Ring main unit modular design method based on multi-cavity coupling

Abstract

The invention discloses a ring main unit modular design method based on multi-cavity coupling, and relates to the technical field of electrical equipment structure design, and the method comprises the following steps: in a cavity structure simulation post-processing stage of finite element simulation software, extracting three-dimensional field variable data in a cavity in real time through a built-in automation script interface of the software; and exporting the obtained data in a structured format in real time to form a standardized data file. According to the invention, through high-dimensional feature extraction, deep learning identification and dynamic load response regulation and control, the micro eddy current circulation risk in the cavity can be accurately identified. The focusing characteristic and the thermoelectric abnormity are effectively quantified by the structure vortex thermal anisotropy index and the electromagnetic dissipation focus index, the vortex evolution path is analyzed in combination with the load change, the intelligent simulation system capable of being verified in a closed loop mode is constructed, and the safety optimization design of the ring main unit is assisted.

Description

Technical Field

[0001] The present invention relates to the technical field of the structural design of electrical equipment, and particularly relates to a modular design method for a ring main unit based on multi-cavity coupling. Background Art

[0002] "Modular design of a ring main unit based on multi-cavity coupling" means that in the design of a ring main unit, the internal space of the entire switch cabinet is divided into multiple structurally independent but coupled cavities (such as a busbar cavity, a switch operation cavity, a cable inlet / outlet cavity, an instrument control cavity, etc.), and the modular design concept is adopted. Each cavity is independently modeled, parameter-configured, and structurally assembled as a standardized functional module. This method usually uses 3D modeling software such as SolidWorks, Creo, and CATIA, combined with finite element simulation tools such as ANSYS and COMSOL, to perform refined simulation analysis on the electromagnetic compatibility, thermal coupling effect, structural strength, and spatial layout between cavities. In the design platform, each functional cavity is managed through a modular assembly library, enabling engineers to flexibly configure functional units according to different power system requirements, and achieving an efficient switch between customized design and batch standard manufacturing. At the same time, with the help of a PLM system (such as Teamcenter) for module version control and collaborative management, the overall machine design is optimized in terms of safety isolation, operation and maintenance, and expansion capabilities.

[0003] The existing technology has the following deficiencies: During actual operation, the ring main unit is often under high-frequency dynamic electrical conditions. Especially during short-circuit shocks, arc arcing, or transient overvoltage events, electromagnetic induction loops with small sizes but continuous closed paths will be formed among multiple metal components inside the cavity in local structural gaps, edge contact areas, or metal lap joints, thereby generating micro-eddy current circulation phenomena. Such areas are usually distributed between busbar connection points, switch housing connection parts, or structural support metal parts, and have the characteristics of small size, fast heat accumulation, and being easily overlooked, belonging to typical "hidden junction areas".

[0004] However, when performing electromagnetic-thermal coupling simulation between cavities based on finite element analysis tools (such as ANSYS and COMSOL), if the above-mentioned microstructural areas are not locally encrypted with meshes, the simulation resolution will not be sufficient to accurately capture the formation and evolution process of such eddy current circulation paths, resulting in a serious underestimation of the evaluation of heat generation, electric field concentration, or magnetic induction intensity in this area in the calculation results, and there are potential hazards such as underestimated thermal fields and misjudgment of the risk of electrical breakdown. This problem has strong concealment and a low occurrence frequency, but once it occurs, it will cause serious consequences such as insulation breakdown, local corrosion, and even fire, seriously threatening the operation stability of the ring main unit and the power supply safety of the system.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide a modular design method for ring main units based on multi-cavity coupling. Through high-dimensional feature extraction, deep learning recognition, and dynamic load response regulation, it can accurately identify the risk of micro-vortex circulation in the cavity. The structural vortex-thermal anisotropy index and the electromagnetic dissipation focus index effectively quantify its focusing characteristics and thermoelectric anomalies. By combining the load change analysis of the vortex evolution path, an intelligent simulation system that can be closed-loop verified is constructed to assist the safe and optimized design of ring main units, so as to solve the problems in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solutions: A modular design method for ring main units based on multi-cavity coupling, comprising the following steps: In the post-processing stage of the cavity structure simulation in the finite element simulation software, through the built-in automated script interface of the software, the three-dimensional field variable data inside the cavity is extracted in real time, and the obtained data is exported in a structured format in real time to form a standardized data file; Preprocess the obtained original three-dimensional field variable data, and extract the key feature indicators representing the potential risk of micro-vortex circulation from the preprocessed high-dimensional field variable data through feature engineering methods. Conduct a comprehensive analysis of the extracted key feature indicators to quantify the true probability and severity of the micro-vortex circulation phenomenon; After formatting adjustment and data enhancement processing of the key feature indicators after risk quantification analysis, input them into a deep learning model that has been fully trained in advance with historical simulation data and on-site operation data, and automatically evaluate the risk of micro-vortex circulation in the cavity structure through the model to achieve automated intelligent determination of the risk of micro-vortex circulation; When a potential risk of micro-vortex circulation in the cavity structure is identified, dynamically adjust the load boundary conditions in the simulation environment, and capture the dynamic evolution path of the vortex circulation by analyzing the transient evolution trends of the field variables under different load conditions.

[0008] Preferably, in the post-processing stage of the finite element simulation software, extracting the three-dimensional field variable data of the cavity structure and exporting it in a standardized file format includes the following steps: Complete the modeling and simulation calculation of the cavity structure in the finite element simulation software to obtain the required three-dimensional field variable distribution results; Call the built-in automated script interface of the software and write a script to achieve batch extraction of the target physical quantity in the entire cavity space; Structurally organize the extracted three-dimensional field variable data according to the correspondence between spatial coordinates and physical quantities to ensure that the data format is standard and unified and convenient for subsequent processing; Use a script to export the organized data into a standardized data file format.

[0009] Preferably, extract key feature indicators characterizing the potential risk of micro-vortex circulation from the preprocessed high-dimensional field variable data through feature engineering methods. The extracted key feature indicators include the degree of deviation of the directional change of temperature rise per unit volume and the degree of aggregation of electromagnetic energy consumption density per unit area in space. The degree of deviation of the directional change of temperature rise per unit volume and the degree of aggregation of electromagnetic energy consumption density per unit area in space are comprehensively analyzed under the monitoring window to generate a structural vortex thermal anisotropy index and an electromagnetic dissipation focus index respectively, and the true probability and severity of the micro-vortex circulation phenomenon are quantified through the structural vortex thermal anisotropy index and the electromagnetic dissipation focus index.

