Remote control auxiliary method based on virtual technology

Abstract

The invention discloses a remote control auxiliary method based on a virtual technology, and the method comprises the steps: constructing a three-dimensional geometric and physical simulation model of electrical equipment, carrying out the verification and optimization through finite element analysis, and forming a virtual digital model. The model is provided with a parameterized control interface and a visual operation interface for real-time adjustment and monitoring so as to obtain optimal parameter configuration. And establishing a data transmission channel between the virtual model and real equipment to realize bidirectional interaction. According to different scenes of a virtual environment, various control schemes and optimization strategies are preset, an optimal control parameter combination is obtained through simulation analysis, and a standardized control configuration template is generated. Equipment operation data is collected in real time through a data transmission channel and compared with a virtual model simulation result, optimization of the model and a control template is conducted through a gradient descent algorithm, and remote control assistance is achieved. According to the invention, intelligent remote control and optimization of the electrical equipment are realized, and the operation efficiency and safety of the equipment are improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent control technology, and in particular relates to a remote control auxiliary method based on virtual technology. Background Art

[0002] Virtualization technology can be used to build digital models of electrical equipment. By modifying and manipulating virtual models, real equipment can be remotely controlled. In a virtual environment, operators can adjust various parameters and optimize functions of the equipment model. The modified configuration can be directly sent to the real equipment to achieve remote control. This method can improve the controllability and flexibility of electrical equipment while reducing the risk and cost of on-site operations. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a remote control assistance method based on virtual technology to solve the problems existing in the above prior art.

[0004] To achieve the above object, the present invention provides a remote control assistance method based on virtual technology, comprising:

[0005] Constructing a three-dimensional geometric model and a physical simulation model of the electrical equipment, verifying and optimizing the three-dimensional geometric model and the physical simulation model through finite element analysis, and obtaining a virtualized digital model;

[0006] By setting a parameterized control interface and a visual operation interface for the virtualized digital model, the virtualized digital model is adjusted and monitored in real time to obtain an optimal parameter configuration of the virtualized digital model;

[0007] Establishing a data transmission channel between the virtualized digital model and the real device, and interacting through the data transmission channel;

[0008] Obtain different scenarios of the virtual environment, preset several control schemes and corresponding optimization strategies for different scenarios, obtain the optimal control parameter combination under different scenarios through simulation analysis, and generate standardized control configuration templates based on the optimal control parameter combination under different scenarios;

[0009] The operating data of the electrical equipment is collected in real time through the data transmission channel and compared with the simulation results of the virtualized digital model. The virtualized digital model and the standardized control configuration template are optimized through the gradient descent algorithm, and remote control assistance is achieved through the optimized virtualized digital model and standardized control configuration template.

[0010] Optionally, the process of obtaining a virtual digital model includes:

[0011] The three-dimensional geometric model and the physical simulation model are meshed to obtain a finite element model; based on the actual working conditions and boundary conditions of the electrical equipment, loads and constraints are set for the finite element model, and finite element solution calculations are performed to obtain finite element analysis results; an electrical equipment model is constructed, and the stress distribution and deformation of the electrical equipment model are evaluated according to the finite element analysis results to determine whether the design requirements are met; if the design requirements are not met, the three-dimensional geometric model and the physical simulation model are optimized according to the evaluation results, and the finite element analysis is repeated until the electrical equipment model meets the design requirements; the verified and optimized three-dimensional geometric model and the physical simulation model are digitized to obtain a virtualized digital model.

[0012] Optionally, the process of determining whether the design requirements are met includes:

[0013] According to the structural parameters and material properties of the electrical equipment, an electrical equipment model is established; load conditions and boundary conditions are set for the electrical equipment model, and finite element meshing is performed; the finite element analysis method is used to simulate and calculate the stress distribution and deformation of the electrical equipment model; stress distribution and deformation data are extracted from the simulation results, and the stress distribution and deformation data are compared with preset design requirement thresholds to determine whether the electrical equipment model meets the design requirements; if the electrical equipment model does not meet the design requirements, the structural layout and dimensional parameters of the electrical equipment are optimized and adjusted according to the stress concentration areas and the parts with larger deformation; the stress distribution and deformation of the optimized electrical equipment model are re-simulated and verified until the design requirements are met.

[0014] Optionally, the process of obtaining the optimal parameter configuration includes:

[0015] Extract key parameters of the virtualized digital model, construct a data model and protocol of a parameterized control interface, map and bind the key parameters to interface controls, graphically display and interactively adjust the key parameters, obtain the operating status data of the virtualized digital model, monitor each key parameter in the operating status data in real time, and determine whether it exceeds a preset threshold range; if the key parameter exceeds the preset threshold range, trigger an early warning mechanism, build a parameter optimization algorithm, train historical adjustment data and real-time monitoring data, obtain the optimal parameter configuration, prompt the user to adjust the parameters through a visual interface, and pass the adjustment instruction to the virtualized digital model through the parameterized control interface.

