A cloud-edge collaborative GIS shell temperature change behavior rapid simulation method and system

Abstract

The present invention provides a cloud-edge collaborative rapid simulation method and system for GIS shell temperature variation behavior. The cloud-edge collaborative rapid simulation system for GIS shell temperature variation behavior includes intelligent acquisition terminal management, simulation model library management, data analysis, visualization, and operational status warnings. The intelligent acquisition terminal management is used to collect GIS temperature displacement data. After simulation using a model library model through a collaborative strategy, the simulation results are analyzed to determine whether a warning is needed, and finally the results are visualized. By leveraging the collaborative efforts of cloud computing and edge computing, the timeliness of GIS shell temperature variation behavior simulation is ensured, reducing the computational burden of cloud computing and improving simulation efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of substation GIS status diagnosis, and in particular to a cloud-edge collaborative GIS shell temperature change behavior rapid simulation method and system. Background Art

[0002] The operating temperature of outdoor GIS equipment in power plants and stations varies. As the temperature changes, the cylinder of the GIS equipment is bound to expand and contract, causing horizontal displacement of the horizontal cylinder axis. The bellows, as the elastic connection between two adjacent busbar barrels, has the functions of adjusting the on-site installation size and compensating for horizontal temperature displacement. However, in actual projects, due to poor construction quality, unreasonable configuration of the bellows and busbar barrel support legs, or product design problems, the performance of the bellows displacement compensation function is easily reduced or lost. When the bellows cannot compensate for the displacement, stress will be released at weak structural points such as the equipment busbar barrel flange connection, the connection between the busbar barrel and the switchgear, and the busbar barrel legs. There is a risk of causing serious consequences such as equipment leakage, leg breakage, and busbar barrel displacement. It is necessary to develop a rapid simulation method and system for the temperature change behavior of the GIS shell.

[0003] In recent years, cloud computing has achieved rapid development. Based on technologies such as cloud computing, 4G communications, and the Internet of Things, combined with the response surface analysis method, a computational model is created. Through the development of cloud computing technology, a cloud-edge collaborative GIS shell temperature change behavior rapid simulation system is created, providing more reliable, efficient, and convenient technical means for GIS equipment operation and maintenance.

[0004] For example, a Chinese patent document, "A Calculation Method for High-Temperature Deformation of a Heating Plate for a Heat Bending Machine Based on ANSYS Simulation Analysis and the Surface Structure of the Heating Plate," published with publication number CN111428408A, describes a calculation method that primarily determines and adds the required material performance parameters based on the heating plate structure and process parameters under stable high-temperature operation. An initial analysis geometry model is then established and meshed. Boundary conditions are then defined and loads applied to solve the calculation output. Based on the simulation analysis results, the deformation of the heating plate is analyzed, and two lower surface structures for the heating plate are designed based on the deformation of the heating plate under stable high-temperature operation: a concave spherical structure or a cylindrical structure. After deformation under high-temperature operation, heating plates with spherical or cylindrical lower surfaces become nearly flat. This ensures the level of the contact surface between the heating plate and the mold, improving glass forming accuracy and yield. However, this calculation method is not applicable to calculating the temperature-dependent behavior of the casing of GIS equipment and does not provide a fast simulation process. Summary of the Invention

[0005] The purpose of the present invention is to address the above problems and provide a cloud-edge collaborative GIS shell temperature change behavior rapid simulation method and system. Through an integrated communication architecture, multi-node detection is realized, and real-time and comprehensive coverage of the intelligent sensor end is achieved. At the same time, edge computing technology is used to perform response surface simulation locally; in the cloud, a system is built to realize model management, three-dimensional visual display, real-time abnormal warning and other functions, thereby realizing rapid simulation of the temperature change behavior of GIS equipment.

