Distribution network special transformer equipment hidden danger risk fusion monitoring and early warning method and system

Abstract

The invention discloses a distribution network special transformer equipment hidden danger risk fusion monitoring and early warning method. The method comprises the following steps: acquiring operation information, online monitoring information and meteorological environment information of special transformer equipment in real time; performing deep analysis on the data by using an equipment hidden danger risk fusion model algorithm, and identifying an abnormal state and a potential hidden danger in equipment operation; based on an analysis result of the equipment hidden danger risk fusion model, in combination with equipment resumes, family defects, operating environments and expert knowledge base information, carrying out quantitative assessment on equipment risks, determining risk levels, and automatically generating a risk assessment analysis report; and when potential safety risks exist in risk assessment analysis, early warning information is automatically generated, and early warning is sent to related personnel in a preset mode. The invention further discloses a corresponding system. By implementing the method, the equipment safety and the operation stability can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring and early warning, and particularly to a method and system for integrated monitoring and early warning of hidden danger risks of distribution network special transformers Background Art

[0002] As an important part of the power system, the safe operation of special transformers is directly related to the stability of the power grid and the safe power consumption of users. However, in a complex operating environment, traditional periodic power consumption inspections are difficult to fully cover all problems. It is often difficult to timely detect potential hidden danger risks caused by equipment aging, maintenance neglect, improper operation, etc. of user equipment, resulting in frequent equipment failures and affecting power supply quality. Traditional monitoring means have limitations such as limited monitoring scope, poor real-time performance, and low early warning accuracy rate, and it is difficult to cover all key nodes, making the early warning and prevention of hidden danger risks of special transformers have obvious lags and difficult to meet the requirements of high efficiency and accuracy of modern power safety management

[0003] Therefore, exploring a more advanced and intelligent early warning and monitoring management mode has become an important way to improve the safety of the power system. By introducing advanced technologies such as the Internet of Things, big data, and artificial intelligence, realizing all-round, all-weather, and intelligent monitoring of special transformers will effectively improve the accuracy and timeliness of hidden danger identification and provide strong support for power safety management Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for integrated monitoring and early warning of hidden danger risks of distribution network special transformers. By comprehensively using a variety of on-line monitoring technologies, communication methods, and equipment hidden danger risk integration models, realizing real-time monitoring of special transformers and analysis and early warning of hidden danger risks, thereby improving equipment safety and operation stability

[0005] To solve the above technical problem, as one aspect of the present invention, a method for integrated monitoring and early warning of hidden danger risks of distribution network special transformers is provided, which includes the following steps

[0006] Step S10, real-time collecting the operation information, on-line monitoring information, and meteorological environment information of the special transformer through high-precision sensors installed at key parts of the transformer

[0007] Step S11, preprocessing, feature extraction, and classification of the collected data, and deeply analyzing the data by using the equipment hidden danger risk integration model algorithm to identify abnormal states and potential hidden dangers in the equipment operation

[0008] Step S12, based on the analysis results of the equipment hidden danger risk integration model, combining equipment resume, family defects, operation environment, and expert knowledge base information, quantitatively evaluating the risk of the equipment, determining the risk level, and automatically generating a risk assessment analysis report

[0009] Step S13: When potential safety risks are identified through risk assessment and analysis, warning information is automatically generated and sent to relevant personnel through a preset method.

[0010] Preferably, the high-precision sensors are installed at key parts of the transformer windings, oil tank, and cooling system to collect real-time operation information of current and voltage, as well as data on oil level, partial discharge, gas, core, vibration monitoring, and temperature and humidity environmental information.

[0011] The data preprocessing includes data cleaning, data normalization, and data missing value handling.

[0012] Preferably, it further includes: organizing and collecting historical defect and potential hazard data records of special transformers, classifying the key features of equipment historical operation data, potential hazard data, and equipment environmental data, and constructing equipment defect models, equipment potential hazard models, and equipment environmental impact models using machine learning and big data analysis technologies, and then integrating them to form an equipment potential hazard risk integration model.

