Multi-dimensional comprehensive online monitoring and fault early warning platform for main transformer of gas turbine power plant

Abstract

The invention discloses a multi-dimensional comprehensive online monitoring and fault early warning platform for a main transformer of a gas turbine power plant, and relates to the technical field of power transformer monitoring. In order to solve the problems that in the prior art, the accuracy of a monitoring result highly depends on the quality of collected data and the reliability of a sensor, wrong early warning is possibly caused when the sensor breaks down or data is inaccurate, specific adjustment and calibration cannot be carried out aiming at different transformers and environmental conditions, and the environmental adaptability is low. Multi-dimensional monitoring is carried out on the main transformer based on the sensor assembly, the load of data transmission is reduced through edge side processing, integrity verification is carried out on received dynamic monitoring data, meanwhile, the real-time performance and integrity of the data are ensured, and the transformer health degree evaluation model carries out comprehensive evaluation on the operation state of the main transformer. The health state and the fault type of the main transformer can be accurately judged, and timely and accurate fault information is provided for operation and maintenance personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of power transformer monitoring, and in particular to a multi-dimensional comprehensive online monitoring and fault early warning platform for main transformers in gas turbine power plants. Background Art

[0002] Traditional power transformer monitoring and fault diagnosis mainly rely on manual inspection and regular maintenance. This method is not only inefficient, but also may lead to misjudgment or missed judgment, making it difficult to timely discover power transformer fault problems. Regarding transformer online monitoring and fault warning, a Chinese patent with publication number: CN116295661 B discloses a transformer fault warning system based on the Internet of Things, including a fault warning platform, which is connected to a temperature monitoring module, an abnormal sound monitoring module, a coil monitoring module, a decision analysis module, and a storage module; a monitoring cycle is generated, and the load data FZ and the external temperature data WW of the monitored object in the monitoring cycle are obtained and numerically calculated to obtain the load factor YZ of the monitored object in the monitoring cycle; the operating temperature of the transformer is monitored and analyzed, and the load factor is obtained by comprehensive analysis and calculation of the operating environment parameters and load parameters of the monitored object, and accurate feedback is given to its temperature state in combination with the application environment of the monitored object.

[0003] Although the above patent can monitor the operating condition of the transformer more efficiently by real-time monitoring and analysis of the operating temperature, abnormal noise and coil status of the transformer, the following problems still exist:

[0004] In the existing technology, the accuracy of monitoring results is highly dependent on the quality of collected data and the reliability of sensors. Sensor failure or inaccurate data may lead to false warnings, and specific adjustments and calibrations cannot be made for different transformers and environmental conditions, and the environmental adaptability is low. Summary of the invention

[0005] The purpose of the present invention is to provide a multi-dimensional comprehensive online monitoring and fault warning platform for the main transformer of a gas turbine power plant, which performs multi-dimensional monitoring of the main transformer based on a sensor component, reduces the load of data transmission through edge-side processing, and ensures the real-time and integrity of the data. It conducts a comprehensive evaluation of the operating status of the main transformer to ensure the stable operation of the power system, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The multi-dimensional comprehensive online monitoring and fault warning platform for main transformers in gas turbine power plants includes:

[0008] A multi-dimensional data acquisition unit is used to comprehensively monitor the main transformer from multiple dimensions based on the sensor components to ensure comprehensive coverage of all key aspects of the main transformer, collect data at preset time intervals according to monitoring requirements, pre-process the acquired dynamic monitoring data of the main transformer, and transmit it to the data analysis and early warning unit;

[0009] The data analysis and early warning unit is used to verify the integrity of the received dynamic monitoring data based on the data transmission channel, and to evaluate the main transformer based on the transformer health assessment model. It combines the health assessment report and the fault identification result to determine whether the main transformer has a fault and identify potential fault risks, and issue corresponding early warning information;

[0010] The online monitoring unit is used to monitor the operating status of the main transformer in real time and visualize the monitoring data and early warning information.

