Oil temperature monitoring system and method for oil-immersed transformer

Abstract

The invention discloses an oil temperature monitoring system and method for an oil-immersed transformer, and relates to the technical power equipment state monitoring field, and the system comprises a temperature sensor module, a data acquisition module, a data processing and analysis module, an early warning module and a fault diagnosis module; the temperature sensor module comprises a plurality of temperature sensors distributed at different positions of the oil-immersed transformer and is used for acquiring oil temperature data in the transformer in real time; the data acquisition module is connected with the temperature sensor module and is used for collecting oil temperature data acquired by a temperature sensor and transmitting the data to the data processing and analyzing module; the data processing and analyzing module is used for processing and analyzing the collected oil temperature data; the early warning module is used for sending out an early warning signal when the data processing and analyzing module detects that the oil temperature is abnormal or predicts that the hot spot temperature exceeds a safety threshold value; according to the invention, the problem that the fault of the transformer cannot be accurately monitored and intelligently diagnosed is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment status monitoring, and in particular to an oil temperature monitoring system and method for an oil-immersed transformer. Background Art

[0002] As a vital equipment in the power system, oil-immersed transformers undertake the key tasks of voltage conversion, power transmission and distribution. Their safe and stable operation is of decisive significance to ensuring the reliability of the power system. In the operation of oil-immersed transformers, oil temperature is an extremely critical parameter. Abnormal changes in oil temperature will not only affect the insulation performance of the transformer, accelerate the aging of insulation materials, and shorten the service life of the transformer, but may also cause serious faults such as local overheating and insulation breakdown, which will lead to power outages and bring huge losses to industrial production, residents' lives and the entire social economy.

[0003] With the rapid development of information technology, although some advanced monitoring technologies have gradually been applied to the field of oil temperature monitoring of oil-immersed transformers, there are still many shortcomings. On the one hand, the research on the internal thermal characteristics of oil-immersed transformers is not detailed enough. Although with the development of computer computing power, there have been some studies on the internal temperature distribution and oil flow characteristics of transformers, the existing three-dimensional model is not detailed enough and cannot accurately reflect the actual situation inside the transformer, resulting in a lack of accurate basis for the design and manufacturing optimization of transformers. On the other hand, when the existing Kalman filter model predicts the hot spot temperature of large transformer windings, there is a time lag when the load changes drastically. This time lag will affect the accurate prediction of the hot spot temperature of the windings, and then affect the safe operation of the transformer. In addition, the existing transformer fault diagnosis model is not perfect enough to achieve accurate monitoring and intelligent diagnosis of transformer faults. Therefore, it is necessary to design an oil-immersed transformer oil temperature monitoring system and method that can monitor the transformer oil temperature in real time, accurately and comprehensively. Summary of the invention

[0004] The object of the present invention is to provide an oil temperature monitoring system and method for an oil-immersed transformer to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an oil temperature monitoring system for an oil-immersed transformer, comprising a temperature sensor module, a data acquisition module, a data processing and analysis module, an early warning module and a fault diagnosis module;

[0006] The temperature sensor module includes a plurality of temperature sensors distributed at different positions of the oil-immersed transformer, and is used to collect oil temperature data inside the transformer in real time;

[0007] The data acquisition module is connected to the temperature sensor module, and is used to collect the oil temperature data collected by the temperature sensor and transmit the data to the data processing and analysis module;

[0008] The data processing and analysis module is used to process and analyze the collected oil temperature data;

[0009] The warning module is used to send a warning signal when the data processing and analysis module detects abnormal oil temperature or predicts that the hot spot temperature exceeds the safety threshold;

[0010] The fault diagnosis module is used to further analyze the cause of the fault, determine the location and type of the fault, and provide corresponding repair suggestions after the warning module sends a warning signal.

