A method for evaluating the internal fault withstand time of a large oil-filled main equipment

Abstract

The invention discloses a method for evaluating the internal fault tolerance time of large oil-filled main equipment, belonging to the technical field of relay protection of oil-filled main equipment in power systems. A plurality of fault currents are obtained within the internal fault current range of the oil-filled main equipment; a three-dimensional geometric simulation model and a grid model of the oil-filled main equipment are established; a transient pressure-based solver is called to simulate the turbulent flow phenomenon and the oil pressure increase phenomenon of the oil-filled main equipment under fault current conditions, determine whether the oil-filled main equipment ruptures, and obtain the allowable fault tolerance time of the oil-filled main equipment under different fault currents. A neural network model for mapping fault current and allowable fault tolerance time is established through the convolutional layer, pooling layer and fully connected layer in the convolutional neural network to realize the evaluation of the allowable fault tolerance time of the oil-filled main equipment. The fracture and failure phenomena of the oil-filled main equipment under high stress conditions are accurately captured, thereby providing a more accurate quantitative method for evaluating the fault tolerance time of the oil-filled main equipment than the traditional empirical method.

Description

Technical Field

[0001] The present invention belongs to the technical field of relay protection for oil-filled main equipment in power systems, and particularly relates to a method for evaluating the internal fault tolerance time of large oil-filled main equipment. Background Art

[0002] In modern power systems, ultra-high voltage and extra-high voltage oil-filled main equipment (such as oil-immersed transformers, oil-immersed reactors, and oil-filled circuit breakers) play a crucial role in maintaining the stable operation of the power grid. Such equipment usually operates under high load and high voltage environments. When a high-energy arc fault occurs inside the equipment, it is extremely likely to cause equipment damage or explosion accidents. In recent years, there have been multiple equipment explosion accidents caused by internal high-energy arc discharges in ultra-high voltage oil-filled main equipment in China, resulting in adverse social impacts and serious economic losses. This highlights the importance of comprehensively evaluating the fault tolerance of equipment. The allowable fault tolerance time is a critical indicator to measure the catastrophic damage of equipment without the intervention of protection measures under fault conditions. In-depth understanding of the allowable tolerance time of oil-filled main equipment under fault conditions is of great significance for accurately determining the equipment protection action time, optimizing protection strategies, and designing preventive measures. However, there is still a lack of research on evaluating the allowable fault tolerance time of oil-filled main equipment. Summary of the Invention

[0003] The present invention provides a method for evaluating the internal fault tolerance time of large oil-filled main equipment to solve the problems in the prior art that there is a lack of research on evaluating the allowable fault tolerance time of oil-filled main equipment and it is impossible to accurately evaluate the allowable fault tolerance time of oil-filled main equipment within the full fault current range.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] A method for evaluating the internal fault tolerance time of large oil-filled main equipment includes the following steps:

[0006] Step 1: Obtain multiple fault currents within the fault current range of the internal arc fault of the oil-filled main equipment ;

[0007] Step 2: Establish a three-dimensional geometric simulation model of the oil-filled main equipment, and establish a grid model of the oil-filled main equipment according to the three-dimensional geometric simulation model of the oil-filled main equipment;

[0008] Step 3: Call a transient pressure-based solver to perform fluid-structure interaction calculations on the oil-filled main equipment;

[0009] S1. Based on multiple fault currents , simulate the oil pressure increase process inside the oil-filled main equipment in the grid model of the oil-filled main equipment, and reflect the oil pressure changes under different fault current conditions;

[0010] S2. Simulate the turbulent phenomenon caused by the dynamic change of the fluid inside the oil-filled main equipment, and set the turbulent phenomenon of the oil-filled main equipment as the model;

[0011] S3. Obtain the oil pressure load according to the oil pressure change and the model;

[0012] S4. Input the oil pressure load into the solid calculation domain of the oil-filled main equipment to obtain the displacement vectors of the grid points of the grid model of the oil-filled main equipment in the x, y, and z directions , and through the displacement vectors , obtain the principal strains of the grid model of the oil-filled main equipment in the three directions of x, y, and z , and ;

[0013] S5. Judge whether the oil-filled main equipment is broken according to the principal strains of the grid model of the oil-filled main equipment in the three directions of x, y, and z , and . If it is broken, record the allowable fault withstand time of the oil-filled main equipment under different fault currents . If it is not broken, re-enter S1;

[0014] Step 4: Based on the allowable fault withstand time of the oil-filled main equipment under different fault currents , establish a neural network model of the fault current and the allowable fault withstand time based on the convolutional neural network, and output the allowable fault withstand time results of the oil-filled main equipment at different fault currents .

[0015] In step 2, the method for establishing the grid model of the oil-filled main equipment is specifically as follows: discretize the three-dimensional geometric simulation model of the oil-filled main equipment by using the progressive size function, and gradually reduce the grid diameter near the boundary, corners, and curves, and gradually increase the grid diameter as the distance increases.