[0011] Furthermore, the multidimensional data acquisition unit comprises:

[0012] The sensor module is used to perform multi-dimensional monitoring of the main transformer based on the sensor components and obtain dynamic monitoring data during the operation of the main transformer;

[0013] The data acquisition module is used to collect sensor components and other monitoring data in real time based on edge-side monitoring equipment, and pre-process the acquired dynamic monitoring data;

[0014] The data transmission module is used to transmit the pre-processed dynamic monitoring data to the data analysis and early warning unit based on the data transmission channel.

[0015] Furthermore, the sensor assembly comprises:

[0016] The temperature sensor is used to monitor the temperature of key parts of the main transformer in real time and record the temperature change trend of key parts of the main transformer.

[0017] The sound sensor is used to monitor the noise of the main transformer in real time during operation, perform spectrum analysis, identify abnormal sound characteristics, and determine whether the main transformer is faulty.

[0018] Current sensor, used to monitor coil current in real time and analyze current waveform.

[0019] The gas sensor is used to detect the dissolved gas in the main transformer oil in real time and analyze the main transformer fault type based on the gas composition and content.

[0020] Environmental sensors are used to monitor environmental parameters in real time and analyze the impact of environmental parameters on the operating status of the main transformer;

[0021] Vibration sensor, used to collect vibration data of the main transformer body and supporting structure in real time.

[0022] Furthermore, the data acquisition module preprocesses the acquired dynamic monitoring data, specifically including:

[0023] The dynamic monitoring data of the sensor component is collected regularly according to a preset collection frequency, and the collected data is classified according to the sensor category of the sensor component to generate multiple monitoring sub-data sets;

[0024] Acquire parameter verification rules for each monitoring sub-data set according to the sensor category, and generate a data verification component for the monitoring sub-data set;

[0025] Performing data verification on the sub-data in each monitoring sub-data set according to the data verification component of each monitoring sub-data set, and determining the abnormal coefficient of each sub-data according to the verification result;

[0026] The sub-data with anomaly coefficients greater than the preset data anomaly threshold are removed as edge data to obtain pre-processed dynamic monitoring data.

[0027] Furthermore, the data analysis and early warning unit includes:

[0028] A data processing module is used to read data based on the time series carried by the pre-processed dynamic monitoring data, determine the integrity of the acquired dynamic monitoring data, and generate complete monitoring data based on the determination result;

[0029] The model building module is used to establish a transformer health assessment model and input the complete monitoring data into the transformer health assessment model, evaluate the main transformer according to the transformer health assessment model, and generate a health assessment report;

[0030] Fault analysis module, used to determine whether the main transformer has faults and potential fault risks based on the health assessment report and fault identification results;

[0031] The fault warning module is used to provide fault warning based on the identified faults and potential fault risk categories, combined with the fault and potential fault risk thresholds, and match the corresponding strategy according to the fault level.

[0032] Furthermore, the data processing module is specifically:

[0033] Reading the sub-data in the pre-processed dynamic monitoring data to determine whether there is any omission in the sub-data;

[0034] When it is determined that there is omission in the sub-data, the adjacent data of the missing data are read, and the missing data are supplemented according to a preset similarity algorithm, and complete monitoring data are generated based on the supplementation result.

[0035] Furthermore, the model building module evaluates the main transformer, specifically:

[0036] Extracting the operating characteristic data of the main transformer from the acquired complete monitoring data, and determining the current operating state of the main transformer according to the operating characteristic data of the main transformer, wherein the operating data corresponds one-to-one to the operating state of the leased battery;

[0037] The operation data are filtered according to the effective operation state of the main transformer to obtain target operation data, and clustering is performed according to the data features of the target operation data to obtain an operation data group of the main transformer;

[0038] Drawing an operation data change curve of the main transformer based on the operation data group of the main transformer, determining the change abnormality coefficient of the main transformer, and obtaining a performance attenuation evaluation value of the main transformer;

[0039] An operating state index and a degradation degree index of the main transformer are determined based on a performance attenuation evaluation value of the main transformer, and a health evaluation value of the main transformer is calculated based on weights of the operating state index and the degradation degree index.