[0011] According to the above technical solution, the data processing and analysis module includes a thermal characteristic analysis unit, a hot spot temperature prediction unit, and a fault diagnosis analysis unit;

[0012] The thermal characteristic analysis unit uses a refined three-dimensional model to numerically simulate the internal temperature distribution and oil flow characteristics of the transformer;

[0013] The hot spot temperature prediction unit improves the Kalman filter model to predict the winding hot spot temperature; optimizes the parameters of the Kalman filter model, combines the actual operation data of the transformer, adjusts the prediction strategy of the model, and reduces the time lag when the load changes violently;

[0014] The fault diagnosis analysis unit, according to the results of the thermal characteristic analysis unit and the hot spot temperature prediction unit, combines the preset fault diagnosis rules to monitor the operation state of the transformer in real time and diagnose faults; sets the oil temperature safety threshold and the hot spot temperature safety threshold, and triggers the fault diagnosis process when the monitored oil temperature or the predicted hot spot temperature exceeds the safety threshold.

[0015] An oil-immersed transformer oil temperature monitoring method includes the following steps:

[0016] Step S1: The temperature sensor module collects the oil temperature data at different positions of the oil-immersed transformer in real time, and the data acquisition module transmits the collected data to the data processing and analysis module;

[0017] Step S2: The thermal characteristic analysis unit of the data processing and analysis module uses a three-dimensional model to numerically simulate the internal temperature distribution and oil flow characteristics of the transformer;

[0018] Step S3: The hot spot temperature prediction unit improves the Kalman filter model to predict the winding hot spot temperature;

[0019] Step S4: The fault diagnosis and analysis unit monitors the operating status of the transformer in real time and conducts fault diagnosis based on the results of the thermal characteristic analysis unit and the hot spot temperature prediction unit, in combination with the preset fault diagnosis rules;

[0020] Step S5: When the warning module detects abnormal oil temperature or predicts that the hot spot temperature exceeds the safety threshold, it issues a warning signal; the fault diagnosis module matches the preset maintenance suggestions according to the fault diagnosis results.

[0021] According to the above technical solution, the specific steps for numerically simulating the internal temperature distribution and oil flow characteristics of the transformer using the three-dimensional model in step S2 are as follows:

[0022] Step S21: Establish a three-dimensional geometric model based on the actual structural parameters of the transformer;

[0023] Step S22: Divide the unstructured grid to ensure that the grid in the key areas is fine enough, where the key areas include windings and oil ducts;

[0024] Step S23: Define the material properties;

[0025] Step S24: Set the boundary conditions, including the ambient temperature and the internal heat sources related to the load;

[0026] Step S25: Establish the control equations, discretize the equations, and select a numerical method for solution, where the numerical methods include the finite element method and the finite difference method;

[0027] Step S26: Iteratively solve until convergence to obtain the temperature distribution and the oil flow velocity distribution.

[0028] According to the above technical solution, in step S25, the solution of the control equations includes the heat conduction equation and the fluid motion equation, where

[0029] The heat conduction equation is as follows:

[0030]

[0031] where ρ is the density, C p is the specific heat capacity, T is the temperature, t is the time, k is the thermal conductivity, Q v is the volume heat source, including eddy current loss and resistance loss;

[0032] The fluid motion equation is as follows:

[0033]

[0034] where p is the pressure, μ is the dynamic viscosity of the oil, g is the acceleration due to gravity, β is the thermal expansion coefficient of the oil, and T0 is the ambient temperature.

[0035] According to the above technical solution, step S3 further includes:

[0036] Step S31: Establish the state equation and observation equation of the Kalman filter model, where the state equation is: x k = A k- 1x k-1 + B k-1 u k-1 + w k-1 ; The observation equation is: y k = H k x k + v k ; Where x k is the state vector, A k-1 is the state transition matrix, B k-1 is the control input matrix, u k-1 is the control input vector, w k-1 is the process noise, y k is the observation vector, H k is the observation matrix, v k is the observation noise;

[0037] Step S32: Optimize the parameters of the Kalman filter model. According to the actual operation data of the transformer, adjust the parameters of the state transition matrix and the observation matrix to reduce the time delay;

[0038] Step S33: Use the optimized Kalman filter model to predict the hot spot temperature of the winding.

[0039] According to the above technical solution, step S32 further includes:

[0040] Step S321: Collect the operation data of the transformer under different load conditions, including the actual measured values of the hot spot temperature of the winding and the relevant control input data;

[0041] Step S322: Adopt the maximum likelihood estimation method to estimate the parameters of the Kalman filter model according to the collected data;

[0042] Step S323: Divide the collected data into two parts. Use one part of the data for model training and the other part for model verification. By comparing the prediction results of the model with the actual measured values, evaluate the performance of the model: If there is a large time delay when the load changes violently, further adjust the parameters.