[0010] Preferably, the specific steps for comprehensively analyzing the degree of deviation of the directional change of temperature rise per unit volume under the monitoring window to generate a structural vortex thermal anisotropy index are as follows: Under the monitoring window, taking the unit volume cell as the basic analysis unit, extract the three-dimensional temperature rise field from the simulation data, and calculate the gradient components of the temperature rise along the three main directions respectively to form a temperature rise direction gradient vector field. The calculation formula of the temperature rise direction gradient vector field is as follows: , where is the temperature rise direction gradient vector field, is the spatial change rate of the temperature field in the axis direction, is the spatial change rate of the temperature field in the axis direction, is the spatial change rate of the temperature field in the axis direction; In each unit volume, calculate the directional deviation tensor. The calculation expression of the directional deviation tensor is as follows: , where is the structural main heat conduction direction vector, is the modulus of the main heat conduction direction vector, is the modulus of the temperature rise gradient, is the directional deviation tensor value; To amplify the structural differences brought about by small deviations, perform spatial coupling sensitivity processing on to highlight the contribution of the direction jump point to thermal anisotropy. The calculation expression of the structural vortex thermal anisotropy index is as follows: , where is the modulus value of the temperature Laplacian operator, is the modulus value of the temperature gradient, It is the structural vortex thermal anisotropy index.

[0011] Preferably, the specific steps for comprehensively analyzing the aggregation degree of the electromagnetic energy consumption density in the unit area in space under the monitoring window to generate the electromagnetic dissipation focus index are as follows: In the finite element simulation environment, through the simulation post-processing module, obtain the three-dimensional electromagnetic energy consumption density distribution field of the unit area within the monitoring window. For the obtained electromagnetic energy consumption density distribution field, calculate the local electromagnetic energy consumption focusing intensity index. The calculation expression is as follows: , where is the electromagnetic energy consumption density distribution field, is the spatial coordinate vector, is the gradient vector of the electromagnetic energy consumption density, representing the energy dissipation per unit volume at the position ; is the modulus of the gradient vector of the electromagnetic energy consumption density, is the divergence operation of the vector field, is the local electromagnetic energy consumption focusing intensity index; After completing the calculation of the local electromagnetic energy consumption focusing intensity index , select the high-aggregation sub-regions with the focusing intensity exceeding the preset threshold within the monitoring area, and define the high-aggregation sub-regions. The definition method is as follows: , where is the high-aggregation sub-region, is the three-dimensional space range covered by the monitoring window, is the focusing intensity threshold; Based on the obtained high-aggregation sub-regions, calculate the electromagnetic dissipation focus index. The calculation expression is as follows: , where is the electromagnetic dissipation focus index, is the volume integral microelement, representing a tiny volume unit in three-dimensional space.

[0012] Preferably, after formatting adjustment and data enhancement processing of the structural vortex thermal anisotropy index and the electromagnetic dissipation focus index after risk quantification analysis, input them into a deep learning model that has been fully trained in advance with historical simulation data and on-site operation data. Generate the micro-vortex circulation risk coefficient through the model, and automatically evaluate the micro-vortex circulation risk of the cavity structure through the micro-vortex circulation risk coefficient to achieve automatic intelligent determination of the micro-vortex circulation risk.

[0013] Preferably, compare and analyze the generated micro-vortex circulation risk coefficient with the pre-set reference threshold of the micro-vortex circulation risk coefficient to make an intelligent determination of whether there is a micro-vortex circulation risk in the cavity structure. The determination logic is as follows: If the micro-vortex circulation risk coefficient is greater than the pre-set reference threshold of the micro-vortex circulation risk coefficient, it is determined that there is a potential micro-vortex circulation risk in the cavity structure; if the micro-vortex circulation risk coefficient is less than or equal to the pre-set reference threshold of the micro-vortex circulation risk coefficient, it is determined that there is no potential micro-vortex circulation risk in the cavity structure.

[0014] Preferably, after identifying the potential micro-vortex circulation risk in the cavity structure, the load boundary conditions in the simulation environment are dynamically adjusted. The specific steps for capturing the dynamic evolution path of the vortex circulation by analyzing the transient evolution trends of the field variables under different load conditions are as follows: In the cavity region where the potential micro-vortex circulation risk has been identified, the dynamic load boundary conditions are adjusted. Through the coordinated excitation of three boundary perturbation methods, namely increasing the short-circuit current amplitude, increasing the steepness of the pulse waveform, and prolonging the arc duration, a composite working condition perturbation intensity index is formed. The calculation formula is as follows: , where is the adjustment increment of the short-circuit current amplitude, is the steepness parameter of the pulse waveform, is the increment of the arc duration, is the reference short-circuit current amplitude, is the reference steepness of the pulse waveform, is the reference arc duration, , and are the adjustment increment of the short-circuit current amplitude the steepness parameter of the pulse waveform and the increment of the arc duration weighting coefficients, satisfying , is the composite working condition perturbation intensity index, is the micro-vortex circulation risk coefficient, is the reference threshold of the micro-vortex circulation risk coefficient, is the risk modulation sensitivity coefficient; After implementing the dynamic adjustment of the load boundary conditions, for the distribution changes of the field variables under different load conditions, the vortex circulation path is captured by the field variable dynamic evolution difference coefficient. The calculation expression of the field variable dynamic evolution difference coefficient is as follows: , where is the spatial volume within the identified potential risk area, is the spatial gradient of the magnetic flux density, representing the change rate of the magnetic flux density in each direction in three-dimensional space, is the spatial gradient of the current density, representing the gradient change of the current density vector field in each direction in space. is the spatial gradient of temperature rise, is the magnetic flux density gradient weight coefficient, is the current density gradient weight coefficient, is the temperature rise gradient weight coefficient, is the volume integral element, is the field variable dynamic evolution difference coefficient; Based on the obtained field variable dynamic evolution difference coefficient , an innovative spatial concentration index is constructed to accurately locate the aggregation degree of the eddy current circulation path in space. The calculation formula is as follows: , where, is the th spatial distance from the spatial sub-unit to the eddy current response center, is the th field variable dynamic evolution difference coefficient of the spatial sub-unit, is the total number of spatial sub-units, is the spatial concentration index of the micro eddy current circulation path.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are as follows: By introducing an analysis mechanism that combines high-dimensional field variable feature extraction, deep learning intelligent discrimination, and dynamic load response regulation, the present invention can achieve comprehensive identification and quantitative evaluation of potential micro eddy current circulation risks in the cavity structure. This method not only breaks through the problem of insufficient accuracy in identifying microstructural anomalies in traditional finite element simulations but also accurately captures the focusing characteristics of eddy current circulation in space and the thermoelectric response characteristics through innovative parameters such as the structural vortex heat anisotropy index and the electromagnetic dissipation focus index. At the same time, by means of the dynamic adjustment and differential analysis of the load boundary conditions, the induction mechanism and evolution path of eddy current risks are further revealed. Finally, a closed-loop technical system from data-driven identification, physical behavior modeling to risk verification and feedback is constructed, providing a practical and expandable intelligent simulation analysis path for the safety design, fault prediction, and manufacturing optimization of the ring main unit structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0017] Figure 1 is the method flow chart of the ring main unit modular design method based on multi-cavity coupling of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

[0019] The present invention provides a modular design method for a ring main unit based on multi-cavity coupling as shown in Figure 1 the following steps: In the post-processing stage of the cavity structure simulation in a finite element simulation software (such as ANSYS or COMSOL), through the built-in automated script interface of the software (such as the APDL script in ANSYS, the Java or Python API interface in COMSOL), the three-dimensional field variable data inside the cavity (such as magnetic flux density, current density, temperature rise distribution, etc.) is extracted in real time, and the obtained data is exported in a structured format in real time to form a standardized data file (such as CSV, HDF5 format file); In the post-processing stage of the finite element simulation, the process of programmatically operating on the simulation results by using the automated programming interface (API) provided by the simulation software to automatically extract and export the key physical field data. For example, in ANSYS, the APDL (ANSYS Parametric Design Language) script can be used, and in COMSOL, the simulation result module can be called through the Java or Python API to extract the distribution data of physical quantities such as magnetic flux density, current density, temperature rise distribution, and electric field strength in three-dimensional space in real time. Through these scripting methods, the post-processing operations in the simulation process can be transformed into automatically executed tasks, greatly improving the efficiency and data consistency.