[0013] Among them, the integration to form the equipment potential hazard risk integration model includes:

[0014] Extracting the features of equipment defect-related data, constructing a training set containing normal data and defect data, and using the training set and test set for prediction to obtain P1 and T1 respectively, thus forming a defect base model M1.

[0015] Extracting the features of equipment potential hazard-related data, following the above steps, to obtain P2 and T2, and forming a potential hazard base model M2.

[0016] Extracting the features of equipment environment-related data, following the above steps, to obtain P3 and T3, and forming an environmental impact base model M3.

[0017] Combining P1, P2, P3 and T1, T2, T3 respectively to obtain a new training set and test set, and forming a final label column.

[0018] Integrating the base models M1, M2, and M3 through a weighted average algorithm and using cross-validation to form a special transformer equipment potential hazard risk integration model.

[0019] Preferably, it further includes: using a warning rule setting unit to set different warning rules and thresholds according to actual needs; using a warning output unit to send a warning to relevant personnel through at least one of sound and light alarms, instant messaging, and system alarms when the risk level reaches the preset threshold.

[0020] Preferably, it also includes:

[0021] Build a unified special transformer monitoring and early warning platform to visually display equipment status, early warning information, and fault history in the form of charts and maps, and achieve remote monitoring and centralized management of special transformer equipment.

[0022] Correspondingly, on the other hand, the present invention also provides a hidden danger risk integration monitoring and early warning system for distribution network special transformers, which includes:

[0023] A data acquisition module for real-time collecting the operation information, on-line monitoring information, and meteorological environment information of special transformer equipment through high-precision sensors installed at key parts of the transformer;

[0024] A data processing module for preprocessing, feature extraction, and classification of the collected data, and deeply analyzing the data using the hidden danger risk integration model algorithm of the equipment to identify abnormal states and potential hidden dangers during equipment operation;

[0025] A risk assessment module for quantitatively evaluating the risk of the equipment based on the analysis results of the hidden danger risk integration model of the equipment, combining equipment resume, family defects, operating environment, and expert knowledge base information, determining the risk level, and automatically generating a risk assessment analysis report;

[0026] An early warning release module for automatically generating early warning information when there are potential safety risks in the risk assessment analysis, and sending out early warnings to relevant personnel through the early warning rule setting unit and the early warning output unit.

[0027] Preferably, in the data acquisition module, the high-precision sensors are installed at key parts of the transformer winding, oil tank, and cooling system for real-time collecting the operation information of current and voltage, and the monitoring information of oil level, partial discharge, gas, iron core, or vibration, as well as the environmental information data of temperature and humidity;

[0028] The data processing module further includes a data cleaning unit, a data normalization unit, and a data missing processing unit.

[0029] Preferably, it further includes:

[0030] A model construction module for sorting and collecting the historical defect and hidden danger data records of special transformer equipment, classifying the key features of the equipment historical operation data, hidden danger data, and equipment environment data, and using machine learning and big data analysis technologies to construct an equipment defect model, an equipment hidden danger model, and an equipment environment impact model, and integrating them to form a hidden danger risk integration model for special transformer equipment;

[0031] Among them, the model construction module synthesizes each sub-model through a weighted average algorithm and uses cross-validation for integration to form an equipment hidden danger risk integration model; including:

[0032] Extract the features of the data related to equipment defects, construct a training set containing normal data and defect data, and use the training set and test set for prediction to obtain P1 and T1 respectively, forming a defect base model M1;

[0033] Extract the features of the data related to equipment hidden dangers, and follow the above steps to obtain P2 and T2, forming a hidden danger base model M2;

[0034] Extract the features of the data related to the equipment environment, and follow the above steps to obtain P3 and T3, forming an environmental impact base model M3;

[0035] Merge P1, P2, P3 and T1, T2, T3 respectively to obtain a new training set and test set, and form a final label column;

[0036] Integrate the base models M1, M2, and M3 through a weighted average algorithm, and use cross-validation to fuse them to form a special transformer equipment hidden danger risk fusion model.

[0037] Preferably, in the early warning release module, the early warning rule setting unit allows users to set different early warning rules and thresholds according to actual needs; the early warning output unit sends out an early warning to relevant personnel in the form of sound and light alarm, instant communication or system alarm when the risk level reaches the preset threshold.