[0016] Optionally, a data transmission channel is established between the virtualized digital model and the real device, and a process of interacting through the data transmission channel includes:

[0017] According to the characteristics of the virtual model and the real device, the network communication protocol and transmission method are selected to establish a data transmission channel. The status data of the real device is obtained through the data transmission channel and mapped to the corresponding parameters of the virtual model to synchronize the virtual and real states. According to the control instructions of the virtual model, the control signal is sent to the real device through the data transmission channel, and the real device is controlled by the virtual model.

[0018] Optionally, the process of generating a standardized control configuration template includes:

[0019] According to different scenarios of the virtual environment, multiple control schemes and optimization strategies are preset for different scenarios to form an initial configuration parameter library; simulation experiments are carried out on each control scheme in the virtual environment to obtain various performance indicator data, and the comprehensive performance score of each control scheme is obtained based on the various performance indicator data; the control parameter combination with the highest score is screened out according to the comprehensive performance score ranking; the screened control parameter combination is associated with the corresponding virtual environment scenario to form a scenario-parameter mapping table; based on the scenario-parameter mapping table, a standardized control configuration template suitable for different virtual environment scenarios is generated.

[0020] Optionally, a state-space equation group is constructed based on the virtualized digital model; a Kalman filtering algorithm is used to estimate the system state by combining the state-space equation group with the equipment operation status data collected in real time by the sensor; the estimated system state is input into the virtualized digital model to obtain the predicted value of each state variable; the error between the actual operation data of the equipment and the simulation result of the virtual model is calculated to construct a cost function; based on the cost function, a gradient descent algorithm is used to optimize the parameters of the virtualized digital model to minimize the error between the simulation result and the actual operation data to obtain an optimized virtual model; based on the optimized virtual model, the operation status of the electrical equipment is predicted; in combination with the performance constraints and task requirements of the equipment, a model predictive control algorithm is used to generate an optimal control sequence for virtual manipulation and update the standardized control configuration template; the optimal control sequence is input into the control system of the electrical equipment to obtain the equipment status data during the virtual manipulation process, and the data is fed back to the virtualized digital model in real time to continuously optimize the standardized control configuration template and the virtualized digital model.

[0021] Optionally, the method further includes:

[0022] Identify abnormal situations during the operation process, automatically analyze the causes of the abnormalities and generate treatment plans based on the preset fault diagnosis logic and decision tree algorithm.

[0023] Optionally, the process of generating a disposal plan includes:

[0024] According to the preset fault diagnosis logic, real-time data in the operation process is obtained to determine whether an abnormal situation occurs; if an abnormal situation is detected, the fault diagnosis process is triggered, and the decision tree algorithm is used to analyze the abnormal data; through the decision tree algorithm, combined with historical fault case data, the abnormal data is inferred to derive the cause of the abnormality; according to the cause of the abnormality, the disposal measures are matched in the preset disposal solution knowledge base; if a suitable disposal solution is matched, the specific operation steps of the solution are presented to the operator; if there is a lack of disposal solutions that meet the requirements, a new disposal solution is generated through case reasoning based on the attributes of the abnormal cause, the operator is guided to handle it, and it is stored in the preset disposal solution knowledge base.

[0025] Compared with the prior art, the present invention has the following advantages and technical effects:

[0026] The present invention discloses a virtual-reality fusion intelligent control system for electrical equipment. The system realizes accurate mapping and two-way interaction of real equipment by constructing a highly consistent three-dimensional virtual model. The system has developed a parametric control interface and a visual operation interface, so that operators can adjust and monitor model parameters in real time. By presetting multiple sets of control schemes and performing simulation comparisons, the optimal control parameter combination is screened out to form a standardized configuration template. During the actual control process, the system collects equipment operation data in real time and compares it with the virtual model, and uses machine learning algorithms to continuously optimize model parameters and control strategies. For abnormal situations, the present invention can automatically analyze the causes and generate disposal plans. The present invention realizes intelligent remote control and optimization of electrical equipment, improves equipment operation efficiency and safety, and provides a new technical path for the intelligent upgrade of power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0028] Figure 1 The figure is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Embodiment 1

[0032] like Figure 1 As shown, this embodiment provides a remote control assistance method based on virtual technology, including:

[0033] Constructing a three-dimensional geometric model and a physical simulation model of the electrical equipment, verifying and optimizing the three-dimensional geometric model and the physical simulation model through finite element analysis, and obtaining a virtualized digital model;

[0034] As a preferred implementation, the process of obtaining a virtualized digital model includes: meshing the three-dimensional geometric model and the physical simulation model to obtain a finite element model; setting loads and constraints on the finite element model based on the actual working conditions and boundary conditions of the electrical equipment, and performing finite element solution calculations to obtain finite element analysis results; constructing an electrical equipment model, and evaluating the stress distribution and deformation of the electrical equipment model according to the finite element analysis results to determine whether the design requirements are met; if the design requirements are not met, optimizing the three-dimensional geometric model and the physical simulation model according to the evaluation results, and repeating the finite element analysis until the electrical equipment model meets the design requirements; and digitizing the verified and optimized three-dimensional geometric model and the physical simulation model to obtain a virtualized digital model.

