Power station digital refined modeling method and system

Abstract

The invention provides a digital refined modeling method and system for a power station, and the method comprises the steps: carrying out the surveying and mapping modeling of the power station through employing the external image data of the power station in combination with a digital elevation model, and carrying out the manual modeling of the power station through employing the internal image data of the power station, a construction drawing and a building information model in combination with a detachable principle. Constructing an initial digital model; acquiring actual operation data of the power station in real time; performing a simulation experiment by using the initial digital model to obtain simulation operation data; and comparing the actual operation data with the simulation operation data, determining an error analysis result, optimizing model parameters of the initial digital model in combination with a machine learning algorithm to obtain a refined digital model, and comparing and optimizing the initial digital model by comparing the actual operation data with the simulation data to obtain a refined digital model. Compared with a simulation model purely constructed through a two-dimensional plane graph, the precision of a refined digital model is effectively improved, and actual data of a power station can be fed back more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of digital modeling, and in particular to a method and system for digital refined modeling of a power station. Background Art

[0002] my country's energy industry is currently experiencing rapid development. As power plant scale and unit capacity continue to increase, the variety and quantity of equipment are increasing. This leads to significant uncertainty in the mechanical structure, electrical system, and overall safety and reliability of the units, posing serious challenges to the safe operation of power plants. Traditional operation and maintenance models identify the operating status of units and related components solely based on their operating parameters. This approach relies on the experience of maintenance personnel and exhibits significant lags. Some power plants have also adopted digital simulation technology to simulate the actual operating conditions of units. These typically rely on two-dimensional plan views or simple three-dimensional models, lacking the ability to monitor equipment operating conditions in real time and provide refined modeling capabilities. This leads to problems such as low fault diagnosis efficiency, high operation and maintenance costs, and inaccurate power generation forecasts.

[0003] Therefore, how to improve the accuracy of power plant models has become a technical problem that technical personnel in this field urgently need to solve. Summary of the Invention

[0004] The present invention provides a method and system for digital and refined modeling of a power station, which are used to solve the defect of poor accuracy of power station models in the prior art.

[0005] In a first aspect, the present invention provides a method for digital and refined modeling of a power plant, comprising:

[0006] The power station was surveyed and modeled using external image data of the power station in combination with a digital elevation model. The power station was also manually modeled using internal image data of the power station, construction drawings, and a building information model in combination with the principle of disassembly.

[0007] constructing an initial digital model based on the results of the surveying and mapping modeling and the results of the manual modeling;

[0008] Using detection devices and a SCADA system to collect actual operating data of the power station in real time;

[0009] Based on the simulation experiment parameters, a simulation experiment is performed using the initial digital model to obtain simulation operation data;

[0010] Using a comparison algorithm and an error assessment model, the actual operation data and the simulated operation data are compared to determine an error analysis result;

[0011] Based on the error analysis results, the model parameters of the initial digital model are optimized in combination with a machine learning algorithm to obtain a refined digital model.

[0012] According to a method for digital and refined modeling of a power station provided by the present invention, the method utilizes external image data of the power station in combination with a digital elevation model to perform surveying and modeling of the power station, including:

[0013] Based on oblique photography, drones were used to conduct a full-scale scan of the power station's topography to obtain external image data;

[0014] The external image data is imported into the 3D reconstruction software for surveying and mapping modeling, and a topographical and building geometric entity structure model that meets the digital elevation model standard is generated to complete the surveying and mapping modeling.

[0015] According to the present invention, a method for digital and refined modeling of a power station is provided, wherein the power station is manually modeled using internal image data, construction drawings, and a building information model of the power station in combination with the principle of disassembly, including:

[0016] Collect internal image data, construction drawings, and building information models of power plants;

[0017] manually constructing the power station's internal mechanical structure, electrical components, piping systems, electrical wiring, external dimensions, and relationship to the surrounding environment based on the internal image data, construction drawings, and building information models;

[0018] The internal mechanical structure, electrical components, piping system, electrical wiring, external dimensions, and relationship with the surrounding environment are input into 3ds Max. In combination with disassembly, a visual model of the internal structure is manually constructed to complete the manual modeling.

[0019] According to a method for digital and refined modeling of a power plant provided by the present invention, the method utilizes a detection device and a SCADA system to collect actual operation data of the power plant in real time, including:

[0020] Collect various power plant operation data through diverse sensors;

[0021] The various operating data are aggregated through the SCADA system to determine the actual operating data of the power station.