[0006] A cloud-edge collaborative rapid simulation method for GIS shell temperature change behavior, the method comprising:

[0007] Step S1: Set the warning value and collect data through intelligent sensing equipment;

[0008] Step S2: The edge computing node obtains data collected by the intelligent sensor device;

[0009] Step S3: The edge computing node simulates the collected data in real time based on the response surface model issued by the cloud computing center, and uploads the simulation results to the cloud computing center;

[0010] Step S4: The cloud computing center performs data analysis and visualization based on the received simulation results, and issues an early warning for the GIS equipment operating status based on the early warning value;

[0011] Step S5: The cloud computing center simulates the data and visualizes the model based on the stored finite element model, response surface model, and real-scene model. When the GIS device morphology changes, the cloud computing center will self-update and modify the response surface model and send the response surface model to the edge computing node.

[0012] Through an integrated communication architecture, multi-node detection is achieved, with comprehensive real-time coverage of intelligent sensor terminals. At the same time, edge computing technology is used to perform local response surface simulation. In the cloud, a system is built to implement multiple functions such as model management, three-dimensional visualization, and real-time warning of abnormalities, thereby achieving rapid simulation of the temperature change behavior of GIS equipment. Changes in the GIS appearance can be perceived in a timely manner, and simulation data can be adjusted in real time according to the status.

[0013] Preferably, the method further comprises: the edge computing node preprocessing and deduplicating the data collected during the interval; performing simulation calculations on the data based on the response surface model issued by the cloud center, and uploading the calculation results to the cloud center. The data preprocessing enables the data to be quickly identified and the corresponding model to be calculated, removing duplicate data and avoiding interference.

[0014] Preferably, simulation calculation and visualization based on the model library stored in the cloud computing center include:

[0015] Step S31: Establish a finite element model based on Abaqus, and the cloud computing center constructs a finite element calculation model;

[0016] Step S32: Simplify the finite element model and use the response surface analysis method to obtain a response surface model through experimental design. The cloud computing center sends the response surface model to the edge computing node;

[0017] Step S33: Use laser scanning technology to scan the GIS equipment in real time to obtain a real-scene model, and deploy the real-scene model to the cloud computing center for visualization in combination with simulation results.

[0018] Preferably, in step S33, the scanned real scene model is spliced ​​and denoised to obtain a real scene model for visual display.

[0019] As an optimal solution, when external changes occur to the GIS shell, the model is updated through deep learning, and the cloud center sends the updated response surface model to the edge computing node. This provides real-time feedback on external conditions and adjusts data in real time to ensure normal operation.

[0020] Preferably, the simulation task is performed according to a collaborative strategy. The strategy includes the following: The edge computing node checks the local response surface model to see if it is functioning properly. If no anomalies are detected, the response surface model is used for simulation, and the simulation results are uploaded to the cloud computing center. If an anomaly is detected, the cloud computing center is asked to see if the simulation model has completed self-correction. If self-correction is complete, the edge node updates the model, then continues the response surface simulation, and uploads the results. If self-correction is not complete, the collected data is directly uploaded for real-time simulation using the finite element model in the cloud computing center's model library. Through multiple judgments and corrections, the model is guaranteed to fit the actual GIS shell, ensuring that the simulation results are authentic and reliable.

[0021] A cloud-edge collaborative GIS shell temperature change behavior rapid simulation system, including intelligent sensing equipment, edge computing center and cloud computing center;

[0022] The intelligent sensing device comprises:

[0023] Data acquisition component, used to collect temperature and displacement data of GIS equipment;

[0024] The edge computing node includes:

[0025] A data processing module is used to obtain data collected by the sensor equipment;

[0026] The data simulation module is used to perform simulation calculations based on the response surface calculation model issued by the cloud center and upload the simulation results to the cloud computing center;

[0027] The model update module is used to check for model updates and automatically download the updated model if an update is found in the cloud computing center;

[0028] Collaborative strategy execution module, used to receive collaborative strategies issued by the cloud center;

[0029] The cloud computing center includes:

[0030] The visualization display module performs visualization based on the simulation results uploaded by the edge nodes and the real-life model in the model library;

[0031] The model library management module performs simulation calculations and visualization based on the computational models and real-scene models stored in the model library; updates the response surface calculation model based on the deep learning component and sends it to the edge computing nodes;

[0032] The device status warning module performs data analysis based on the simulation results uploaded by the edge computing node and determines whether to issue a warning based on the warning value.