[0020] The key physical field data in the finite element simulation results is exported in a standardized and structured manner to form common data format files such as CSV and HDF5, which is convenient for further processing and analysis in an external data analysis platform (such as Pandas and TensorFlow in a Python environment). Such data export not only makes the simulation results no longer limited to the internal graphical interface display of the software, but also transforms them into computable, trainable, and reusable data resources, laying a solid data foundation for subsequent risk identification, deep learning modeling, feature analysis, and dynamic regulation.

[0021] In the post-processing stage of the finite element simulation software, the steps for extracting the three-dimensional field variable data of the cavity structure and exporting it in a standardized file format include the following: First, complete the modeling and simulation calculation of the cavity structure in the finite element simulation software to obtain the required three-dimensional field variable distribution results; Secondly, call the automated script interface built into the software (such as the APDL script of ANSYS or the Java / Python API of COMSOL), and write a script to achieve batch extraction of target physical quantities (such as magnetic flux density, current density, temperature rise distribution, etc.) in the entire cavity space; Thirdly, structurally organize the extracted three-dimensional field variable data according to the corresponding relationship between spatial coordinates and physical quantities, ensuring that the data format is standard and unified and convenient for subsequent processing; Fourthly, finally, use the script to export the organized data into a standardized data file format (such as CSV, HDF5) for further data analysis, modeling, or archiving on an external platform.

[0022] Preprocess the obtained original three-dimensional field variable data, and extract key feature indicators characterizing the potential risk of micro-vortex circulation from the preprocessed high-dimensional field variable data through feature engineering methods. Conduct a comprehensive analysis of the extracted key feature indicators to quantify the true probability and severity of the micro-vortex circulation phenomenon; In the field variable data obtained from finite element simulation, there are often data noises and outliers caused by numerical discretization, grid errors, or low solver convergence accuracy. Therefore, before the data officially enters the analysis or modeling stage, systematic data preprocessing operations must be carried out. The process mainly includes the following aspects of processing content: Firstly, data denoising and filtering. For the spatial discrete data of three-dimensional physical field variables such as magnetic flux density, current density, and temperature rise distribution, a low-pass filter can be used to filter out high-frequency pseudo-signal components and retain the main trend information; or a sliding window smoothing filter (such as moving average, weighted average) can be used to smooth local fluctuations, thereby reducing local spikes caused by factors such as too dense discrete points and sudden gradient changes during the simulation process. For some abnormally mutated points, an outlier removal method based on statistical thresholds (such as Z-Score or IQR discrimination) can be used to automatically detect and remove extreme values that do not conform to physical laws, improving the overall data quality.

[0023] Secondly, data normalization processing. Since the dimensions and value ranges of different field variables (such as magnetic flux density in T, current density in A / m², and temperature rise in K) vary greatly, if normalization processing is not carried out, subsequent feature extraction and deep learning model analysis will not be able to achieve comparison on the same scale. Common methods include Min-Max Scaling and Z-Score normalization to map all data to the same interval or standard normal distribution, which helps to balance the weights between different field variables.

[0024] Finally, format standardization is also a crucial step, which is to organize data under multiple dimensions, multiple moments, or multiple working conditions into a unified structural format (such as tensors, DataFrames, or nested dictionary structures), and unify field naming, spatial coordinate mapping, and data arrangement order. This operation facilitates efficient invocation and batch processing in subsequent data fusion, feature engineering, or deep model training processes.

[0025] Generally speaking, the roles of the above preprocessing steps are as follows: First, to improve the authenticity and stability of the original simulation data and remove interference signals; second, to enhance the comparability and fusion of different physical variables and lay a foundation for constructing a multi-field coupling analysis model; third, to improve the convergence speed and recognition accuracy of subsequent AI model training and prediction, and ensure the data reliability and engineering practicability of the entire simulation-identification system from the source.

[0026] Key feature indicators characterizing the potential risk of micro-vortex circulation are extracted from the preprocessed high-dimensional field variable data through feature engineering methods. The extracted key feature indicators include the deviation degree of the directional change of temperature rise per unit volume and the aggregation degree of electromagnetic energy consumption density per unit area in space. The deviation degree of the directional change of temperature rise per unit volume and the aggregation degree of electromagnetic energy consumption density per unit area in space are comprehensively analyzed under the monitoring window to generate a structural vortex thermal anisotropy index and an electromagnetic dissipation focus index respectively. The real probability and severity of the micro-vortex circulation phenomenon are quantified through the structural vortex thermal anisotropy index and the electromagnetic dissipation focus index.

[0027] Through the comprehensive extraction and analysis of the structural vortex thermal anisotropy index and the electromagnetic dissipation focus index, the real probability and severity of the micro-vortex circulation phenomenon can be effectively quantified, with a clear physical basis and high operability. The structural vortex thermal anisotropy index reflects the uneven degree of the gradient distribution of temperature rise per unit volume in different directions. If there is an abnormally high deviation in the direction of heat conduction in a certain area, it indicates that the heat source is likely not caused by a uniform load, but triggered by local electromagnetic induction heating (i.e., eddy current), belonging to the characteristic of non-uniform strong directional heating. The electromagnetic dissipation focus index is used to measure the degree of focus of electromagnetic energy consumption per unit spatial area. When the electromagnetic energy consumption density is highly concentrated in space (rather than diffusely distributed), it usually indicates the existence of local energy convergence, that is, the eddy current energy accumulates in some narrow areas, leading to the risk of melting or breakdown. Therefore, the structural vortex thermal anisotropy index can be used as a "spatial criterion for abnormal heat distribution", and the electromagnetic dissipation focus index is an "intensity criterion for electromagnetic dissipation focus". The combination of the two can jointly reflect the formation mechanism and damage trend of eddy current circulation from the aspects of heat response mechanism and electromagnetic driving force. Through spatio-temporal synchronous extraction and index quantification analysis under the monitoring window, not only can it judge whether there is a risk of eddy current circulation, but also further estimate its evolution potential, damage level, and the urgency of response, with high engineering practicability and prediction value.

