Method for determining oil extraction position of oil-immersed transformer, device and electronic equipment thereof

Abstract

The application discloses a method and device for determining an oil extraction position of an oil-immersed transformer and electronic equipment, and relates to the technical field of fault diagnosis, wherein the method comprises: performing multi-physical field coupling simulation calculation on the oil-immersed transformer to obtain simulation data; simulating gas generation and gas diffusion under different faults based on the simulation data to obtain a migration path and concentration data of the gas; and determining a target oil extraction position of an oil tank in the oil-immersed transformer based on the migration path and the concentration data. The application solves the technical problem that the oil extraction position of the oil-immersed transformer cannot be accurately determined in the related art.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology, and more specifically, to a method, apparatus, and electronic device for determining the oil sampling location of an oil-immersed transformer. Background Technology

[0002] Oil-immersed transformers are key equipment in power transmission and distribution systems, and their operating status affects the reliability and economy of the power grid. Due to long-term continuous operation, transformers are susceptible to various faults due to both external environmental factors and internal insulation aging. Once a fault occurs, it will threaten the stable operation of the power grid and may even cause large-scale power outages, resulting in economic losses.

[0003] Currently, transformer fault diagnosis is mainly achieved through dissolved gas analysis (DGA), which determines the fault type by detecting the content and ratio of specific gases in the oil. However, most current oil sampling ports are located in fixed positions within the transformer tank (usually the lower drain valve), failing to fully consider the dynamics of oil flow, gas diffusion paths, and the non-uniformity of spatial distribution during a fault. Especially in cases of sudden faults or high-intensity gas generation, the gas is collected before it has fully diffused, and the obtained gas concentration data cannot accurately reflect the fault state, easily leading to misdiagnosis or missed diagnosis.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, and electronic device for determining the oil sampling location of an oil-immersed transformer, thereby at least solving the technical problem in related technologies that cannot accurately determine the oil sampling location of an oil-immersed transformer.

[0006] According to one aspect of the embodiments of this application, a method for determining the oil sampling location of an oil-immersed transformer is provided, comprising: performing multiphysics coupling simulation calculations on the oil-immersed transformer to obtain simulation data; simulating gas generation and gas diffusion under different fault conditions based on the simulation data to obtain gas migration paths and concentration data; and determining the target oil sampling location in the oil tank inside the oil-immersed transformer based on the migration paths and concentration data.

[0007] Furthermore, before performing multiphysics coupling simulation calculations on the oil-immersed transformer to obtain simulation data, the process includes: determining multiple structural parameters of the oil-immersed transformer; and constructing a three-dimensional model based on all structural parameters, wherein the three-dimensional model is used to perform multiphysics coupling simulation calculations on the oil-immersed transformer.

[0008] Furthermore, after performing multiphysics coupling simulation calculations on the oil-immersed transformer and obtaining simulation data, the process also includes: analyzing the simulation data to obtain analysis data; and based on the analysis data, determining the first target region and the second target region for oil flow in the oil-immersed transformer.

[0009] Furthermore, the step of determining the target oil sampling location in the oil tank of the oil-immersed transformer based on the migration path and concentration data includes: determining a preset region set based on the first target region and the second target region; determining the region in the oil tank other than the preset region set as candidate regions; and determining the target oil sampling location from the candidate regions based on the migration path and concentration data.

[0010] Furthermore, after determining the target oil sampling location in the oil tank of the oil-immersed transformer based on the migration path and concentration data, the process further includes: collecting oil samples from the target oil sampling location and analyzing the oil samples to obtain gas data; using a preset fault identification model to identify the gas data and obtain identification results. The preset fault identification model has a model structure that includes at least a target network structure, which includes at least multiple nodes and multiple directed edges. Each node corresponds to a target conditional probability table. The gas data is processed through the nodes, multiple directed edges, and the target conditional probability table to obtain the identification results.

[0011] Furthermore, before using a preset fault identification model to identify the gas data and obtain the identification results, the process includes: acquiring historical gas data sets of oil-immersed transformers under multiple fault types; constructing feature data based on the historical gas data sets for each fault type; adjusting the initial network structure and the initial conditional probability table corresponding to each node in the initial fault identification model based on all feature data to obtain the target network structure and the target conditional probability table corresponding to each node; and adjusting the initial fault identification model based on the target network structure and the target conditional probability table corresponding to each node to obtain the preset fault identification model.

[0012] Furthermore, before constructing feature data based on the historical gas data set for each fault type, the process includes: acquiring simulation data of the oil-immersed transformer under multiple fault types, wherein the simulation data includes at least: multiple gas data; and constructing a supplementary data set based on all gas data, wherein each gas data in the supplementary data set is used to populate the historical gas data set.

[0013] Furthermore, the identification results include at least: the category to which the gas data belongs and the probability value of the category. After identifying the gas data using a preset fault identification model and obtaining the identification results, the results also include: issuing an alarm for the oil-immersed transformer when the category indicates that there is a fault in the oil-immersed transformer; generating alarm information based on the gas data, category, and probability value of the category, and visualizing the alarm information.

[0014] According to another aspect of the embodiments of this application, a device for determining the oil sampling location of an oil-immersed transformer is also provided, comprising: a simulation unit for performing multi-physics coupling simulation calculations on the oil-immersed transformer to obtain simulation data; a simulation unit for simulating gas generation and gas diffusion under different fault conditions based on the simulation data to obtain gas migration paths and concentration data; and a determination unit for determining the target oil sampling location of the oil tank inside the oil-immersed transformer based on the migration paths and concentration data.

