A switch cabinet model compression and reconstruction method and system and a monitoring terminal

Abstract

The application belongs to the technical field of computers and provides a switch cabinet model compression and reconstruction method and system and a monitoring terminal, and the technical scheme is as follows: space node compression is realized through model grid coarsening and dictionary tree deduplication algorithm; and temperature reconstruction of dimension reduction model space nodes is realized by using KNN algorithm. Firstly, the grid coarsening technology is used to compress the space nodes of the switch cabinet model, thereby reducing the number of nodes; secondly, the dictionary tree deduplication algorithm is used to eliminate the redundant information in the model, thereby avoiding repeated storage and further compressing the size of the model; finally, the KNN algorithm is used in combination with the nodes and temperature data of the fine grid model to construct the temperature characteristics of the dimension reduction model space nodes, and through the overall reconstruction algorithm, the repair and optimization of the model after dimension reduction are realized. Compared with the prior art, the application can effectively reduce the storage space and calculation complexity of the switch cabinet model and improve the operation efficiency and simulation accuracy of the system.

Description

Technical Field

[0001] This invention belongs to the field of computer technology, and in particular relates to a method, system and monitoring terminal for compressing and reconstructing switchgear models. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] High-voltage switchgear, as a crucial piece of equipment in power systems, requires online monitoring to intuitively control its operational status. Switchgear digital twins utilize advanced computer modeling and simulation technologies to map the physical switchgear to a digital model, enabling real-time monitoring, prediction, and optimization. Through digital twins, full lifecycle management of the switchgear can be achieved, including all stages such as design, manufacturing, operation, and maintenance. During operation, the switchgear generates heat through resistive losses, ferromagnetic losses, and dielectric losses, which is dissipated through heat conduction, convection, and radiation, thus stabilizing the internal temperature of the switchgear.

[0004] Faced with the problem of numerous internal components and complex structure of switchgear, the increased dimensionality of the problem significantly increases the number of sample points and time required to build the surrogate model. This reduces the accuracy of the surrogate model to some extent, affects the reliability of the information it provides, and leads to a decline in the surrogate model's auxiliary capabilities. In summary, this reduces the efficiency and accuracy of system simulation. Summary of the Invention

[0005] To address at least one of the technical problems mentioned above, this invention provides a method, system, and monitoring terminal for compressing and reconstructing switchgear models. By combining data dimensionality reduction methods with proxy models, the operating efficiency and prediction performance of the models for high-dimensional complex problems can be improved.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] The first aspect of this invention provides a method for compressing and reconstructing a switchgear model, comprising the following steps:

[0008] Obtain the 3D model of the switchgear before compression;

[0009] The first mesh division result is obtained by performing a first mesh division on the three-dimensional model of the switch cabinet before compression. Hot spot coupling simulation is performed on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data.

[0010] The second mesh is divided into two grids to obtain the second mesh division result. The second spatial node data of the second mesh division result is traversed, a trie is inserted into the second spatial node data, and the third spatial node data is obtained by compression.

[0011] By combining the data from the first spatial node, temperature data, and third spatial node, node reconstruction is performed to obtain the node temperature reconstruction data of the three-dimensional model of the switchgear.

[0012] Further, the first mesh generation result obtained by performing a first mesh generation on the three-dimensional model of the switchgear includes:

[0013] The spatial nodes of the 3D model of the switchgear are compressed using model mesh coarsening technology. First, the component mesh is coarsened in the first step. Based on the first step of coarsening, the structural components that are not affected by the simulation temperature are coarsened in the second step to obtain the first mesh division result.

[0014] Furthermore, when performing hotspot coupling simulation on the first grid division result, the temperature field control equation is used for simulation.

[0015] Furthermore, the step of inserting a trie into the second spatial node data and compressing it to obtain the third spatial node data includes:

[0016] In the second spatial node data, each spatial node corresponds to a three-dimensional coordinate (X,Y,Z). Each spatial node corresponding to a three-dimensional coordinate can be regarded as a string consisting of three characters.

[0017] Traverse the spatial nodes, starting from the root node X and continuing to the target node Z, to obtain the string of the corresponding spatial node;

[0018] By integrating repeatedly traversed spatial nodes with the same string, the common points of the strings can be used to reduce traversal and query time;

[0019] Traverse the second space node again, insert it into the trie, and then query all trie paths to obtain the third space node data.