[0043] According to the above technical solution, step S33 further includes:

[0044] Step S331: Set the initial state vector x0 and the initial covariance matrix P0;

[0045] Step S332: According to the state equation Predict the prior state vector at time k where x k-1 is the posterior state vector at time k-1; at the same time, according to the covariance prediction formula Predict the prior covariance matrix at time k Where P k-1 is the posterior covariance matrix at time k-1;

[0046] Step S333: According to the observation equation y k =H k x k +v k and the actual observed value y k , calculate the Kalman gain, Then update the formula based on the posterior state vector Update the posterior state vector x at time k k , according to the posterior covariance matrix update formula Update the posterior covariance matrix P at time k k ;

[0047] Step S334: Repeat the prediction phase and the update phase, continuously use the new observation value to predict the hot spot temperature of the winding, and obtain the predicted value of the hot spot temperature of the winding at a future moment.

[0048] According to the above technical solution, in step S334, when performing winding hot spot temperature prediction in the repeated prediction stage and the update stage, a prediction time window and a prediction accuracy threshold are set; when the prediction time window reaches a preset time length or the accuracy of multiple consecutive prediction results meets the preset threshold, the prediction process is stopped; at the same time, the predicted winding hot spot temperature prediction value is compared with the preset hot spot temperature safety threshold in real time. If the prediction value exceeds the safety threshold, the early warning module is immediately triggered to send a warning signal, and the relevant prediction data is synchronized to the fault diagnosis module for further analysis.

[0049] According to the above technical solution, after receiving the warning signal and prediction data sent by the warning module, the fault diagnosis module conducts a comprehensive analysis of the historical fault data, current operating status data and prediction data, and uses time series analysis methods and machine learning algorithms to establish a fault development trend prediction model to predict the development of the fault in the future. The fault development trend prediction results are fed back to relevant personnel so that more complete maintenance plans and response measures can be formulated in advance.

[0050] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: Through refining the research on the internal thermal characteristics of oil-immersed transformers, improving the prediction method of winding hot-spot temperature, and establishing a fault diagnosis model including thermal state parameters, the present invention realizes accurate monitoring and fault diagnosis of the oil temperature of oil-immersed transformers, improving the operation safety and reliability of transformers. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention.

[0052] In the accompanying drawings:

[0053] Figure 1 is a schematic diagram of the composition of an oil temperature monitoring system for an oil-immersed transformer according to the present invention;

[0054] Figure 2 is a schematic diagram of the composition of the data processing and analysis module of the present invention;

[0055] Figure 3 is a schematic diagram of a method for monitoring the oil temperature of an oil-immersed transformer according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0057] Embodiment 1

[0058] Please refer to Figure 1 and Figure 2 , the present invention provides a technical solution: An oil temperature monitoring system for an oil-immersed transformer includes a temperature sensor module, a data acquisition module, a data processing and analysis module, an early warning module, and a fault diagnosis module;

[0059] The temperature sensor module includes a plurality of temperature sensors distributed at different positions of the oil-immersed transformer, and is used to collect the oil temperature data inside the transformer in real time; The temperature sensors are installed at key parts such as the windings, iron cores, and oil channels of the transformer to comprehensively obtain the temperature information of the transformer;

[0060] The data acquisition module is connected to the temperature sensor module, and is used to collect the oil temperature data collected by the temperature sensor and transmit the data to the data processing and analysis module; the data acquisition module has high-speed and stable data transmission capabilities, and adopts advanced data transmission protocols and technologies to ensure the real-time and accuracy of the data;

[0061] The data processing and analysis module is used to process and analyze the collected oil temperature data;

[0062] The warning module is used to send a warning signal when the data processing and analysis module detects abnormal oil temperature or predicts that the hot spot temperature exceeds the safety threshold; the warning signal is sent to relevant personnel through means such as audible and visual alarms and SMS notifications;

[0063] The fault diagnosis module is used to further analyze the cause of the fault, determine the location and type of the fault, and provide corresponding repair suggestions after the warning module sends a warning signal; by using a transformer fault diagnosis model containing thermal state parameters and comprehensively considering the thermal characteristics, electrical characteristics and operation history data of the transformer, the accuracy and reliability of fault diagnosis are improved.