[0028] A severe deviation in the directional change of temperature rise per unit volume can serve as an important characteristic feature indicating the risk of micro-vortex circulation in multiple metal components inside the cavity. Under normal heat transfer conditions, the temperature rise typically shows a uniform distribution along the main direction of thermal conductivity (such as along the axis of a metal plate or structure), and the thermal gradient change has obvious continuity and isotropy. When multiple conductive metal components in the cavity form a closed eddy current path due to electromagnetic induction coupling, the induced current circulates at high speed in a local area, accompanied by a highly localized electromagnetic heating phenomenon, causing the heat energy to no longer diffuse uniformly but to accumulate and rapidly heat up along abnormal directions. This heating mechanism will break the directional consistency of heat conduction at the microscale, resulting in an obvious deflection or jump in the temperature rise gradient direction in some small areas, manifested as an anisotropic mutation in the heat conduction field. Therefore, when there is a severe deviation in the directional change of temperature rise per unit volume, it often means that there is a non-uniform energy input source in this area, and this energy input is very likely caused by the eddy current effect in the local metal component coupling area, which is an important physical signal for judging the formation and evolution of micro-vortex circulation.

[0029] The specific steps for comprehensively analyzing the deviation degree of the directional change of temperature rise per unit volume under the monitoring window to generate the structural vortex heat anisotropy index are as follows: Under the monitoring window, taking the unit volume cell as the basic analysis unit, extract the three-dimensional temperature rise field from the simulation data, and calculate the gradient components of the temperature rise along the three main directions respectively to form a temperature rise direction gradient vector field. The calculation formula for the temperature rise direction gradient vector field is as follows: , where is the temperature rise direction gradient vector field, and is the three-dimensional temperature field The first-order derivative in space represents the rate of change of the temperature rise along the three main directions , is the temperature field at The spatial rate of change in the axis direction represents the change in temperature when moving a unit distance along the direction, is the temperature field at The spatial rate of change in the axis direction represents the change in temperature when moving a unit distance along the direction, is the temperature field at The spatial rate of change in the axis direction represents the change in temperature when moving a unit distance along the direction; Within each unit volume, calculate the directional deviation tensor, which represents the degree of deviation between the temperature rise gradient vector at that point and the main structure heat conduction direction (such as the normal direction of the metal plate surface or the cable routing direction). The calculation expression of the directional deviation tensor is as follows: , where is the main heat conduction direction vector of the structure, representing the dominant heat conduction direction of the material or device under normal operating conditions, used as a reference direction to compare the angle with the current temperature rise direction to determine whether the temperature rise is transmitted along the designed heat conduction channel. If eddy currents induce local heating in non-heat conduction paths, and will deviate significantly, is the modulus of the main heat conduction direction vector, is a unit vector with a constant modulus of 1, used to maintain the normalized ratio calculation. In practical applications, it can be omitted (because it is always equal to 1), and it is retained to fully express the normalized structure of the vector dot product, is the modulus of the temperature rise gradient, the Euclidean norm of the temperature rise gradient vector in three-dimensional space, representing the intensity of heat flow change, independent of direction, only reflecting the spatial change speed of the temperature field at that point, used as a normalization reference, is the value of the directional deviation tensor, quantifying the degree of deviation between the temperature rise gradient direction and the main heat direction of the structure within the unit volume, used to identify whether there is abnormal local heating caused by micro-eddy current circulation. The value range is 0 - 2. The larger the value, the more the temperature rise direction at that position deviates from the main heat conduction direction of the structure, and it can be used as an effective quantification index for the risk of micro-eddy current circulation; The above steps extract the spatial variation characteristics of the local temperature rise conduction direction from the three-dimensional temperature rise field. By calculating the degree of angular deviation between the temperature rise gradient and the main heat conduction direction of the structure, a quantification index reflecting the abnormal heat flow direction is constructed. This index can effectively identify the non-designed local heat flow deflection behavior caused by micro-eddy currents inside the cavity and is an important leading criterion for judging the potential path of eddy current circulation.

[0030] To amplify the structural differences brought about by small deviations, perform spatial coupling sensitivity processing on to highlight the contribution of the direction jump point to thermal anisotropy. The calculation expression of the structural eddy current thermal anisotropy index is as follows: , where is the modulus of the temperature Laplace operator (i.e., the modulus of the second-order spatial derivative of temperature), representing the degree of bending or mutation of the local temperature field in space, and is a key parameter for measuring whether the temperature rapidly aggregates or dissipates at a certain point, used to capture the spatial mutation behavior in the temperature field. For example, eddy current heating causes the local temperature at a certain point to rise abnormally rapidly, or heat accumulates at the structural defect, and the larger the value, the more abnormal the temperature distribution at that point, is the modulus of the temperature gradient (i.e., the magnitude of the first-order spatial derivative of the temperature field), representing the rate of temperature change per unit distance, that is, the instantaneous rate of change of temperature along the spatial direction, and is used for standardization , to prevent misjudging local fluctuations due to too large a basic temperature gradient. The "1 +" processing in the formula is to avoid a zero denominator and maintain calculation stability. is the structural vorticity thermal anisotropy index. The larger the value, the more serious the thermal conductivity discontinuity exists in the spatial direction of this region, and it is very likely caused by micro-vortices.

[0031] The above steps introduce the coupling relationship between the spatial second derivative (Laplace operator) and the first-order gradient of the temperature field, amplify the thermal discontinuity characteristics generated by the sudden change of curvature in the local area due to the deviation of the temperature rise directionality, so as to highlight the abnormal heat accumulation effect caused by eddy currents. This process strengthens the recognition ability of the local high-energy density aggregation and thermal conductivity jump phenomenon caused by micro-eddy current circulation, making the structural vorticity thermal anisotropy index more sensitive and distinguishable in spatial distribution.

[0032] The deviation degree of the temperature rise directionality change per unit volume is comprehensively analyzed under the monitoring window to generate the structural vorticity thermal anisotropy index. The structural vorticity thermal anisotropy index is an index used to quantify the conduction deviation degree of the temperature rise in different spatial directions per unit volume. When its value is larger, it indicates that the temperature rise change direction in this local area has obvious non-uniformity and strong directional deviation. Under normal working conditions, heat conduction follows the law of material isotropy or weak anisotropy, and the deviation of the temperature rise directionality is small. When multiple metal components inside the cavity generate micro-eddy current circulation due to electromagnetic coupling, local induction heating will be formed on the non-designed path, causing heat to accumulate and diffuse along the induction circulation path, resulting in sudden changes and asymmetric growth of the thermal gradient direction per unit volume, and then significantly increasing the value of the structural vorticity thermal anisotropy index. Therefore, the higher the value of the structural vorticity thermal anisotropy index, the more it can characterize the existence of an abnormal energy input source in this region, that is, the micro-eddy current circulation phenomenon; on the contrary, when its value approaches the thermal field isotropy reference value, it indicates that the heat conduction in this region is uniform and there is no sign of eddy current coupling inside the structure.