[0020] Furthermore, the node reconstruction process, which combines the first spatial node, temperature data, and third spatial node data, includes:

[0021] The first spatial node, temperature data, and third spatial node data are used as the training and test datasets, respectively. The K-fold cross-validation method is used to divide the dataset evenly into K subsets. Each time, one subset is selected as the validation set, and the remaining K-1 subsets are used as the training set. The node temperature reconstruction model is trained based on the training set, and prediction and evaluation are performed on the validation set.

[0022] Furthermore, the construction process of the node temperature reconstruction model includes:

[0023] In the set consisting of the first spatial node and temperature data, the KNN algorithm is used to find the K-nearest neighbor samples of the third spatial node data through nearest neighbor search.

[0024] Based on the K-nearest neighbor samples of the third spatial node data, the temperature of the third spatial node data is predicted by combining the Gaussian kernel function RBF interpolation, and the corresponding temperature prediction value is obtained.

[0025] Based on the corresponding temperature prediction values, the temperature reconstruction results of the third spatial node data are obtained. A second aspect of this invention provides a system for compressing and reconstructing a three-dimensional model of a switchgear, comprising:

[0026] The data extraction module is used to perform a first mesh division on the three-dimensional model of the switch cabinet before compression to obtain the first mesh division result, and to perform hot spot coupling simulation on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes first spatial node data and temperature data.

[0027] The model compression model is used to perform a second mesh division on the 3D model of the switch cabinet to obtain the second mesh division result, traverse the second spatial node data of the second mesh division result, insert a trie into the second spatial node data, and compress to obtain the third spatial node data.

[0028] The model reconstruction module is used to combine the first spatial node, temperature data and the third spatial node data to reconstruct the nodes and obtain the temperature reconstruction data of the three-dimensional model of the switchgear.

[0029] In the data extraction module, the step of performing a first mesh division on the 3D model of the switchgear to obtain the first mesh division result includes:

[0030] The spatial nodes of the 3D model of the switchgear are compressed using model mesh coarsening technology. First, the component mesh is coarsened in the first step. Based on the first step of coarsening, the structural components that are not affected by the simulation temperature are coarsened in the second step to obtain the first mesh division result.

[0031] The step of inserting a trie into the second spatial node data and compressing it to obtain the third spatial node data includes:

[0032] In the model compression model, in the second spatial node data, each spatial node corresponds to a three-dimensional coordinate (X,Y,Z). Each spatial node corresponding to a three-dimensional coordinate is regarded as a string composed of three characters.

[0033] Traverse the spatial nodes, starting from the root node X and continuing to the target node Z, to obtain the string of the corresponding spatial node;

[0034] By integrating repeatedly traversed spatial nodes with the same string, the common points of the strings can be used to reduce traversal and query time;

[0035] Traverse the second space node again, insert it into the trie, and then query all trie paths to obtain the third space node data.

[0036] In the model reconstruction module, the node reconstruction process, which combines the first spatial node, temperature data, and third spatial node data, includes:

[0037] The first spatial node, temperature data, and third spatial node data are used as the training and test datasets, respectively. The K-fold cross-validation method is used to divide the dataset evenly into K subsets. Each time, one subset is selected as the validation set, and the remaining K-1 subsets are used as the training set. The node temperature reconstruction model is trained based on the training set, and prediction and evaluation are performed on the validation set.

[0038] The construction process of the node temperature reconstruction model includes:

[0039] In the set consisting of the first spatial node and temperature data, the KNN algorithm is used to find the K-nearest neighbor samples of the third spatial node data through nearest neighbor search.

[0040] Based on the K-nearest neighbor samples of the third spatial node data, the temperature of the third spatial node data is predicted by combining the Gaussian kernel function RBF interpolation, and the corresponding temperature prediction value is obtained.

[0041] Based on the corresponding temperature prediction values, the temperature reconstruction results of the third spatial node data are obtained.

[0042] A third aspect of the present invention provides a switchgear monitoring terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the steps of the switchgear model compression and reconstruction method described in the first aspect:

[0043] Obtain the 3D model of the switchgear before compression;

[0044] The first mesh division result is obtained by performing a first mesh division on the three-dimensional model of the switch cabinet before compression. Hot spot coupling simulation is performed on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data.

[0045] The second mesh is divided into two grids to obtain the second mesh division result. The second spatial node data of the second mesh division result is traversed, a trie is inserted into the second spatial node data, and the third spatial node data is obtained by compression.

