Remote control early warning system and method for main transformer gas expansion and medium

Abstract

The invention provides a remote management and control early warning system and method for main transformer gas expansion and a medium, and relates to the technical field of intelligent monitoring, and the system comprises a sensor installation module which is used for carrying out key part identification and sensor installation to obtain a pipeline monitoring sensor group; the data preprocessing module is used for collecting pipeline humidity pressure data flow, preprocessing the pipeline humidity pressure data flow and wirelessly transmitting the pipeline humidity pressure data flow to the data center; the expansion analysis module is used for calling the main transformer gas expansion analysis network, performing expansion analysis and outputting a main transformer gas expansion risk coefficient; and the remote management and control module is used for carrying out early warning judgment and evaluation, determining an expansion early warning level, and carrying out main transformer gas expansion early warning and monitoring end remote management and control. The method solves the technical problem that the prior art usually depends on simple rules and historical experience to predict the gas expansion risk of the main transformer and cannot dynamically adjust a risk analysis mechanism according to real-time data change in real time, so that risk prediction has errors and lags.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring technology, specifically to a remote control and early warning system, method, and medium for the expansion of main transformer gas. Background Technology

[0002] In power systems, gas expansion is a common physical phenomenon, typically occurring in equipment such as power transformers and their gas pipelines. Expansion can lead to equipment malfunctions, system outages, and even more serious safety accidents. To ensure the safety and stability of power systems, timely monitoring of gas expansion and effective remote control and early warning are crucial. Many traditional monitoring systems rely on simple rules and historical experience to predict expansion risks, lacking advanced machine learning and deep learning technologies for intelligent analysis of multi-dimensional data. This results in inaccurate expansion risk predictions, limiting their application to specific scenarios and preventing real-time adjustments to the risk analysis model based on changing data, leading to errors and lags in risk prediction. Summary of the Invention

[0003] This application provides a remote control and early warning system, method and medium for main transformer gas expansion, which aims to solve the technical problem that the existing technology usually relies on simple rules and historical experience to predict the risk of main transformer gas expansion, and cannot dynamically adjust the risk analysis mechanism according to real-time data changes, resulting in errors and lags in risk prediction.

[0004] The first aspect disclosed in this application provides a remote control and early warning system for the expansion of main transformer gas. The system includes: a sensor installation module for acquiring structural design information of a target main transformer gas pipeline, identifying key components and installing sensors based on the structural design information to obtain a pipeline monitoring sensor group; a data preprocessing module for collecting pipeline humidity and pressure data streams detected by the pipeline monitoring sensor group through a pipeline-type humidity and pressure online monitoring terminal, preprocessing the pipeline humidity and pressure data streams, and wirelessly transmitting them to a data center; an expansion analysis module for calling a main transformer gas expansion analysis network through the data center, performing expansion analysis on the pipeline humidity and pressure data streams based on the main transformer gas expansion analysis network, and outputting a main transformer gas expansion risk coefficient; and a remote control module for triggering a remote early warning mechanism to assess the expansion risk coefficient of the main transformer gas, determine the expansion early warning level, and perform main transformer gas expansion early warning and remote control at the monitoring end based on the expansion early warning level.

[0005] The second aspect of this application discloses a remote control and early warning method for main transformer gas expansion. This method is implemented using the aforementioned remote control and early warning system for main transformer gas expansion. The method includes: acquiring structural design information of the target main transformer gas pipeline; identifying key components and installing sensors based on the structural design information to obtain a pipeline monitoring sensor group; collecting pipeline humidity and pressure data streams detected by the pipeline monitoring sensor group through a pipeline-type humidity and pressure online monitoring terminal; preprocessing the pipeline humidity and pressure data streams and wirelessly transmitting them to a data center; calling a main transformer gas expansion analysis network through the data center; performing expansion analysis on the pipeline humidity and pressure data streams based on the main transformer gas expansion analysis network; outputting a main transformer gas expansion risk coefficient; triggering a remote early warning mechanism to assess the main transformer gas expansion risk coefficient, determining the expansion early warning level, and performing main transformer gas expansion early warning and remote control at the monitoring end based on the expansion early warning level.