[0033] The highly concentrated aggregation of the electromagnetic energy consumption density within a unit area in space usually indicates the risk of micro-vortex circulation among multiple metal components inside the cavity. This is because micro-vortex circulation is essentially a closed current path formed inside a conductor due to the induced electromotive force. Under the perturbation of a high-frequency magnetic field, these induced circulations form local circular paths in the gaps, overlapping edges, or uninsulated connection areas between components, resulting in the repeated dissipation of energy in a very narrow space and its conversion into heat energy. When this electromagnetic energy consumption density no longer diffuses evenly in space but is highly concentrated in certain areas and highly coincides with the positions of the metal structure boundaries or junctions, it usually means that there are unexpected induced circulation paths in these areas, which is a typical manifestation of eddy currents. Especially near an asymmetric structure layout or a coupling gap, the eddy current path is more likely to be "confined" in a local area, causing an energy superposition effect, manifested as an electromagnetic dissipation hot spot. Therefore, the highly concentrated energy consumption density not only reflects a significant increase in the probability of the existence of eddy currents but also implies that engineering consequences such as structural overheating, insulation degradation, or material erosion may occur in this area, which is an important physical indicator for judging the risk of micro-vortex circulation.

[0034] The specific steps for comprehensively analyzing the aggregation degree of the electromagnetic energy consumption density within a unit area in space under the monitoring window to generate the electromagnetic dissipation focus index are as follows: In a finite element simulation environment, obtain the three-dimensional electromagnetic energy consumption density distribution field of the unit area within the monitoring window through the simulation post-processing module. For the obtained electromagnetic energy consumption density distribution field, calculate the local electromagnetic energy consumption focusing intensity index, and the calculation expression is as follows: , where is the electromagnetic energy consumption density distribution field, representing the electromagnetic energy consumption density at the spatial point , that is, the energy loss caused by electromagnetic action (such as induced eddy currents, electric field coupling, etc.) per unit volume, is the spatial coordinate vector, is the gradient vector of the electromagnetic energy consumption density, representing the energy dissipation per unit volume at the position , is the modulus of the gradient vector of the electromagnetic energy consumption density, indicating the absolute intensity (i.e., the gradient magnitude) of the gradient vector. If this value is larger, it means that the energy consumption changes violently near this point, and there may be a "energy section" or inflection point. is the divergence operation of the vector field, used to calculate the "divergence" or "focusing" ability of the vector field at a certain point in space. If the divergence value is positive, it indicates that the energy "diffuses outward"; if it is negative, it indicates that the energy "aggregates inward". The absolute value of this formula is taken to capture the focusing intensity magnitude without distinguishing the direction. is the local electromagnetic energy consumption focusing intensity index, representing at the spatial position ​The aggregation intensity of electromagnetic energy consumption density at a location, which is used to measure whether the electromagnetic energy consumption shows spatial focusing at this location, and can also be understood as "whether the local energy density concentrates towards this point". The above steps are to take the divergence after coupling the energy consumption density with its directional normalized gradient, so as to characterize the aggregation trend of the local energy density. When The larger the value, the stronger the local concentration of the energy distribution near this spatial point, which is a sensitive characteristic index of the potential eddy current coupling focus.

[0035] Complete the local electromagnetic energy consumption focusing intensity index After the calculation, select the high-aggregation sub-region in the monitoring area where the focusing intensity exceeds the preset threshold . Define the high-aggregation sub-region, and the definition method is as follows: , where is the high-aggregation sub-region, representing the entire monitoring area In, the local electromagnetic energy consumption focusing intensity index exceeds the preset threshold The area set composed of all points, which is used to extract the location area with the strongest energy consumption focusing degree and the most likely eddy current risk. is the three-dimensional space range covered by the monitoring window, is the focusing intensity threshold, which is the critical value for dividing the "high-aggregation area" and the "normal area"; Based on the obtained high-aggregation sub-region, calculate the electromagnetic dissipation focus index, and the calculation expression is as follows: , in the formula, is the electromagnetic dissipation focus index, is the volume integral microelement, representing a tiny volume unit in three-dimensional space, which is used to sum the spatial continuous variables in the integral calculation and is used to perform volume-weighted accumulation on the focusing intensity or energy consumption density of the entire region.

[0036] In the above formula, the numerator part represents the total focusing amount in the area with significant energy aggregation intensity, and the denominator represents the total electromagnetic energy consumption in the entire region. The obtained ratio is the electromagnetic dissipation focus index described in the present invention. Its physical meaning is: when The larger the value, the higher the proportion of the unit energy consumption concentrated in the local structure area, which is extremely likely to induce the micro-eddy current circulation phenomenon; on the contrary, The smaller the value, the more uniform the energy consumption distribution and the lower the eddy current risk.

[0037] The aggregation degree of the electromagnetic energy consumption density within a unit area in space is comprehensively analyzed under a monitoring window to generate an electromagnetic dissipation focus index. The electromagnetic dissipation focus index reflects the degree of aggregation of the electromagnetic energy consumption density within a unit area in space, that is, whether the energy is highly concentrated in a local area rather than evenly distributed. When the performance value of this index is larger, it means that there is obvious electromagnetic energy accumulation in the local area, usually because a non-designed closed induction path - namely, a micro-vortex circulation - is formed between multiple metal components, making the electromagnetic energy unable to effectively diffuse in space but repeatedly dissipating and converting into heat in a narrow area. On the contrary, if the electromagnetic dissipation focus index is small, it indicates that the energy consumption is more evenly distributed in the structure, and there is no abnormal coupled vortex path between the metal components, indicating that the structure is in a normal electromagnetic response state and there is no risk of micro-vortex circulation.

[0038] After formatting and data augmentation processing of the key feature indicators after risk quantification analysis, they are input into a deep learning model that has been fully trained in advance with historical simulation data and on-site operation data. The model automatically evaluates the micro-vortex circulation risk of the cavity structure to achieve automated intelligent determination of the micro-vortex circulation risk. After formatting and data augmentation processing of the structural vortex heat anisotropy index and the electromagnetic dissipation focus index after risk quantification analysis, they are input into a deep learning model that has been fully trained in advance with historical simulation data and on-site operation data. The model generates a micro-vortex circulation risk coefficient, and the micro-vortex circulation risk of the cavity structure is automatically evaluated through the micro-vortex circulation risk coefficient to achieve automated intelligent determination of the micro-vortex circulation risk.

[0039] A deep learning model that has been fully trained in advance with historical simulation data and on-site operation data refers to an artificial intelligence model (such as a convolutional neural network CNN, a long short-term memory network LSTM, or a Transformer architecture, etc.) constructed and optimized based on a large number of historical finite element simulation data sets and actual equipment operation monitoring data sets before officially engaging in the micro-vortex circulation risk determination task. This model has the ability to identify the mapping relationship between complex field variable patterns and risk characteristics. In the training stage, developers first use a large amount of data with known labels (i.e., simulation samples and actual fault instances that have been confirmed whether there is a micro-vortex circulation) as input samples. Through feature extraction, data normalization, and augmentation, etc., high-dimensional feature vectors such as the structural vortex heat anisotropy index (AHT-Index) and the electromagnetic dissipation focus index (EDF-Index) are input into the model. The model is iteratively optimized, continuously adjusts the network weights through backpropagation, and learns how to effectively match these spatial field variable features with the actual risk state. Finally, the model can accurately output its risk assessment result when facing new unknown samples.