[0046] By combining the data from the first spatial node, temperature data, and third spatial node, node reconstruction is performed to obtain the node temperature reconstruction data of the three-dimensional model of the switchgear.

[0047] A fourth aspect of the present invention provides a computer-readable storage medium.

[0048] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the compression and reconstruction of a switchgear model as described in the first aspect:

[0049] Obtain the 3D model of the switchgear before compression;

[0050] The first mesh division result is obtained by performing a first mesh division on the three-dimensional model of the switch cabinet before compression. Hot spot coupling simulation is performed on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data.

[0051] The second mesh is divided into two grids to obtain the second mesh division result. The second spatial node data of the second mesh division result is traversed, a trie is inserted into the second spatial node data, and the third spatial node data is obtained by compression.

[0052] By combining the data from the first spatial node, temperature data, and third spatial node, node reconstruction is performed to obtain the node temperature reconstruction data of the three-dimensional model of the switchgear.

[0053] A fifth aspect of the present invention provides a computer device.

[0054] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps in the switch cabinet model compression and reconstruction as described in the first aspect:

[0055] Obtain the 3D model of the switchgear before compression;

[0056] The first mesh division result is obtained by performing a first mesh division on the three-dimensional model of the switch cabinet before compression. Hot spot coupling simulation is performed on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data.

[0057] The second mesh is divided into two grids to obtain the second mesh division result. The second spatial node data of the second mesh division result is traversed, a trie is inserted into the second spatial node data, and the third spatial node data is obtained by compression.

[0058] By combining the data from the first spatial node, temperature data, and third spatial node, node reconstruction is performed to obtain the node temperature reconstruction data of the three-dimensional model of the switchgear.

[0059] Compared with the prior art, the beneficial effects of the present invention are:

[0060] 1. This invention designs a method for reconstructing the temperature of spatial nodes in a switchgear model. By using a prediction algorithm and combining the data information of a refined mesh model, the temperature characteristics of spatial nodes are constructed, thereby achieving the repair and optimization of the model after dimensionality reduction. This improves the speed and accuracy of switchgear model simulation and greatly facilitates subsequent research on switchgear thermoelectric field coupling simulation, condition monitoring, and fault diagnosis.

[0061] 2. This invention designs a spatial node compression method for switchgear models. By using mesh coarsening and trie deduplication techniques, the data volume of switchgear models can be significantly reduced, improving the compactness of the data structure and query efficiency. When processing large-scale models, it can improve computational efficiency and reduce operating costs.

[0062] 3. When dealing with switchgear models, this invention is not limited to a specific size or structure, and is applicable to switchgear models of varying complexity. Therefore, it has a wide range of applications and good scalability.

[0063] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0064] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0065] Figure 1 A flowchart of the switchgear model compression and spatial node temperature reconstruction method provided in this embodiment of the invention;

[0066] Figure 2 This is a schematic diagram of the switchgear model mesh provided in an embodiment of the present invention;

[0067] Figure 3 This is a flowchart illustrating the construction process of temperature nodes in a dimensionality reduction model provided in an embodiment of the present invention.

[0068] Figure 4 This is a schematic diagram of the dimensionality reduction model reconstruction with different K values ​​provided in the embodiments of the present invention. Detailed Implementation

[0069] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0070] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0071] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0072] This invention addresses the issue of generating heat and dissipating it through heat conduction, convection, and radiation to stabilize the temperature inside the switchgear. However, given the large number of components and complex structures within the switchgear, the increased complexity of the problem significantly increases the number of sample points and time required to build the proxy model. This reduces the accuracy of the proxy model, affects the reliability of the information it provides, and ultimately diminishes its auxiliary capabilities.

[0073] This invention designs a method for reconstructing the temperature of spatial nodes in a switchgear model. By using a prediction algorithm and combining data information from a refined mesh model, the temperature characteristics of spatial nodes are constructed, thereby achieving the repair and optimization of the model after dimensionality reduction. This improves the speed and accuracy of switchgear model simulation and greatly facilitates subsequent research on thermoelectric field coupling simulation, condition monitoring, and fault diagnosis of switchgear.

[0074] This invention designs a spatial node compression method for switchgear models. By using mesh coarsening and trie deduplication techniques, the data volume of switchgear models can be significantly reduced, improving the compactness of the data structure and query efficiency. When processing large-scale models, it can improve computational efficiency and reduce operating costs.