[0006] The third aspect disclosed in this application provides a storage medium having a computer program stored thereon, which, when executed by a processor, is implemented based on the remote control and early warning system for main transformer gas expansion described in the first aspect.

[0007] One or more technical solutions provided in this application have at least the following beneficial effects:

[0008] By installing a pipeline monitoring sensor array on the target main transformer gas pipeline, key parameters of the gas pipeline can be continuously monitored in real time. This step, by acquiring detailed structural design information, ensures that the sensors are accurately installed at critical parts of the pipeline, thereby enhancing the monitoring accuracy and data representativeness. A pipeline-type humidity and pressure online monitoring terminal can collect real-time data streams from the pipeline monitoring sensor array, preprocess them, and finally transmit the data wirelessly to the data center. This step ensures the integrity, accuracy, and efficiency of the data. The data center then calls upon the main transformer gas expansion analysis network to intelligently analyze the main transformer gas expansion based on the real-time collected humidity and pressure data streams, thereby outputting an expansion risk coefficient. This process utilizes advanced algorithms and artificial intelligence technology to predict and analyze the risk of gas expansion based on historical and real-time data. Based on the output expansion risk coefficient, a remote early warning mechanism is used to determine the expansion risk in real time and trigger corresponding early warning levels according to the set risk warning classification system. The hierarchical nature of the early warning mechanism allows the system to take different response measures according to the severity of the risk, preventing equipment damage, system failures, or safety accidents caused by gas expansion.

[0009] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0010] Figure 1 This is a schematic diagram of a remote control and early warning system for the expansion of main transformer gas, provided as an embodiment of this application.

[0011] Figure 2 This is a schematic diagram of a remote control and early warning method for the expansion of main transformer gas, provided as an embodiment of this application.

[0012] Explanation of reference numerals in the attached diagram: Sensor mounting module 10, data preprocessing module 20, expansion analysis module 30, remote control module 40. Detailed Implementation

[0013] This application provides a remote control and early warning system, method, and medium for main transformer gas expansion, which solves the technical problem that the prior art usually relies on simple rules and historical experience to predict the risk of main transformer gas expansion, and cannot dynamically adjust the risk analysis mechanism according to real-time data changes, resulting in errors and lags in risk prediction.

[0014] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0015] Example 1, as Figure 1 As shown in the figure, this application provides a remote control and early warning system for the expansion of gas in a main transformer. The system includes:

[0016] The sensor installation module 10 is used to acquire the structural design information of the target main variable gas pipeline, identify key parts and install sensors based on the structural design information, and obtain a pipeline monitoring sensor group.

[0017] The data preprocessing module 20 is used to collect the pipeline humidity and pressure data stream detected by the pipeline monitoring sensor group through the pipeline-type humidity and pressure online monitoring terminal, preprocess the pipeline humidity and pressure data stream, and wirelessly transmit it to the data center.

[0018] The expansion analysis module 30 is used to call the main transformer gas expansion analysis network through the data center, perform expansion analysis on the pipeline humidity and pressure data stream based on the main transformer gas expansion analysis network, and output the main transformer gas expansion risk coefficient.

[0019] The remote control module 40 is used to trigger a remote early warning mechanism to assess the risk coefficient of the main transformer gas expansion, determine the expansion early warning level, and remotely control the main transformer gas expansion early warning and monitoring terminal based on the expansion early warning level.

[0020] Furthermore, the sensor mounting module 10 includes:

[0021] The 3D modeling unit is used to perform 3D modeling based on the structural design information to generate a main variable gas pipeline model.

[0022] The critical component identification unit is used to identify critical components of the main variable gas pipeline model, and determine the critical components affected by pressure changes and humidity changes.

[0023] The selection unit is used to select pressure sensors and humidity sensors based on the monitoring accuracy requirements and measurement range of the target main variable gas pipeline.

[0024] The mounting unit is used to integrate the pressure sensor and humidity sensor and install them on the key pressure change parts and the humidity change parts to obtain the pipeline monitoring sensor group.

[0025] Furthermore, the sensor mounting module 10 includes:

[0026] The parameter setting unit is used to set gas flow simulation parameters according to the application scenario of the target main transformer gas pipeline.