[0064] The data processing and analysis module includes a thermal characteristic analysis unit, a hot spot temperature prediction unit and a fault diagnosis analysis unit;

[0065] The thermal characteristic analysis unit uses a refined three-dimensional model to numerically simulate the internal temperature distribution and oil flow characteristics of the transformer; by establishing an unstructured grid and considering factors such as the structural parameters, material properties, and load conditions of the transformer, the internal temperature distribution and oil flow velocity distribution of the transformer are obtained;

[0066] The hot spot temperature prediction unit improves the Kalman filter model to predict the winding hot spot temperature; optimizes the parameters of the Kalman filter model, combines the actual operation data of the transformer, adjusts the prediction strategy of the model, and reduces the time lag when the load changes violently;

[0067] The fault diagnosis analysis unit, according to the results of the thermal characteristic analysis unit and the hot spot temperature prediction unit, combines the preset fault diagnosis rules to monitor the operation state of the transformer in real time and diagnose faults; sets the oil temperature safety threshold and the hot spot temperature safety threshold, and triggers the fault diagnosis process when the monitored oil temperature or the predicted hot spot temperature exceeds the safety threshold.

[0068] Embodiment 2

[0069] Please refer to Figure 3 , based on the same inventive concept as Embodiment 1, the present invention provides a technical solution: an oil-immersed transformer oil temperature monitoring method, including the following steps:

[0070] Step S1: The temperature sensor module collects the oil temperature data at different positions of the oil-immersed transformer in real time, and the data acquisition module transmits the collected data to the data processing and analysis module;

[0071] Step S2: The thermal characteristic analysis unit of the data processing and analysis module numerically simulates the internal temperature distribution and oil flow characteristics of the transformer using a three-dimensional model;

[0072] Step S3: The hot spot temperature prediction unit improves the Kalman filter model to predict the winding hot spot temperature;

[0073] Step S4: The fault diagnosis and analysis unit monitors the operating state of the transformer in real time and diagnoses faults according to the results of the thermal characteristic analysis unit and the hot spot temperature prediction unit, combined with the preset fault diagnosis rules;

[0074] Step S5: The warning module issues a warning signal when abnormal oil temperature is detected or the predicted hot spot temperature exceeds the safety threshold; the fault diagnosis module matches the preset maintenance suggestions according to the fault diagnosis results.

[0075] The specific steps for numerically simulating the internal temperature distribution and oil flow characteristics of the transformer using a three-dimensional model in Step S2 are as follows:

[0076] Step S21: Establish a three-dimensional geometric model based on the actual structural parameters of the transformer;

[0077] Step S22: Divide the unstructured grid to ensure that the grid in the key areas is fine enough, where the key areas include windings and oil ducts;

[0078] Step S23: Define material properties such as density, specific heat capacity, thermal conductivity, etc.;

[0079] Step S24: Set boundary conditions, including ambient temperature and internal heat sources related to the load;

[0080] Step S25: Establish control equations, discretize the equations, and select numerical methods for solving, where the numerical methods include the finite element method and the finite difference method;

[0081] Step S26: Iteratively solve until convergence to obtain the temperature distribution and oil flow velocity distribution.

[0082] In Step S25, the solution of the control equations includes the heat conduction equation and the fluid motion equation, where

[0083] The heat conduction equation is as follows:

[0084]

[0085] Among them, ρ is the density, C pis the specific heat capacity, T is the temperature, t is the time, k is the thermal conductivity, and Q v is the volumetric heat source, including eddy current loss and resistance loss. This equation describes the transient heat transfer process of the oil temperature inside the transformer, comprehensively considering the effects of heat conduction, heat convection, and internal heat sources;

[0086] The fluid motion equation is as follows:

[0087]

[0088] Among them, p is the pressure, μ is the dynamic viscosity of the oil, g is the acceleration due to gravity, β is the thermal expansion coefficient of the oil, and T0 is the ambient temperature, which is used to simulate the motion characteristics of the oil flow inside the transformer. Combining with the heat conduction equation to calculate the coupling effect of the temperature field and the flow field;