[0022] According to a method for digital refined modeling of a power station provided by the present invention, the method includes: performing a simulation experiment based on simulation experiment parameters and using the initial digital model to obtain simulation operation data, including:

[0023] Determine simulation test parameters based on various parameter thresholds in power plant operation technical standards and specifications, actual operation characteristic parameters, known basic operation parameters, and characteristic parameters under known abnormal operation conditions;

[0024] Based on the simulation test parameters, a simulation test is run to generate simulation operation data covering all characteristic parameters of the power station operation data.

[0025] According to a power plant digital refined modeling method provided by the present invention, before determining simulation test parameters based on various parameter thresholds in power plant operation technical standards and specifications, actual operation characteristic parameters, known basic operation parameters, and characteristic parameters under known abnormal operation conditions, the method further includes:

[0026] Collect the accumulated operation data of the power station within a preset historical period, including operation data under different external environmental conditions, different operating conditions, and different fault conditions;

[0027] Based on the operating data under the different external environmental conditions, different operating conditions, and different fault states, combined with the aerodynamic principles, electrochemical principles, electromagnetic principles, mechanical transmission principles, and electrical control principles of the unit, the operating behavior of the unit under normal and abnormal conditions is determined to obtain the actual operating characteristic parameters.

[0028] According to a method for digital refined modeling of a power plant provided by the present invention, the method optimizes the model parameters of the initial digital model based on the error analysis result in combination with a machine learning algorithm to obtain a refined digital model, including:

[0029] Using the error analysis results as training samples, deep learning model training is performed;

[0030] During the training process, the weights and biases of the model are continuously updated through a back-propagation algorithm to control the model to learn the difference pattern between the actual operation data and the simulated operation data;

[0031] The parameters of the initial digital model are optimized through the difference pattern to obtain a refined digital model.

[0032] A method for digital and refined modeling of a power plant provided by the present invention further includes:

[0033] Based on the responsive principle, the overall layout of the power station and the operating status of the equipment are displayed in a 3D visual manner, and various key operating parameters are displayed in real time;

[0034] Receive user operation instructions, and change the display style of the three-dimensional visualization method and the switching of the various key operating parameters according to the operation instructions.

[0035] A method for digital and refined modeling of a power plant provided by the present invention further includes:

[0036] Establish user rights management mechanism based on different user roles;

[0037] Based on the user authority management mechanism, combined with multi-level protection, different operation permissions are matched for users, and based on the different operation permissions, operation logs are pushed to corresponding personnel for security warning protection.

[0038] In a second aspect, the present invention further provides a power plant digital refined modeling system, comprising:

[0039] A modeling module is configured to perform surveying and modeling of the power station using external image data of the power station in combination with a digital elevation model, and to perform manual modeling of the power station using internal image data of the power station, construction drawings, and a building information model in combination with the principle of disassembly; and to construct an initial digital model based on the results of the surveying and modeling and the results of the manual modeling;

[0040] An acquisition module, for collecting actual operation data of the power station in real time using a detection device and a SCADA system;

[0041] A simulation module, configured to perform a simulation experiment using the initial digital model based on simulation experiment parameters to obtain simulation operation data;

[0042] A comparison module, configured to compare the actual operation data with the simulated operation data using a comparison algorithm and an error evaluation model to determine an error analysis result;

[0043] The optimization module is used to optimize the model parameters of the initial digital model based on the error analysis results in combination with a machine learning algorithm to obtain a refined digital model.

[0044] In a third aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for digital and refined modeling of a power station as described above is implemented.

[0045] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for digital and refined modeling of power plants.

[0046] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for digital and refined modeling of power plants.

[0047] The present invention provides a method and system for digital refined modeling of a power station. The method uses the external image data of the power station in combination with a digital elevation model to survey and model the power station, and uses the internal image data of the power station, construction drawings and building information models, in combination with the principle of disassembly to manually model the power station; constructs an initial digital model based on the results of surveying and modeling and the results of manual modeling; uses a detection device and a SCADA system to collect actual operation data of the power station in real time; uses the initial digital model to conduct simulation experiments based on simulation experiment parameters to obtain simulation operation data; uses a comparison algorithm and an error evaluation model to compare the actual operation data with the simulation operation data to determine the error analysis results; based on the error analysis results, combines the machine learning algorithm to optimize the model parameters of the initial digital model to obtain a refined digital model. Compared with the simulation model simply constructed by a two-dimensional plane diagram, the method of comparing and optimizing the initial digital model by comparing the actual operation data with the simulation data effectively improves the accuracy of the refined digital model and can more accurately feedback the actual data of the power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 This is a flow chart of the method for digital and refined modeling of a power station provided in this embodiment;