[0027] The simulation recording unit is used to simulate and record the main variable gas pipeline model according to the gas flow simulation parameters to obtain gas flow pressure data and gas flow humidity data.

[0028] The critical component identification unit is used to identify critical components based on the gas flow pressure data and gas flow humidity data, and to determine the critical components affected by pressure changes and the components affected by humidity changes.

[0029] Furthermore, the data preprocessing module 20 includes:

[0030] The missing value imputation unit is used to identify outliers and impute missing values ​​in the pipeline humidity and pressure data stream to obtain a usable pipeline humidity and pressure data stream.

[0031] The normalization unit is used to perform low-pass filtering and data normalization on the available pipeline humidity and pressure data stream to generate a standard pipeline humidity and pressure data stream.

[0032] The wireless transmission unit is used to wirelessly transmit the standard pipeline humidity and pressure data stream to the data center through the pipeline-type humidity and pressure online monitoring terminal.

[0033] Furthermore, the expansion analysis module 30 includes:

[0034] The data acquisition unit is used to acquire the historical expansion dataset of the main variable gas, which includes historical pipeline humidity and pressure data as well as expansion risk data.

[0035] The network structure selection unit is used to select the expansion analysis network structure according to the requirements of the main transformer gas expansion risk analysis.

[0036] The identification training unit is used to perform identification training on the historical expansion dataset of the main variable gas using the expansion analysis network structure, obtain the main variable gas expansion analysis network, and store the main variable gas expansion analysis network in the data center.

[0037] Furthermore, the expansion analysis module 30 includes:

[0038] The assessment index construction unit is used to construct a set of risk assessment indicators for the expansion of the main variable gas.

[0039] The classification and identification unit is used to classify and identify the historical expansion dataset of the main variable gas based on the risk assessment index set of the main variable gas expansion, so as to obtain the historical expansion sample set of the main variable gas.

[0040] The supervised training unit is used to supervise the training of the historical expansion sample set of the main variable gas using the expansion analysis network structure, so as to obtain the expansion analysis network of the main variable gas.

[0041] Furthermore, the remote control module 40 includes:

[0042] The early warning classification system determination unit is used to determine the risk early warning threshold and the early warning classification system based on the remote early warning mechanism.

[0043] The early warning judgment and evaluation unit is used to perform early warning judgment and evaluation on the expansion risk coefficient of the main variable gas based on the risk early warning threshold and early warning classification system, and to determine the expansion early warning level.

[0044] Through the detailed description of a remote control and early warning method for gas expansion in a main transformer, those skilled in the art will clearly understand that this embodiment is a remote control and early warning system for gas expansion in a main transformer. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant parts can be referred to in the method section.

[0045] Example 2, based on the same inventive concept as the remote control and early warning system for main transformer gas expansion in the foregoing examples, such as... Figure 2 As shown in the figure, this application provides a remote control and early warning method for the expansion of gas in a main transformer, the method comprising:

[0046] Obtain the structural design information of the target main gas pipeline, identify key components and install sensors based on the structural design information, and obtain a pipeline monitoring sensor group.

[0047] Obtain the structural design information of the target main gas pipeline from relevant design documents, including technical parameters such as pipeline dimensions, materials, shape, layout, bend locations, and connection methods. Based on the structural design information, identify critical areas within the pipeline where pressure and humidity changes are significant. Typical critical areas include pipeline bends, support points, and joint locations. These areas typically experience higher pressure and humidity fluctuations and are prone to gas expansion risks, thus requiring focused monitoring. Based on the identified critical areas, select and install appropriate sensors. Common sensors include pressure sensors, humidity sensors, and temperature sensors. These sensors must be installed at critical points in the pipeline and ensure they can monitor pressure and humidity changes in real time and accurately. During installation, ensure the sensors are securely connected to the pipeline and can operate stably over the long term.

[0048] The pipeline humidity and pressure data stream detected by the pipeline monitoring sensor group is collected by the pipeline-type online humidity and pressure monitoring terminal, and the pipeline humidity and pressure data stream is preprocessed and wirelessly transmitted to the data center.