[0035] As a preferred implementation, the process of determining whether the design requirements are met includes: establishing an electrical equipment model according to the structural parameters and material properties of the electrical equipment; setting load conditions and boundary conditions for the electrical equipment model, and performing finite element meshing; using a finite element analysis method to perform simulation calculations on the stress distribution and deformation of the electrical equipment model; extracting stress distribution and deformation data from the simulation results, and comparing the stress distribution and deformation data with preset design requirement thresholds to determine whether the electrical equipment model meets the design requirements; if the electrical equipment model does not meet the design requirements, optimizing and adjusting the structural layout and dimensional parameters of the electrical equipment according to stress concentration areas and large deformation areas; and re-simulating and verifying the stress distribution and deformation of the optimized electrical equipment model until the design requirements are met.

[0036] Specifically, according to the structural parameters and material properties of the electrical equipment, the CAD software SolidWorks is used to build a three-dimensional geometric model. For example, for a transformer, its core is made of laminated silicon steel sheets, the winding is wound with enameled wire, and the shell is made of stainless steel. Through the modeling function of SolidWorks, the three-dimensional solid model of the transformer is accurately drawn. At the same time, combined with the physical characteristics of the transformer, such as electromagnetic field distribution and heat conduction, the corresponding electromagnetic field simulation model and thermal simulation model are established in ANSYS Maxwell and ANSYS Icepak respectively. Using the finite element analysis method, the three-dimensional geometric model is tetrahedral meshed to obtain a finite element model containing about 500,000 nodes and 1.2 million units. According to the actual working conditions of the transformer, a 10kV voltage excitation is applied to the winding, the core and the shell are grounded, and the ambient temperature is considered to be 40℃, and the load and constraint settings are performed on the finite element model. The ANSYS finite element analysis software is used for solution calculation, and the distribution results of the electromagnetic field and temperature field are obtained in about 30 minutes through the Newton-Raphson iterative algorithm. According to the stress analysis results, the maximum stress of the transformer core and winding is 50MPa and 30MPa respectively, which is less than the allowable stress of the material and meets the strength requirements. At the same time, the maximum temperature of the transformer is 95℃, which is lower than the maximum allowable temperature of the insulating material of 105℃, meeting the heat dissipation requirements. After repeated modeling, simulation and optimization, a transformer design that meets various performance indicators was finally obtained. The three-dimensional model was exported in Parasolid format and fused with the physical simulation model data to construct a digital twin model that is highly consistent with the real transformer. The model is applied to the forward design, performance prediction and virtual testing of the transformer, which greatly improves the design efficiency and product quality, and reduces the trial production cost and R&D cycle.

[0037] Furthermore, the material properties and geometric dimension parameters of the electrical equipment are obtained, and the boundary constraints of the finite element model are determined according to the boundary conditions of the electrical equipment; a finite element solver is used to perform numerical solution calculations on the finite element model with load and constraint settings to obtain the physical field distribution results of the electrical equipment under actual working conditions; if the values ​​of key physical quantities do not meet the design requirements and performance indicators, then according to the design optimization and improvement needs of the electrical equipment, the relevant parameters of the finite element model are adjusted, and the solution calculations and result analysis are performed again until the requirements are met, thereby completing the design optimization of the electrical equipment.

[0038] Specifically, in order to obtain the material properties and geometric size parameters of electrical equipment, 3D scanning technology can be used to digitally model the electrical equipment, and the scanning data can be processed by reverse engineering software such as Geomagic Design X to extract the geometric size information of the equipment. At the same time, according to the material composition of the equipment, the physical property parameters of the material, such as conductivity, dielectric constant, density, etc., are queried and obtained from the material database. According to the actual working environment and conditions of the electrical equipment, the boundary constraints of the finite element model, such as fixed constraints, symmetry constraints, etc., are determined. Finite element solvers such as ANSYSMaxwell are used to numerically solve and calculate the finite element model with load and constraint settings. During the solution process, the Newton-Raphson iterative algorithm is used, and the iteration error is set to 1e-6, and the maximum number of iterations is 100. Through the cloud computing platform, high-performance computing resources with 32-core CPUs and 64GB of memory are used to perform parallel computing to shorten the simulation time. After the calculation is completed, the physical field distribution results of the electrical equipment under actual working conditions, such as electric field strength, magnetic induction strength, etc., are obtained. If the key physical quantity, such as the maximum electric field strength, exceeds 30MV / m, it indicates that the design does not meet the insulation performance requirements and needs to be optimized and improved. Using parametric modeling and optimization algorithms, such as Latin hypercube sampling and genetic algorithms, the dimensional parameters of the finite element model, such as the thickness of the insulation layer, are automatically adjusted, and the solution calculation and result analysis are re-performed until the design requirements are met, completing the design optimization of the electrical equipment. After optimization, the thickness of the insulation layer is increased from 5mm to 8mm, and the maximum electric field strength is reduced to 25MV / m, meeting the design indicators.