[0015] Furthermore, the device for determining the oil sampling location of the oil-immersed transformer also includes: a first determining module, used to determine multiple structural parameters of the oil-immersed transformer before performing multi-physics coupling simulation calculations on the oil-immersed transformer to obtain simulation data; and a first constructing module, used to construct a three-dimensional model based on all structural parameters, wherein the three-dimensional model is used to perform multi-physics coupling simulation calculations on the oil-immersed transformer.

[0016] Furthermore, the device for determining the oil sampling location of the oil-immersed transformer also includes: a first analysis module, used to analyze the simulation data after performing multi-physics coupling simulation calculations on the oil-immersed transformer to obtain analysis data; and a second determination module, used to determine the first target area and the second target area of ​​oil flow in the oil-immersed transformer based on the analysis data.

[0017] Furthermore, the determining unit includes: a third determining module, used to determine a preset region set based on the first target region and the second target region; a fourth determining module, used to determine the region in the oil tank other than the preset region set as candidate regions; and a fifth determining module, used to determine the target oil extraction location from the candidate regions based on the migration path and concentration data.

[0018] Furthermore, the device for determining the oil sampling location of an oil-immersed transformer also includes: a second analysis module, used to collect an oil sample from the target oil sampling location after determining the target oil sampling location of the oil tank inside the oil-immersed transformer based on the migration path and concentration data, and to analyze the oil sample to obtain gas data; and a first identification module, used to identify the gas data using a preset fault identification model to obtain identification results, wherein the model structure of the preset fault identification model includes at least: a target network structure, the target network structure includes at least: multiple nodes and multiple directed edges, each node corresponds to a target conditional probability table, and the gas data is processed through nodes, multiple directed edges and the target conditional probability table to obtain identification results.

[0019] Furthermore, the device for determining the oil sampling location of an oil-immersed transformer also includes: a first acquisition module, used to acquire a set of historical gas data of the oil-immersed transformer under multiple fault types before identifying the gas data using a preset fault identification model and obtaining the identification result; a second construction module, used to construct feature data based on the historical gas data set for each fault type; a first adjustment module, used to adjust the initial network structure in the initial fault identification model and the initial conditional probability table corresponding to each node in the initial network structure based on all feature data, to obtain the target network structure and the target conditional probability table corresponding to each node; and a second adjustment module, used to adjust the initial fault identification model based on the target network structure and the target conditional probability table corresponding to each node, to obtain the preset fault identification model.

[0020] Furthermore, the device for determining the oil sampling location of the oil-immersed transformer also includes: a second acquisition module, used to acquire simulated data of the oil-immersed transformer under multiple fault types before constructing feature data based on the historical gas data set for each fault type, wherein the simulated data includes at least: multiple gas data; and a third construction module, used to construct a supplementary data set based on all gas data, wherein each gas data in the supplementary data set is used to fill the historical gas data set.

[0021] Furthermore, the identification result includes at least: the category to which the gas data belongs and the probability value of the category. The device for determining the oil sampling location of the oil-immersed transformer also includes: a first alarm module, used to issue an alarm to the oil-immersed transformer when the category indicates that there is a fault in the oil-immersed transformer after the gas data is identified using a preset fault identification model and the identification result is obtained; and a first generation module, used to generate alarm information based on the gas data, category, and probability value of the category, and to visualize the alarm information.

[0022] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements any of the above-described methods for determining the oil sampling location of an oil-immersed transformer.

[0023] According to another aspect of the embodiments of this application, an electronic device is also provided, including one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any of the above-described methods for determining the oil sampling location of an oil-immersed transformer.

[0024] In this invention, multiphysics coupling simulation calculations are performed on oil-immersed transformers to obtain simulation data. Based on the simulation data, the generation and diffusion of gas under different fault conditions are simulated to obtain the gas migration path and concentration data. Based on the migration path and concentration data, the target oil sampling location in the oil tank of the oil-immersed transformer is determined, which solves the technical problem in related technologies that it is impossible to accurately determine the oil sampling location of oil-immersed transformers.

[0025] In this invention, multiphysics coupling simulation can simulate the dynamics of oil flow and gas diffusion paths inside the transformer under different fault conditions, optimize the selection strategy of the oil sampling port location, determine the optimal oil sample collection location, and enable the capture of key gas information reflecting the transformer state. This ensures that the oil sample is representative of the overall oil state and fault characteristics, avoids the data distortion problem caused by unreasonable oil sampling location and neglect of gas diffusion process in current methods, and provides a highly reliable data foundation for subsequent diagnosis, thereby improving the accuracy of model fault identification and classification. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0027] Figure 1 A hardware block diagram of a computer terminal (or mobile device) for determining the oil sampling location of an oil-immersed transformer is shown.

[0028] Figure 2 This is a flowchart of the method for determining the oil sampling location of an oil-immersed transformer according to Embodiment 1 of this application;

[0029] Figure 3 This is a time-series diagram of the change in dissolved gas concentration in oil according to an optional embodiment of this application;

[0030] Figure 4This is a flowchart of an optional method for identifying faults in an oil-immersed transformer according to an embodiment of this application;

[0031] Figure 5 This is a schematic diagram of the software interface of an optional online monitoring and sensing system for transformer oil chromatography according to an embodiment of this application;

[0032] Figure 6 This is a schematic diagram of an optional device for determining the oil sampling location of an oil-immersed transformer according to an embodiment of this application;

[0033] Figure 7 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] It should be noted that all related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) collected and involved in this invention are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, and necessary confidentiality measures have been taken. These measures do not violate public order and good morals, and corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has an interface with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface. After receiving consent from the aforementioned user or organization, the relevant information is obtained. If the user chooses to refuse, the process proceeds to an expert decision-making process.