[0049] The pipeline-type humidity and pressure online monitoring terminal is responsible for collecting humidity and pressure data in the pipeline from the installed sensor group, preprocessing the pipeline humidity and pressure data stream, including outlier identification, missing value imputation, low-pass filtering, normalization, etc. The processed data is transmitted to a remote data center through a wireless communication system. The data is encrypted during the transmission process to ensure data security.

[0050] The main transformer gas expansion analysis network is invoked through the data center, and expansion analysis is performed on the pipeline humidity and pressure data stream based on the main transformer gas expansion analysis network to output the main transformer gas expansion risk coefficient.

[0051] The main transformer gas expansion analysis network is accessed through the data center. This network is a machine learning model or deep learning network trained on historical data. It can analyze the humidity and pressure data streams of the pipeline and predict the risk of gas expansion. During the analysis, the main transformer gas expansion analysis network compares the real-time transmitted humidity and pressure data with the historical expansion dataset to identify potential expansion risks. After analysis, it outputs the main transformer gas expansion risk coefficient, which measures whether the pipeline is currently facing an expansion risk. Generally, the higher the risk coefficient, the greater the expansion risk.

[0052] The remote early warning mechanism is triggered to assess the risk coefficient of the main transformer gas expansion, determine the expansion early warning level, and remotely control the main transformer gas expansion early warning and monitoring terminal based on the expansion early warning level.

[0053] Based on preset risk warning thresholds and a warning grading system, an early warning mechanism is triggered. The risk warning thresholds are set based on historical data, industry standards, and expert experience. The warning grading system classifies risks according to different expansion risk coefficients, typically into multiple levels. The current main transformer gas expansion risk coefficient is compared with the risk warning thresholds and the warning grading system to determine the expansion warning level. Each level corresponds to a different operational response. For example, when a red warning is reached, the pipeline needs to be immediately shut down and emergency procedures initiated. Depending on the expansion warning level, corresponding remote control measures are implemented, such as directly adjusting or shutting down the pipeline via remote control equipment to prevent damage caused by gas expansion.

[0054] Furthermore, the obtained pipeline monitoring sensor set includes:

[0055] Based on the structural design information, a three-dimensional model is created to generate a main variable gas pipeline model; key components of the main variable gas pipeline model are identified to determine key pressure change components and components affected by humidity changes; pressure sensors and humidity sensors are selected according to the monitoring accuracy requirements and measurement range of the target main variable gas pipeline; the pressure sensors and humidity sensors are integrated and installed on the key pressure change components and components affected by humidity changes to obtain the pipeline monitoring sensor group.

[0056] Using professional modeling software, such as AutoCAD, a 3D model is generated based on the structural design information. The model can accurately reflect the geometry of the pipeline, the connection between the pipeline and the equipment, the supporting structure, etc., to ensure that the subsequent sensor installation and data acquisition can match the actual physical environment. 3D modeling also needs to consider the hydrodynamic performance of the pipeline, such as the gas flow direction and possible pressure fluctuation areas, to facilitate subsequent analysis and identification of key parts.

[0057] Based on the generated main variable gas pipeline model and fluid dynamics analysis, key locations in the pipeline where pressure changes may occur are identified. For example, at pipeline bends, drastic pressure changes may occur in gas flow; at joints or flange connections, pressure fluctuations may occur due to improper pipeline installation or physical stress concentration; at pipeline ends or branch points, gas velocity and pressure are prone to change. Humidity affects factors such as temperature, gas velocity, and pipeline surface properties. Locations affected by humidity include areas with significant internal temperature variations, such as pipeline sections near heating or cooling devices, as well as areas with complex gas flow, such as bends, expansions, or contractions, where condensation or moisture accumulation is likely to occur.

[0058] The required monitoring accuracy for each critical component must be clearly defined. This depends on the pipeline's operating conditions and actual application. For example, pressure-sensitive areas such as joints and elbows require high-precision pressure sensors; areas with large humidity fluctuations, such as high-temperature regions, require humidity sensors with high response accuracy. Based on the pressure and humidity range of the pipeline's operating environment, select sensors with appropriate ranges. For instance, if the pipeline's operating pressure range is 0-10 MPa, the selected pressure sensor's range should cover this range with a certain margin. The appropriate pressure and humidity sensors are then selected based on the required monitoring accuracy and the application range.