[0039] Furthermore, a three-dimensional solid model of the electrical equipment is established based on the structural parameters and material properties of the electrical equipment; for the established electrical equipment model, load conditions and boundary conditions are set, and finite element meshing is performed; the finite element analysis method is used to simulate and calculate the stress distribution and deformation of the electrical equipment model; the stress distribution and deformation data are extracted from the simulation calculation results, and the data are visualized and analyzed; the stress distribution and deformation data are compared with the preset design requirement thresholds to determine whether the electrical equipment model meets the design requirements; if the electrical equipment model does not meet the design requirements, the structural layout and dimensional parameters of the electrical equipment are optimized and adjusted according to the stress concentration areas and the parts with larger deformation; the optimized electrical equipment model is re-simulated and verified for stress distribution and deformation until the design requirements are met.

[0040] Specifically, according to the structural parameters and material properties of the electrical equipment, the electrical equipment is solid modeled using 3D modeling software such as SolidWorks to obtain a 3D solid model of the electrical equipment. For the established electrical equipment model, set the load conditions and boundary conditions, such as the working voltage of the electrical equipment is 10kV, the ambient temperature is 40℃, and the relative humidity is 60%. Then, the electrical equipment model is meshed using finite element analysis software such as ANSYS, and the number of mesh units is set to 500,000. The finite element analysis method is adopted, and a suitable solver such as Sparse solver is selected, and the convergence accuracy is set to 1e-6 to simulate the stress distribution and deformation of the electrical equipment model. The stress distribution and deformation data are extracted from the simulation calculation results, and the data are visualized using visualization software such as Tecplot to generate stress cloud maps and deformation cloud maps, and the stress concentration areas and large deformation parts are analyzed. The stress distribution and deformation data are compared with the preset design requirement thresholds, such as the maximum stress value does not exceed the yield strength of the material, and the maximum deformation does not exceed 1% of the size of the electrical equipment, to determine whether the electrical equipment model meets the design requirements. If the electrical equipment model does not meet the design requirements, the structural layout and dimensional parameters of the electrical equipment are optimized according to the stress concentration areas and the parts with large deformation, using topology optimization algorithms such as the variable density method, such as adding reinforcing ribs in the stress concentration areas, adding support structures in the parts with large deformation, and using parametric modeling technology to adjust the key dimensional parameters of the electrical equipment. The optimized electrical equipment model is re-simulated and verified for stress distribution and deformation, and the calculation results are analyzed to see whether they meet the design requirements. If they do, the optimized design of the electrical equipment is completed. If not, the iterative optimization is continued until the design requirements are met.

[0041] By setting a parameterized control interface and a visual operation interface for the virtualized digital model, the virtualized digital model is adjusted and monitored in real time to obtain an optimal parameter configuration of the virtualized digital model;

[0042] As a preferred implementation, the process of obtaining the optimal parameter configuration includes: extracting the key parameters of the virtualized digital model, constructing a data model and protocol of a parameterized control interface, mapping and binding the key parameters to interface controls, graphically displaying and interactively adjusting the key parameters, obtaining the operating status data of the virtualized digital model, and monitoring each key parameter in the operating status data in real time to determine whether it exceeds a preset threshold range; if the key parameter exceeds the preset threshold range, triggering an early warning mechanism, constructing a parameter optimization algorithm, training historical adjustment data and real-time monitoring data, obtaining the optimal parameter configuration, prompting the user to adjust the parameters through a visual interface, and passing the adjustment instruction to the virtualized digital model through the parameterized control interface.

[0043] Specifically, in the virtualized digital model of electrical equipment, the key parameters of the model, such as voltage, current, and temperature, are first obtained through high-precision sensors, and these parameters are transmitted to the central processing unit through the data interface. In the central processing unit, the key parameters are mapped and bound to the controls of the graphical user interface using the data model of the parameterized control interface to achieve a graphical display of the parameters. For example, the current value is displayed through a real-time curve chart, and the user can adjust the current size in real time through the slider, and the system immediately displays the effect of the adjustment. At the same time, the system monitors key parameters in real time, such as whether the current exceeds the preset threshold of 100 amperes. Once the current exceeds the standard, the system immediately triggers the early warning mechanism, warns the user through a pop-up window, and provides a quick adjustment option. In addition, data visualization technology is used to convert real-time monitoring data into charts and indicators, such as comparing the historical data and real-time data of current and voltage through a line chart, which helps users intuitively understand the operating status of the equipment. In order to further optimize the parameter settings, a parameter optimization algorithm based on support vector machine (SVM) is constructed, which automatically recommends the optimal current and voltage settings by analyzing historical adjustment data and real-time monitoring data. In this way, users can not only monitor and adjust equipment parameters in real time, but also optimize equipment performance through intelligent algorithms to ensure that the equipment operates in the best condition.