[0040] Furthermore, the operation characteristic data of the main transformer is extracted from the complete monitoring data, which also includes:

[0041] Extract features from the complete monitoring data, and obtain an initial feature set of the complete monitoring data based on the extraction results;

[0042] And extract the feature data related to the transformer health from the initial feature set and integrate them into a key feature subset;

[0043] Determine the weight value of each main transformer according to the node attributes and operation mode of the main transformer in the gas turbine power plant;

[0044] The weight value of each main transformer is applied to each feature in its corresponding key feature subset, and the weighted feature value is standardized;

[0045] The weights of the operating status index and degradation degree index of each main transformer are determined according to the weighted and processed eigenvalue data.

[0046] Furthermore, the fault analysis module determines the fault and potential fault risk, specifically:

[0047] Obtain the health assessment report generated by the health assessment module, extract the current health assessment value of the main transformer, the change abnormal coefficient of the main transformer, and possible abnormal indicators;

[0048] Extract and integrate the historical fault records of the main transformer, and build a fault identification model for the main transformer based on the integration results;

[0049] Compare the score in the health assessment report with the preset health standard to determine whether the health status of the main transformer is within the normal range;

[0050] Based on the fault identification model, the main transformer fault is identified, and combined with the change abnormal coefficient of the main transformer, it is identified whether the possible abnormal indicators match the known fault mode;

[0051] Based on the results of comparative analysis, the probability index of main transformer fault is evaluated, and the risk assessment of possible faults is carried out.

[0052] Furthermore, the online monitoring unit comprises:

[0053] Visualization modules for:

[0054] Integrate the location information of the main transformers of the gas turbine power plant into the electronic map, display the specific location of each main transformer, mark the location of each main transformer on the map in real time, and dynamically update the mark according to its operating status;

[0055] When the monitoring data exceeds the preset safety threshold, the corresponding main transformer operating status dynamic mark on the map is updated to the warning state, and the warning information and recommended operating measures are provided on the mark side;

[0056] The interactive control module is used to quickly locate each main transformer based on user instructions, and adjust parameters and set thresholds for each main transformer according to control instructions.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] Based on the sensor components, the main transformer is monitored in multiple dimensions, and the dynamic monitoring data of the main transformer during operation is fully obtained. The data transmission load is reduced through edge-side processing, and the integrity of the received dynamic monitoring data is verified, while ensuring the real-time and integrity of the data. The transformer health assessment model conducts a comprehensive assessment of the operating status of the main transformer, integrating a variety of monitoring data and historical experience. It can accurately judge the health status and fault type of the main transformer, provide timely and accurate fault information for operation and maintenance personnel, and reduce the workload of operation and maintenance personnel through visual display and interactive control, improve operation and maintenance efficiency, provide reliable safety protection for the main transformer of the gas turbine power plant, and ensure the stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a module diagram of the multi-dimensional comprehensive online monitoring and fault warning platform for the main transformer of a gas turbine power plant of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] In order to solve the technical problems in the existing technology, the accuracy of monitoring results is highly dependent on the quality of collected data and the reliability of sensors. Sensor failure or inaccurate data may lead to false warnings, and specific adjustments and calibrations cannot be made for different transformers and environmental conditions, and the environmental adaptability is low. Please refer to Figure 1 , this embodiment provides the following technical solutions:

[0062] The multi-dimensional comprehensive online monitoring and fault warning platform for main transformers in gas turbine power plants includes:

[0063] The multi-dimensional data acquisition unit is used to comprehensively monitor the main transformer from multiple dimensions based on the sensor components to ensure comprehensive coverage of all key aspects of the main transformer, collect data at preset time intervals according to monitoring requirements, pre-process the acquired dynamic monitoring data of the main transformer, and transmit it to the data analysis and early warning unit, including:

[0064] The sensor module is used to perform multi-dimensional monitoring of the main transformer based on the sensor components and obtain dynamic monitoring data during the operation of the main transformer;

[0065] The data acquisition module is used to collect sensor components and other monitoring data in real time based on edge monitoring devices, and pre-process the acquired dynamic monitoring data, including:

[0066] The dynamic monitoring data of the sensor component is collected regularly according to a preset collection frequency, and the collected data is classified according to the sensor category of the sensor component to generate multiple monitoring sub-data sets;

[0067] Acquire parameter verification rules for each monitoring sub-data set according to the sensor category, and generate a data verification component for the monitoring sub-data set;