[0038] Preferably, it further includes:

[0039] A monitoring and early warning platform module for constructing a unified special transformer monitoring and early warning platform to visually display equipment status, early warning information, and fault history in the form of charts and maps.

[0040] Implementing the embodiments of the present invention has the following beneficial effects:

[0041] The present invention provides a method and system for fusing monitoring and early warning of hidden dangers of distribution network special transformers. By comprehensively applying a variety of online monitoring technologies, communication methods, and equipment hidden danger risk fusion models, it realizes real-time monitoring of special transformer equipment and analysis and early warning of hidden danger risks, thereby improving equipment safety and operation stability.

[0042] Specifically, the present invention collects the operation information, online monitoring information, and meteorological environment information of special transformer equipment in real time through high-precision sensors to ensure the timeliness and accuracy of the data. Through the equipment hidden danger risk fusion model, the collected data is deeply mined and analyzed to identify abnormal states and potential hidden dangers in the operation of the equipment, realizing comprehensive monitoring. Once potential safety risks are found in the risk assessment and analysis, the system will automatically generate early warning information and send out early warnings in a variety of ways in a timely manner to help users take measures before the hidden dangers occur.

[0043] The present invention constructs a risk integration model for equipment hidden dangers by using advanced technologies such as machine learning and big data analysis, including sub-models such as an equipment defect model, an equipment hidden danger model, and an equipment environment impact model. Through data feature extraction technology, key feature data that can reflect the operating conditions of special transformer equipment are extracted from the data as a training data set for the model to learn, so as to improve the accuracy of risk model evaluation.

[0044] The present invention allows users to set different warning rules and thresholds according to actual needs, making equipment monitoring more comprehensive, flexible, and adaptable. Through the cooperation of the warning rule setting unit and the warning output unit, when the risk level reaches the preset threshold, warning information can be sent out in a timely and accurate manner.

[0045] The present invention constructs a unified monitoring and warning platform for special transformers, visually displaying equipment status, warning information, fault history, camera monitoring, etc. in the form of charts, maps, etc. Maintenance personnel can quickly understand the equipment status through the platform and realize remote monitoring and centralized management of special transformer equipment, improving work efficiency and response speed.

[0046] In summary, through the comprehensive application of various advanced technical means, the present invention realizes comprehensive, real-time, and accurate monitoring and warning of special transformer equipment, effectively improving the safety and operation stability of the equipment. At the same time, the present invention also has the advantages of flexible setting of warning rules and thresholds, convenient remote monitoring and centralized management, etc., providing strong support for power safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, obtaining other drawings based on these drawings still belongs to the scope of the present invention;

[0048] Figure 1 It is a schematic diagram of the main process of an embodiment of a method for monitoring and warning the risk integration of hidden dangers of distribution network special transformer equipment provided by the present invention;

[0049] Figure 2 It is a more detailed schematic diagram of the process of the method involved in the present invention;

[0050] Figure 3 It is a schematic diagram of the structure of an embodiment of a system for monitoring and warning the risk integration of hidden dangers of distribution network special transformer equipment provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings.

[0052] As Figure 1 shown, a main process schematic diagram of an embodiment of a hidden danger risk fusion monitoring and early warning method for distribution network dedicated transformer equipment provided by the present invention is shown; in combination with Figure 2 shown, in this embodiment, the method at least includes the following steps:

[0053] Step S10, real-time collection of the operation information, online monitoring information, and meteorological environment information of the dedicated transformer equipment through high-precision sensors installed at key parts of the transformer;

[0054] Among them, the high-precision sensors are installed at key parts of the transformer winding, oil tank, and cooling system, and real-time collection of operation information of current and voltage, and oil level, partial discharge, gas, iron core, and vibration monitoring information, as well as temperature and humidity environment information data;

[0055] For example, on the main transformer of a 110 kV substation, the following high-precision sensors are installed:

[0056] Current sensor: Installed on the high-voltage side and low-voltage side of the transformer to collect the current data of each phase in real time.

[0057] Voltage sensor: Also installed on the high-voltage side and low-voltage side of the transformer to collect the voltage data of each phase in real time.