[0044] Establishing a data transmission channel between the virtualized digital model and the real device, and interacting through the data transmission channel;

[0045] As a preferred implementation, a data transmission channel is established between the virtualized digital model and the real device, and the process of interacting through the data transmission channel includes: selecting a network communication protocol and a transmission method to establish a data transmission channel according to the characteristics of the virtual model and the real device; obtaining the status data of the real device through the data transmission channel, and mapping it to the corresponding parameters of the virtual model to synchronize the virtual and real states; sending the control signal to the real device through the data transmission channel according to the control instruction of the virtual model, and controlling the real device through the virtual model.

[0046] Furthermore, according to the characteristics of the virtual model and the real device, select the appropriate network communication protocol and transmission method to establish a stable and reliable data transmission channel; obtain the status data of the real device through the transmission channel, and map it to the corresponding parameters of the virtual model to achieve synchronization of the virtual and real states; according to the control instructions of the virtual model, send the control signal to the real device through the transmission channel to achieve the control of the real device by the virtual model; in the data transmission process, use data compression, encryption and other technologies to improve transmission efficiency and data security; design a reasonable data format and parsing mechanism to ensure that the data interaction between the virtual model and the real device is accurate; in view of factors such as network delay and jitter, use prediction algorithms and buffering mechanisms to improve the real-time and stability of virtual-reality interaction; establish a virtual-reality mapping relationship table to record the correspondence between the virtual model and the real device, so as to facilitate quick search and maintenance.

[0047] Specifically, when selecting the network communication protocol, considering the security and efficiency of data transmission, the MQTT protocol based on TLS encryption was selected. This protocol supports low-power and efficient communication between devices and servers. Through this protocol, the status data of the real device is transmitted once per second, and the data packet size is controlled within 500 bytes. The GZIP algorithm is used for compression, and the compression ratio reaches 3:1, which effectively reduces the load of data transmission. In terms of data mapping, a set of JSON format data parsing mechanisms is designed to parse the received status data and map it to the corresponding parameters of the virtual model, ensuring the accuracy and real-time performance of the data. In order to deal with network delay and jitter, an algorithm based on time series prediction is introduced, and the ARIMA model is used to predict the device status in the short term in the future. The prediction accuracy reaches more than 95%. At the same time, a 500 millisecond data buffer is set to balance the real-time performance and stability of data transmission. In addition, a detailed virtual-real mapping relationship table is established, and a hash table storage structure is used to achieve fast search and correspondence between virtual model and real device parameters. The search time complexity is O(1), which greatly improves the response speed and maintenance efficiency of the system.

[0048] Furthermore, a reasonable data format and parsing mechanism are designed to ensure accurate data interaction between the virtual model and the real device. Acquire virtual model data and real device data, wherein the virtual model data and the real device data have different data formats; design a unified data format standard according to the characteristics of the virtual model data and the real device data, wherein the data format standard adopts the JSON data description language to define the data structure and field meaning of the virtual model data and the real device data; adopt the data format standard to perform format conversion on the virtual model data and the real device data to obtain virtual model data and real device data in a unified format; acquire multi-source heterogeneous features of the virtual model data and the real device data in the unified format, wherein the multi-source heterogeneous features include timestamp, coordinate system and semantic attributes; adopt data fusion technology to associate and integrate the multi-source heterogeneous features to obtain a fused unified data view, wherein the data fusion technology includes data registration and calibration; the data registration is used to perform spatial mapping and conversion on data in different coordinate systems, and the data calibration is used to eliminate conflicts and inconsistencies between different data sources; according to the fused unified data view, construct a data mapping relationship between the virtual model and the real device to achieve data interoperability and synchronization between the virtual model and the real device.

[0049] Specifically, in order to achieve data interoperability and synchronization between virtual models and real devices, it is necessary to first obtain virtual model data and real device data. Virtual model data is usually generated by 3D modeling software, such as AutoCAD, SolidWorks, etc., and the data formats include STL, OBJ, etc.; while real device data comes from various sensors and control systems, such as PLC, DCS, etc., and the data formats include Modbus, OPC, etc. In order to unify these heterogeneous data, a JSON-based data format standard is designed to define the data structure and field meaning of virtual models and real devices, such as the geometric dimensions and material properties of virtual models, and the state parameters and control instructions of real devices. Through format conversion tools such as FME and Kettle, the original data is mapped to the JSON format to obtain unified virtual model data and real device data. On this basis, the multi-source heterogeneous features of the data are extracted, such as timestamps, coordinate systems, and semantic attributes. For timestamps, the NTP protocol is used for clock synchronization, and the error is controlled within 1 millisecond; for coordinate systems, the quaternion representation method is used to achieve conversion between different coordinate systems through rotation matrices, with an accuracy of 1 mm; for semantic attributes, ontology mapping technology is used to build semantic associations between virtual models and real devices, such as "virtual valves" corresponding to "real valves". Finally, multi-sensor data fusion algorithms, such as Kalman filtering and Bayesian reasoning, are used to associate and integrate multi-source heterogeneous data to obtain a consistent unified data view. In the data fusion process, data registration and calibration technologies are used to eliminate conflicts and errors between different data sources. For example, the deviation between the position of the virtual model and the GPS coordinates of the real device is fitted by the least squares method, and the error is reduced to within 5 meters. Based on the unified data view after fusion, the mapping relationship between the virtual model and the real device is constructed to achieve two-way data transmission and synchronous update. For example, the change in the valve opening of the virtual model is reflected in the control instructions of the real valve in real time, and vice versa.