[0075] This invention is not limited to a specific size or structure when dealing with switchgear models; it is applicable to switchgear models of varying complexity. Therefore, it has a wide range of applications and good scalability.

[0076] Example 1

[0077] This embodiment provides a method for compressing and reconstructing a switchgear model. The aim is to reduce the dimensionality of the refined mesh model of the switchgear and reconstruct the node temperatures, thereby achieving a lightweight switchgear model and significantly improving the efficiency of system simulation. The execution flow of this method is as follows: Figure 1 As shown, it includes the following steps:

[0078] S101: Perform a first mesh division on the three-dimensional model of the switch cabinet to obtain the first mesh division result. Perform hot spot coupling simulation on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data.

[0079] S102: Perform a second mesh generation on the 3D model of the switchgear to obtain the second mesh generation result;

[0080] S103: Traverse the second spatial node data of the second grid partitioning result, insert a trie into the second spatial node data, and compress to obtain the third spatial node data;

[0081] S104: Combine the first spatial node, temperature data and the third spatial node data to reconstruct the nodes and obtain the temperature reconstruction data of the three-dimensional model of the switchgear.

[0082] To more clearly illustrate the technical solution of the present invention, specific embodiments are described below.

[0083] In S101, the three-dimensional model of the switchgear is finely meshed, and the internal temperature distribution of the model is obtained through thermo-electric coupling simulation based on the temperature field control equation. Based on the internal temperature distribution of the model, the spatial nodes and temperature data are exported.

[0084] The temperature field refers to the temperature distribution at each node in space, described by mathematical equations. The governing equations of the temperature field describe its evolution and variation.

[0085] The governing equation for temperature is described by the heat conduction equation, and its formula is:

[0086] Where T is the temperature field and α is the thermal diffusivity. Let S be the Laplace operator, and let S be the heat source term.

[0087] Specifically, this includes: using model mesh coarsening technology to compress the spatial nodes of the 3D model of the switchgear, firstly coarsening the component mesh, and then coarsening the structural components that are unaffected by the simulation temperature to obtain the first mesh division result.

[0088] like Figure 2 As shown, when the 3D model of the switch cabinet is coarsened to obtain the coarsened mesh, the mesh of components such as busbars, cables, and insulating supports is appropriately coarsened, while the mesh of structural components such as the cabinet body that have no effect on the simulation temperature is coarsened to a greater extent.

[0089] In S102, a second mesh is generated on the 3D model of the switchgear. The purpose of this second mesh is to retain a more refined mesh for key parts of the switchgear model (busbars, cables, insulating supports, contact surfaces of different components, etc.) and specific areas that experience abnormal heating during actual operation. It also accurately captures and preserves the geometric features of the switchgear model at the boundaries of parts, ensuring the continuity of the boundaries.

[0090] In S103, the step of inserting the trie into the second spatial node data and compressing it to obtain the third spatial node data includes:

[0091] The second spatial node (X,Y,Z) is considered as a string consisting of three characters, and the path from the root node X to the target node Z forms the spatial node coordinates.

[0092] Based on the coordinates of the spatial nodes, query all trie paths and perform node deduplication and compression.

[0093] Specifically, it includes:

[0094] In the second spatial node data, each spatial node corresponds to a three-dimensional coordinate (X,Y,Z). Each spatial node corresponding to a three-dimensional coordinate can be regarded as a string consisting of three characters.

[0095] Traverse the spatial nodes, starting from the root node X and continuing to the target node Z, to obtain the string of the corresponding spatial node;

[0096] By integrating repeatedly traversed spatial nodes with the same string, the common points of the strings can be used to reduce traversal and query time;

[0097] The second space node is traversed again, inserted into the trie, and then all trie paths are queried to obtain the third space node data, thus completing the node deduplication and compression.

[0098] like Figure 3 As shown, in S104, the node reconstruction process, which combines the first spatial node, temperature data, and third spatial node data, includes:

[0099] The first spatial node, temperature data, and third spatial node data are used as the training and test datasets, respectively. The K-fold cross-validation method is used to divide the dataset evenly into K subsets. Each time, one subset is selected as the validation set, and the remaining K-1 subsets are used as the training set. The node temperature reconstruction model is trained based on the training set, and prediction and evaluation are performed on the validation set.