[0059] Pressure and humidity sensors are integrated and installed at critical locations where pressure changes and humidity fluctuations occur. For example, pressure sensors are installed on straight sections or joints of pipelines to capture pressure changes, while humidity sensors are installed in areas with complex gas flow or large temperature fluctuations. During installation, it is necessary to ensure that the connections between the pressure and humidity sensors and the pipeline are secure and do not affect the normal operation of the pipeline. The installation positions of the sensors should ensure that they can accurately measure pressure and humidity changes.

[0060] Furthermore, determining the key locations of pressure changes and the locations affected by humidity changes includes:

[0061] Based on the application scenario of the target main transformer gas pipeline, gas flow simulation parameters are set; the main transformer gas pipeline model is simulated and recorded according to the gas flow simulation parameters to obtain gas flow pressure data and gas flow humidity data; based on the gas flow pressure data and gas flow humidity data, key parts are identified to determine the key parts of pressure change and the parts affected by humidity change.

[0062] Based on the actual working conditions and environment of the target main gas pipeline, relevant application scenario information is collected, including gas type, pipeline pressure range, temperature conditions, flow velocity, pipeline length, bends and support structures, etc. Based on this information, the flow characteristics of the gas in the pipeline are determined, such as whether the fluid is laminar or turbulent, and whether multiphase flow exists. In the fluid dynamics simulation, gas flow simulation parameters are set, including flow velocity, pressure, temperature, humidity, pipeline geometry, etc., to set the initial conditions for gas flow simulation.

[0063] Based on the gas flow simulation parameters, fluid dynamics software is used to simulate the main variable gas pipeline model. The simulation process simulates the gas flow in the pipeline based on the set parameters, including changes in pressure and humidity, gas velocity distribution, and flow state. The obtained gas flow pressure data shows the pressure changes of the gas in different sections of the pipeline. For example, there will be large pressure fluctuations at joints, bends, and other locations. The gas flow humidity data records the distribution of humidity during the gas flow process, especially in areas with large temperature differences, where moisture may condense or evaporate.

[0064] Based on gas flow pressure data analysis, identify the locations where pressure fluctuations are most significant. For example, fluids may experience drastic pressure changes at bends and joints, leading to gas expansion; at branch points and pipe intersections, changes in gas flow paths may generate large pressure gradients. Statistical analysis of the pressure data identifies areas of significant pressure variation, which are designated as key pressure change locations.

[0065] By analyzing gas flow humidity data, areas of significant humidity variation can be identified. For example, turbulence may occur when gas flows through bends, leading to uneven humidity distribution; low-velocity areas may cause moisture accumulation, affecting humidity distribution. Spatial distribution analysis of humidity variation data can determine areas with significant humidity variations, which are then identified as the locations of humidity variation.

[0066] Furthermore, the preprocessing of the pipeline humidity and pressure data stream and its wireless transmission to the data center includes:

[0067] The pipeline humidity and pressure data stream is subjected to outlier identification and missing value imputation to obtain a usable pipeline humidity and pressure data stream; the usable pipeline humidity and pressure data stream is subjected to low-pass filtering and data normalization to generate a standard pipeline humidity and pressure data stream; the standard pipeline humidity and pressure data stream is wirelessly transmitted to the data center through the pipeline-type online humidity and pressure monitoring terminal.

[0068] Outliers are data points that deviate excessively from the majority of the data. Statistical measures such as standard deviation and mean can be used to define the normal data range; values ​​exceeding this range are considered outliers. Missing values ​​refer to data lost during data acquisition due to sensor malfunctions, communication packet loss, or other reasons. Missing value imputation can be performed using linear interpolation, filling in missing values ​​based on the trend of preceding and following data points. After outlier identification and missing value imputation, the resulting usable pipeline humidity and pressure data stream is cleaned and can be used for further analysis and processing.

[0069] Low-pass filtering is a common method for removing high-frequency noise from raw data, especially when measuring sensor data. Irregular high-frequency noise, such as electromagnetic interference and short-term sensor fluctuations, may occur, affecting the accuracy of data analysis. For example, weighted average filtering assigns different weights to each point in the data, typically with the center point having the highest weight and the weights of surrounding points gradually decreasing. Data normalization standardizes the different dimensions or ranges of data, ensuring that all features are on the same scale and avoiding the influence of differences in magnitude on subsequent processing. For example, min-max normalization linearly scales the data to the [0,1] interval according to its minimum and maximum values. After low-pass filtering and smoothing, the resulting standard pipeline humidity and pressure data stream becomes more stable and less susceptible to noise.