[0016] Simulate the oil pressure increase process inside the oil-filled main equipment in the grid model of the oil-filled main equipment, and use bubble dynamics to simulate the oil pressure increase process inside the oil-filled main equipment. The bubble dynamics equation is:

[0017]

[0018] In the formula, represents the radius of the bubble, represents the normal velocity of the bubble surface, represents the normal acceleration of the bubble surface; represents the insulating oil density, represents the pressure at the fluid domain boundary, represents the heat transfer coefficient, represents the specific heat ratio, represents the dynamic viscosity of the fluid, represents the surface tension of the fluid, represents the work done by the external surface of the bubble during the bubble expansion process, represents the work done by the surface tension during the bubble expansion process, represents the work done by the viscous force during the bubble expansion process, represents the initial internal energy of the bubble, represents the arc energy.

[0019] Arc energy The calculation formula is:

[0020]

[0021] In the formula, represents the fault current, represents the arc voltage corresponding to the fault current , represents the fault duration.

[0022] The method for simulating the turbulent phenomenon caused by the dynamic change of the fluid inside the oil-filled main equipment is specifically as follows: Use the dynamic mesh to update the instantaneous fluid field inside the oil-filled main equipment, and simulate the turbulent phenomenon caused by the dynamic change of the fluid due to the bubble expansion inside the oil-filled main equipment by capturing the flow characteristics and transient changes of physical quantities during the structural change of the oil-filled main equipment. The calculation formula is:

[0023]

[0024] In the formula, represents the derivative with respect to time, is the density of the fluid, u is the velocity vector of the fluid, is the area vector, is the diffusion coefficient, represents the source term of is the turbulent characteristic quantity, is the grid velocity of the moving grid, is the control volume, is the vector differential operator, represents the turbulent characteristic quantity of the gradient, is the control volume of the boundary.

[0025] The dynamic mesh update uses the Laplacian smoothing model, and the calculation formula of the Laplacian smoothing model is:

[0026]

[0027] In the formula, represents the new position of node i . represents the number of adjacent nodes of node , is the position of adjacent node .

[0028] The turbulent phenomenon of the oil-filled main equipment is set as model, and its setting equation is:

[0029]

[0030]

[0031] In the formula, represents the turbulent kinetic energy, represents the differential change of the turbulent kinetic energy , represents the differential of time, represents the differential of the spatial coordinate , represents the partial derivative symbol, represents the turbulent kinetic energy, of the turbulent Prandtl number, represents the turbulent specific dissipation rate, represents the turbulent Prandtl number of the turbulent specific dissipation rate , represents the average velocity of the fluid, represents the specific dissipation rate, represents the molecular viscosity, represents the turbulent viscosity, represents the Prandtl number of the kinetic energy equation, represents the generation term of the turbulent kinetic energy, generated by shear stress, represents the magnitude of the strain rate, and represent the model constants, is the position of adjacent node .

[0032] According to the oil pressure change and model, the oil pressure load is obtained, and it still needs to be further calculated through the momentum equation. The calculation formula of the momentum equation is:

[0033]

[0034] In the formula, represents the dynamic viscosity, represents the external force vector per unit volume acting on the fluid, is the pressure, is the density of the fluid, is the flow velocity of the fluid inside the main oil-filled equipment, represents the dot product operation of the vector field on the vector differential; the pressure is obtained by iteratively solving the momentum equation and the flow velocity of the fluid inside the main oil-filled equipment , and by coupling the pressure and the flow velocity of the fluid inside the main oil-filled equipment , the pressure distribution is obtained, and combined with the oil pressure change and model, the oil pressure load is thus obtained.

[0035] The displacement vector of the grid points of the main oil-filled equipment grid model in the x, y, and z directions is obtained through explicit dynamics calculation. The specific calculation method is as follows: The central difference method is used for discrete integration of acceleration, velocity, and displacement with respect to the time step to obtain the displacement vector of the grid points of the main oil-filled equipment grid model, corresponding to the displacement of the grid points of the main oil-filled equipment grid model in the x direction, corresponding to the displacement of the grid points of the main oil-filled equipment grid model in the y direction, corresponding to the displacement of the grid points of the main oil-filled equipment grid model in the z direction. The principal strain formulas for the main oil-filled equipment grid model in the three directions of x, y, and z , and are as follows: .

[0036] The method for judging whether the main oil-filled equipment is ruptured is specifically as follows: According to the constant strain failure criterion, it is judged whether the main oil-filled equipment is ruptured. The judgment formula is:

[0037]

[0038] In the formula, represents the failure strain, represents the equivalent plastic strain. If the equivalent plastic strain > the failure strain , then the main oil-filled equipment ruptures. If the equivalent plastic strain ≤ the failure strain , then the main oil-filled equipment does not rupture.