[0058] Oil level sensor: Installed on the oil tank of the transformer to monitor the change of the oil level in real time.

[0059] Partial discharge sensor: Built into the transformer oil tank for detecting partial discharge phenomena.

[0060] Gas sensor: Monitoring the concentration of dissolved gases in the transformer oil, such as hydrogen, acetylene, etc.

[0061] Iron core grounding current sensor: Monitoring the magnitude of the iron core grounding current to judge whether there are abnormalities such as multi-point grounding of the iron core.

[0062] Vibration sensor: Installed on the outer shell of the transformer to monitor the vibration of the transformer.

[0063] Temperature and humidity sensor: Installed near the transformer to monitor the ambient temperature and humidity.

[0064] These sensors transmit the real-time data to the data processing center through wireless or wired means.

[0065] Step S11: Preprocess, extract features from, and classify the collected data, and deeply analyze the data using the equipment hidden danger risk fusion model algorithm to identify abnormal states and potential hidden dangers during equipment operation;

[0066] It can be understood that, among them, data preprocessing includes data cleaning, data normalization, and data missing value handling. For example, key features can be extracted from the preprocessed data, such as the fluctuation of current, the harmonic content of voltage, the change rate of oil level, the frequency and amplitude of partial discharge, the change trend of gas concentration, the magnitude and change rate of core grounding current, the spectral characteristics of vibration, etc.

[0067] Step S12: Based on the analysis results of the equipment hidden danger risk fusion model, combined with equipment resume, family defects, operating environment, and expert knowledge base information, quantitatively evaluate the risk of the equipment, determine the risk level, and automatically generate a risk assessment analysis report;

[0068] For example, for a certain transformer, input its real-time operation data (such as current, voltage, oil level, etc.) and environmental data (such as temperature, humidity, etc.) into the special transformer equipment hidden danger risk fusion model to obtain the risk score of the transformer. Then, combine the resume information of the transformer (such as manufacturer, operation years, etc.), "family" defect information (such as common problems existing in the same batch of transformers), and the current operating environment to correct the risk score. Finally, determine the risk level of the transformer according to the corrected risk score and generate a risk assessment analysis report.

[0069] Step S13: When there are potential safety risks in the risk assessment analysis, automatically generate warning information and send out warnings to relevant personnel through a preset method.

[0070] Specifically, in this step, it further includes: using the warning rule setting unit to set different warning rules and thresholds according to actual needs; using the warning output unit to send out warnings to relevant personnel through at least one of the ways of sound and light alarm, instant communication, and system alarm when the risk level reaches the preset threshold.

[0071] For example, in a specific example, set the warning rule as: when the risk level of the transformer reaches "high", immediately send out a warning. When the risk level of a certain transformer is evaluated as "high", the warning system will emit an alarm sound through the sound and light alarm device and send warning information to the operation and maintenance personnel through instant communication software (such as WeChat, text messages, etc.). At the same time, display the warning status and risk level of the transformer on the system interface.

[0072] It can be understood that in the method of the present invention, the following steps need to be included:

[0073] Pre-organize and collect the historical defect and potential hazard data records of special transformer equipment, classify the key features of the equipment's historical operation data, potential hazard data, and equipment environment data, and use machine learning and big data analysis technologies to construct an equipment defect model, an equipment potential hazard model, and an equipment environment impact model, and integrate them to form an equipment potential hazard risk integration model;

[0074] Specifically, collect the historical defect and potential hazard data of special transformers, and preprocess, classify, label, etc. the key features of the data reflecting the operation status of transformers, such as the equipment's historical operation data, potential hazard data, and equipment environment that cause risks.

[0075] Collect various defect records and historical operation data that occur during the operation of the equipment, including data such as defect types, specific manifestations of defects, cause analysis, and handling measures, and classify and label them. For example, it is possible to collect the defect records of all transformers in this substation in the past 5 years, such as overheating, short circuit, oil leakage, etc., and label the types of each defect and analyze the causes. Collect potential hazard records during the same period, such as abnormal decline in oil level, excessive gas concentration, etc., and record the type labels and handling measures. Collect the meteorological data of the region where the substation is located over the years, such as temperature, humidity, number of thunderstorm days, etc., and classify and label them.