[0033] The beneficial effects of the present invention are:

[0034] The present invention proposes to use 3D laser scanning technology, edge computing, finite element modeling and simulation, cloud-edge collaboration and other technologies to achieve all-round collection of GIS equipment temperature, displacement and other data at the terminal based on IoT sensor technology. On the edge side, through an integrated communication architecture, multi-node detection is achieved, with real-time and comprehensive coverage of the intelligent sensor terminal. At the same time, edge computing technology is used to perform response surface simulation locally. In the cloud, a system is built to implement multiple functions such as model management, 3D visualization, and real-time warning of abnormalities, thereby achieving rapid simulation of the temperature change behavior of GIS equipment. The present invention provides a new technology for the evaluation and measurement of the temperature change behavior of GIS shell equipment, which has important engineering value for improving the management level of the operating status of GIS equipment and ensuring the safe and stable operation of the power grid and equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is the system architecture diagram;

[0036] Figure 2 This is the system workflow diagram. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0038] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0039] like Figure 1 Shown is a system architecture diagram of the present invention.

[0040] In the disclosed method for rapid simulation of GIS shell temperature variation based on cloud-edge collaboration, the cloud computing center is used for visualization of simulation results, data analysis, equipment status warning, and automatic correction and distribution of simulation models. The edge computing node simulates locally based on the response surface model issued by the cloud computing and uploads the results. The cloud computing center visualizes the results and performs data analysis. When it is determined that the warning value is exceeded, the cloud computing center sends an equipment status warning message to the operation and maintenance personnel.

[0041] The construction of a cloud-edge collaborative GIS shell temperature change behavior rapid simulation system mainly consists of three steps: GIS equipment data collection, model library establishment, cloud-edge collaborative strategy establishment, and data analysis and early warning.

[0042] Step 1: GIS equipment data collection.

[0043] The temperature displacement measured data of the target position of the GIS equipment is collected through the intelligent sensor terminal. Multiple monitoring points are selected at the GIS equipment, and the intelligent sensor terminal is installed at the point. The temperature displacement data of the equipment is obtained in real time through the sensor terminal to prepare parameters for the subsequent model simulation.

[0044] Step 2: Create a model library.

[0045] The model library contains finite element calculation models, response surface calculation models and GIS real-scene models. The models are deployed to the cloud computing center to achieve simulation, model self-update and distribution, and visual display. The creation methods of each model are introduced below.

[0046] 1) When building a finite element model using Abaqus, it is necessary to select and discard various structures of the GIS equipment. The main structures, such as the busbar barrel, support legs, bellows, and pot insulators, are retained, while secondary structures with less impact on the finite element simulation, such as the outlet bushing, are ignored.

[0047] 2) Based on the finite element model, the response surface methodology was used for experimental design. Thirty groups of samples were selected, and parameter screening and significance testing were performed using the stepwise regression method. Finally, the response surface model was obtained by fitting the response surface function.

[0048] 3) Use 3D LiDAR sensing technology to perform multi-site scanning of outdoor GIS equipment, then stitch and de-noise the scanned real-scene models to obtain a real-scene model for visualization.

[0049] Step 3: Cloud-edge collaboration strategy.

[0050] The edge collects data through intelligent sensor terminals. After collecting the data, it first checks whether the local response surface model is normal. If there are no anomalies, it directly uses the response surface model for simulation and uploads the simulation results to the cloud computing center. If an anomaly is detected (such as a change in the GIS equipment modification), the cloud computing center is asked whether an update to the simulation model has been issued. If an update is available, the edge updates the model, continues the response surface simulation, and then uploads the results. If there are no updates, the collected data is directly uploaded and simulated in real time using the finite element model in the cloud model library. Users can also initiate real-time simulation in the cloud, directly simulating the collected data using the cloud finite element model.

[0051] Step 4: Data analysis and early warning

[0052] The data collected by the intelligent sensor terminal is used as parameters and brought into the model for simulation calculation. The calculation results are analyzed to determine whether the GIS equipment is in a safe and reliable operating state. If it exceeds the warning value, an alarm message will be sent to the operation and maintenance personnel.