[0089] Step S3 further includes:

[0090] Step S31: Establish the state equation and observation equation of the Kalman filter model, where the state equation is: x k = A k- 1x k-1 + B k-1 u k-1 + w k-1 ; The observation equation is: y k = H k x k + v k ; Where x k is the state vector, A k-1 is the state transition matrix, B k-1 is the control input matrix, u k-1 is the control input vector, w k-1 is the process noise, y k is the observation vector, H k is the observation matrix, and v k is the observation noise; The state equation predicts the current state x k-1 through the previous state x k-1 and the control input u k , and introduces the process noise w k-1 to represent the model error, while the observation equation maps the state vector x k to the actual observation value y k , and superimposes the observation noise v k ; Dynamically predict the hot spot temperature of the winding, and iteratively update the prediction result (prediction-update loop) in combination with real-time sensor data to trigger an early warning in advance;

[0091] Step S32: Optimize the parameters of the Kalman filter model, and adjust the parameters of the state transition matrix and the observation matrix according to the actual operation data of the transformer to reduce the time lag;

[0092] Step S33: Predict the winding hot-spot temperature using the optimized Kalman filter model.

[0093] Step S32 further includes:

[0094] Step S321: Collect the operation data of the transformer under different load conditions, including the actual measured values of the winding hot-spot temperature and the data of related control inputs (such as load current);

[0095] Step S322: Adopt the maximum likelihood estimation method to estimate the parameters of the Kalman filter model according to the collected data; for example, for the process noise covariance Q k-1 and the observation noise covariance R k , they can be estimated by minimizing the sum of the squared errors between the predicted values and the actual measured values;

[0096] Step S323: Divide the collected data into two parts, use one part of the data for model training, and the other part of the data for model verification. Evaluate the performance of the model by comparing the predicted results of the model with the actual measured values: If there is a large time delay when the load changes drastically, further adjust the parameters, such as increasing the process noise covariance Q k-1 to improve the adaptability of the model to the dynamic changes of the system.

[0097] Step S33 further includes:

[0098] Step S331: Set the initial state vector x0 and the initial covariance matrix P0; the initial state vector can be determined according to the initial operating conditions of the transformer. For example, the initial winding hot-spot temperature can be set to the ambient temperature or set according to empirical values. The initial covariance matrix P0 can be set to a relatively large diagonal matrix, indicating the uncertainty of the initial state;

[0099] Step S332: According to the state equation predict the prior state vector at time k where x k-1 is the posterior state vector at time k - 1; meanwhile, according to the covariance prediction formula predict the prior covariance matrix at time k where P k-1 is the posterior covariance matrix at time k - 1;

[0100] Step S333: According to the observation equation y k = H k x k + v k and the actual observed value y k , calculate the Kalman gain, then according to the posterior state vector update formula Update the posterior state vector \(x\) at time \(k\). k , and update the posterior covariance matrix \(P\) at time \(k\) according to the posterior covariance matrix update formula Update the posterior covariance matrix \(P\) at time \(k\). k ;

[0101] Step S334: Repeat the prediction stage and the update stage, continuously predict the winding hot-spot temperature using new observation values, and obtain the predicted values of the winding hot-spot temperature at future times.

[0102] In step S334, when predicting the winding hot-spot temperature during the repeated prediction stage and update stage, set a prediction time window and a prediction accuracy threshold; when the prediction time window reaches a preset duration or the accuracy of consecutive multiple prediction results meets the preset threshold, stop the prediction process; at the same time, compare the predicted values of the winding hot-spot temperature obtained by prediction with a preset hot-spot temperature safety threshold in real time. If the predicted value exceeds the safety threshold, immediately trigger the warning module to send a warning signal, and synchronize the relevant prediction data to the fault diagnosis module for further analysis.