[0100] The construction process of the node temperature reconstruction model includes:

[0101] In the set consisting of the first spatial node and temperature data, the KNN algorithm is used to find the K-nearest neighbor samples of the third spatial node data through nearest neighbor search.

[0102] Based on the K-nearest neighbor samples of the third spatial node data, the temperature of the third spatial node data is predicted by combining the Gaussian kernel function RBF interpolation, and the corresponding temperature prediction value is obtained.

[0103] Based on the corresponding temperature prediction values, the temperature reconstruction results of the third spatial node data are obtained.

[0104] For each K value to be tried, train the model using the training set and make predictions and evaluations on the validation set. Calculate the performance metrics of the model on the validation set for each K value, such as accuracy and F1 score, and select the K value with the best performance metrics as the optimal K value.

[0105] The nodes of the dimensionality reduction model are predicted by selecting sample points and using Gaussian radial basis interpolation. The reliability is used to evaluate the topological similarity between the dimensionality reduction space and the original space, and the continuity is used to evaluate the preservation of neighborhood relations of the original space by the dimensionality reduction space.

[0106] Using simulation data of switchgear under ambient temperature as training samples, the model was validated for different K values. The resulting dimensionality reduction model was then used to reconstruct the cloud map. A suitable K value was selected and combined with Gaussian radial basis interpolation to predict the temperature of the dimensionality-reduced nodes, thus completing the spatial node temperature reconstruction. Figure 4 As shown, Figure 4 In the diagrams (a)-(f), we get schematic diagrams of dimensionality reduction model reconstruction with different K values. The output result is the temperature reconstruction of the nodes in the dimensionality reduction model.

[0107] By combining the data information of the refined mesh model with the technical solution of this invention, the temperature characteristics of the spatial nodes are constructed, and the repair and optimization of the model after dimensionality reduction are realized. This improves the speed and accuracy of switchgear model simulation and provides great convenience for subsequent research on switchgear thermoelectric field coupling simulation, condition monitoring, fault diagnosis, etc.

[0108] Example 2

[0109] This embodiment provides a switchgear model compression and reconstruction system, including:

[0110] The switchgear 3D model acquisition module is used to acquire the switchgear 3D model before compression.

[0111] The data extraction module is used to perform a first mesh division on the three-dimensional model of the switch cabinet before compression to obtain the first mesh division result, and to perform hot spot coupling simulation on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes first spatial node data and temperature data.

[0112] The model compression model is used to perform a second mesh division on the 3D model of the switch cabinet to obtain the second mesh division result, traverse the second spatial node data of the second mesh division result, insert a trie into the second spatial node data, and compress to obtain the third spatial node data.

[0113] The model reconstruction module is used to combine the first spatial node, temperature data and the third spatial node data to reconstruct the nodes and obtain the temperature reconstruction data of the three-dimensional model of the switchgear.

[0114] In the data extraction module, the step of performing a first mesh division on the 3D model of the switchgear to obtain the first mesh division result includes:

[0115] The spatial nodes of the 3D model of the switchgear are compressed using model mesh coarsening technology. First, the component mesh is coarsened in the first step. Based on the first step of coarsening, the structural components that are not affected by the simulation temperature are coarsened in the second step to obtain the first mesh division result.

[0116] The step of inserting a trie into the second spatial node data and compressing it to obtain the third spatial node data includes:

[0117] In the model compression model, in the second spatial node data, each spatial node corresponds to a three-dimensional coordinate (X,Y,Z). Each spatial node corresponding to a three-dimensional coordinate is regarded as a string composed of three characters.

[0118] Traverse the spatial nodes, starting from the root node X and continuing to the target node Z, to obtain the string of the corresponding spatial node;

[0119] By integrating repeatedly traversed spatial nodes with the same string, the common points of the strings can be used to reduce traversal and query time;

[0120] Traverse the second space node again, insert it into the trie, and then query all trie paths to obtain the third space node data.

[0121] In the model reconstruction module, the node reconstruction process, which combines the first spatial node, temperature data, and third spatial node data, includes:

[0122] The first spatial node, temperature data, and third spatial node data are used as the training and test datasets, respectively. The K-fold cross-validation method is used to divide the dataset evenly into K subsets. Each time, one subset is selected as the validation set, and the remaining K-1 subsets are used as the training set. The node temperature reconstruction model is trained based on the training set, and prediction and evaluation are performed on the validation set.