[0037] The current determination of the oil sampling location does not take into account the electromagnetic-thermal-fluid multiphysics coupling effect inside the transformer. This coupling effect affects the generation and migration of gases, making it impossible to accurately determine the behavior of gases under fault modes. In this invention, oil samples can be collected from the target sampling location, and gas analysis can be performed to obtain gas data of various gas components and concentrations. Then, this gas data is input into a preset fault identification model for processing. This model structure is trained and optimized using historical gas data, forming a target network containing multiple nodes and directed edges. Each node is associated with a target conditional probability table, which is used to map the probabilistic relationship between gas characteristics and fault types. The model parses the gas data through the connections between nodes and the calculation of the target conditional probability table, and finally outputs the fault category to which the gas data belongs and its corresponding probability value, realizing accurate identification of transformer faults and improving the accuracy of fault diagnosis. The preset fault identification model trained by this invention can achieve continuous perception of transformer status and early anomaly warning based on real-time gas data from the optimal oil sampling port, which helps maintenance personnel to intervene in a timely manner, avoid the escalation of faults, and improve the safety and reliability of power grid operation.

[0038] The present invention will now be described in detail with reference to various embodiments.

[0039] Example 1

[0040] According to an embodiment of this application, an embodiment of a method for determining the oil sampling location of an oil-immersed transformer is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0041] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for determining the oil sampling location of an oil-immersed transformer is shown. Figure 1 As shown, computer terminal 10 (or mobile device) may include one or more ( Figure 1 The processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions may also be included. In addition, it may include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera, wherein the network interface can be connected to wired and / or wireless networks. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0042] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0043] The memory 104 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the method for determining the oil sampling location of an oil-immersed transformer in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned method for determining the oil sampling location of an oil-immersed transformer. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0044] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0045] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0046] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for determining the oil sampling location of an oil-immersed transformer is shown. Figure 2 This is a flowchart of the method for determining the oil sampling location of an oil-immersed transformer according to Embodiment 1 of this application, as follows: Figure 2 As shown, the method includes the following steps:

[0047] Step S201: Perform multiphysics coupling simulation calculations on the oil-immersed transformer to obtain simulation data.

[0048] Optionally, oil sampling is an important step in the oil chromatography analysis process. The selection of the sampling point should meet the following requirements: 1) the oil sample should be representative of the oil in the transformer body; 2) the dissolved gas in the oil should remain as constant as possible throughout the entire process from sampling to analysis; 3) the sampling method should be simple and easy to implement. When the equipment is running, oil samples can be taken from the drain valve at the bottom of the transformer tank. During operation, convection ensures a uniform distribution of dissolved gas in all parts, and the gas generated by latent faults with slower gas production has already diffused evenly. Therefore, the measurement results will be the same regardless of where the oil sample is taken. However, in cases of severe faults or large amounts of gas generated by the decomposition of insulating materials, the gas may not have time to dissolve before rising in bubbles. This results in more dissolved gas in the oil above the gas production point, leading to a significant difference in gas content between the upper and lower parts of the oil. In such cases, it is better to sample from both the upper and lower parts simultaneously. In oil chromatography analysis, the current selection of the oil sampling port only considers factors such as transformer structure and operational complexity, without conducting in-depth analysis of dissolved gases in the oil inside the tank. This makes it impossible to guarantee that the oil sample from the sampling port is sufficiently representative. Therefore, there is a lack of reliable data basis for online diagnosis of transformer operating status based on the oil sample from the sampling port.

[0049] In this embodiment of the invention, finite element simulation software can be used to perform coupled simulation of electromagnetic field-temperature field-fluid field to obtain simulation data (such as temperature, flow rate and pressure distribution, etc.) of the transformer under normal operation and typical fault conditions.

[0050] Step S202: Based on simulation data, simulate the gas generation and gas diffusion under different fault conditions to obtain the gas migration path and concentration data.

[0051] In this embodiment of the invention, based on simulation data, the generation and diffusion process of dissolved gases in oil under different fault types (such as high temperature overheating, partial discharge, etc.) can be simulated. This simulation combines a gas diffusion kinetic model to obtain the migration path of gases (such as hydrogen (H2), methane (CH4), acetylene (C2H2), ethylene (C2H4), carbon monoxide (CO), etc.) from the gas generation source to various parts of the oil tank, as well as the spatial and temporal concentration distribution of the gases.

[0052] Figure 3 This is a time-series diagram of the change in dissolved gas concentration in oil, according to an optional embodiment of this application, such as... Figure 3As shown, the graphs include gas concentration changes at multiple time points, such as (a), (b), (c), and (d), corresponding to time = 0 min, time = 4 min, time = 128 min, and time = 512 min, respectively. From (a) to (d), the color gradually changes from gray, purple, and green to orange, indicating that the concentration of the gaseous substance is increasing. In each graph after the gas begins to diffuse, there are lighter-colored areas at the winding points compared to the global range of the graph, indicating that the gas in these areas changes more slowly than the global range.

[0053] It should be noted that the above Figure 3 This is for illustrative purposes only. The timeline diagram can also include other time points, which can be set by the user.

[0054] Step S203: Based on the migration path and concentration data, determine the target oil sampling location in the oil tank of the oil-immersed transformer.

[0055] Based on the simulation results of gas diffusion, the optimal oil sampling location inside the tank is determined by considering the oil flow state, gas solubility, diffusion coefficient, and heat dissipation conditions. For example, in a high-temperature overheating fault, C2H2 and C2H4 have higher concentrations in the lower middle part of the tank, and the oil flow velocity in this area is moderate, ensuring sufficient mixing of dissolved gases and avoiding the influence of stagnant oil areas. Therefore, this location can be designated as the target oil sampling location. This sampling point, representing the optimal diffusion path of gases in the oil, is the optimal location obtained through simulation calculations after fully considering complex factors such as gas generation, gas diffusion paths, oil flow dynamics, and temperature distribution under different fault conditions, ensuring the highest representativeness of the collected oil sample.