[0040] "Sufficient training" in this process means that the model has learned sufficient feature distribution patterns and risk evolution trends from data samples covering diverse boundary conditions such as various structural layouts, current excitations, material parameters, and external perturbation variations. Additionally, online monitoring data from industrial sites (such as infrared thermal imaging maps, local temperature rise sensor data, current mutation records, etc.) may be incorporated to enhance the model's robustness and generalization ability against non-ideal perturbation factors under real operating conditions. After sufficient training, the deep learning model can perform rapid, automated, and probabilistic risk assessments on newly input data (i.e., new simulation samples), outputting a "miniature eddy current circulation risk coefficient" with quantifiable meaning (which can be a probability value between 0–1 or a multi-level risk score), and based on this, determining whether there are high-risk circulation hazards inside the cavity, the risk intensity level, and whether subsequent structural optimization or operation warning is required. This intelligent evaluation method effectively replaces the traditional method relying on manual experience judgment, and has the characteristics of high efficiency, real-time performance, and batch scalability, which is one of the key technical paths for modern electrical structure simulation risk control.

[0041] Compare and analyze the generated miniature eddy current circulation risk coefficient with the pre-set reference threshold of the miniature eddy current circulation risk coefficient to make an intelligent determination of whether there is a risk of miniature eddy current circulation in the cavity structure. The determination logic is as follows: If the miniature eddy current circulation risk coefficient is greater than the pre-set reference threshold of the miniature eddy current circulation risk coefficient, it is determined that there is a potential risk of miniature eddy current circulation in the cavity structure; if the miniature eddy current circulation risk coefficient is less than or equal to the pre-set reference threshold of the miniature eddy current circulation risk coefficient, it is determined that there is no potential risk of miniature eddy current circulation in the cavity structure.

[0042] After identifying the potential risk of miniature eddy current circulation in the cavity structure, dynamically adjust the load boundary (such as short-circuit current amplitude, pulse waveform, arc duration) conditions in the simulation environment, and capture the dynamic evolution path of the eddy current circulation by analyzing the transient evolution trends of field variables (such as magnetic flux density, current density, temperature rise distribution, etc.) under different load conditions; By dynamically adjusting the load boundary conditions in the simulation environment, actively stimulate the potential response behavior of the miniature eddy current circulation, thereby enhancing its observability and differential characteristics in the simulation results to achieve precise identification and traceability analysis of the dynamic evolution path of the eddy current circulation.

[0043] After initially identifying the areas with the risk of eddy current circulation in the cavity structure, the distribution of field variables under a single static simulation condition often provides only limited information and cannot fully reveal the complete dynamic process of the eddy current from "germination" to "expansion". Especially inside a cavity with a complex structure and interlaced arrangement of multiple metal components, the generation mechanism of micro eddy current circulation usually depends on high-frequency electromagnetic excitation or an unsteady disturbance environment. Therefore, introducing a multi-condition dynamic excitation mechanism in the simulation, such as increasing the short-circuit current amplitude, changing the rising edge steepness of the arc pulse waveform, or extending its duration, can artificially amplify the induced current density, magnetic flux disturbance, and energy coupling effect, making the eddy current paths that were originally in a weak coupling or boundary state show obvious responses in the electromagnetic and thermal fields.

[0044] By performing time-series sampling and difference analysis on key field variables such as magnetic flux density, current density, and temperature rise distribution under different load conditions, the evolution trends and mutation behaviors of these variables in high-risk areas can be dynamically captured, and further the formation path, expansion direction, and focusing area of the eddy current circulation can be deduced. Especially when comparing the response differences of multiple excitation conditions, the non-linear enhancement effect of the eddy current response can be revealed, providing a basis for judging its development severity and critical transition. In addition, dynamic simulation can also assist in verifying the authenticity of the risk area, preventing misjudgments caused by initial simulation modeling errors, and thus providing strong support in terms of structural optimization, fault prediction, and simulation modeling accuracy control. In summary, this step is the key link to transform "passive identification" into "active excitation + dynamic tracking", and is the core technical support for accurately quantifying the micro eddy current risk mechanism and analyzing its path.

[0045] When it is identified that there is a potential risk of micro eddy current circulation in the cavity structure, the specific steps to dynamically adjust the load boundary conditions in the simulation environment and capture the dynamic evolution path of the eddy current circulation by performing difference analysis on the transient evolution trends of field variables under different load conditions are as follows: In the cavity area where the potential risk of micro eddy current circulation has been identified, implement the adjustment of the dynamic load boundary conditions, and perform cooperative excitation through three boundary disturbance methods: increasing the short-circuit current amplitude, increasing the pulse waveform steepness, and extending the arc duration, to form a composite condition disturbance intensity index. The calculation formula is as follows: , where is the adjustment increment of the short-circuit current amplitude, indicating how much the short-circuit current has increased under the current excitation compared to the original simulation conditions, is the pulse waveform steepness parameter, indicating the speed of the rising edge of the current or voltage excitation signal. The larger the value, the more rapid the signal change, is the arc duration increment, indicating how much longer the arc action time applied in this round of simulation is compared to the reference situation, is the reference short-circuit current amplitude, which is the reference current value and usually comes from a standard simulation model, industry regulations, or the rated short-circuit current under normal operating conditions , is the reference steepness of the pulse waveform, representing the steepness parameter under default pulse conditions, is the reference arc duration, which is the set value of the arc duration under the standard simulation model, 、 and are the adjustment increments of the short-circuit current amplitude pulse waveform steepness parameter and the arc duration increment are the weighting coefficients, satisfying , is the composite operating condition disturbance intensity index, which is a quantitative index for the degree of enhanced excitation of the simulation boundary conditions in the finite element simulation to identify its evolution path. It is used to characterize the "disturbance injection intensity" of the simulation excitation on the system response and introduces a risk coefficient modulation to form a quantifiable and controllable dynamic excitation intensity control variable, is the micro-vortex circulation risk coefficient, is the reference threshold of the micro-vortex circulation risk coefficient, is the risk modulation sensitivity coefficient, which controls the amplification factor of the risk coefficient deviation on the overall excitation intensity. The larger the value, the more sensitive it is to risk changes; The function of this step is to actively and significantly amplify the eddy current response phenomenon by precisely adjusting the load conditions in the simulation environment, so as to highlight the differential change characteristics of the eddy current circulation path under different operating conditions. The generated key parameter values will be used as a measure of the excitation conditions when analyzing the eddy current response in the next step.