[0076] Collect various potential hazard records and operation data that occur during the commissioning period of the equipment, including data such as potential hazard types, causes of potential hazards, and handling measures, and classify and label them.

[0077] Collect the equipment area environment information, including data such as the equipment installation location, climate environment, and meteorology, and classify and label them.

[0078] Through data classification and labeling in different dimensions, use data machine learning and intelligent algorithms to construct sub-models such as a comprehensive equipment defect model, an equipment potential hazard model, and an equipment environment impact model, and integrate them to form a special transformer equipment potential hazard risk integration model.

[0079] Among them, integrating to form an equipment potential hazard risk integration model includes the following steps:

[0080] Step S20, extract the features of the data related to equipment defects, construct a training set containing normal data and defect data, and use the training set and test set for prediction to obtain P1 and T1 respectively, and form a defect base model M1;

[0081] In a specific example, it may include the following steps:

[0082] Data collection: Collect the defect data of all transformers in the substation in the past 5 years, including the data of normal operation (as a control) and the data of defects such as overheating, short circuit, and oil leakage.

[0083] Feature engineering: Construct a feature vector according to the features extracted in step S20.

[0084] Training set construction: Combine the feature vectors with the corresponding labels (normal or defect type) to form a training set.

[0085] Model training: Use machine learning algorithms (such as decision trees or random forests) to train the training set to obtain a basic model M1 that can identify transformer defects.

[0086] Step S21: Extract the features of the data related to equipment hidden dangers. Similar to the above steps, obtain P2 and T2 to form the construction of the hidden danger basic model M2.

[0087] In a specific example, the following steps can be included:

[0088] Data collection: Collect the hidden danger data during the same period of the substation, including the data of normal operation and the data of hidden dangers such as abnormal decline in oil level and excessive gas concentration.

[0089] Feature engineering: Construct feature vectors according to the features extracted in step S21.

[0090] Training set construction: Combine the feature vectors with the corresponding labels (normal or hidden danger type) to form a training set.

[0091] Model training: Use machine learning algorithms (such as support vector machines or neural networks) to train the training set to obtain a basic model M2 that can predict transformer hidden dangers. For example, by analyzing the relationship between abnormal decline in oil level and temperature and load, an oil level hidden danger prediction model is constructed.

[0092] Step S22: Extract the features of the data related to the equipment environment. Similar to the above steps, obtain P3 and T3 to form the construction of the environmental impact basic model M3.

[0093] Merge P1, P2, P3 and T1, T2, T3 respectively to obtain a new training set and test set, and form the final label column.

[0094] In an example, the following steps can be included:

[0095] Data collection: Collect the meteorological data (such as temperature, humidity, number of thunderstorm days) of the area where the substation is located over the years and the equipment operation status data (such as transformer failure rate, operating temperature, etc.).

[0096] Feature engineering: Construct feature vectors according to the features extracted in step S22.

[0097] Training set construction: Combine the environmental data feature vectors with the corresponding equipment operation status data (such as failure rate) to form a training set.

[0098] Model training: Use machine learning algorithms (such as linear regression or gradient boosting trees) to train the training set to obtain an environmental impact base model M3 that can analyze the impact of environmental factors on transformers. For example, by analyzing the relationship between temperature and transformer failure rate, a temperature impact model is constructed.

[0099] Step S23, comprehensively combine the base models M1, M2, and M3 through a weighted average algorithm, and use cross-validation to fuse them into a hidden danger risk fusion model for special-purpose transformers. This model can comprehensively consider equipment defects, hidden dangers, and environmental factors to comprehensively evaluate the operating status of the equipment.

[0100] In the embodiments of the present invention, it further includes:

[0101] Build a unified monitoring and early warning platform for special-purpose transformers, and intuitively display equipment status, early warning information, and fault history in the form of charts and maps to achieve remote monitoring and centralized management of special-purpose transformers.