[0070] The pipeline humidity and pressure online monitoring terminal transmits processed standard pipeline humidity and pressure data streams to a data center via wireless communication. Wireless transmission features low latency and real-time performance, enabling remote monitoring of pipeline status. The data center receives real-time data streams from multiple sensors, centrally stores, analyzes, and processes them, providing reliable data support for subsequent analysis, monitoring, and early warning.

[0071] Furthermore, the step of calling the main transformer gas expansion analysis network through the data center includes:

[0072] A historical expansion dataset of the main variable gas is collected, which includes historical pipeline humidity and pressure data as well as expansion risk data. Based on the requirements of the main variable gas expansion risk analysis, an expansion analysis network structure is selected. The expansion analysis network structure is used to train the historical expansion dataset of the main variable gas to obtain the main variable gas expansion analysis network, and the main variable gas expansion analysis network is stored in the data center.

[0073] Historical pipeline humidity and pressure data includes humidity and pressure data of gas in the pipeline. Through historical data, the gas expansion situation under different time periods and operating conditions can be displayed. Expansion risk data records the actual occurrence of expansion and is used to establish the correlation between gas expansion and actual risk.

[0074] The requirements for main variable gas expansion risk analysis are based on the following factors: the analysis objective, such as whether to predict only the risk level of expansion, or whether to further predict the specific expansion magnitude and probability of occurrence; and the data characteristics, i.e., selecting an appropriate model structure based on the scale and dimensionality of historical data. If the data volume is large, a deep learning model is needed; if the data volume is small, traditional machine learning methods can be chosen. The expansion analysis network structure is selected according to the requirements of the main variable gas expansion risk analysis. For example, if the data volume is large and the expansion risk analysis needs to capture complex nonlinear relationships, deep learning methods such as deep neural networks, convolutional neural networks, or long short-term memory networks can be used to ensure that the model can achieve optimal performance in expansion risk assessment.

[0075] Using a historical expansion dataset of primary variable gases, a selected expansion analysis network structure was trained. The training objective was to enable the network to predict the risk level or probability of expansion from input features such as humidity and pressure. Specifically, the historical expansion dataset of primary variable gases was divided into training, validation, and test sets. Appropriate loss functions, such as cross-entropy loss and mean squared error, were defined. The network parameters were optimized using algorithms such as backpropagation and gradient descent. The model's performance was evaluated on the validation set, and hyperparameters were adjusted to improve the model's predictive ability. After training, a primary variable gas expansion analysis network capable of predicting expansion risk was obtained. At this point, the network had learned to automatically identify expansion risk patterns from features such as humidity and pressure. The primary variable gas expansion analysis network was stored in a data center for later retrieval.

[0076] Furthermore, the method for obtaining the main variable gas expansion analysis network includes:

[0077] Construct a set of risk assessment indicators for the expansion of the main transformer gas; classify and label the historical expansion dataset of the main transformer gas based on the set of risk assessment indicators to obtain a historical expansion sample set of the main transformer gas; use the expansion analysis network structure to supervise the training of the historical expansion sample set of the main transformer gas to obtain the expansion analysis network of the main transformer gas.

[0078] The main transformer gas expansion risk assessment index set is the core of expansion risk prediction and classification. Based on actual operating conditions, influencing factors of gas expansion, and system requirements, appropriate indicators are selected to quantify the risk. For example: pressure change rate (gas expansion is often closely related to pressure changes, and areas with large pressure change rates may be high-risk areas); humidity change rate (humidity changes may affect the speed and magnitude of expansion, especially when temperature and humidity affect the physical properties of the gas); temperature (gas expansion is usually related to temperature changes, and excessively high temperatures may lead to accelerated expansion); and the pressure resistance rating of the pipeline material (the pressure resistance and material of the pipeline affect the expansion risk; the weaker the material, the greater the risk).