[0056] Figure 4 This is a flowchart of an optional method for identifying faults in an oil-immersed transformer according to an embodiment of this application, such as... Figure 4 As shown, firstly, a finite element method (FEM) simulation of the oil-immersed transformer is performed using thermal-fluid coupling to analyze the oil flow and temperature variation patterns. Then, the diffusion paths of characteristic gases inside the tank under typical transformer faults (i.e., gas diffusion paths within the tank under various fault conditions) are analyzed. Based on these paths, the optimal oil sampling point is selected to obtain the characteristic gas composition and concentration at that point. A mapping relationship between fault types and characteristic gas composition and concentration is established to train the model and obtain a preset fault identification model. Subsequently, online monitoring of the operating oil-immersed transformer is performed. Using the trained model (i.e., the preset fault identification model), unknown faults are diagnosed, and the fault type and confidence level are obtained. Through multiphysics coupling simulation and oil gas diffusion path analysis, the oil sampling point location is optimized, and an accurate fault diagnosis model is established, thereby improving the reliability of online monitoring data and the accuracy of fault diagnosis.

[0057] In summary, finite element simulation technology was used to perform comprehensive calculations of the electromagnetic, thermal, fluid, and rarefied material transfer fields of the transformer, obtaining physical simulation data of the transformer's interior. Then, based on the simulation data, the generation and diffusion processes of gas under different fault scenarios were simulated, depicting the migration path and concentration distribution of gas within the oil tank. This provided a scientific basis for the selection of the oil sampling port. Subsequently, based on the gas diffusion characteristics, the optimal oil sampling location was determined, thus solving the technical problem of accurately determining the oil sampling location of oil-immersed transformers in related technologies.

[0058] To accurately determine the target oil sampling location, a three-dimensional model needs to be constructed first. In the method for determining the oil sampling location of an oil-immersed transformer provided in Embodiment 1 of this application, multiple structural parameters of the oil-immersed transformer are determined; based on all structural parameters, a three-dimensional model is constructed, wherein the three-dimensional model is used to perform multiphysics coupling simulation calculations on the oil-immersed transformer.

[0059] In this embodiment of the invention, all structural parameters of the oil-immersed transformer are first determined, such as the diameter and number of turns of the windings, the permeability and resistivity of the core, the thickness and oil absorption characteristics of the insulating paper, and the viscosity and thermal conductivity of the cooling oil. Based on all structural parameters of the transformer, a three-dimensional model is constructed. By setting boundary conditions and initial conditions for electromagnetic fields, temperature fields, and fluid fields in the three-dimensional model, including power supply parameters, ambient temperature, and oil inlet velocity, coupled simulation calculations can be performed. First, the loss distribution in the windings and core is calculated as a heat source, then the temperature field distribution within the oil domain is solved, and finally, based on the temperature field results, fluid dynamics simulation is performed to obtain the flow velocity and pressure distribution cloud map of the oil inside the transformer.

[0060] To improve the accuracy of the target oil sampling location, it is necessary to first determine the first target area and the second target area where the oil flows in the oil-immersed transformer. In the method for determining the oil sampling location of the oil-immersed transformer provided in Embodiment 1 of this application, simulation data is analyzed to obtain analysis data; based on the analysis data, the first target area and the second target area where the oil flows in the oil-immersed transformer are determined.

[0061] In this embodiment of the invention, the oil flow velocity distribution in key areas such as the oil passage between windings, the surface of the iron core and the corner of the oil tank can be analyzed by the simulation results of the flow field. A flow velocity contour map can be drawn to identify low-speed areas or backflow areas (i.e. dead oil areas) with flow velocities below 0.01 m / s, which are the first target area and the second target area. Dissolved gas migration is slow in these areas, and it is not advisable to set up oil sampling ports.

[0062] Optionally, sampling should be avoided in dead volumes where oil circulation is insufficient, and sampling should be performed during operation. If the equipment is stopped or the radiator is not in use, oil convection may be insufficient.

[0063] To further improve the accuracy of the target oil sampling location, in the method for determining the oil sampling location of an oil-immersed transformer provided in Embodiment 1 of this application, a preset region set is determined based on a first target region and a second target region; the region inside the oil tank other than the preset region set is determined as a candidate region; and the target oil sampling location is determined from the candidate regions based on the migration path and concentration data.

[0064] In this embodiment of the invention, a preset set of regions, i.e., a set of locations unsuitable for oil sampling, is determined based on a first target region and a second target region. Regions within the oil tank other than the preset set of regions are designated as candidate regions. Based on a gas diffusion dynamics model, the migration paths of characteristic gases from the gas source to various locations within the oil tank under fault conditions can be analyzed. Gas concentration data within different candidate regions are compared, and regions that can provide stable and representative gas components under various fault types are selected. This determines the target oil sampling location, ensuring that oil samples collected at the target sampling location accurately reflect the transformer's operating status and potential faults.

[0065] To accurately obtain the fault diagnosis results of the transformer, in the method for determining the oil sampling location of the oil-immersed transformer provided in Embodiment 1 of this application, an oil sample is collected from the target oil sampling location and analyzed to obtain gas data; a preset fault identification model is used to identify the gas data to obtain the identification result. The model structure of the preset fault identification model includes at least a target network structure, which includes at least multiple nodes and multiple directed edges. Each node corresponds to a target conditional probability table. The gas data is processed through the nodes, multiple directed edges, and the target conditional probability table to obtain the identification result.