[0102] For example, a Web-based monitoring and early warning platform for special-purpose transformers can be developed. On this platform, the geographical locations and operating statuses of all transformers can be displayed through a map. For transformers in the early warning state, they can be marked in red on the map, and an early warning information window will pop up. Clicking on the early warning information window can view the real-time operating data, historical fault records, and camera monitoring images of the transformer. Maintenance personnel can remotely monitor the operating status of all transformers through this platform and promptly handle early warning information. In addition, this platform also provides a function to download risk assessment analysis reports, which is convenient for maintenance personnel to conduct subsequent analysis and processing.

[0103] As Figure 3 shown, a structural schematic diagram of an embodiment of a hidden danger risk fusion monitoring and early warning system for distribution network special-purpose transformers provided by the present invention is presented. In this embodiment, the system 1 includes:

[0104] A data acquisition module 10, which is used to collect the operating information, on-line monitoring information, and meteorological environment information of special-purpose transformers in real time through high-precision sensors installed at key parts of the transformers;

[0105] Among them, in the data acquisition module 10, the high-precision sensors are installed at key parts of the transformer windings, oil tanks, and cooling systems, and are used to collect the operating information of current and voltage, and the environmental information data of oil level, partial discharge, gas, iron core, or vibration monitoring information, as well as temperature and humidity.

[0106] The data processing module 11 is used to preprocess, extract features and classify the collected data, and deeply analyze the data by using the equipment hidden danger risk fusion model algorithm to identify abnormal states and potential hidden dangers during equipment operation; wherein, the data processing module 11 further includes a data cleaning unit, a data normalization unit and a data missing processing unit.

[0107] The risk assessment module 12 is used to quantitatively evaluate the risk of the equipment based on the analysis results of the equipment hidden danger risk fusion model, combined with equipment resume, family defects, operating environment and expert knowledge base information, determine the risk level, and automatically generate a risk assessment analysis report;

[0108] The early warning release module 13 is used to automatically generate early warning information when there are potential safety risks in the risk assessment analysis, and send out early warnings to relevant personnel through the early warning rule setting unit and the early warning output unit.

[0109] Preferably, in the early warning release module 13, the early warning rule setting unit allows users to set different early warning rules and thresholds according to actual needs; the early warning output unit sends out early warnings to relevant personnel in the form of sound and light alarms, instant messaging or system alarms when the risk level reaches the preset threshold.

[0110] It further includes: a model construction module 14, which is used to sort out and collect the historical defect and hidden danger data records of special transformer equipment, classify the key features of equipment historical operation data, hidden danger data and equipment environment data, and use machine learning and big data analysis technologies to construct an equipment defect model, an equipment hidden danger model and an equipment environment impact model, and fuse them to form a special transformer equipment hidden danger risk fusion model;

[0111] Among them, the model construction module 14 synthesizes each sub-model through a weighted average algorithm and uses cross-validation for fusion to form an equipment hidden danger risk fusion model; including:

[0112] Extract the features of equipment defect-related data, construct a training set containing normal data and defect data, and use the training set and test set for prediction to obtain P1 and T1 respectively, and form a defect base model M1;

[0113] Extract the features of equipment hidden danger-related data, and in the same way as the above steps, obtain P2 and T2 to form a constructed hidden danger base model M2;

[0114] Extract the features of equipment environment-related data, and in the same way as the above steps, obtain P3 and T3 to form a constructed environment impact base model M3;

[0115] Merge P1, P2, P3 and T1, T2, T3 respectively to obtain a new training set and test set, and form a final label column;

[0116] Integrate the M1, M2, and M3 base models through the weighted average algorithm, and use cross-validation to fuse them to form a special transformer equipment hidden danger risk fusion model.

[0117] It can be understood that in this embodiment, it further includes:

[0118] The monitoring and warning platform module 15 is used to build a unified special transformer monitoring and warning platform, and intuitively display the equipment status, warning information, and fault history in the form of charts and maps.

[0119] For more details, reference can be made to and combined with the foregoing description of Figures 1 to 2 which will not be elaborated here.

[0120] Implementing the embodiments of the present invention has the following beneficial effects:

[0121] The present invention provides a method and system for fusing monitoring and warning of hidden dangers and risks of distribution network special transformers. By comprehensively applying various online monitoring technologies, communication methods, and equipment hidden danger risk fusion models, it realizes real-time monitoring of special transformer equipment and analysis and warning of hidden danger risks, thereby improving equipment safety and operation stability.