[0068] Performing data verification on the sub-data in each monitoring sub-data set according to the data verification component of each monitoring sub-data set, and determining the abnormal coefficient of each sub-data according to the verification result;

[0069] The sub-data with anomaly coefficient greater than the preset data anomaly threshold are removed as edge data to obtain pre-processed dynamic monitoring data;

[0070] A data transmission module, used to transmit the pre-processed dynamic monitoring data to the data analysis and early warning unit based on the data transmission channel;

[0071] The data analysis and early warning unit is used to verify the integrity of the received dynamic monitoring data based on the data transmission channel, and to evaluate the main transformer based on the transformer health assessment model. It combines the health assessment report and the fault identification result to determine whether the main transformer has a fault and identify potential fault risks, and issue corresponding early warning information;

[0072] The online monitoring unit is used to monitor the operating status of the main transformer in real time and visualize the monitoring data and early warning information, including:

[0073] Visualization modules for:

[0074] Integrate the location information of the main transformers of the gas turbine power plant into the electronic map, display the specific location of each main transformer, mark the location of each main transformer on the map in real time, and dynamically update the mark according to its operating status;

[0075] Use different colors to indicate the operating status of the main transformer, such as green for normal operation, yellow for caution, and red for warning or fault status. Different icons are used to distinguish the type and function of the main transformer, and a brief operating status information is displayed next to the icon;

[0076] When the monitoring data exceeds the preset safety threshold, the corresponding main transformer operating status dynamic mark on the map is updated to a warning state, such as flashing or changing color, and provides warning information and recommended operating measures on the mark side;

[0077] The interactive control module is used to quickly locate each main transformer based on user instructions, and adjust parameters and set thresholds for each main transformer according to control instructions.

[0078] In this embodiment, multi-dimensional monitoring of the main transformer is performed based on the sensor component, and dynamic monitoring data of the main transformer during operation is fully acquired. The data transmission load is reduced through edge-side processing, and the integrity of the received dynamic monitoring data is verified. At the same time, the real-time and integrity of the data are ensured. The transformer health assessment model comprehensively evaluates the operating status of the main transformer, integrates a variety of monitoring data and historical experience, and can accurately judge the health status and fault type of the main transformer, providing timely and accurate fault information for operation and maintenance personnel. Through visual display and interactive control, the workload of operation and maintenance personnel is reduced, the operation and maintenance efficiency is improved, and reliable safety protection is provided for the main transformer of the gas turbine power plant, ensuring the stable operation of the power system.

[0079] In this embodiment, the sensor assembly includes:

[0080] The temperature sensor is used to monitor the temperature of key parts of the main transformer in real time, such as winding, core, oil temperature, etc., and record the temperature change trend of key parts of the main transformer to detect abnormal conditions such as overheating in time.

[0081] The sound sensor is used to monitor the noise of the main transformer in real time during operation, and perform spectrum analysis to identify abnormal sound characteristics, such as discharge sound, vibration sound, etc., to determine whether there is a fault in the main transformer, such as partial discharge, mechanical failure, etc.

[0082] The current sensor is used to monitor the coil current in real time and analyze the current waveform, such as harmonic content, current change rate, etc., in order to determine whether the main transformer has overload, short circuit and other faults.

[0083] Gas sensor is used to detect dissolved gases in the main transformer oil in real time, such as hydrogen, methane, ethane, etc., and analyze the main transformer fault type according to the gas composition and content, such as insulation aging, overheating, discharge, etc.

[0084] Environmental sensors are used to monitor environmental parameters in real time, such as temperature, humidity, air pressure and other data parameters, and analyze the impact of environmental parameters on the operating status of the main transformer. For example, excessive temperature may cause the transformer to overheat, and excessive humidity may cause insulation performance to deteriorate.

[0085] The vibration sensor is used to collect vibration data of the main transformer body and supporting structure in real time, and analyze parameters such as vibration frequency and amplitude to determine whether the transformer has mechanical faults such as looseness and wear.