[0050] Obtain different scenarios of the virtual environment, preset several control schemes and corresponding optimization strategies for different scenarios, obtain the optimal control parameter combination under different scenarios through simulation analysis, and generate standardized control configuration templates based on the optimal control parameter combination under different scenarios;

[0051] As a preferred implementation, the process of generating a standardized control configuration template includes:

[0052] According to different scenarios of the virtual environment, multiple control schemes and optimization strategies are preset for different scenarios to form an initial configuration parameter library; simulation experiments are carried out on each control scheme in the virtual environment to obtain various performance indicator data, and the comprehensive performance score of each control scheme is obtained based on the various performance indicator data; the control parameter combination with the highest score is screened out according to the comprehensive performance score ranking; the screened control parameter combination is associated with the corresponding virtual environment scenario to form a scenario-parameter mapping table; based on the scenario-parameter mapping table, a standardized control configuration template suitable for different virtual environment scenarios is generated.

[0053] Specifically, when constructing the control scheme of the virtual environment, five different control schemes are preset first, and each scheme is optimized for a specific virtual scenario. For example, when dealing with high-concurrency scenarios, the initial configuration parameters preset by control scheme A are the upper limit of the number of concurrent operations of 1000 and the response time optimized to 50ms. The performance of each scheme is tested by conducting simulation experiments in the virtual environment using simulated user requests. In the data collection phase, a data mining script written in Python is used to analyze the log files and extract key performance indicators such as average response time and error rate. Then, the decision tree algorithm is used to assign weights and comprehensively score each indicator. The construction of the decision tree adjusts the weight of each indicator based on the performance in historical data. By comparing the comprehensive performance scores of the five schemes, scheme B with the highest comprehensive score is selected, with an average response time of 45ms and an error rate of less than 0.1%. The control parameters of scheme B are associated with high-concurrency scenarios to form a detailed scenario-parameter mapping table. This mapping table is then converted into a standardized control configuration template and stored in a preset template library. When the system detects a similar high-concurrency scenario, the template is automatically called to achieve rapid response and performance optimization of the scenario. Through this approach, not only the adaptability and efficiency of the virtual environment are improved, but also the automation and intelligence of data processing are ensured.

[0054] The operating data of the electrical equipment is collected in real time through the data transmission channel and compared with the simulation results of the virtualized digital model. The virtualized digital model and the standardized control configuration template are optimized through the gradient descent algorithm, and remote control assistance is achieved through the optimized virtualized digital model and standardized control configuration template.

[0055] As a preferred implementation, the process of optimizing the virtualized digital model and the standardized control configuration template includes: constructing a state space equation group according to the virtualized digital model; using the Kalman filter algorithm, combining the state space equation group with the equipment operation status data collected by the sensor in real time, to estimate the system state; inputting the estimated system state into the virtualized digital model to obtain the predicted value of each state variable; calculating the error between the actual operation data of the equipment and the simulation result of the virtual model, and constructing a cost function; based on the cost function, using the gradient descent algorithm to optimize the parameters of the virtualized digital model, so as to minimize the error between the simulation result and the actual operation data, and obtain the optimized virtual model; predicting the operation state of the electrical equipment according to the optimized virtual model; combining the performance constraints and task requirements of the equipment, using the model predictive control algorithm, generating the optimal control sequence of the virtual control, and updating the standardized control configuration template; inputting the optimal control sequence into the control system of the electrical equipment, obtaining the equipment status data in the virtual control process, and feeding it back to the virtualized digital model in real time, and continuously optimizing the standardized control configuration template and the virtualized digital model.

[0056] Specifically, according to the three-dimensional model of the equipment, the mathematical model of the equipment is established, the key parameters of the equipment such as temperature, pressure, flow rate are selected as state variables, the adjustable parameters such as heating power and feed speed of the equipment are selected as control variables, and the state space equation group is constructed based on the laws of physics. The extended Kalman filter algorithm is used, combined with the equipment operation status data collected in real time by pressure sensors, temperature sensors, etc., to estimate the temperature field, pressure field and other states of the equipment, and the estimation accuracy is better than 90%. The estimated equipment state is input into the equipment virtual simulation model built by Simulink, and the temperature, pressure and other state variables of the equipment after running for 1 hour in the current state are simulated, and compared with the actual operation results, and the root mean square error is calculated as the cost function. The Levenberg-Marquardt optimization algorithm is used to calibrate the parameters such as thermal conductivity and specific heat capacity in the virtual model by minimizing the cost function. After 10 iterations of optimization, the error between the simulation results and the measured data is reduced to less than 5%. The optimized virtual model is used to predict the temperature and pressure change curves of the equipment in the next 24 hours. Under the constraint of safe operation of the equipment, the sequential quadratic programming algorithm is used to solve the optimal control sequence of virtual control, including the optimal heating power curve and feed speed curve, to maximize the output of the equipment. The optimal control sequence is converted into a control instruction executable by the PLC and sent to the control system of the equipment to realize automatic virtual control of the equipment. During the virtual control process, the real-time status data of the equipment is collected every 1 minute and fed back to the virtual model for verification and correction of model parameters. At the same time, the Q-learning reinforcement learning algorithm is used to adjust the training samples and learning rate of the virtual model according to the difference between the actual operation data and the simulation results, and optimize the reward function design of the control strategy. After 7 consecutive days of online learning, the virtual control accuracy has increased from 90% to 95%, laying the foundation for the long-term automatic operation of the equipment.