[0039] Based on the convolutional neural network, a neural network model of fault current and allowable fault withstand time is established as follows: The allowable fault withstand time data under different fault current conditions obtained are used as input values, and the data are model-trained through the convolutional neural network to generate a neural network model of the relationship between fault current and allowable fault withstand time. The convolutional neural network includes a convolutional layer, a pooling layer, and a fully connected layer. Among them, the convolutional layer extracts features from different fault currents and the corresponding allowable fault withstand time data. The pooling layer optimizes the extracted features, and the fully connected layer maps the optimized feature data to fault current and allowable fault withstand time; the calculation formula for feature extraction by the convolutional layer is:

[0040]

[0041] In the formula, represents the value of the k th feature quantity at the position ( i , j ), represents the value of the input data at the position , represents the weight matrix of the convolutional kernel in the k channel, represents the bias term; the calculation for the pooling layer to optimize the extracted features includes average pooling and max pooling, and the calculation formulas for average pooling and max pooling are as follows:

[0042]

[0043]

[0044] Among them represents average pooling, represents max pooling, N represents the dimension of the convolutional kernel, represents the data points in the pooling area; the fully connected layer maps the optimized feature data to fault current and allowable fault withstand time, and uses the Softmax function, and its calculation formula is as follows:

[0045]

[0046]

[0047] In the formula, is the output of the j th neuron in the fully connected layer, and b represent the weight and bias respectively, represents the th optimized feature data output by the pooling layer, andj The output probability corresponding to a neuron in Softmax is, is the probability distribution in the Softmax function.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention discloses a method for evaluating the internal fault tolerance time of a large oil-filled main equipment. The present application establishes a fluid-solid coupling calculation model of the oil-filled main equipment, comprehensively considers the bubble dynamics of the fluid domain, the oil pressure change and the structural mechanical response of the solid domain during an arc fault, and fully reflects the interaction between multiple physical fields. By accurately simulating the physical process inside the oil-filled main equipment, the allowable fault tolerance time of the oil-filled main equipment under different fault currents can be more accurately determined, thereby improving the accuracy of the evaluation results. The relationship between the fault current and the fault tolerance time within the full fault current range is modeled using machine learning methods such as convolutional neural networks. The machine learning model can handle complex nonlinear relationships, train and learn through a large amount of sample data, and mine the potential laws in the data, thereby achieving accurate prediction of the fault tolerance time under any fault current, making up for the shortcomings of traditional methods in handling complex relationships. Combined with the constant strain failure criterion, the present invention can accurately capture the fracture and failure process of the structural material of the oil-filled main equipment under high stress, thereby providing a more accurate evaluation method than the traditional empirical data method for determining the allowable fault tolerance time of the oil-filled main equipment. In addition, the present invention applies deep neural networks to model the relationship between fault current and fault tolerance time for the first time, which can achieve high-precision evaluation within the full fault current range and successfully solve the problem of fitting complex nonlinear relationships. This machine learning-based method significantly improves the efficiency of fault tolerance time evaluation and provides efficient and intelligent technical support for the design and optimization of oil-filled main equipment protection systems.

[0050] Furthermore, the present application not only analyzes the allowable fault tolerance time under the sampled fault current conditions, but also expands the evaluation range to the full fault current range through a machine learning model. This allows the fault tolerance capacity of the oil-filled main equipment to be accurately evaluated in practical applications, regardless of the level of the fault current, providing a more comprehensive and reliable basis for equipment protection. During the evaluation process, the effects of multiple factors on the fault tolerance time, such as arc energy, bubble expansion, fluid turbulence, and mechanical properties of structural materials, are comprehensively considered. This comprehensive consideration method can more realistically reflect the performance changes of the oil-filled main equipment under actual fault conditions, and avoid evaluation errors caused by ignoring certain important factors.

[0051] Furthermore, based on the accurate evaluation results of the fault tolerance time, the protection action time of the oil-filled main equipment can be set more precisely. This helps avoid exacerbating equipment damage due to an overly long protection action time or causing unnecessary power outages and incorrect equipment operations due to an overly short protection action time, thereby enhancing the safety and reliability of equipment operation. The evaluation method of this application provides a scientific basis for the design and optimization of the protection system for oil-filled main equipment. By deeply understanding the relationship between the fault current and the fault tolerance time, the parameters and structure of the protection system can be improved accordingly, enhancing the performance and adaptability of the protection system and reducing the losses caused by equipment failures. Description of the Drawings

[0052] Figure 1 : Geometric model diagram of the riser of the oil-filled equipment;

[0053] Figure 2 : Mesh division diagram of the riser of the oil-filled equipment;

[0054] Figure 3 : Flow chart for evaluating the allowable fault tolerance time in the embodiment of the present invention;

[0055] Figure 4 : Relationship diagram between the fault current and the allowable fault tolerance time in the embodiment of the present invention. Detailed Embodiments

[0056] To further understand the content of the present invention, the following provides a detailed description of the present invention in combination with the drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention rather than limiting it. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0057] The following provides a detailed description of the embodiments of the present invention in combination with the drawings.