[0050] Figure 2 This embodiment provides Figure 1 The corresponding modular schematic diagram;

[0051] Figure 3 This is a schematic diagram of the structure of the power plant digital refined modeling system provided in this embodiment;

[0052] Figure 4 Schematic diagram of the structure of the electronic device provided in this embodiment. DETAILED DESCRIPTION

[0053] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0054] Figure 1 This is a flow chart of the method for digital and refined modeling of a power station provided in this embodiment. Figure 2 This embodiment provides Figure 1 Corresponding modular schematic diagram.

[0055] like Figure 1 and Figure 2 As shown, the embodiment of the present invention provides a method for digital and refined modeling of a power station, which mainly includes the following steps:

[0056] 101. Use the external image data of the power station in combination with the digital elevation model to survey and model the power station. Use the internal image data of the power station, construction drawings and building information model, and combine the principle of disassembly to manually model the power station.

[0057] In a specific implementation, a drone is first used to comprehensively scan the power plant's topography based on oblique photography to obtain external image data. Using an oblique photography drone with high-precision positioning and high-resolution imaging capabilities, a comprehensive and detailed scan of geometric structures such as the wind farm's topography, wind turbines, substation buildings, and the tall solar thermal towers, large-scale concentrators, and the outlines of thermal storage devices is performed to obtain high-resolution image data. During the scanning process, a flight route is planned based on the power plant's topographical characteristics and equipment distribution to ensure comprehensive, comprehensive image data. During flight, the drone's altitude, speed, and attitude are strictly controlled to ensure image data quality.

[0058] After the exterior photography is complete, the image data is imported into professional 3D reconstruction software, such as ContextCapture, using its advanced algorithms for data processing and 3D model generation. When generating models of topography and building geometry, the requirements of the "Basic Geographic Information Digital Product 1:500, 1:1000, and 1:2000 Digital Elevation Model" standard are strictly adhered to, maintaining accuracy within 5cm. Model accuracy is repeatedly verified and corrected to ensure that the model accurately reflects the actual site conditions, ultimately completing the surveying and mapping modeling.

[0059] The power station's internal image data, construction drawings, and building information model were collected. Based on these data, the internal mechanical structure, electrical wiring, external dimensions, and the relationship with the surrounding environment were manually constructed. These internal mechanical structure, electrical wiring, external dimensions, and the relationship with the surrounding environment were input into 3ds Max, and a visual model of the internal structure was manually constructed, taking into account disassembly capabilities.

[0060] Specifically, using the 3D modeling software 3ds Max, a power plant model was manually constructed based on the aforementioned data, fully depicting the power plant's structures, transmission equipment, substation equipment, control and monitoring equipment, security and fire protection equipment, and other components. During the modeling process, the principle of disassembly was adhered to, with components assembled using virtual connectors to ensure the model's flexible disassembly and display in subsequent applications. For example, the wind turbine gearbox model was equipped with movable connectors to demonstrate the gear meshing process and transmission principles. The generator model constructed the internal winding and core structure to visualize the internal structure. The concentrator's reflective mirror surface and bracket connection were carefully depicted, and the internal heat transfer medium channel structure of the solar collector was displayed. The models of key equipment such as the concentrator, solar collector, and steam turbine were ensured to be disassembled, laying the foundation for creating equipment animations and demonstrating their internal workings. The model covers all components of a solar thermal power station, including buildings, concentrating and collecting equipment, heat storage equipment, power generation equipment, heat transfer and exchange equipment, control and monitoring equipment, environmental protection equipment, metering equipment, auxiliary equipment, security and fire protection equipment. The modeling is ultimately completed manually.

[0061] 102. Based on the results of surveying and mapping modeling and manual modeling, construct the initial digital model.

[0062] Specifically, by integrating the results of external surveying and modeling with those of internal manual modeling, we can fully integrate the internal structure and the external environment, thereby constructing a complete initial digital model. This includes buildings, power generation equipment, fuel supply and processing equipment, power transmission equipment, power transformation equipment, control and monitoring equipment, environmental protection equipment, metering equipment, auxiliary equipment, security and fire protection equipment, etc.