[0079] The historical expansion dataset of main transformer gas is labeled and classified according to the risk assessment index set of main transformer gas expansion. Each historical record's humidity, pressure, temperature, and other data are associated with a corresponding risk label, indicating the risk level of the expansion, such as low risk, medium risk, and high risk. After classification and labeling, each historical record will have a corresponding risk label, forming a labeled historical expansion sample set of main transformer gas. This sample set contains information such as humidity, pressure, and temperature of the gas pipeline, and each sample is labeled with the corresponding risk label.

[0080] A historical expansion sample set of the main variable gas is input as training data into the expansion analysis network structure. Each data point has features including humidity, pressure, temperature, and pipeline condition, while the label represents the corresponding expansion risk level. In supervised learning, the model adjusts its parameters based on the known feature data and label information, enabling it to predict the expansion risk of unknown data. If the model performs poorly, performance can be optimized by adjusting hyperparameters, increasing the amount of data, or using a more complex model structure. After training, the resulting main variable gas expansion analysis network can predict the expansion risk level corresponding to new humidity, pressure, and other data points.

[0081] Furthermore, determining the inflation warning level includes:

[0082] Based on the remote early warning mechanism, a risk early warning threshold and an early warning classification system are determined; based on the risk early warning threshold and the early warning classification system, an early warning judgment and assessment are performed on the expansion risk coefficient of the main variable gas to determine the expansion early warning level.

[0083] Based on operational experience, industry standards, and historical data of the main transformer gas pipeline, risk warning thresholds for different risk levels are determined. For example, a warning is triggered when the expansion risk coefficient exceeds a certain value. The warning classification system divides the risk coefficient into multiple different risk levels according to different ranges. For example, low risk indicates that the expansion risk is small and has little impact on the system, so continued monitoring is sufficient; medium risk indicates that the risk is slightly higher and may lead to some equipment damage or increased energy consumption, so vigilance and appropriate control are required; high risk indicates that the expansion risk is extremely high and may lead to equipment damage or safety accidents, requiring immediate intervention, which may involve on-site inspections or shutdowns.

[0084] Based on the established risk warning thresholds and warning classification system, the expansion risk coefficient of the main variable gas is assessed. For example, if the expansion risk coefficient is below the low-risk threshold, it is determined to be low risk, and no warning is issued; if the expansion risk coefficient is in the medium-risk range, it is determined to be medium risk, and a medium-risk warning is issued; if the expansion risk coefficient exceeds the high-risk threshold, it is determined to be high risk, and a high-risk alarm is triggered. After the warning is issued, changes in the risk coefficient are continuously monitored. If the risk level changes, such as downgrading or upgrading, the warning level will be automatically adjusted to ensure the accuracy and effectiveness of the warning system.

[0085] Example 3 provides a storage medium storing a computer program, which, when executed by a processor, is based on a remote control and early warning system for main transformer gas expansion according to Example 1.

[0086] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A remote control and early warning system for the expansion of gas in a main transformer, characterized in that, The system includes: The sensor installation module is used to acquire the structural design information of the target main variable gas pipeline, and to identify key parts and install sensors based on the structural design information to obtain a pipeline monitoring sensor group. The data preprocessing module is used to collect the pipeline humidity and pressure data stream detected by the pipeline monitoring sensor group through the pipeline-type humidity and pressure online monitoring terminal, preprocess the pipeline humidity and pressure data stream and wirelessly transmit it to the data center; The expansion analysis module is used to call the main transformer gas expansion analysis network through the data center, perform expansion analysis on the pipeline humidity and pressure data stream based on the main transformer gas expansion analysis network, and output the main transformer gas expansion risk coefficient. The remote control module is used to trigger a remote early warning mechanism to assess the risk coefficient of the main transformer gas expansion, determine the expansion early warning level, and remotely control the main transformer gas expansion early warning and monitoring terminal based on the expansion early warning level.