[0058] Embodiment 1

[0059] This embodiment proposes a method for evaluating the fault tolerance time inside a large oil-filled main equipment, including the following steps:

[0060] Step 1: Obtain multiple fault currents within the range of the fault current of the internal arc fault of the oil-filled main equipment ;

[0061] Step 2: Establish a three-dimensional geometric simulation model of the oil-filled main equipment, and establish a mesh model of the oil-filled main equipment based on the three-dimensional geometric simulation model;

[0062] Step 3: Invoke the transient pressure-based solver to perform fluid-structure interaction calculations on the oil-filled main equipment;

[0063] S1. Based on multiple fault currents Simulate the process of oil pressure increase inside the oil-filled main equipment in the grid model of the oil-filled main equipment, and reflect different fault currents The oil pressure change under conditions;

[0064] S2. Simulate the turbulence phenomenon caused by the dynamic change of the fluid inside the oil-filled main equipment, and set the turbulence phenomenon of the oil-filled main equipment as Model;

[0065] S3. Obtain the oil pressure load according to the oil pressure change and Model;

[0066] S4. Input the oil pressure load into the solid calculation domain of the oil-filled main equipment to obtain the displacement vectors of the grid points of the grid model of the oil-filled main equipment in the x, y, and z directions Through the displacement vector Obtain the principal strains of the grid model of the oil-filled main equipment in the three directions of x, y, and z 、 And ;

[0067] S5. Judge whether the oil-filled main equipment is ruptured according to the principal strains of the grid model of the oil-filled main equipment in the three directions of x, y, and z 、 And If the oil-filled main equipment ruptures, record the allowable fault tolerance time of the oil-filled main equipment under different fault currents If not, re-enter step three;

[0068] Step four: Based on the allowable fault tolerance time of the oil-filled main equipment under different fault currents Establish a neural network model of fault current and allowable fault tolerance time based on a convolutional neural network, and output the allowable fault tolerance time results of the oil-filled main equipment at different fault currents ;

[0069] Example 2

[0070] In this example, the oil-filled main equipment is taken as the elevation seat of the oil-filled equipment. The elevation seat of the oil-filled equipment takes the elevation seat of the oil-filled equipment with a diameter of 600 mm and a height of 1000 mm as the research object. The barrel wall material of the elevation seat of the oil-filled equipment is carbon steel, and an insulator structure with a height of 2040 mm is installed on it. See Figure 1 This implementation is for Figure 1 In the elevation seat of the oil-filled equipment, a method for evaluating the internal fault tolerance time of a large oil-filled main equipment is carried out. The specific implementation method includes the following steps:

[0071] Step 1: Determine the fault current range of the arc fault in the riser of the oil-filled equipment. After determination, the arc fault current range inside the riser of the oil-filled equipment is: 50 kA - 80 kA.

[0072] Step 2: Set uniform sampling points within the determined fault current range from 50 kA to 80 kA, and use the several fault currents collected at the sampling points as the input values for the subsequent fluid-structure interaction calculation of the riser of the oil-filled equipment, and obtain the corresponding arc voltage according to the fault current at the sampling points. .

[0073] Step 3: Use SolidWorks software to establish a 1:1 equivalent three-dimensional geometric simulation model of the riser of the oil-filled equipment.

[0074] Step 4: Import the three-dimensional geometric simulation model of the riser of the oil-filled equipment into ANSYS software.

[0075] Step 5: In ANSYS software, select the progressive sizing function to discretize the spatial region defined by the three-dimensional geometric simulation model of the riser of the oil-filled equipment, establish a mesh model of the riser of the oil-filled equipment, generate finer meshes near the boundaries, corners, and curves, and gradually generate coarser meshes as the distance increases. The meshing diagram of the mesh model of the riser of the oil-filled equipment is as shown in Figure 2 .

[0076] Step 6: Call the transient pressure-based solver in ANSYS software, apply the transient pressure-based solver to the mesh model of the riser of the oil-filled equipment, and perform the fluid-structure interaction calculation of the riser of the oil-filled equipment.

[0077] First step: By applying the bubble dynamics equation considering the continuous injection of arc energy, simulate the increase in oil pressure caused by the arc fault-induced bubbles inside the riser of the oil-filled equipment, and obtain the oil pressure change situation. The bubble dynamics equation is:

[0078]

[0079] In the formula, represents the radius of the bubble, represents the normal velocity of the bubble surface, represents the normal acceleration of the bubble surface; represents the density of the insulating oil, represents the pressure at the boundary of the fluid domain, represents the heat transfer coefficient, represents the specific heat ratio, represents the dynamic viscosity of the fluid, represents the surface tension of the fluid, Represents the external work done by the bubble's convenient surface during the bubble expansion process, Represents the external work done by the surface tension during the bubble expansion process, Represents the external work done by the viscous force during the bubble expansion process, Represents the initial internal energy of the bubble, Represents the arc energy, and its calculation formula is:

[0080]

[0081] In the formula, Represents the arc voltage, Represents the fault current, Represents the fault duration.