[0086] In this embodiment, the sensor component can monitor and record small status changes in real time, so that the fault can be detected in the early stage, so that maintenance measures can be taken in advance to avoid the expansion of the fault. Comprehensive analysis of various sensor data such as temperature, sound, current, gas, environment and vibration, and multi-dimensional data collection make the transformer status assessment more comprehensive, and can more accurately identify and diagnose potential faults of the transformer, reduce false alarms and missed alarms, ensure the stable operation of the main transformer, reduce downtime, and extend equipment life.

[0087] In this embodiment, the data analysis and early warning unit includes:

[0088] The data processing module is used to read data based on the time series carried by the pre-processed dynamic monitoring data, and determine the integrity of the acquired dynamic monitoring data, and generate complete monitoring data based on the determination result, specifically:

[0089] Reading the sub-data in the pre-processed dynamic monitoring data to determine whether there is any omission in the sub-data;

[0090] When it is determined that there is omission in the sub-data, the adjacent data of the missing data are read, and the missing data are supplemented according to a preset similarity algorithm, and complete monitoring data is generated based on the supplementation result;

[0091] The model building module is used to establish a transformer health assessment model and input the complete monitoring data into the transformer health assessment model, evaluate the main transformer according to the transformer health assessment model, and generate a health assessment report;

[0092] Fault analysis module, used to determine whether the main transformer has faults and potential fault risks based on the health assessment report and fault identification results;

[0093] The fault warning module is used to provide fault warning based on the identified faults and potential fault risk categories, combined with the fault and potential fault risk thresholds, and match the corresponding strategy according to the fault level;

[0094] In this embodiment, through accurate data processing and model evaluation, the reliability of the entire monitoring and early warning system is improved, more serious equipment damage is avoided, thereby reducing maintenance costs, timely and effective fault warning and response, ensuring the continuity and safety of power supply, preventing and reducing the occurrence of faults, and intuitive health assessment reports and timely fault warning information, so that users can better understand the operating status of the transformer, improving user experience;

[0095] In this embodiment, the model building module evaluates the main transformer, specifically:

[0096] Extracting the operating characteristic data of the main transformer from the acquired complete monitoring data, and determining the current operating state of the main transformer according to the operating characteristic data of the main transformer, wherein the operating data corresponds one-to-one to the operating state of the leased battery;

[0097] The operation data are filtered according to the effective operation state of the main transformer to obtain target operation data, and clustering is performed according to the data features of the target operation data to obtain an operation data group of the main transformer;

[0098] Drawing an operation data change curve of the main transformer based on the operation data group of the main transformer, determining the change abnormality coefficient of the main transformer, and obtaining a performance attenuation evaluation value of the main transformer;

[0099] An operating state index and a degradation degree index of the main transformer are determined based on a performance attenuation evaluation value of the main transformer, and a health evaluation value of the main transformer is calculated based on weights of the operating state index and the degradation degree index.

[0100] In this embodiment, extracting the operating characteristic data of the main transformer from the complete monitoring data also includes:

[0101] Extract features from the complete monitoring data, and obtain an initial feature set of the complete monitoring data based on the extraction results;

[0102] And extract the feature data related to the health of the transformer from the initial feature set and integrate it into a key feature subset, including load features, temperature features, electrical features, etc.;

[0103] Determine the weight value of each main transformer according to the node attributes and operation mode of the main transformer in the gas turbine power plant;

[0104] The weight value of each main transformer is applied to each feature in its corresponding key feature subset, and the weighted feature value is standardized;

[0105] The weights of the operating status index and degradation degree index of each main transformer are determined according to the weighted and processed eigenvalue data.

[0106] In this embodiment, by extracting a subset of key features from the complete monitoring data and combining weight allocation and standardization processing, the scientificity and accuracy of the evaluation process are ensured, information redundancy and error accumulation are avoided, cluster analysis and anomaly detection can timely discover the performance degradation and abnormal changes of the main transformer, improve the sensitivity and accuracy of fault warning, and help operation and maintenance personnel take measures in advance to avoid the expansion of faults. The weight value is determined according to the node attributes and operation mode of the main transformer in the gas turbine power plant, and personalized evaluation of different transformers is realized, which is more in line with the actual situation, improves the pertinence and effectiveness of the evaluation, and calculates the health assessment value, providing intuitive and quantitative evaluation results for operation and maintenance personnel, which helps them make scientific decisions and arrange maintenance plans to ensure the stable operation of the power system.