[0066] In this embodiment of the invention, by collecting an oil sample from the target oil sampling location inside the oil-immersed transformer and analyzing the oil sample, gas data can be obtained for subsequent fault identification. For example, the type, concentration, and ratio of dissolved gases in the oil sample can be detected by chromatographic and other technical means. Dissolved gases include, but are not limited to, hydrogen (H2), methane (CH4), acetylene (C2H2), ethylene (C2H4), carbon monoxide (CO), etc.

[0067] Optionally, for various typical faults (including but not limited to mild overheating, medium-temperature overheating, high-temperature overheating, partial discharge, surface discharge, gas gap discharge, corona discharge, and suspension discharge), the concentration data of each gas component (H2, CH4, C2H2, C2H4, CO, etc.) at the optimal oil sampling port (i.e., the target oil sampling location) are extracted as features, and machine learning algorithms (such as Bayesian networks, support vector machines, recurrent neural networks, long short-term memory networks, etc.) are used to establish a mapping model between fault types and gas features.

[0068] In this embodiment of the invention, historical data or simulation data can be used to train and validate an initial model (such as a Bayesian network) to obtain a preset fault identification model. The model structure of the preset fault identification model includes at least the target network structure, i.e., the trained Bayesian network. The Bayesian network consists of multiple nodes and directed edges. Each node corresponds to a specific fault conditional probability distribution. The directed edges between nodes represent the probabilistic dependence between gas characteristics and fault types. The conditional probability table on the node is used to quantify these relationships. Based on the input gas data, the preset fault identification model outputs a diagnosis of the probability of transformer faults, including information such as fault type, severity, and confidence level.

[0069] To accurately obtain the preset fault identification model, in the method for determining the oil sampling location of an oil-immersed transformer provided in Embodiment 1 of this application, historical gas data sets of the oil-immersed transformer under multiple fault types are obtained; feature data is constructed based on the historical gas data sets of each fault type; based on all feature data, the initial network structure in the initial fault identification model and the initial conditional probability table corresponding to each node in the initial network structure are adjusted to obtain the target network structure and the target conditional probability table corresponding to each node; based on the target network structure and the target conditional probability table corresponding to each node, the initial fault identification model is adjusted to obtain the preset fault identification model.

[0070] In this embodiment of the invention, a historical gas data set of the oil-immersed transformer under multiple fault types (such as mild overheating, low-temperature overheating, medium-temperature overheating, high-temperature overheating, surface discharge, air gap discharge, corona discharge, and floating discharge) is obtained. This historical gas data set is obtained by taking oil samples at the target oil sampling location and analyzing the samples. Feature data is extracted from the historical gas data set and consists of key gas concentration and proportion information (i.e., feature data) associated with specific fault types.

[0071] The initial fault identification model is an untrained or uncalibrated fault identification model that can be set based on prior domain knowledge, including the initial network structure and the initial conditional probability table for each node. Then, the initial fault identification model is trained based on all feature data. By learning the patterns and correlations in the feature data, the initial network structure and the initial conditional probability table are adjusted to obtain the target network structure and the target conditional probability table for each node, so that the model can be gradually optimized to accurately distinguish and predict various fault types.

[0072] The target network structure is the adjusted and optimized model network architecture, which better reflects the intrinsic relationship between fault types and gas characteristics. The target conditional probability table is a table showing the conditional probability relationships between each node (representing different gases or fault types) and other nodes in the model, used for probabilistic inference and model decision-making. Based on the target network structure and the target conditional probability table corresponding to each node, the initial fault identification model can be adjusted to obtain the preset fault identification model.

[0073] In order to accurately construct a supplementary data set, in the method for determining the oil sampling location of an oil-immersed transformer provided in Embodiment 1 of this application, simulation data of the oil-immersed transformer under multiple fault types is obtained, wherein the simulation data includes at least: multiple gas data; based on all gas data, a supplementary data set is constructed, wherein each gas data in the supplementary data set is used to fill the historical gas data set.

[0074] In this embodiment of the invention, the simulated data refers to a set of gas data obtained through multiphysics coupling simulation calculations, reflecting the generation, diffusion, and dissolution characteristics of dissolved gases in the oil of an oil-immersed transformer under different fault types. When the historical gas data set lacks gas data for certain fault types, a supplementary data set is constructed based on all gas data for data supplementation. By increasing the coverage of fault types in the historical data, the accuracy of fault diagnosis for oil-immersed transformers is improved.

[0075] The identification results include at least the category of the gas data and the probability value of the category. In order to efficiently handle transformer faults, in the method for determining the oil sampling location of an oil-immersed transformer provided in Embodiment 1 of this application, when the category indicates that there is a fault in the oil-immersed transformer, an alarm is issued for the oil-immersed transformer; based on the gas data, category, and probability value of the category, alarm information is generated and the alarm information is visualized.

[0076] In this embodiment of the invention, when the category output by the preset fault identification model indicates that there is a fault in the oil-immersed transformer, an alarm is issued for the oil-immersed transformer, and alarm information (such as fault type, fault probability and specific gas concentration information) is generated based on gas data, category and probability value of the category. The alarm information is visualized to clearly convey the fault status and urgency of the transformer to the operation and maintenance personnel, and to notify the operation and maintenance personnel to take corresponding measures.