[0082] Second step: Due to the complex fluid state inside the elevated seat of the oil-filled equipment, the fluid dynamic changes caused by the bubble expansion of the fluid trigger a turbulence phenomenon. Use dynamic meshing to update the instantaneous fluid field inside the elevated seat of the oil-filled equipment, and simulate the turbulence phenomenon inside the elevated seat of the oil-filled equipment by capturing the flow characteristics and transient changes of physical quantities during the fluid change process inside the elevated seat of the oil-filled equipment. Its calculation formula is:

[0083]

[0084] In the formula, Represents the derivative with respect to time, Is the density of the fluid, u Is the velocity vector of the fluid, Is the area vector, Is the diffusion coefficient, Represents The source term of, Is the turbulence characteristic quantity, Is the grid velocity of the moving grid, Is the control volume, Is the vector differential operator, Represents the turbulence characteristic quantity The gradient of, Is the control volume The boundary of. By solving this equation, the instantaneous fluid field can be updated according to the bubble expansion velocity.

[0085] Step 3: During the moving mesh update process, due to factors such as bubble expansion, the positions of mesh nodes will change, which may lead to a decrease in mesh quality, affecting the accuracy and stability of numerical calculations. By using the Laplacian smoothing model to redistribute the mesh nodes, reduce mesh distortion and deformation, improve mesh quality, and keep the mesh in a better shape and topological structure to achieve an accurate simulation of the complex fluid dynamic changes in the riser of the oil-filled equipment. The moving mesh update uses the Laplacian smoothing model, and the calculation formula of the Laplacian smoothing model is:

[0086]

[0087] In the formula, represents the new position of node i , represents the number of adjacent nodes of node , is the position of adjacent node .

[0088] Step 4: In the simulation analysis of the fault arc in the riser of the oil-filled equipment, the fluid inside will exhibit complex turbulent phenomena under arc fault conditions. Therefore, the turbulent phenomenon in the fluid domain is set as model to be able to more accurately simulate the turbulent phenomenon. The turbulent model of the fluid domain is set as model equation:

[0089]

[0090]

[0091] In the formula, represents the turbulent kinetic energy, represents the differential change of the turbulent kinetic energy , represents the differential of time, represents the differential of the spatial coordinate , represents the partial derivative symbol, represents the turbulent kinetic energy, is the turbulent Prandtl number of the turbulent kinetic energy, represents the turbulent specific dissipation rate, represents the turbulent Prandtl number of the turbulent specific dissipation rate , represents the average velocity of the fluid, represents the specific dissipation rate, represents the molecular viscosity, represents the turbulent viscosity, represents the Prandtl number of the kinetic energy equation, represents the generation term of the turbulent kinetic energy, generated by shear stress, represents the magnitude of the strain rate, and represents the model constant, is the position of adjacent nodes in the model.

[0092] Step 5: Based on the oil pressure change and the model, calculate the oil pressure load through the momentum equation. The calculation formula of the momentum equation is:

[0093]

[0094] In the formula, represents the dynamic viscosity, represents the gravity, is the pressure, is the density of the fluid, is the flow velocity of the fluid inside the riser of the oil-filled equipment, represents the dot product operation of the vector field on the vector differential; solve the pressure and the flow velocity of the fluid inside the riser of the oil-filled equipment by iterative solution of the momentum equation. Through the coupling of the pressure and the flow velocity of the fluid inside the riser of the oil-filled equipment obtain the pressure distribution, and combine it with the oil pressure change and the model to obtain the oil pressure load.

[0095] Step 6: Input the oil pressure load into the solid calculation domain of the riser of the oil-filled equipment, and calculate the structural response of the riser through explicit dynamics. Explicit dynamics uses the central difference method for discrete integration of acceleration, velocity, and displacement with respect to time step,

[0096] The displacement update formula is

[0097]

[0098] In the formula, represents the displacement at time step n +1, represents the displacement at time step n t, represents the velocity at time step n t, represents the acceleration at time step n t, represents the time step size.

[0099] The velocity update formula is:

[0100]

[0101] In the formula, represents the velocity at the time step n +1 / 2, represents the time step n -1 / 2 moment velocity.

[0102] The acceleration update formula is:

[0103]

[0104] In the formula, M represents the mass matrix, represents the external force, represents the internal force.

[0105] After solving the above displacement update formula, velocity update formula, and acceleration update formula, the displacement vector of the grid points of the elevated seat of the oil-filled equipment grid model is obtained under the action of the oil pressure load caused by the internal arc fault , corresponding to the displacement of the grid points of the elevated seat grid model of the oil-filled equipment in the x direction, corresponding to the displacement of the grid points of the elevated seat grid model of the oil-filled equipment in the y direction, corresponding to the displacement of the grid points of the elevated seat grid model of the oil-filled equipment in the z direction. Through the displacement vector , the principal strains in the x, y, and z directions are obtained. The strain calculation formula is as follows:

[0106]

[0107] Step 7: Judge whether the structural material of the elevated seat of the oil-filled equipment is cracked according to the constant strain failure criterion. The judgment calculation formula is:

[0108]

[0109] In the formula, represents the failure strain, represents the equivalent plastic strain, , , represent the principal strains in three directions. If the equivalent plastic strain is greater than the failure strain , then the structural material of the elevated seat of the oil-filled equipment is cracked. If the equivalent plastic strain is less than the failure strain , then the structural material of the elevated seat of the oil-filled equipment is not cracked, and the fluid-structure interaction calculation of the fault arc at this test point is restarted, that is, re-enter the first process in step 6 until it is judged that the structural material of the elevated seat of the oil-filled equipment is cracked, and record the time at this time, which is the allowable fault tolerance time of the elevated seat of the oil-filled equipment under this fault arc current.