[0053] The above-described embodiments merely illustrate the implementation methods of the present invention. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous modifications and variations without departing from the scope of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A cloud-edge collaborative GIS shell temperature change behavior rapid simulation method, characterized by: The method comprises: Step S1: Set the warning value and collect data through intelligent sensing equipment; Step S2: The edge computing node obtains data collected by the intelligent sensor device; Step S3: The cloud computing center constructs a finite element calculation model and uses the response surface analysis method to obtain a response surface model. The edge computing node performs real-time simulation on the collected data based on the response surface model issued by the cloud computing center, and uploads the simulation results to the cloud computing center. The GIS equipment is scanned in real time to obtain a real-scene model, and the real-scene model is deployed to the cloud computing center. Step S4: The cloud computing center performs data analysis and visualization based on the received simulation results, and issues an early warning for the GIS equipment operating status based on the early warning value; Step S5: The cloud computing center simulates the data and visualizes the model based on the stored finite element model, response surface model, and real-scene model. When changes are found in the GIS device shell, the response surface model will be updated and corrected, and the response surface model will be sent to the edge computing node.

2. The cloud-edge collaborative GIS shell temperature change behavior rapid simulation method according to claim 1 is characterized in that: The method further includes: the edge computing node preprocessing and deduplicating the data collected within the interval time; performing simulation calculations on the data based on the response surface model issued by the cloud center, and uploading the calculation results to the cloud center.

3. The cloud-edge collaborative GIS shell temperature change behavior rapid simulation method according to claim 2 is characterized in that: Simulation calculations and visualizations based on the model library stored in the cloud computing center include: Step S31: Establish a finite element model based on Abaqus, and the cloud computing center constructs a finite element calculation model; Step S32: Simplify the finite element model and use the response surface analysis method to obtain a response surface model through experimental design. The cloud computing center sends the response surface model to the edge computing node; Step S33: Use laser scanning technology to scan the GIS equipment in real time to obtain a real-scene model, and deploy the real-scene model to the cloud computing center for visualization in combination with simulation results.

4. The cloud-edge collaborative GIS shell temperature change behavior rapid simulation method according to claim 3 is characterized by: In step S33, the scanned real scene model is spliced ​​and denoised to obtain a real scene model for visual display.

5. The cloud-edge collaborative GIS shell temperature change behavior rapid simulation method according to claim 3 is characterized in that: When external changes occur to the GIS shell, the model is self-corrected and updated through deep learning, and the cloud center sends the updated response surface model to the edge computing node.

6. The cloud-edge collaborative GIS shell temperature change behavior rapid simulation method according to claim 1 is characterized in that: The simulation task is carried out according to the collaborative strategy, which includes: the edge computing node detects whether the status of the local response surface calculation model is normal. If there is no abnormality, the response surface model is directly used for simulation, and the simulation results are uploaded to the cloud computing center; if an abnormality is detected, the cloud computing center is asked whether the simulation model has completed self-correction; if self-correction is completed, the edge updates the model, continues the response surface simulation, and then uploads the results; if self-correction is not completed, the collected data is directly uploaded, and real-time simulation is performed through the finite element model in the cloud computing center model library.

7. A cloud-edge collaborative GIS shell temperature change behavior rapid simulation system, characterized by: Including intelligent sensor devices, edge computing nodes and cloud computing centers; The intelligent sensing device comprises: Data acquisition component, used to collect temperature and displacement data of GIS equipment; Edge computing nodes, including: A data processing module is used to obtain data collected by the sensor equipment; The data simulation module is used to perform simulation calculations based on the response surface calculation model issued by the cloud center and upload the simulation results to the cloud computing center; The model update module is used to check for updates to the response surface model and automatically download the updated model if an update is found in the cloud computing center; Collaborative strategy execution module, used to receive collaborative strategies issued by the cloud center; The cloud computing center includes: The visualization display module performs visualization based on the simulation results uploaded by the edge nodes and the real-life model in the model library; The model library management module performs simulation calculations and visualization based on the computational finite element and response surface models and real-scene models stored in the model library; updates the response surface calculation model based on the deep learning component and sends it to the edge computing node; The device status warning module performs data analysis based on the simulation results uploaded by the edge computing node and determines whether to issue a warning based on the warning value.

Images