[0123] The construction process of the node temperature reconstruction model includes:

[0124] In the set consisting of the first spatial node and temperature data, the KNN algorithm is used to find the K-nearest neighbor samples of the third spatial node data through nearest neighbor search.

[0125] Based on the K-nearest neighbor samples of the third spatial node data, the temperature of the third spatial node data is predicted by combining the Gaussian kernel function RBF interpolation, and the corresponding temperature prediction value is obtained.

[0126] Based on the corresponding temperature prediction values, the temperature reconstruction results of the third spatial node data are obtained.

[0127] Example 3

[0128] This embodiment provides a switchgear monitoring terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the switchgear model compression and reconstruction method described in the first embodiment: obtaining the three-dimensional model of the switchgear before compression.

[0129] The first mesh division result is obtained by performing a first mesh division on the three-dimensional model of the switch cabinet before compression. Hot spot coupling simulation is performed on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data.

[0130] The second mesh is divided into two grids to obtain the second mesh division result. The second spatial node data of the second mesh division result is traversed, a trie is inserted into the second spatial node data, and the third spatial node data is obtained by compression.

[0131] By combining the data from the first spatial node, temperature data, and third spatial node, node reconstruction is performed to obtain the node temperature reconstruction data of the three-dimensional model of the switchgear.

[0132] Example 4

[0133] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the switch cabinet model compression and reconstruction method described in Embodiment 1:

[0134] Obtain the 3D model of the switchgear before compression;

[0135] The first mesh division result is obtained by performing a first mesh division on the three-dimensional model of the switch cabinet before compression. Hot spot coupling simulation is performed on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data.

[0136] The second mesh is divided into two grids to obtain the second mesh division result. The second spatial node data of the second mesh division result is traversed, a trie is inserted into the second spatial node data, and the third spatial node data is obtained by compression.

[0137] By combining the data from the first spatial node, temperature data, and third spatial node, node reconstruction is performed to obtain the node temperature reconstruction data of the three-dimensional model of the switchgear.

[0138] Example 5

[0139] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the switch cabinet model compression and reconstruction method described in Embodiment 1:

[0140] Obtain the 3D model of the switchgear before compression;

[0141] The first mesh division result is obtained by performing a first mesh division on the three-dimensional model of the switch cabinet before compression. Hot spot coupling simulation is performed on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data.

[0142] The second mesh is divided into two grids to obtain the second mesh division result. The second spatial node data of the second mesh division result is traversed, a trie is inserted into the second spatial node data, and the third spatial node data is obtained by compression.

[0143] By combining the data from the first spatial node, temperature data, and third spatial node, node reconstruction is performed to obtain the node temperature reconstruction data of the three-dimensional model of the switchgear.

[0144] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0145] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0146] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0148] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0149] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for compressing and reconstructing a switchgear model, characterized in that, Includes the following steps: Obtain the 3D model of the switchgear before compression; The first mesh division result is obtained by performing a first mesh division on the three-dimensional model of the switch cabinet before compression. Hot spot coupling simulation is performed on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes the first spatial node data and temperature data. The 3D model of the switchgear is divided into a second mesh to obtain the second mesh division result. The second spatial node data of the second mesh division result is traversed, a trie is inserted into the second spatial node data, and the data is compressed to obtain the third spatial node data, which specifically includes: In the second spatial node data, each spatial node corresponds to a three-dimensional coordinate (X,Y,Z). Each spatial node corresponding to a three-dimensional coordinate can be regarded as a string consisting of three characters. Traverse the spatial nodes, starting from the root node X and continuing to the target node Z, to obtain the string of the corresponding spatial node; By integrating repeatedly traversed spatial nodes with the same string, the common points of the strings can be used to reduce traversal and query time; Traverse the second space node again, insert it into the trie, and then query all trie paths to obtain the third space node data; By combining the data from the first spatial node, temperature data, and third spatial node data, node reconstruction is performed to obtain the temperature reconstruction data of the switchgear 3D model nodes, specifically including: The first spatial node, temperature data, and third spatial node data are used as the training and test datasets, respectively. The K-fold cross-validation method is used to divide the dataset evenly into K subsets. Each time, one subset is selected as the validation set, and the remaining K-1 subsets are used as the training set. The node temperature reconstruction model is trained based on the training set, and prediction and evaluation are performed on the validation set. The construction process of the node temperature reconstruction model includes: In the set consisting of the first spatial node and temperature data, the KNN algorithm is used to find the K-nearest neighbor samples of the third spatial node data through nearest neighbor search. Based on the K-nearest neighbor samples of the third spatial node data, the temperature of the third spatial node data is predicted by combining the Gaussian kernel function RBF interpolation, and the corresponding temperature prediction value is obtained. Based on the corresponding temperature prediction values, the temperature reconstruction results of the third spatial node data are obtained.