[0110] After performing the calculation in Step 6 on the fault currents obtained from different sampling points, the allowable fault withstand time data under different sampled fault current conditions are obtained.

[0111] Step 7: Using a machine learning algorithm, take the allowable fault withstand time data obtained under different fault current conditions as input values, and perform model training on the data through a convolutional neural network to generate a neural network model for the relationship between fault current and allowable fault withstand time. Among them, the data used for model training in the convolutional neural network is shown in Table 1 below.

[0112] Table 1

[0113]

[0114] The operation formula of the convolutional layer is:

[0115]

[0116] In the formula, represents the value of the k th feature quantity at the position ([[$ i , j ), represents the value of the input data at the position , represents the weight matrix of the convolutional kernel in the k channel, represents the bias term. In the convolutional layer, feature extraction is performed on the allowable fault withstand time data under different sampled fault current conditions input through the above convolutional layer operation formula to obtain the corresponding feature map.

[0117] After the data is extracted by the convolutional layer features, a pooling operation is performed. The pooling of the neural network is mainly divided into average pooling and max pooling. Average pooling can retain the information of all features within the feature region, reflecting the average state of the fault current at different sampling points and its corresponding allowable fault withstand time, providing a stable feature input for the subsequent accurate evaluation of the allowable fault withstand time. The calculation formula of average pooling is as follows:

[0118]

[0119] where N represents the dimension of the convolutional kernel, represents the data points in the pooling region. Max pooling takes the maximum value within the pooling region as the feature output, reflecting the significant information features, capturing the maximum strain value when a fault occurs in the stress concentration region inside the riser of the oil-filled equipment, so as to more accurately evaluate the allowable fault withstand time of the riser of the oil-filled equipment under different fault currents. The calculation formula of max pooling is as follows:

[0120]

[0121] After the convolution and pooling operations of the convolutional layer and the pooling layer, the data of different fault currents and the corresponding allowable fault withstand times are transformed from the original input form into a feature representation with a certain degree of abstraction. The length is M of the sequence, the pooling window size is F , the stride is L , and the length after pooling is . The fully connected layer displays and connects all the feature maps output by the aforementioned convolutional layer and pooling layer, enabling the neural network model to comprehensively consider all these feature information, determine the relationship between the fault current and the allowable fault withstand time within the full fault current range, and establish a mapping relationship between the fault current and the allowable fault withstand time within the full fault current range. The last layer of the fully connected layer uses the Softmax function to transform the input into a probability distribution with a sum of 1, where the largest probability is the category to which the sample belongs, that is, the allowable fault withstand time category. The fully connected layer completes the classification prediction of the allowable fault withstand time through the mapping relationship between the fault current and the allowable fault withstand time within the full fault current range. The formulas of the fully connected layer and the Softmax function are as follows:

[0122]

[0123]

[0124] In the formula, is the output of the j th neuron in the fully connected layer, and b represent the weight and bias respectively, represents the th optimized feature data output by the pooling layer, and j represents the output probability corresponding to the th neuron in the Softmax,

[0125] Step 8: Output the allowable fault withstand time results of the riser of the oil-filled equipment under different fault current conditions.

[0126] The present invention constructs a multi-physical field coupling simulation model, laying a solid theoretical foundation for the dynamic evaluation of the allowable fault withstand time of the riser of the oil-filled equipment. Combining with the deep neural network technology, it further optimizes the non-linear mapping relationship between the fault current and the allowable fault withstand time, and realizes the efficient and accurate evaluation within the full fault current range. This method provides strong technical support for the scientific setting of the protection action time of the riser of the oil-filled equipment.