[0057] Identify abnormal situations during the operation process, automatically analyze the causes of the abnormalities and generate treatment plans based on the preset fault diagnosis logic and decision tree algorithm.

[0058] As a preferred implementation, the process of generating a treatment plan includes: according to a preset fault diagnosis logic, obtaining real-time data during the operation process to determine whether an abnormal situation occurs; if an abnormal situation is detected, triggering the fault diagnosis process, and using a decision tree algorithm to analyze the abnormal data; through the decision tree algorithm, combined with historical fault case data, reasoning about the abnormal data to derive the cause of the abnormality; according to the cause of the abnormality, matching treatment measures in a preset treatment plan knowledge base; if a suitable treatment plan is matched, presenting the specific operation steps of the plan to the operator; if there is a lack of a treatment plan that meets the requirements, generating a new treatment plan through case reasoning based on the attributes of the cause of the abnormality, guiding the operator to handle it, and storing it in a preset treatment plan knowledge base.

[0059] Specifically, during the virtual control process, the system collects the operation data of the equipment in real time, including key parameters such as temperature, pressure, and flow. By comparing with the simulation results of the virtual model, if the deviation between the actual data and the simulation results exceeds the preset threshold (such as 5%), it is determined to be an abnormal situation. When an abnormal situation is detected, the system automatically triggers the fault diagnosis process and uses the decision tree algorithm to analyze the abnormal data. The decision tree model is trained based on historical fault case data. By judging characteristic parameters such as temperature and pressure, it can quickly infer the possible causes of the abnormality, such as "temperature sensor failure" and "pressure exceeds the safe range". According to the abnormal cause obtained by diagnosis, the system matches it in the preset disposal solution knowledge base. The knowledge base stores a large number of fault disposal solutions, each of which contains attributes such as abnormal cause and disposal measures. By calculating the similarity between the abnormal cause and the solution in the knowledge base, the solution with the highest matching degree will be selected and presented to the operator. The solution describes the disposal steps in detail, such as "restarting the temperature sensor" and "adjusting the pressure valve opening to 30%". If there is a lack of disposal solutions with high matching degree in the knowledge base, the system will generate a new disposal solution through case reasoning based on the attributes of the abnormal cause. Case-based reasoning generates the appropriate handling steps for the current abnormal situation by analyzing the association rules between abnormal causes and handling measures in historical cases. The newly generated handling plan will be added to the knowledge base and immediately used to guide operators to handle abnormal situations. Through the above process, the system can realize intelligent fault diagnosis and handling, and improve the safety and reliability of equipment operation.

[0060] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A remote control assistance method based on virtual technology, characterized in that: The following steps are involved: Constructing a three-dimensional geometric model and a physical simulation model of the electrical equipment, verifying and optimizing the three-dimensional geometric model and the physical simulation model through finite element analysis, and obtaining a virtualized digital model; By setting a parameterized control interface and a visual operation interface for the virtualized digital model, the virtualized digital model is adjusted and monitored in real time to obtain an optimal parameter configuration of the virtualized digital model; Establishing a data transmission channel between the virtualized digital model and the real device, and interacting with each other through the data transmission channel; Obtain different scenarios of the virtual environment, preset several control schemes and corresponding optimization strategies for different scenarios, obtain the optimal control parameter combination under different scenarios through simulation analysis, and generate standardized control configuration templates based on the optimal control parameter combination under different scenarios; The operating data of the electrical equipment is collected in real time through the data transmission channel and compared with the simulation results of the virtualized digital model. The virtualized digital model and the standardized control configuration template are optimized through the gradient descent algorithm, and remote control assistance is achieved through the optimized virtualized digital model and standardized control configuration template.

2. The remote control assistance method based on virtual technology according to claim 1 is characterized in that: The process of obtaining a virtual digital model includes: The three-dimensional geometric model and the physical simulation model are meshed to obtain a finite element model; based on the actual working conditions and boundary conditions of the electrical equipment, loads and constraints are set for the finite element model, and finite element solution calculations are performed to obtain finite element analysis results; an electrical equipment model is constructed, and the stress distribution and deformation of the electrical equipment model are evaluated according to the finite element analysis results to determine whether the design requirements are met; if the design requirements are not met, the three-dimensional geometric model and the physical simulation model are optimized according to the evaluation results, and the finite element analysis is repeated until the electrical equipment model meets the design requirements; the verified and optimized three-dimensional geometric model and the physical simulation model are digitized to obtain a virtualized digital model.