[0107] In this embodiment, the fault analysis module determines the fault and potential fault risk, specifically:

[0108] Obtain the health assessment report generated by the health assessment module, extract the current health assessment value of the main transformer, the change abnormal coefficient of the main transformer, and possible abnormal indicators;

[0109] Extract and integrate the historical fault records of the main transformer, and build a fault identification model for the main transformer based on the integration results;

[0110] Compare the score in the health assessment report with the preset health standard to determine whether the health status of the main transformer is within the normal range;

[0111] Based on the fault identification model, the main transformer fault is identified, and combined with the change abnormal coefficient of the main transformer, it is identified whether the possible abnormal indicators match the known fault mode;

[0112] Based on the results of comparative analysis, the probability index of main transformer fault is evaluated, and a risk assessment is conducted on possible faults, including the possible consequences of the faults, the scope of impact, and the difficulty of maintenance.

[0113] In this embodiment, by combining health assessment and fault identification models, the accuracy and reliability of fault diagnosis are improved. Early identification of abnormal indicators allows measures to be taken in the early stages of fault development to avoid fault expansion. A more reasonable maintenance plan is formulated based on fault risk assessment, maintenance resources and time arrangements are optimized, potential fault risks are discovered and handled in a timely manner, and the failure rate of the main transformer is effectively reduced. Manual intervention is reduced, the safety level of power production is improved, the safety of personnel and equipment is guaranteed, and important guarantees are provided for the stable operation and safe production of power plants.

[0114] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A multi-dimensional integrated online monitoring and fault warning platform for main transformers in gas turbine power plants, characterized by: include: A multi-dimensional data acquisition unit is used to comprehensively monitor the main transformer from multiple dimensions based on the sensor components, collect data at preset time intervals according to monitoring requirements, pre-process the acquired dynamic monitoring data of the main transformer, and transmit it to the data analysis and early warning unit; The data analysis and early warning unit is used to verify the integrity of the received dynamic monitoring data based on the data transmission channel, and to evaluate the main transformer based on the transformer health assessment model. It combines the health assessment report and the fault identification result to determine whether the main transformer has a fault and identify potential fault risks, and issue corresponding early warning information; The online monitoring unit is used to monitor the operating status of the main transformer in real time and visualize the monitoring data and early warning information.

2. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 1, characterized in that: Multi-dimensional data acquisition unit, including: The sensor module is used to perform multi-dimensional monitoring of the main transformer based on the sensor components and obtain dynamic monitoring data during the operation of the main transformer; The data acquisition module is used to collect sensor components and other monitoring data in real time based on edge-side monitoring equipment, and pre-process the acquired dynamic monitoring data; The data transmission module is used to transmit the pre-processed dynamic monitoring data to the data analysis and early warning unit based on the data transmission channel.

3. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 2, characterized in that: The sensor assembly comprises: Temperature sensor, used to monitor the temperature of key parts of the main transformer in real time and record the temperature change trend of key parts of the main transformer; Sound sensor, used to monitor the noise of the main transformer in real time during operation, and perform spectrum analysis to identify abnormal sound characteristics and determine whether the main transformer is faulty; Current sensor, used to monitor coil current in real time and analyze current waveform; Gas sensor, used to detect dissolved gas in the main transformer oil in real time and analyze the main transformer fault type based on gas composition and content; Environmental sensors are used to monitor environmental parameters in real time and analyze the impact of environmental parameters on the operating status of the main transformer; Vibration sensor, used to collect vibration data of the main transformer body and supporting structure in real time.

4. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 3 is characterized by: The data acquisition module preprocesses the acquired dynamic monitoring data, including: The dynamic monitoring data of the sensor component is collected regularly according to a preset collection frequency, and the collected data is classified according to the sensor category of the sensor component to generate multiple monitoring sub-data sets; Acquire parameter verification rules for each monitoring sub-data set according to the sensor category, and generate a data verification component for the monitoring sub-data set; Performing data verification on the sub-data in each monitoring sub-data set according to the data verification component of each monitoring sub-data set, and determining the abnormal coefficient of each sub-data according to the verification result; The sub-data with anomaly coefficients greater than the preset data anomaly threshold are removed as edge data to obtain pre-processed dynamic monitoring data.

5. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 4, characterized in that: Data analysis and early warning unit, including: A data processing module is used to read data based on the time series carried by the pre-processed dynamic monitoring data, determine the integrity of the acquired dynamic monitoring data, and generate complete monitoring data based on the determination result; The model building module is used to establish a transformer health assessment model and input the complete monitoring data into the transformer health assessment model, evaluate the main transformer according to the transformer health assessment model, and generate a health assessment report; Fault analysis module, used to determine whether the main transformer has faults and potential fault risks based on the health assessment report and fault identification results; The fault warning module is used to provide fault warning based on the identified faults and potential fault risk categories, combined with the fault and potential fault risk thresholds, and match the corresponding strategy according to the fault level.

6. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 5, characterized in that: Data processing module, specifically: Reading the sub-data in the pre-processed dynamic monitoring data to determine whether there is any omission in the sub-data; When it is determined that there is omission in the sub-data, the adjacent data of the missing data are read, and the missing data are supplemented according to a preset similarity algorithm, and complete monitoring data are generated based on the supplementation result.

7. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 6, characterized in that: The model building module evaluates the main transformer, specifically: Extracting the operating characteristic data of the main transformer from the acquired complete monitoring data, and determining the current operating state of the main transformer according to the operating characteristic data of the main transformer, wherein the operating data corresponds one-to-one to the operating state of the leased battery; The operation data are filtered according to the effective operation state of the main transformer to obtain target operation data, and clustering is performed according to the data features of the target operation data to obtain an operation data group of the main transformer; Drawing an operation data change curve of the main transformer based on the operation data group of the main transformer, determining the change abnormality coefficient of the main transformer, and obtaining a performance attenuation evaluation value of the main transformer; An operating state index and a degradation degree index of the main transformer are determined based on a performance attenuation evaluation value of the main transformer, and a health evaluation value of the main transformer is calculated based on weights of the operating state index and the degradation degree index.

8. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 7, characterized in that: Extract the operating characteristic data of the main transformer from the complete monitoring data, including: Extract features from the complete monitoring data, and obtain an initial feature set of the complete monitoring data based on the extraction results; And extract the feature data related to the transformer health from the initial feature set and integrate them into a key feature subset; Determine the weight value of each main transformer according to the node attributes and operation mode of the main transformer in the gas turbine power plant; The weight value of each main transformer is applied to each feature in its corresponding key feature subset, and the weighted feature value is standardized; The weights of the operating status index and degradation degree index of each main transformer are determined according to the weighted and processed eigenvalue data.

9. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 8, characterized in that: The fault analysis module determines faults and potential fault risks, specifically: Obtain the health assessment report generated by the health assessment module, extract the current health assessment value of the main transformer, the change abnormal coefficient of the main transformer, and possible abnormal indicators; Extract and integrate the historical fault records of the main transformer, and build a fault identification model for the main transformer based on the integration results; Compare the score in the health assessment report with the preset health standard to determine whether the health status of the main transformer is within the normal range; Based on the fault identification model, the main transformer fault is identified, and combined with the change abnormal coefficient of the main transformer, it is identified whether the possible abnormal indicators match the known fault mode; Based on the results of comparative analysis, the probability index of main transformer fault is evaluated, and the risk assessment of possible faults is carried out.

10. The multi-dimensional integrated online monitoring and fault warning platform for main transformers of gas turbine power plants according to claim 9, characterized in that: Online monitoring unit, including: Visualization modules for: Integrate the location information of the main transformers of the gas turbine power plant into the electronic map, display the specific location of each main transformer, mark the location of each main transformer on the map in real time, and dynamically update the mark according to its operating status; When the monitoring data exceeds the preset safety threshold, the corresponding main transformer operating status dynamic mark on the map is updated to the warning state, and the warning information and recommended operating measures are provided on the mark side; The interactive control module is used to quickly locate each main transformer based on user instructions, and adjust parameters and set thresholds for each main transformer according to control instructions.

Images