[0077] Optionally, a trained Bayesian network diagnostic model (i.e., a preset fault identification model) can be embedded into the current transformer's online oil chromatography monitoring system. By installing a sampling unit at the optimal oil sampling port (i.e., the target oil sampling location), oil samples are collected in real time and gas concentrations are analyzed. The data is then input into the Bayesian network diagnostic model to achieve automatic identification of fault types and early warning. Figure 5This is a schematic diagram of the software interface of an optional online monitoring and sensing system for transformer oil chromatography according to an embodiment of this application, such as... Figure 5 As shown, the software interface displays a status result display area, a real-time data display area in tabular form, a real-time data display area in curve form, and an alarm information area. The status result display area shows icons for normal, warning, and fault status. When the model output is a fault, the fault icon lights up. The icon color can also distinguish between normal, warning, and fault status, and displays the fault type and confidence level (e.g., fault type is medium-temperature overheating, confidence level is 92%). The real-time data display area shows the names and concentration values ​​of different gases, such as 1: hydrogen (H2), 2: methane (CH4), 3: acetylene (C2H2), 4: ethylene (C2H4), 5: ethane (C2H6), 6: carbon monoxide (CO), 7: carbon dioxide (CO2), 8: total hydrocarbons, etc. The alarm information area displays historical alarm records at different times (e.g., high-temperature overheating at 15:32 on 2025-5-02).

[0078] The method for determining the oil sampling location of an oil-immersed transformer provided in this application embodiment can construct a three-dimensional model of the transformer using finite element simulation software and perform electromagnetic-thermal-fluid multiphysics coupling analysis to simulate the diffusion path of gas under different fault scenarios. Then, combined with gas analysis data under historical fault scenarios, an initial fault identification model is trained and optimized to obtain a preset fault identification model. This model can accurately determine the fault type and its confidence level based on the characteristics of dissolved gases in the oil. Subsequently, the optimized preset fault identification model is applied to an online monitoring system. Oil samples are collected in real time through a precisely selected target oil sampling port. The model can automatically analyze gas data and generate identification results containing fault categories and probabilities, thereby improving the accuracy and efficiency of transformer condition monitoring.

[0079] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0080] Example 2

[0081] This application also provides a device for determining the oil sampling location of an oil-immersed transformer. It should be noted that this device can be used to execute the method for determining the oil sampling location of an oil-immersed transformer provided in this application. The following describes the device for determining the oil sampling location of an oil-immersed transformer provided in this application.

[0082] According to an embodiment of this application, an apparatus for implementing the above-described method for determining the oil sampling location of an oil-immersed transformer is also provided. Figure 6 This is a schematic diagram of an optional oil-immersed transformer oil sampling location determination device according to an embodiment of this application, as shown below. Figure 6 As shown, the device for determining the oil sampling location of the oil-immersed transformer may include: a simulation unit 60, a simulation unit 61, and a determination unit 62.

[0083] Among them, simulation unit 60 is used to perform multi-physics coupling simulation calculations on oil-immersed transformers to obtain simulation data;

[0084] Simulation unit 61 is used to simulate gas generation and gas diffusion under different fault conditions based on simulation data, and obtain gas migration path and concentration data.

[0085] The determination unit 62 is used to determine the target oil sampling location in the oil tank of the oil-immersed transformer based on the migration path and concentration data.

[0086] The oil sampling location determination device for an oil-immersed transformer provided in this application embodiment can perform multi-physics coupling simulation calculations on the oil-immersed transformer through the simulation unit 60 to obtain simulation data. Based on the simulation data, the simulation unit 61 can simulate the gas generation and gas diffusion under different faults to obtain the gas migration path and concentration data. Based on the migration path and concentration data, the determination unit 62 can determine the target oil sampling location in the oil tank inside the oil-immersed transformer.

[0087] Optionally, the device for determining the oil sampling location of the oil-immersed transformer further includes: a first determining module, used to determine multiple structural parameters of the oil-immersed transformer before performing multi-physics coupling simulation calculations on the oil-immersed transformer to obtain simulation data; and a first constructing module, used to construct a three-dimensional model based on all structural parameters, wherein the three-dimensional model is used to perform multi-physics coupling simulation calculations on the oil-immersed transformer.

[0088] Optionally, the device for determining the oil sampling location of the oil-immersed transformer further includes: a first analysis module, used to analyze the simulation data after performing multi-physics coupling simulation calculations on the oil-immersed transformer to obtain analysis data; and a second determination module, used to determine the first target area and the second target area of ​​oil flow in the oil-immersed transformer based on the analysis data.

[0089] Optionally, the determining unit 62 includes: a third determining module, used to determine a preset region set based on the first target region and the second target region; a fourth determining module, used to determine the region in the oil tank other than the preset region set as candidate regions; and a fifth determining module, used to determine the target oil extraction location from the candidate regions based on the migration path and concentration data.

[0090] Optionally, the device for determining the oil sampling location of an oil-immersed transformer further includes: a second analysis module, used to collect an oil sample from the target oil sampling location after determining the target oil sampling location of the oil tank inside the oil-immersed transformer based on the migration path and concentration data, and to analyze the oil sample to obtain gas data; and a first identification module, used to identify the gas data using a preset fault identification model to obtain identification results, wherein the model structure of the preset fault identification model includes at least: a target network structure, the target network structure includes at least: multiple nodes and multiple directed edges, each node corresponds to a target conditional probability table, and the gas data is processed through nodes, multiple directed edges and the target conditional probability table to obtain identification results.

[0091] Optionally, the device for determining the oil sampling location of an oil-immersed transformer further includes: a first acquisition module, used to acquire a set of historical gas data of the oil-immersed transformer under multiple fault types before identifying the gas data using a preset fault identification model and obtaining the identification result; a second construction module, used to construct feature data based on the historical gas data set for each fault type; a first adjustment module, used to adjust the initial network structure in the initial fault identification model and the initial conditional probability table corresponding to each node in the initial network structure based on all feature data, to obtain a target network structure and a target conditional probability table corresponding to each node; and a second adjustment module, used to adjust the initial fault identification model based on the target network structure and the target conditional probability table corresponding to each node, to obtain a preset fault identification model.