2. The remote control and early warning system for gas expansion in a main transformer as described in claim 1, characterized in that, The sensor mounting module includes: A 3D modeling unit is used to perform 3D modeling based on the structural design information and generate a main variable gas pipeline model. The critical component identification unit is used to identify critical components of the main variable gas pipeline model, and determine the critical components affected by pressure changes and humidity changes. The selection unit is used to select pressure sensors and humidity sensors based on the monitoring accuracy requirements and range of the target main transformer gas pipeline. The mounting unit is used to integrate the pressure sensor and humidity sensor and install them on the key pressure change parts and the humidity change parts to obtain the pipeline monitoring sensor group.

3. The remote control and early warning system for gas expansion in a main transformer as described in claim 2, characterized in that, The sensor mounting module includes: The parameter setting unit is used to set gas flow simulation parameters according to the application scenario of the target main transformer gas pipeline; The simulation recording unit is used to simulate and record the main variable gas pipeline model according to the gas flow simulation parameters to obtain gas flow pressure data and gas flow humidity data. The critical component identification unit is used to identify critical components based on the gas flow pressure data and gas flow humidity data, and to determine the critical components affected by pressure changes and the components affected by humidity changes.

4. The remote control and early warning system for gas expansion in a main transformer as described in claim 1, characterized in that, The data preprocessing module includes: The missing value imputation unit is used to identify outliers and impute missing values ​​in the pipeline humidity and pressure data stream to obtain a usable pipeline humidity and pressure data stream. The normalization unit is used to perform low-pass filtering and data normalization on the available pipeline humidity and pressure data stream to generate a standard pipeline humidity and pressure data stream. The wireless transmission unit is used to wirelessly transmit the standard pipeline humidity and pressure data stream to the data center through the pipeline-type humidity and pressure online monitoring terminal.

5. The remote control and early warning system for gas expansion in a main transformer as described in claim 1, characterized in that, The expansion analysis module includes: The data acquisition unit is used to acquire the historical expansion dataset of the main variable gas, which includes historical pipeline humidity and pressure data as well as expansion risk data. The network structure selection unit is used to select the expansion analysis network structure according to the requirements of the main transformer gas expansion risk analysis. The identification training unit is used to perform identification training on the historical expansion dataset of the main variable gas using the expansion analysis network structure, obtain the main variable gas expansion analysis network, and store the main variable gas expansion analysis network in the data center.

6. The remote control and early warning system for main transformer gas expansion as described in claim 5, characterized in that, The expansion analysis module includes: The assessment index construction unit is used to construct a set of risk assessment indicators for the expansion of the main variable gas. The classification and identification unit is used to classify and identify the historical expansion dataset of the main variable gas based on the main variable gas expansion risk assessment index set, so as to obtain the historical expansion sample set of the main variable gas. The supervised training unit is used to supervise the training of the historical expansion sample set of the main variable gas using the expansion analysis network structure, so as to obtain the expansion analysis network of the main variable gas.

7. The remote control and early warning system for gas expansion in a main transformer as described in claim 1, characterized in that, The remote control module includes: The early warning classification system determination unit is used to determine the risk early warning threshold and the early warning classification system based on the remote early warning mechanism. The early warning judgment and evaluation unit is used to perform early warning judgment and evaluation on the expansion risk coefficient of the main variable gas based on the risk early warning threshold and early warning classification system, and to determine the expansion early warning level.

8. A remote control and early warning method for gas expansion in a main transformer, characterized in that, Based on the implementation of the remote control and early warning system for main transformer gas expansion according to any one of claims 1 to 7, the method includes: Obtain the structural design information of the target main gas pipeline, identify key components and install sensors based on the structural design information, and obtain a pipeline monitoring sensor group; The pipeline humidity and pressure data stream detected by the pipeline monitoring sensor group is collected by the pipeline-type online humidity and pressure monitoring terminal, and the pipeline humidity and pressure data stream is preprocessed and wirelessly transmitted to the data center. The main transformer gas expansion analysis network is invoked through the data center, and expansion analysis is performed on the pipeline humidity and pressure data stream based on the main transformer gas expansion analysis network to output the main transformer gas expansion risk coefficient. The remote early warning mechanism is triggered to assess the risk coefficient of the main transformer gas expansion, determine the expansion early warning level, and remotely control the main transformer gas expansion early warning and monitoring terminal based on the expansion early warning level.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it is implemented based on a remote control and early warning system for the expansion of main transformer gas according to any one of claims 1 to 7.

Images