3. The remote control assistance method based on virtual technology according to claim 2 is characterized in that: The process of determining whether the design requirements are met includes: According to the structural parameters and material properties of the electrical equipment, an electrical equipment model is established; load conditions and boundary conditions are set for the electrical equipment model, and finite element meshing is performed; the finite element analysis method is used to simulate and calculate the stress distribution and deformation of the electrical equipment model; stress distribution and deformation data are extracted from the simulation results, and the stress distribution and deformation data are compared with preset design requirement thresholds to determine whether the electrical equipment model meets the design requirements; if the electrical equipment model does not meet the design requirements, the structural layout and dimensional parameters of the electrical equipment are optimized and adjusted according to the stress concentration areas and the parts with larger deformation; the stress distribution and deformation of the optimized electrical equipment model are re-simulated and verified until the design requirements are met.

4. The remote control assistance method based on virtual technology according to claim 1, characterized in that: The process of obtaining the optimal parameter configuration includes: Extract key parameters of the virtualized digital model, construct a data model and protocol of a parameterized control interface, map and bind the key parameters to interface controls, graphically display and interactively adjust the key parameters, obtain the operating status data of the virtualized digital model, monitor each key parameter in the operating status data in real time, and determine whether it exceeds a preset threshold range; if the key parameter exceeds the preset threshold range, trigger an early warning mechanism, build a parameter optimization algorithm, train historical adjustment data and real-time monitoring data, obtain the optimal parameter configuration, prompt the user to adjust the parameters through a visual interface, and pass the adjustment instruction to the virtualized digital model through the parameterized control interface.

5. The remote control assistance method based on virtual technology according to claim 1, characterized in that: A data transmission channel is established between the virtualized digital model and the real device, and the process of interacting through the data transmission channel includes: According to the characteristics of the virtual model and the real device, the network communication protocol and transmission method are selected to establish a data transmission channel. The status data of the real device is obtained through the data transmission channel and mapped to the corresponding parameters of the virtual model to synchronize the virtual and real states. According to the control instructions of the virtual model, the control signal is sent to the real device through the data transmission channel, and the real device is controlled by the virtual model.

6. The remote control assistance method based on virtual technology according to claim 1, characterized in that: The process of generating a standardized control configuration template includes: According to different scenarios of the virtual environment, multiple control schemes and optimization strategies are preset for different scenarios to form an initial configuration parameter library; simulation experiments are carried out on each control scheme in the virtual environment to obtain various performance indicator data, and the comprehensive performance score of each control scheme is obtained based on the various performance indicator data; the control parameter combination with the highest score is screened out according to the comprehensive performance score ranking; the screened control parameter combination is associated with the corresponding virtual environment scenario to form a scenario-parameter mapping table; based on the scenario-parameter mapping table, a standardized control configuration template suitable for different virtual environment scenarios is generated.

7. The remote control assistance method based on virtual technology according to claim 1, characterized in that: Constructing a state space equation group according to the virtualized digital model; using a Kalman filter algorithm, combining the state space equation group with the equipment operation status data collected in real time by the sensor, to estimate the system state; inputting the estimated system state into the virtualized digital model to obtain the predicted value of each state variable; The error between the actual operation data of the equipment and the simulation result of the virtual model is calculated to construct a cost function; based on the cost function, the gradient descent algorithm is used to optimize the parameters of the virtualized digital model to minimize the error between the simulation result and the actual operation data, and an optimized virtual model is obtained; according to the optimized virtual model, the operation status of the electrical equipment is predicted; in combination with the performance constraints and task requirements of the equipment, the model predictive control algorithm is used to generate the optimal control sequence of the virtual control and update the standardized control configuration template; the optimal control sequence is input into the control system of the electrical equipment, the equipment status data during the virtual control process is obtained, and the data is fed back to the virtualized digital model in real time, and the standardized control configuration template and the virtualized digital model are continuously optimized.

8. The remote control assistance method based on virtual technology according to claim 1, characterized in that: The method further comprises: Identify abnormal situations during the operation process, automatically analyze the causes of the abnormalities and generate treatment plans based on the preset fault diagnosis logic and decision tree algorithm.

9. The remote control assistance method based on virtual technology according to claim 8, characterized in that: The process of generating a disposal plan includes: According to the preset fault diagnosis logic, real-time data in the operation process is obtained to determine whether an abnormal situation occurs; if an abnormal situation is detected, the fault diagnosis process is triggered, and the decision tree algorithm is used to analyze the abnormal data; through the decision tree algorithm, combined with historical fault case data, the abnormal data is inferred to derive the cause of the abnormality; according to the cause of the abnormality, the disposal measures are matched in the preset disposal solution knowledge base; if a suitable disposal solution is matched, the specific operation steps of the solution are presented to the operator; if there is a lack of disposal solutions that meet the requirements, a new disposal solution is generated through case reasoning based on the attributes of the abnormal cause, the operator is guided to handle it, and it is stored in the preset disposal solution knowledge base.

Images