[0127] In a specific embodiment of the present invention, the allowable fault withstand time of the riser of the oil-filled equipment under a 60KA fault current is evaluated. According to the strain conditions occurring in the grid model of the riser of the oil-filled equipment, the strain conditions of the riser of the oil-filled equipment at 5 ms, 10 ms, 20 ms, and 34.8 ms under the action of a 60KA fault current are tested. As the duration of the 60KA fault current increases, the strain distribution of the riser of the oil-filled equipment gradually expands. Especially after 10 ms, the strain in the areas near the bottom and manhole of the riser of the oil-filled equipment increases significantly, indicating obvious stress concentration phenomena at these positions. According to the stress distribution test of the riser of the oil-filled equipment under the condition of a 60KA fault current, at 34.8 ms, the oil pressure load caused by the 60KA fault current leads to the fracture of the manhole bolts of the riser of the oil-filled equipment. Therefore, under this fault current condition, the upper limit of the allowable arc fault duration of the riser of the oil-filled equipment is 34.8 ms. Comparing this result with actual fault cases, the same fault current and the same equipment are used in the actual fault cases. Under the condition of a 60KA fault current, the allowable fault withstand time in the actual fault test cases is 30 - 40 ms. The allowable fault withstand time evaluated by the present invention for the riser of the oil-filled equipment under the same fault current condition is 34.8 ms. Therefore, the evaluation result of the present invention is highly consistent with the actual test cases, proving the correctness and effectiveness of the present invention. Based on the above analysis results and the calculation results at other sampling points under different fault current conditions, the present invention accurately establishes a non-linear mapping relationship between the fault current and the allowable fault withstand time within the full fault current range through a convolutional neural network model, as Figure 3 shown, multiple fault currents collected at sampling points are used as the input values of the input layer, that is, the multiple collected fault currents correspond to X1, X2, X3... X in the figure n , and finally the output of the output layer represents the different allowable fault withstand times of the riser of the oil-filled equipment corresponding to different fault currents . Finally, Figure 4 shows the quantitative relationship between the peak value of the arc current and the allowable fault withstand time. The greater the arc fault current , the higher the peak value of the generated arc current. The results show that when the peak value of the arc current increases from 50 kA to 80 kA, the allowable fault withstand time of the riser of the oil-filled equipment decreases from about 39 ms to about 21 ms, indicating that under high-current fault conditions, the allowable fault withstand time of the riser of the oil-filled equipment is shortened by about 50%. The above quantitative analysis results provide a solid theoretical support for the dynamic protection strategy of the riser of the oil-filled equipment under arc faults and provide a theoretical basis for setting the equipment protection action time in engineering design, having important engineering application value.

[0128] In addition, it should be understood that although this specification is described in terms of embodiments, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of the present invention and cannot be used to limit the protection scope of the present invention. Any modification made on the basis of the technical solution according to the technical idea proposed by the present invention falls within the protection scope of the claims of the present invention.

Claims

1. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment, characterized in that: The following steps are involved: Step 1: Obtain multiple fault currents within the fault current range of the arc fault inside the oil-filled main equipment ; Step 2: Establish a three-dimensional geometric simulation model of the oil filling main equipment, and establish a grid model of the oil filling main equipment based on the three-dimensional geometric simulation model of the oil filling main equipment; Step 3: Call the transient pressure-based solver to perform fluid-solid coupling calculations on the main oil-filled equipment; S1, based on multiple fault currents , the oil pressure increase process inside the oil-filled main equipment is simulated in the grid model of the oil-filled main equipment to reflect different fault currents Oil pressure changes under certain conditions; S2, simulate the turbulence phenomenon caused by the dynamic changes of the fluid inside the oil-filled main equipment, and set the turbulence phenomenon of the oil-filled main equipment to Model; S3, according to the oil pressure changes and The model obtains the oil pressure load; S4. Input the oil pressure load into the solid calculation domain of the oil-filled main equipment to obtain the displacement vectors of the grid points of the grid model of the oil-filled main equipment in the x, y and z directions. , through the displacement vector , obtain the principal strains of the mesh model of the oil-filled main equipment in the x, y and z directions , and ; S5. According to the main strain of the mesh model of the oil-filled main equipment in the x, y and z directions , and Determine whether the main oil-filled equipment is broken. If broken, record the main oil-filled equipment at different fault currents. If no rupture occurs, the system will re-enter S1. Step 4: According to the different fault currents of the oil-filled main equipment Based on the convolutional neural network, a neural network model of fault current and allowable fault tolerance time is established to output the allowable fault tolerance time of the oil-filled main equipment under different fault currents. The allowable fault tolerance time result.

2. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment according to claim 1, characterized in that: In the step 2, the method for establishing the grid model of the oil-filling main equipment is specifically: using a progressive size function to discretize the three-dimensional geometric simulation model of the oil-filling main equipment, gradually reducing the grid diameter near the boundaries, corners and curves, and gradually increasing the grid diameter as the distance increases.

3. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment according to claim 1, characterized in that: The oil pressure increase process inside the oil filling main equipment is simulated in the grid model of the oil filling main equipment, and the oil pressure increase process inside the oil filling main equipment is simulated using bubble dynamics. The bubble dynamics equation is: In the formula, represents the radius of the bubble, is the normal velocity of the bubble surface, represents the normal acceleration of the bubble surface; Indicates the density of insulating oil, represents the pressure at the boundary of the fluid domain, represents the heat transfer coefficient, represents the specific heat ratio, represents the fluid dynamic viscosity, represents the surface tension of the fluid, represents the external work done by the bubble surface during the bubble expansion process, It means that the surface tension does work on the outside during the bubble expansion process. It means that the viscous force does work externally during the bubble expansion process. represents the initial internal energy of the bubble, Arc energy The calculation formula is: In the formula, Indicates the fault current, Indicates the fault current The corresponding arc voltage, Indicates the fault duration.

4. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment according to claim 1, characterized in that: The method for simulating the turbulence phenomenon caused by the dynamic change of the fluid inside the oil-filled main device is specifically: using a dynamic grid to update the instantaneous fluid field inside the oil-filled main device, and simulating the turbulence phenomenon caused by the dynamic change of the fluid caused by the expansion of bubbles inside the oil-filled main device by capturing the flow characteristics and transient changes of physical quantities of the fluid during the structural change of the oil-filled main device. The calculation formula is: In the formula, represents the time derivative, is the density of the fluid, u is the velocity vector, is the area vector, is the diffusion coefficient, express The source term of is the turbulence characteristic quantity, is the mesh speed of the moving mesh, is the control volume, is the vector differential operator, Turbulence characteristic quantity The gradient of is the control volume the border.

5. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment according to claim 4, characterized in that: The dynamic mesh update uses the Laplace smoothing model, and the calculation formula of the Laplace smoothing model is: In the formula, Representation Node i The new location, Representation Node The number of adjacent nodes of Is an adjacent node location.

6. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment according to claim 1, characterized in that: Set the turbulence phenomenon of the oil-filled main equipment to Model, which sets the equation: In the formula, represents the turbulent kinetic energy, Turbulent kinetic energy The differential change of represents the time differential, Represents spatial coordinates The differential of represents the symbol of partial derivative, represents the turbulent kinetic energy, The turbulent Prandtl number, represents the turbulence specific dissipation rate, represents the turbulence specific dissipation rate The turbulent Prandtl number, represents the average velocity of the fluid, represents the specific dissipation rate, represents the molecular viscosity, represents the turbulent viscosity, The Prandtl number representing the kinetic energy equation, represents the generation term of turbulent kinetic energy, which is generated by shear stress, represents the magnitude of the strain rate, and represents the model constant, Is an adjacent node location.

7. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment according to claim 1, characterized in that: According to the oil pressure changes and The model obtains the oil pressure load, which needs to be further calculated through the momentum equation. The calculation formula of the momentum equation is: In the formula, is the dynamic viscosity, represents the external force vector per unit volume acting on the fluid, It's pressure. is the density of the fluid, is the flow rate of the fluid inside the oil-filled main equipment, Represents the dot product operation of the vector field on the vector micromolecule; the pressure is solved by iteratively solving the momentum equation and the flow rate of the fluid inside the oil-filled main equipment , through the pressure and the flow rate of the fluid inside the oil-filled main equipment The pressure distribution is obtained by coupling and compared with the oil pressure change and The models are combined to obtain the oil pressure load.

8. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment according to claim 1, characterized in that: The displacement vectors of the grid points of the oil-filled main equipment grid model in the x, y and z directions It is obtained through explicit dynamics calculation. The specific calculation method is: use the central difference method to perform discrete integration of acceleration, velocity and displacement in time steps to obtain the displacement vector of the grid point of the grid model of the oil-filled main equipment , The displacement of the grid points of the oil-filled main equipment grid model in the x direction, The displacement of the grid points of the oil-filled main equipment grid model in the y direction, The displacement of the grid points of the oil-filled main equipment grid model in the z direction, and the principal strains of the oil-filled main equipment grid model in the x, y and z directions , and The strain calculation formula is: .

9. A method for evaluating the internal fault tolerance time of a large oil-filled main equipment according to claim 1, characterized in that: The method for judging whether the oil-filled main device is broken is specifically: judging whether the oil-filled main device is broken according to the constant strain failure criterion, and the calculation formula for the judgment is: In the formula, represents the failure strain, represents the equivalent plastic strain. If the equivalent plastic strain >Failure strain , then the oil-filled main equipment breaks. If the equivalent plastic strain ≤Failure strain , the main oil-filled equipment has not been broken.

10. A method for evaluating internal fault tolerance time of large oil-filled main equipment according to claim 1, characterized in that: The method is based on a convolutional neural network to establish a neural network model of fault current and allowable fault tolerance time. Specifically, the obtained allowable fault tolerance time data under different fault current conditions are used as input values, and the data are trained by a convolutional neural network to generate a neural network model of the relationship between the fault current and the allowable fault tolerance time. The convolutional neural network includes a convolutional layer, a pooling layer, and a fully connected layer. The convolutional layer is used for different fault currents. The corresponding allowable fault tolerance time data is used for feature extraction. The pooling layer optimizes the extracted features. The fully connected layer maps the optimized feature data between the fault current and the allowable fault tolerance time. The calculation formula for feature extraction by the convolution layer is: In the formula, Indicates k The feature quantity is at the position ( i , j ), Indicates that the input data is at position The value at Indicates that the convolution kernel is k The weight matrix of the channel, Represents the bias term; the calculation of the pooling layer to optimize the extracted features includes average pooling and maximum pooling. The calculation formulas of average pooling and maximum pooling are as follows: in represents average pooling, represents the maximum pooling, N represents the dimension of the convolution kernel, It represents the data points in the pooled area. The fully connected layer maps the optimized feature data between the fault current and the allowable fault tolerance time, using the Softmax function, and its calculation formula is as follows: In the formula, It is the fully connected layer j The output of a neuron, and b Represent the weight and bias respectively, represents the i-th optimized feature data output by the pooling layer, and Represents the j The output probability corresponding to a neuron in Softmax is, is the probability distribution in the Softmax function.

Images