[0046] After implementing the dynamic load boundary condition adjustment, for the distribution changes of field variables under different load conditions, the eddy current circulation path is captured through the field variable dynamic evolution difference coefficient. The calculation expression of the field variable dynamic evolution difference coefficient is as follows: , where, is the spatial volume within the identified potential risk area, which refers to the local spatial area with potential micro-vortex circulation risk identified through structural risk screening, thermal / electrical / magnetic feature focusing, etc. during the simulation post-processing. It is usually a three-dimensional sub-region at the intersection of multiple metal components or at the structural neck, is the spatial gradient of the magnetic flux density, representing the magnetic flux density in the three-dimensional space in each direction. It is used to reflect the spatial violent fluctuation degree of the local magnetic field and is a key index for evaluating whether induced current may be induced, is the spatial gradient of the current density, representing the current density vector field The gradient changes in all directions in space reflect the concentration or diffusion state of the induced current inside the conductor. It is used to determine whether the induced current is enhanced along a closed path and whether it changes dramatically in a specific area. It is the spatial gradient of temperature rise, which indicates the gradient of the distribution change of the temperature field in three-dimensional space, especially the spatial derivative of the temperature rise mutation area, which is used to judge whether the heat in the cavity shows abnormal non-uniform diffusion. is the flux density gradient weight coefficient, which indicates the weight distribution of the magnetic field gradient in the total response. For high-frequency excitation conditions, it should be appropriately increased. , such as setting it to 0.5-0.6, is the current density gradient weight coefficient, which indicates the weight of the contribution of the current density spatial variation to the eddy current path formation. If the simulation goal is to identify the current induced circulating current path, it is more appropriate to set it to 0.2-0.4. is the temperature rise gradient weight coefficient, which indicates the influence of the temperature change gradient on the comprehensive response. For a sealed gas insulated cabin, Set to 0.1-0.3 to emphasize temperature sensitivity and meet , is the volume differential element, It is the difference coefficient of the dynamic evolution of field variables. It is a composite index used to quantitatively analyze the difference in the change trend of field variables such as magnetic flux density, current density and temperature rise in space under different load conditions. The larger the value, the more drastic the changes in magnetic field, current and temperature in this area when excited. The purpose of this step is to comprehensively consider the spatial gradient distribution characteristics of three key field variables (magnetic field, current, and temperature) and quantitatively capture the evolution trend of field variables in the micro-eddy current circulation area under dynamic working condition excitation. The significant increase in the value reveals the dynamic formation and development characteristics of the eddy circulation path. The specific value of this coefficient will be further used to identify the core position of the circulation path in the next step.

[0047] Based on the obtained field variable dynamic evolution difference coefficient , an innovative spatial concentration index is constructed to accurately locate the degree of spatial aggregation of eddy circulation paths. The calculation formula is as follows: , where It is The spatial distance from the spatial subunit to the eddy response center refers to the current unit The Euclidean distance relative to the center of the eddy current response characterizes the degree to which the point deviates from the center of the eddy current response in space and is used to determine whether the response is highly focused. It is The difference coefficient of the dynamic evolution of field variables of the spatial subunits, is the total number of spatial subunits, It is the spatial concentration index of the micro-vortex circulation path, representing the "distribution radius" or "diffusion center of gravity" of the vortex circulation response in space, and is used to quantitatively evaluate its concentration. The smaller the value, the more concentrated the response of the micro-vortex circulation in a small area, manifested as vortex energy focusing and local enhancement. This situation has a higher risk and is prone to serious problems such as local overheating, breakdown, or structural melting. The larger the value, the more dispersed the vortex response in a larger spatial range, the path is in a "spread" state, and the energy density is lower than the concentrated state, and it is not easy to form destructive consequences at a certain position, but it may bring system-level energy loss or hidden heat accumulation.

[0048] The function of this step is to combine the dynamic evolution trend of the vortex circulation with spatial aggregation, by calculating the spatial concentration index , to judge the spatial concentration degree of the vortex circulation path. The smaller the index value, the more concentrated the vortex circulation path in a specific area; the larger the index value, the more extensive the path diffusion. Through this index, the specific position and severity of the micro-vortex circulation can be further clarified, providing effective support for subsequent structural optimization and safety guarantee.

[0049] The present invention can realize the comprehensive identification and quantitative evaluation of the potential micro-vortex circulation risk in the cavity structure by introducing an analysis mechanism combining high-dimensional field variable feature extraction, deep learning intelligent discrimination, and dynamic load response regulation. This method not only breaks through the problem of insufficient accuracy in identifying microstructural abnormalities by traditional finite element simulation, but also accurately captures the focusing characteristics and thermoelectric response characteristics of the vortex circulation in space through innovative parameters such as the structural vortex-thermal anisotropy index and the electromagnetic dissipation focus index. At the same time, by means of the dynamic adjustment and differential analysis of the load boundary conditions, the induction mechanism and evolution path of the vortex risk are further revealed. Finally, a closed-loop technical system from data-driven identification, physical behavior modeling to risk verification and feedback is constructed, providing a practical and scalable intelligent simulation analysis path for the safety design, fault prediction, and manufacturing optimization of the ring main unit structure.

[0050] The above formulas are all dimensionless and take their numerical calculations. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0051] Only some exemplary embodiments of the present invention have been described above by way of illustration. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0052] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0053] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0054] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0055] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0056] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0057] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0058] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

[0059] Only some exemplary embodiments of the present invention have been described above by way of illustration. Undoubtedly, for those of ordinary skill in the art, various different ways can be used to modify the described embodiments without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. A modular design method for ring main units based on multi-cavity coupling, characterized in that, It includes the following steps: In the post - processing stage of the cavity structure simulation in the finite - element simulation software, through the built - in automated script interface of the software, the three - dimensional field variable data inside the cavity is extracted in real - time, and the obtained data is exported in a structured format in real - time to form a standardized data file; Pre - process the obtained original three - dimensional field variable data, and extract the key feature indicators characterizing the potential risk of micro - vortex circulation from the pre - processed high - dimensional field variable data through feature engineering methods. Comprehensively analyze the extracted key feature indicators to quantify the true probability and severity of the micro - vortex circulation phenomenon; After formatting adjustment and data enhancement processing of the key feature indicators after risk quantification analysis, input them into a deep - learning model that has been fully trained with historical simulation data and on - site operation data. Automatically evaluate the micro - vortex circulation risk of the cavity structure through the model to achieve automated intelligent determination of the micro - vortex circulation risk; When a potential micro - vortex circulation risk in the cavity structure is identified, dynamically adjust the load boundary conditions in the simulation environment. By analyzing the difference in the transient evolution trend of field variables under different load conditions, capture the dynamic evolution path of the vortex circulation.

2. The modular design method of the ring main unit based on multi-cavity coupling according to claim 1, wherein In the post - processing stage of the finite - element simulation software, extracting the three - dimensional field variable data of the cavity structure and exporting it in a standardized file format includes the following steps: Complete the modeling and simulation calculation of the cavity structure in the finite - element simulation software to obtain the required three - dimensional field variable distribution results; Call the automated script interface provided by the software and write a script to achieve batch extraction of the target physical quantity in the entire cavity space; Structurally organize the extracted three - dimensional field variable data according to the correspondence between spatial coordinates and physical quantities to ensure that the data format is standard and unified and convenient for subsequent processing; Use the script to export the organized data in a standardized data file format.