[0092] Optionally, the device for determining the oil sampling location of the oil-immersed transformer further includes: a second acquisition module, used to acquire simulated data of the oil-immersed transformer under multiple fault types before constructing feature data based on the historical gas data set for each fault type, wherein the simulated data includes at least: multiple gas data; and a third construction module, used to construct a supplementary data set based on all gas data, wherein each gas data in the supplementary data set is used to populate the historical gas data set.

[0093] Optionally, the identification result includes at least: the category to which the gas data belongs and the probability value of the category. The device for determining the oil sampling location of the oil-immersed transformer further includes: a first alarm module, used to issue an alarm to the oil-immersed transformer when the category indicates that there is a fault in the oil-immersed transformer after the gas data is identified using a preset fault identification model and the identification result is obtained; and a first generation module, used to generate alarm information based on the gas data, category, and probability value of the category, and to visualize the alarm information.

[0094] The aforementioned device for determining the oil sampling location of an oil-immersed transformer may also include a processor and a memory. The aforementioned simulation unit 60, simulation unit 61, determination unit 62, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0095] The aforementioned processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and by adjusting kernel parameters, the target oil sampling location within the oil-immersed transformer's oil tank can be determined based on the migration path and concentration data.

[0096] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0097] It should be noted that the simulation unit 60, simulation unit 61, and determination unit 62 mentioned above correspond to steps S201 to S203 in Embodiment 1. The instances and application scenarios implemented by the above units and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0098] Example 3

[0099] Embodiments of this application may provide a computer terminal, which may be any computer terminal device in a group of computer terminals. Optionally, in this embodiment, the aforementioned computer terminal may also be replaced with a mobile terminal or an electronic device, etc.

[0100] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0101] In this embodiment, the computer terminal can execute the program code for the following steps in the method for determining the oil sampling location of an oil-immersed transformer: perform multi-physics coupling simulation calculations on the oil-immersed transformer to obtain simulation data; based on the simulation data, simulate gas generation and gas diffusion under different fault conditions to obtain gas migration paths and concentration data; based on the migration paths and concentration data, determine the target oil sampling location in the oil tank of the oil-immersed transformer.

[0102] Optionally, the aforementioned computer terminal can execute program code for the following steps in the method for determining the oil sampling location of an oil-immersed transformer: determining multiple structural parameters of the oil-immersed transformer; and constructing a three-dimensional model based on all structural parameters, wherein the three-dimensional model is used for multi-physics coupling simulation calculations of the oil-immersed transformer.

[0103] Optionally, the aforementioned computer terminal can execute program code for the following steps in the method for determining the oil sampling location of an oil-immersed transformer: analyzing simulation data to obtain analysis data; and based on the analysis data, determining the first target area and the second target area where oil flows in the oil-immersed transformer.

[0104] Optionally, the aforementioned computer terminal can execute program code for the following steps in the method for determining the oil sampling location of an oil-immersed transformer: determining a preset region set based on a first target region and a second target region; determining regions within the oil tank other than the preset region set as candidate regions; and determining the target oil sampling location from the candidate regions based on the migration path and concentration data.

[0105] Optionally, the aforementioned computer terminal can execute the program code for the following steps in the method for determining the oil sampling location of an oil-immersed transformer: collecting an oil sample from the target oil sampling location and analyzing the oil sample to obtain gas data; using a preset fault identification model to identify the gas data and obtain the identification result, wherein the model structure of the preset fault identification model includes at least: a target network structure, the target network structure includes at least: multiple nodes and multiple directed edges, each node corresponds to a target conditional probability table, and the gas data is processed through the nodes, multiple directed edges, and the target conditional probability table to obtain the identification result.

[0106] Optionally, the aforementioned computer terminal can execute the program code for the following steps in the method for determining the oil sampling location of an oil-immersed transformer: acquiring historical gas data sets of the oil-immersed transformer under multiple fault types; constructing feature data based on the historical gas data sets for each fault type; adjusting the initial network structure in the initial fault identification model and the initial conditional probability table corresponding to each node in the initial network structure based on all feature data to obtain the target network structure and the target conditional probability table corresponding to each node; and adjusting the initial fault identification model based on the target network structure and the target conditional probability table corresponding to each node to obtain the preset fault identification model.

[0107] Optionally, the aforementioned computer terminal can execute program code for the following steps in the method for determining the oil sampling location of an oil-immersed transformer: acquiring simulation data of the oil-immersed transformer under multiple fault types, wherein the simulation data includes at least: multiple gas data; constructing a supplementary data set based on all gas data, wherein each gas data in the supplementary data set is used to populate a historical gas data set.

[0108] Optionally, the aforementioned computer terminal can execute program code for the following steps in the method for determining the oil sampling location of an oil-immersed transformer: issuing an alarm for the oil-immersed transformer when the category indicates a fault in the oil-immersed transformer; generating alarm information based on gas data, category, and probability value of the category, and visualizing the alarm information.

[0109] Optionally, Figure 7 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 7 As shown, the electronic device may include: one or more ( Figure 7 (Only one is shown) processor 702, memory 704, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0110] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and apparatus for determining the oil sampling location of an oil-immersed transformer in this embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned method for determining the oil sampling location of an oil-immersed transformer. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0111] The processor can call the information and application program stored in the memory through the transmission device to execute the above steps in the method for determining the oil sampling location of the oil-immersed transformer.