[0103] After receiving the warning signal and prediction data sent by the warning module, the fault diagnosis module comprehensively analyzes the historical fault data, the current operating state data, and the prediction data, and uses time series analysis methods and machine learning algorithms to establish a fault development trend prediction model to predict the development of the fault in the future for a period of time, such as the fault deterioration speed, the possible affected range, etc., and feedback the fault development trend prediction results to relevant personnel together, so as to formulate a more perfect maintenance plan and response measures in advance. Thus, not only can the transformer fault diagnosis model containing thermal state parameters be used to analyze the fault causes and provide maintenance suggestions, but also it has the function of predicting the fault development trend.

[0104] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes 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 processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0105] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the function.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the function.

[0107] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit and scope of the present invention as protected by the claims. All of these are within the protection scope of the present invention.

Claims

1. An oil-immersed transformer oil temperature monitoring system, characterized in that: The oil-immersed transformer oil temperature monitoring system includes a temperature sensor module, a data acquisition module, a data processing and analysis module, an early warning module, and a fault diagnosis module; The temperature sensor module includes multiple temperature sensors distributed at different positions of the oil-immersed transformer, which are used to collect the oil temperature data inside the transformer in real time; The data acquisition module is connected to the temperature sensor module, and is used to collect the oil temperature data collected by the temperature sensors and transmit the data to the data processing and analysis module; The data processing and analysis module is used to process and analyze the collected oil temperature data; The early warning module is used to issue an early warning signal when the data processing and analysis module detects abnormal oil temperature or predicts that the hot spot temperature exceeds the safety threshold; The fault diagnosis module is used to further analyze the cause of the fault, determine the location and type of the fault, and provide corresponding maintenance suggestions after the early warning module issues an early warning signal.

2. The oil-immersed transformer oil temperature monitoring system according to claim 1, wherein: The data processing and analysis module includes a thermal characteristic analysis unit, a hot spot temperature prediction unit, and a fault diagnosis analysis unit; The thermal characteristic analysis unit numerically simulates the internal temperature distribution and oil flow characteristics of the transformer using a fine three-dimensional model; The hot spot temperature prediction unit improves the Kalman filter model to predict the winding hot spot temperature; Optimize the parameters of the Kalman filter model, combine the actual operation data of the transformer, adjust the prediction strategy of the model, and reduce the time lag when the load changes violently; The fault diagnosis analysis unit, based on the results of the thermal characteristic analysis unit and the hot spot temperature prediction unit, combines the preset fault diagnosis rules to monitor the operation status of the transformer in real time and diagnose faults; set the oil temperature safety threshold and the hot spot temperature safety threshold, and trigger the fault diagnosis process when the monitored oil temperature or the predicted hot spot temperature exceeds the safety threshold.

3. An oil-immersed transformer oil temperature monitoring method, characterized in that, It includes the following steps: Step S1: The temperature sensor module collects the oil temperature data at different positions of the oil-immersed transformer in real time, and the data acquisition module transmits the collected data to the data processing and analysis module; Step S2: The thermal characteristic analysis unit of the data processing and analysis module numerically simulates the internal temperature distribution and oil flow characteristics of the transformer using a three-dimensional model; Step S3: The hot spot temperature prediction unit improves the Kalman filter model to predict the winding hot spot temperature; Step S4: The fault diagnosis analysis unit, based on the results of the thermal characteristic analysis unit and the hot spot temperature prediction unit, combines the preset fault diagnosis rules to monitor the operation status of the transformer in real time and diagnose faults; Step S5: The early warning module issues an early warning signal when it detects abnormal oil temperature or predicts that the hot spot temperature exceeds the safety threshold; the fault diagnosis module matches the preset maintenance suggestions according to the fault diagnosis results.

4. A method for monitoring the oil temperature of an oil-immersed transformer according to claim 3, characterized in that: The specific steps of numerically simulating the internal temperature distribution and oil flow characteristics of the transformer using a three-dimensional model in step S2 are as follows: Step S21: Establish a three-dimensional geometric model based on the actual structural parameters of the transformer; Step S22: Divide the unstructured grid to ensure that the grid in the key areas is fine enough, where the key areas include windings and oil ducts; Step S23: Define the material properties; Step S24: Set boundary conditions, including ambient temperature and internal heat sources related to the load; Step S25: Establish control equations, discretize the equations, and select numerical methods for solving, where the numerical methods include the finite element method and the finite difference method; Step S26: Iteratively solve until convergence to obtain the temperature distribution and the oil flow velocity distribution.