2. The method for compressing and reconstructing a switchgear model as described in claim 1, characterized in that, The process of performing a first mesh division on the 3D model of the switchgear to obtain the first mesh division result includes: The spatial nodes of the 3D model of the switchgear are compressed using model mesh coarsening technology. First, the component mesh is coarsened in the first step. Based on the first step of coarsening, the structural components that are not affected by the simulation temperature are coarsened in the second step to obtain the first mesh division result.

3. The method for compressing and reconstructing a switchgear model as described in claim 1, characterized in that, When performing hotspot coupling simulation on the first grid division result, the temperature field domain control equation is used for simulation.

4. A switchgear model compression and reconstruction system, characterized in that, include: The data extraction module is used to perform a first mesh division on the three-dimensional model of the switch cabinet before compression to obtain the first mesh division result, and to perform hot spot coupling simulation on the first mesh division result to obtain the internal temperature distribution of the model. The internal temperature distribution includes first spatial node data and temperature data. The model compression model is used to perform second mesh generation on the 3D model of the switchgear to obtain the second mesh generation result. It then traverses the second spatial node data of the second mesh generation result, inserts a trie into the second spatial node data, and compresses it to obtain the third spatial node data. Specifically, this includes: In the second spatial node data, each spatial node corresponds to a three-dimensional coordinate (X,Y,Z). Each spatial node corresponding to a three-dimensional coordinate can be regarded as a string consisting of three characters. Traverse the spatial nodes, starting from the root node X and continuing to the target node Z, to obtain the string of the corresponding spatial node; By integrating repeatedly traversed spatial nodes with the same string, the common points of the strings can be used to reduce traversal and query time; Traverse the second space node again, insert it into the trie, and then query all trie paths to obtain the third space node data; The model reconstruction module is used to reconstruct nodes by combining the first spatial node data, temperature data, and third spatial node data to obtain the temperature reconstruction data of the switchgear 3D model nodes. Specifically, it includes: The first spatial node, temperature data, and third spatial node data are used as the training and test datasets, respectively. The K-fold cross-validation method is used to divide the dataset evenly into K subsets. Each time, one subset is selected as the validation set, and the remaining K-1 subsets are used as the training set. The node temperature reconstruction model is trained based on the training set, and prediction and evaluation are performed on the validation set. The construction process of the node temperature reconstruction model includes: In the set consisting of the first spatial node and temperature data, the KNN algorithm is used to find the K-nearest neighbor samples of the third spatial node data through nearest neighbor search. Based on the K-nearest neighbor samples of the third spatial node data, the temperature of the third spatial node data is predicted by combining the Gaussian kernel function RBF interpolation, and the corresponding temperature prediction value is obtained. Based on the corresponding temperature prediction values, the temperature reconstruction results of the third spatial node data are obtained.

5. The switchgear model compression and reconstruction system as described in claim 4, characterized in that, The method for compressing and reconstructing a switchgear model as described in any one of claims 1-3 includes: obtaining a first mesh division result by performing a first mesh division on the three-dimensional model of the switchgear, including: The spatial nodes of the 3D model of the switchgear are compressed using model mesh coarsening technology. First, the component mesh is coarsened in the first step. Based on the first step of coarsening, the structural components that are not affected by the simulation temperature are coarsened in the second step to obtain the first mesh division result.

6. The switchgear model compression and reconstruction system as described in claim 4, characterized in that, The method for compressing and reconstructing a switchgear model as described in any one of claims 1-3 includes: when performing hotspot coupling simulation on the first mesh division result, using the temperature field control equation for simulation.

7. A switchgear monitoring terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps in the switch cabinet model compression and reconstruction method as described in any one of claims 1-3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the switch cabinet model compression and reconstruction method as described in any one of claims 1-3.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the switch cabinet model compression and reconstruction method as described in any one of claims 1-3.

Images