[0122] Specifically, the present invention collects the operation information, online monitoring information, and meteorological environment information of special transformer equipment in real time through high-precision sensors to ensure the timeliness and accuracy of data. Through the equipment hidden danger risk fusion model, the collected data is deeply mined and analyzed to identify abnormal states and potential hidden dangers in the operation of the equipment, realizing comprehensive monitoring. Once potential safety risks are found in the risk assessment and analysis, the system will automatically generate warning information and send out warnings in a timely manner through various methods to help users take measures before the hidden dangers occur.

[0123] The present invention constructs an equipment hidden danger risk fusion model by using advanced technologies such as machine learning and big data analysis, including sub-models such as equipment defect models, equipment hidden danger models, and equipment environment impact models. Through data feature extraction technology, key feature data that can reflect the operation status of special transformer equipment is extracted from the data as a training data set for the model to learn, so as to improve the accuracy of risk model evaluation.

[0124] The present invention allows users to set different warning rules and thresholds according to actual needs, making equipment monitoring more comprehensive, flexible, and adaptable. Through the cooperation of the warning rule setting unit and the warning output unit, when the risk level reaches the preset threshold, warning information can be sent out in a timely and accurate manner.

[0125] The present invention constructs a unified special transformer monitoring and early warning platform, which visually displays device status, early warning information, fault history, camera monitoring, etc. in the form of charts, maps, etc. Maintenance personnel can quickly understand the device status through the platform, and achieve remote monitoring and centralized management of special transformers, improving work efficiency and response speed.

[0126] In summary, through the comprehensive application of a variety of advanced technical means, the present invention realizes the comprehensive, real-time, and accurate monitoring and early warning of special transformers, effectively improving the safety and operation stability of the devices. At the same time, the present invention also has the advantages of flexible setting of early warning rules and thresholds, convenient remote monitoring and centralized management, etc., providing strong support for power safety management.

[0127] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, units, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0128] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate units for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0129] The above-disclosed is only a preferred embodiment of the present invention, and of course, it cannot be used to limit the scope of the rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A hidden danger risk integration monitoring and early warning method for distribution network dedicated transformer equipment, characterized in that It includes the following steps: Step S10: Real-time collect the operation information, online monitoring information, and meteorological environment information of the dedicated transformer equipment through high-precision sensors installed at key parts of the transformer; Step S11: Preprocess, extract features, and classify the collected data, and use the equipment hidden danger risk fusion model algorithm to deeply analyze the data to identify abnormal states and potential hidden dangers during equipment operation; Step S12: Based on the analysis results of the equipment hidden danger risk fusion model, combine the equipment resume, family defects, operating environment, and expert knowledge base information to quantitatively evaluate the risk of the equipment, determine the risk level, and automatically generate a risk assessment analysis report; Step S13: When there are potential safety risks in the risk assessment analysis, automatically generate warning information and send out warnings to relevant personnel through preset methods.

2. The method according to claim 1, wherein Wherein: The high-precision sensors are installed at key parts of the transformer winding, oil tank, and cooling system to real-time collect the operation information of current and voltage, and the monitoring information of oil level, partial discharge, gas, iron core, and vibration, as well as temperature and humidity environment information data; The data preprocessing includes data cleaning, data normalization, and data missing value processing.

3. The method according to claim 2, characterized in that, It further includes: Sort out and collect the historical defect and hidden danger data records of the dedicated transformer equipment, classify and summarize the key features of the equipment historical operation data, hidden danger data, and equipment environment data, and use machine learning and big data analysis technologies to construct an equipment defect model, an equipment hidden danger model, and an equipment environment impact model, and fuse them to form an equipment hidden danger risk fusion model; Among them, fusing to form an equipment hidden danger risk fusion model includes: Extract the features of the equipment defect-related data, construct a training set including normal data and defect data, and use the training set and test set for prediction to obtain P1 and T1 respectively, and form a defect base model M1; Extract the features of the equipment hidden danger-related data, and in the same way as the above steps, obtain P2 and T2, and form a hidden danger base model M2; Extract the features of the equipment environment-related data, and in the same way as the above steps, obtain P3 and T3, and form an environment impact base model M3; Merge P1, P2, P3 and T1, T2, T3 respectively to obtain a new training set and test set, and form a final label column; Integrate the M1, M2, and M3 base models through a weighted average algorithm and use cross-validation to fuse and form a dedicated transformer equipment hidden danger risk fusion model.