[0112] The embodiments of this application provide a scheme for determining the oil sampling location of an oil-immersed transformer. By comprehensively simulating the electromagnetic field, temperature field, and fluid field of the transformer under normal operation and specific fault conditions, simulation data is obtained. Based on the simulation data, the generation, migration, and dissolution processes of gas under different fault conditions are simulated. By analyzing the correlation between the gas diffusion path and the oil flow dynamics, the optimal oil sampling location is accurately located in the area within the oil tank with moderate flow velocity, uniform gas distribution, and the ability to capture fault signals. This solves the technical problem in related technologies that it is impossible to accurately determine the oil sampling location of an oil-immersed transformer.

[0113] Those skilled in the art will understand that Figure 7The structure shown is for illustrative purposes only. Electronic devices can also be terminal devices such as smartphones, tablets, PDAs, and mobile internet devices (MIDs). Figure 7 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 7 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 7 The different configurations shown.

[0114] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0115] Example 4

[0116] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for determining the oil sampling location of an oil-immersed transformer provided in Embodiment 1.

[0117] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0118] This application also provides a computer program product, which, when executed on a data processing device, is suitable for performing the steps of a method for determining the oil sampling location of an oil-immersed transformer.

[0119] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0120] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0122] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0124] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0125] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining the oil sampling location of an oil-immersed transformer, characterized in that, include: Multiphysics coupling simulation calculations were performed on an oil-immersed transformer to obtain simulation data; Based on the simulation data, the gas generation and gas diffusion under different fault conditions are simulated to obtain the gas migration path and concentration data. Based on the migration path and the concentration data, the target oil sampling location in the oil tank of the oil-immersed transformer is determined.

2. The method for determining the oil sampling location of an oil-immersed transformer according to claim 1, characterized in that, Before performing multiphysics coupling simulation calculations on oil-immersed transformers to obtain simulation data, the following steps are also included: Determine multiple structural parameters of the oil-immersed transformer; Based on all the structural parameters, a three-dimensional model is constructed, wherein the three-dimensional model is used to perform multiphysics coupling simulation calculations on the oil-immersed transformer.

3. The method for determining the oil sampling location of an oil-immersed transformer according to claim 1, characterized in that, After obtaining simulation data through multiphysics coupling simulation of the oil-immersed transformer, the following steps are also included: The simulation data is analyzed to obtain analytical data; Based on the analysis data, a first target region and a second target region for oil flow in the oil-immersed transformer are determined.

4. The method for determining the oil sampling location of an oil-immersed transformer according to claim 1, characterized in that, The step of determining the target oil sampling location in the oil-immersed transformer's inner tank based on the migration path and the concentration data includes: Based on the first target region and the second target region, a preset region set is determined; The area within the fuel tank other than the preset area set is identified as a candidate area; Based on the migration path and the concentration data, the target oil extraction location is determined from the candidate region.

5. The method for determining the oil sampling location of an oil-immersed transformer according to claim 1, characterized in that, After determining the target oil sampling location of the oil tank inside the oil-immersed transformer based on the migration path and the concentration data, the method further includes: Oil samples are collected from the target oil sampling location, and the oil samples are analyzed to obtain gas data; The gas data is identified using a preset fault identification model to obtain an identification result. The preset fault identification model includes at least a target network structure, which includes at least multiple nodes and multiple directed edges. Each node corresponds to a target conditional probability table. The gas data is processed through the nodes, the multiple directed edges, and the target conditional probability table to obtain the identification result.

6. The method for determining the oil sampling location of an oil-immersed transformer according to claim 5, characterized in that, Before using a preset fault identification model to identify the gas data and obtain the identification result, the process also includes: Obtain the historical gas data set of the oil-immersed transformer under multiple fault types; Based on the historical gas data set for each of the aforementioned fault types, feature data is constructed. Based on all the aforementioned feature data, the initial network structure in the initial fault identification model and the initial conditional probability table corresponding to each node in the initial network structure are adjusted to obtain the target network structure and the target conditional probability table corresponding to each node. Based on the target network structure and the target conditional probability table corresponding to each node, the initial fault identification model is adjusted to obtain the preset fault identification model.

7. The method for determining the oil sampling location of an oil-immersed transformer according to claim 6, characterized in that, Before constructing feature data based on the historical gas data set for each of the aforementioned fault types, the following is also included: Acquire simulation data of the oil-immersed transformer under multiple fault types, wherein the simulation data includes at least: multiple gas data; Based on all the gas data, a supplementary data set is constructed, wherein each of the gas data in the supplementary data set is used to populate the historical gas data set.

8. The method for determining the oil sampling location of an oil-immersed transformer according to claim 5, characterized in that, The identification result includes at least: the category to which the gas data belongs and the probability value of the category. After identifying the gas data using a preset fault identification model and obtaining the identification result, it also includes: If the category indicates that the oil-immersed transformer has a fault, an alarm will be issued for the oil-immersed transformer; Based on the gas data, the category, and the probability value of the category, an alarm message is generated and visualized.

9. A device for determining the oil sampling location of an oil-immersed transformer, characterized in that, include: The simulation unit is used to perform multiphysics coupling simulation calculations on oil-immersed transformers to obtain simulation data. The simulation unit is used to simulate gas generation and gas diffusion under different fault conditions based on the simulation data, and to obtain the gas migration path and concentration data. The determining unit is used to determine the target oil sampling location of the oil tank inside the oil-immersed transformer based on the migration path and the concentration data.

10. A computer program product, characterized in that, The method includes a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for determining the oil sampling location of an oil-immersed transformer as described in any one of claims 1 to 8.

11. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method for determining the oil sampling location of an oil-immersed transformer as described in any one of claims 1 to 8.

Images