3. The modular design method of the ring main unit based on multi-cavity coupling according to claim 1, characterized in that Extract the key feature indicators characterizing the potential risk of micro - vortex circulation from the pre - processed high - dimensional field variable data through feature engineering methods. The extracted key feature indicators include the deviation degree of the directional change of temperature rise per unit volume and the aggregation degree of electromagnetic energy consumption density per unit area in space. Comprehensively analyze the deviation degree of the directional change of temperature rise per unit volume and the aggregation degree of electromagnetic energy consumption density per unit area in space under the monitoring window, and generate the structural vortex heat anisotropy index and the electromagnetic dissipation focus index respectively. Quantify the true probability and severity of the micro - vortex circulation phenomenon through the structural vortex heat anisotropy index and the electromagnetic dissipation focus index.

4. The modular design method of the ring main unit based on multi-cavity coupling according to claim 3, characterized in that, The specific steps for comprehensively analyzing the deviation degree of the directional change of temperature rise per unit volume under the monitoring window to generate the structural vortex heat anisotropy index are as follows: Under the monitoring window, taking the unit volume cell as the basic analysis unit, a three-dimensional temperature rise field is extracted from the simulation data, and the gradient components of the temperature rise along the three main directions are calculated respectively to form a temperature rise direction gradient vector field. The calculation formula of the temperature rise direction gradient vector field is as follows: , where is the temperature rise direction gradient vector field, is the spatial change rate of the temperature field in the axis direction, is the spatial change rate of the temperature field in the axis direction, is the spatial change rate of the temperature field in the axis direction; In each unit volume, calculate the directional deviation tensor, and the calculation expression of the directional deviation tensor is as follows: , where is the main thermal conductivity direction vector of the structure, is the modulus of the main thermal conductivity direction vector, is the modulus of the temperature rise gradient, is the value of the directional deviation tensor; To magnify the structural differences brought about by minute deviations, spatial coupling sensitivity processing is carried out to highlight the contribution of the direction jump point to the thermal anisotropy. The calculation expression of the structural vorticity thermal anisotropy index is as follows: , where, is the modulus value of the temperature Laplacian operator, is the modulus value of the temperature gradient, is the structural vorticity thermal anisotropy index.

5. The modular design method of the ring main unit based on multi-cavity coupling according to claim 3, wherein, The specific steps for comprehensively analyzing the aggregation degree of electromagnetic energy consumption density per unit area in space under the monitoring window to generate the electromagnetic dissipation focus index are as follows: In the finite element simulation environment, the three-dimensional electromagnetic energy consumption density distribution field of the unit area within the monitoring window is obtained through the simulation post-processing module. For the obtained electromagnetic energy consumption density distribution field, the local electromagnetic energy consumption focusing intensity index is calculated, and the calculation expression is as follows: , where is the electromagnetic energy consumption density distribution field, is the spatial coordinate vector, is the gradient vector of the electromagnetic energy consumption density, representing the energy dissipation per unit volume at the position , is the modulus of the gradient vector of the electromagnetic energy consumption density, is the divergence operation of the vector field, is the local electromagnetic energy consumption focusing intensity index; Complete the local electromagnetic energy consumption focusing intensity index After calculation, select the high-focusing sub-region where the focusing intensity exceeds the preset threshold in the monitoring area Define the high-focusing sub-region. The definition method is as follows: , where is the high-focusing sub-region, is the three-dimensional space range covered by the monitoring window, is the focusing intensity threshold; Based on the obtained high-aggregation sub-region, calculate the electromagnetic dissipation focus index, and the calculation expression is as follows: , where is the electromagnetic dissipation focus index, is the volume integral differential element, representing a tiny volume unit in three-dimensional space.

6. The modular design method of the ring main unit based on multi-cavity coupling according to claim 3, characterized in that, After formatting and data augmentation of the structural vortex thermal anisotropy index and the electromagnetic dissipation focus index obtained from risk quantification analysis, they are input into a deep learning model that has been fully trained with historical simulation data and on-site operation data. The model generates a micro-vortex circulation risk coefficient, and the micro-vortex circulation risk of the cavity structure is automatically evaluated based on this coefficient, achieving an automated intelligent determination of the micro-vortex circulation risk.

7. The modular design method of the ring main unit based on multi-cavity coupling according to claim 6, characterized in that, The generated micro-vortex circulation risk coefficient is compared and analyzed with a pre-set reference threshold for the micro-vortex circulation risk coefficient to make an intelligent determination of whether there is a micro-vortex circulation risk in the cavity structure. The determination logic is as follows: If the micro-vortex circulation risk coefficient is greater than the pre-set reference threshold for the micro-vortex circulation risk coefficient, it is determined that there is a potential micro-vortex circulation risk in the cavity structure; if the micro-vortex circulation risk coefficient is less than or equal to the pre-set reference threshold for the micro-vortex circulation risk coefficient, it is determined that there is no potential micro-vortex circulation risk in the cavity structure.

8. The modular design method of the ring main unit based on multi-cavity coupling according to claim 7, characterized in that, After identifying a potential micro-vortex circulation risk in the cavity structure, the load boundary conditions in the simulation environment are dynamically adjusted. By analyzing the transient evolution trends of field variables under different load conditions, the specific steps to capture the dynamic evolution path of the vortex circulation are as follows: In the cavity area where the potential risk of micro-vortex circulation has been identified, dynamic load boundary condition adjustment is implemented. Through three boundary perturbation methods of increasing the short-circuit current amplitude, improving the steepness of the pulse waveform, and prolonging the arc duration for collaborative excitation, a composite operating condition perturbation intensity index is formed. The calculation formula is as follows: , where is the adjustment increment of the short-circuit current amplitude, is the steepness parameter of the pulse waveform, is the increment of the arc duration, is the reference short-circuit current amplitude, is the reference steepness of the pulse waveform, is the reference arc duration, , and are the adjustment increments of the short-circuit current amplitude the steepness parameter of the pulse waveform and the increment of the arc duration weighting coefficients, satisfying , is the composite operating condition perturbation intensity index, is the micro-vortex circulation risk coefficient, is the reference threshold of the micro-vortex circulation risk coefficient, is the risk modulation sensitivity coefficient; After implementing the adjustment of dynamic load boundary conditions, for the changes in the distribution of field variables under different load conditions, the eddy current circulation path is captured by the field variable dynamic evolution difference coefficient. The calculation expression of the field variable dynamic evolution difference coefficient is as follows: , where is the spatial volume within the identified potential risk area, is the spatial gradient of the magnetic flux density, representing the change rate of the magnetic flux density in each direction in three-dimensional space, is the spatial gradient of the current density, representing the gradient change of the current density vector field in each direction in space, is the spatial gradient of the temperature rise, is the magnetic flux density gradient weight coefficient, is the current density gradient weight coefficient, is the temperature rise gradient weight coefficient, is the volume integral element, is the field variable dynamic evolution difference coefficient; Based on the obtained dynamic evolution difference coefficient of the field variable , an innovative spatial concentration index is constructed to accurately locate the degree of aggregation of the eddy current circulation path in space. The calculation formula is as follows: , where is the spatial distance from the th spatial sub-unit to the eddy current response center, is the dynamic evolution difference coefficient of the field variable of the th spatial sub-unit, is the total number of spatial sub-units, is the spatial concentration index of the micro eddy current circulation path.

Images