5. A method for monitoring the oil temperature of an oil-immersed transformer according to claim 4, characterized in that: In the said Step S25, the solution of the control equations includes the heat conduction equation and the fluid motion equation, where The heat conduction equation is as follows: where ρ is the density, C p is the specific heat capacity, T is the temperature, t is the time, k is the thermal conductivity, Q v is the volume heat source, including eddy current loss and resistance loss; The fluid motion equation is as follows: where p is the pressure, μ is the dynamic viscosity of the oil, g is the acceleration due to gravity, β is the thermal expansion coefficient of the oil, and T0 is the ambient temperature.

6. The oil temperature monitoring method of an oil-immersed transformer according to claim 3, wherein: The said Step S3 further includes: Step S31: Establish the state equation and observation equation of the Kalman filter model. The state equation is: x k = A k-1 x k-1 + B k-1 u k-1 + w k-1 ; The observation equation is: y k = H k x k + v k ; Where x k is the state vector, A k-1 is the state transition matrix, B k-1 is the control input matrix, u k-1 is the control input vector, w k-1 is the process noise, y k is the observation vector, H k is the observation matrix, v k is the observation noise; Step S32: Optimize the parameters of the Kalman filter model. According to the actual operation data of the transformer, adjust the parameters of the state transition matrix and the observation matrix to reduce the time delay; Step S33: Use the optimized Kalman filter model to predict the hot spot temperature of the winding.

7. A method for monitoring the oil temperature of an oil-immersed transformer according to claim 6, characterized in that: The said Step S32 further includes: Step S321: Collect the operation data of the transformer under different load conditions, including the actual measured values of the hot spot temperature of the winding and the relevant control input data; Step S322: Adopt the maximum likelihood estimation method to estimate the parameters of the Kalman filter model according to the collected data; Step S323: Divide the collected data into two parts. Use one part of the data for model training and the other part for model verification. Evaluate the performance of the model by comparing the predicted results of the model with the actual measured values: If there is a large time delay when the load changes drastically, further adjust the parameters.

8. A method for monitoring the oil temperature of an oil-immersed transformer according to claim 6, characterized in that: The said Step S33 further includes: Step S331: Set the initial state vector x0 and the initial covariance matrix P0; Step S332: According to the state equation Predict the prior state vector at time k where x k-1 is the posterior state vector at time k-1; meanwhile, according to the covariance prediction formula Predict the prior covariance matrix at time k where P k-1 is the posterior covariance matrix at time k-1; Step S333: According to the observation equation y k = H k x k + v k and the actual observed value y k , calculate the Kalman gain, then update the posterior state vector at time k according to the posterior state vector update formula x k , and update the posterior covariance matrix at time k according to the posterior covariance matrix update formula P k ; Step S334: Repeat the prediction stage and the update stage, continuously use the new observation values to predict the hot spot temperature of the winding, and obtain the predicted values of the hot spot temperature of the winding at future moments.

9. A method for monitoring the oil temperature of an oil-immersed transformer according to claim 8, characterized in that: In the said Step S334, when predicting the hot spot temperature of the winding in the repeated prediction stage and update stage, set the prediction time window and the prediction accuracy threshold; When the prediction time window reaches the preset duration or the accuracy of the continuous multiple prediction results meets the preset threshold, stop the prediction process; At the same time, compare the predicted hot spot temperature prediction value with the preset hot spot temperature safety threshold in real time. If the predicted value exceeds the safety threshold, immediately trigger the warning module to send a warning signal, and synchronize the relevant prediction data to the fault diagnosis module for further analysis.

10. A method for monitoring the oil temperature of an oil-immersed transformer according to claim 9, characterized in that: After receiving the warning signal and the prediction data sent by the warning module, the said fault diagnosis module comprehensively analyzes the historical fault data, the current operation status data, and the prediction data, adopts the time series analysis method and the machine learning algorithm to establish a fault development trend prediction model, predicts the development of the fault in the future period of time, and feeds back the fault development trend prediction results to the relevant personnel together, so as to formulate a more perfect maintenance plan and countermeasures in advance.

Images