probability value and the potential loss value respectively.

7. The transformer operation monitoring system based on the Internet of Things according to claim 6 is characterized in that: The calculation formula of the real-time index of the operating data of each type of transformer is: Where TRI i represents the real-time index of the operating data of the i-th type transformer; T min,i represents the minimum response time of the operating data of the i-th type transformer; T avg,i represents the average response time of the operating data of the i-th type transformer; D max,i Represents the maximum tolerated delay of the operating data of the i-th transformer.

8. The transformer operation monitoring system based on the Internet of Things according to claim 7 is characterized in that: The calculation formula for the data volume index of the operating data of each type of transformer is: In the formula, DVI i represents the data volume index of the operating data of the i-th type transformer; V avg,i represents the average data packet size of the operating data of the i-th type transformer; V peak,i represents the maximum data transmission volume of the operating data of the i-th type transformer; β represents the adjustment coefficient, which is used to adjust the importance ratio of the average packet size to the maximum data transmission amount.

9. The transformer operation monitoring system based on the Internet of Things according to claim 8 is characterized in that: The calculation formula for the comprehensive score of the operating data of each type of transformer is: CS i [w1·CI i +w2·TRI i +w3·DVI i 4 In the formula, CS i Represents the comprehensive score of the operating data of the i-th type transformer; CI i represents the importance index of the operating data of the i-th type transformer; TRI i represents the real-time index of the operating data of the i-th type transformer; DVI i Represents the data volume index of the operating data of the i-th type transformer; w1, w2 and w3 represent the weight coefficients of the importance index, real-time index and data volume index respectively, and w1+w2+w3=1.

Images