4. The method according to claim 3, wherein In step S13, it further includes: Use the warning rule setting unit to set different warning rules and thresholds according to actual needs; Use the warning output unit to send out warnings to relevant personnel through at least one of sound and light alarms, instant messaging, and system alarms when the risk level reaches the preset threshold.

5. The method according to claim 1, wherein It also includes: Construct a unified dedicated transformer monitoring and warning platform to visually display the equipment status, warning information, and fault history in the form of charts and maps, and realize remote monitoring and centralized management of the dedicated transformer equipment.

6. A hidden danger risk integration monitoring and early warning system for distribution network dedicated transformer equipment, characterized in that, It includes: A data collection module for real-time collecting the operation information, online monitoring information, and meteorological environment information of the dedicated transformer equipment through high-precision sensors installed at key parts of the transformer; A data processing module, which is used to preprocess, extract features and classify the collected data, and deeply analyze the data by using the equipment hidden danger risk fusion model algorithm to identify abnormal states and potential hidden dangers during the operation of the equipment; A risk assessment module, which is used to quantitatively evaluate the risk of the equipment based on the analysis results of the equipment hidden danger risk fusion model, combine the equipment resume, family defects, operating environment and expert knowledge base information, determine the risk level, and automatically generate a risk assessment analysis report; An early warning release module, which is used to automatically generate early warning information when there are potential safety risks in the risk assessment analysis, and send out early warnings to relevant personnel through the early warning rule setting unit and the early warning output unit.

7. The system according to claim 6, wherein Wherein: In the data acquisition module, the high-precision sensors are installed at key parts of the transformer windings, oil tanks, and cooling systems to collect real-time operation information of current and voltage, as well as environmental information data such as oil level, partial discharge, gas, iron core or vibration monitoring information, and temperature and humidity; The data processing module further includes a data cleaning unit, a data normalization unit and a data missing processing unit.

8. The system according to claim 7, wherein It further includes: A model construction module, which is used to sort out and collect the historical defect and hidden danger data records of special transformer equipment, classify the key features of the equipment historical operation data, hidden danger data and equipment environment data, and use machine learning and big data analysis technologies to construct an equipment defect model, an equipment hidden danger model and an equipment environment impact model, and fuse them to form a special transformer equipment hidden danger risk fusion model; Among them, the model construction module synthesizes each sub-model through a weighted average algorithm and uses cross-validation to fuse and form an equipment hidden danger risk fusion model; it includes: Extract the features of the equipment defect-related data, construct a training set containing normal data and defect data, and use the training set and test set for prediction to obtain P1 and T1 respectively, and form a defect base model M1; Extract the features of the equipment hidden danger-related data, and perform the same steps as above to obtain P2 and T2, and form a hidden danger base model M2; Extract the features of the equipment environment-related data, and perform the same steps as above to obtain P3 and T3, and form an environment impact base model M3; Merge P1, P2, P3 and T1, T2, T3 respectively to obtain a new training set and test set, and form a final label column; Comprehensively combine the M1, M2, and M3 base models through a weighted average algorithm, and use cross-validation to fuse and form a special transformer equipment hidden danger risk fusion model.

9. The system according to claim 8, wherein In the early warning release module, the early warning rule setting unit allows users to set different early warning rules and thresholds according to actual needs; the early warning output unit sends out early warnings to relevant personnel through sound and light alarms, instant messaging or system alarms when the risk level reaches the preset threshold.

10. The system according to claim 9, characterized in that It also includes: A monitoring and early warning platform module, which is used to build a unified special transformer monitoring and early warning platform to visually display the equipment status, early warning information and fault history in the form of charts and maps.

Images