[0063] The initial digital model utilizes WebGL technology, enabling 3D scene rendering capabilities and flexible 3D scene camera adjustments, allowing users to observe the details of the power plant model from various angles and distances. Point of Interest (POI) point drawing is supported, allowing users to easily mark key equipment and monitoring points. Path drawing is provided to visualize transmission lines and equipment inspection routes within the power plant. Heat map rendering provides intuitive visualization of power generation efficiency distribution and equipment operating status across different areas of the power plant. Furthermore, model optimization is supported, utilizing model simplification, texture compression, and Level of Detail (LOD) technology to ensure smooth operation across various devices (including desktops, laptops, tablets, and smartphones), providing a superior user experience. Furthermore, a rich set of model editing tools, including particle effects, cutaway effects, and transparency, allow users to customize and display the model according to their specific needs. For example, adding particle effects to simulate airflow through wind turbine blades, using cutaway effects to visualize the internal structure of a wind turbine, and using transparency effects to visualize the connections between internal components of the device. Collaborative modeling and simulation is supported, facilitating teamwork.

[0064] 103. Use detection devices and SCADA system to collect actual operation data of the power station in real time.

[0065] Specifically, rigorously calibrated and quality-tested sensors are installed on key equipment and components in the power plant. A distributed data acquisition architecture can be adopted, leveraging edge computing technology to perform preliminary data analysis and processing locally at the sensor nodes. The collected data parameters are rich and diverse, such as wind speed, wind direction, temperature, humidity, fan speed, power, voltage, current, power factor, and vibration at the wind farm; and collector tube temperature, heat storage medium temperature, turbine inlet steam temperature, ambient humidity, wind speed in the concentrating field, steam pressure, pipeline pressure, turbine speed, heat transfer medium flow rate, steam flow rate, concentrator tracking speed, heat storage material weight, spacing between concentrators, transmission component torque, generated power, heat collection power, voltage, current, power factor, vibration during equipment operation, sound power, water tank level, cooling water flow rate, heat transfer medium quality, and makeup water quality at the CSP plant.

[0066] When collecting data, industrial-grade sensors are used to ensure reliability and stability in harsh environments. For example, for offshore wind farms, waterproof and corrosion-resistant sensors are selected; for high-altitude wind farms, sensors adapted to low-pressure environments are used. A regular sensor calibration and maintenance mechanism is established to ensure accurate measurements. Backup sensors are also provided to automatically switch to the backup sensor in the event of a primary sensor failure, ensuring continuous data collection.

[0067] Data acquisition methods are diverse. Wind farms primarily utilize direct measurements through various sensors installed on components such as wind turbine blades, towers, and nacelles. For solar thermal power stations, temperature sensors are evenly distributed across the surface of the collector tubes to monitor temperature changes in different locations in real time. Pressure sensors are installed at key points in steam pipelines to obtain steam pressure data, and speed sensors are installed on the turbine shafts to measure turbine speed. The SCADA system aggregates and integrates data from various sensors, while cameras capture the appearance of equipment, microphones monitor operating sounds, gas monitoring equipment detects exhaust gas composition, and fluid monitoring equipment analyzes parameters such as the flow rate and flow rate of the heat transfer medium.

[0068] At the same time, all sensors are connected to the data acquisition terminal via wired or wireless means. The data acquisition terminal is responsible for collecting, organizing and preliminarily processing sensor data, and transmitting the data in real time to the data processing and storage module via industrial Ethernet or wireless transmission technology.

[0069] Therefore, the actual operation data of the power station was successfully collected.

[0070] After data collection is complete, big data processing and high-performance database management systems are employed to efficiently process and securely store massive amounts of data. The collected data undergoes real-time preprocessing, including cleaning, denoising, and normalization, to remove outliers and noise. Data from various formats and sources is converted to a standardized format for subsequent analysis and processing. Distributed storage technologies, such as the Hadoop Distributed File System (HDFS), are used to store data across multiple nodes, ensuring data security and reliability. Furthermore, data indexes and data warehouses are established to facilitate rapid query and access of historical data, providing a data foundation for model building, simulation analysis, and decision support. Data mining techniques are used to uncover potential patterns and insights from historical data, providing insights for optimizing power plant operations. For example, a sliding window algorithm aggregates data such as wind speed and power to generate statistical values ​​at different time granularities, providing data support for subsequent trend analysis and anomaly detection.

[0071] 104. Based on the simulation experiment parameters, the initial digital model is used to conduct simulation experiments to obtain simulation operation data.

[0072] Specifically, it relies on the technical standards and specifications for power station operation, such as the industry's commonly used thermal collection efficiency standards and power generation indicators. At the same time, it collects the accumulated operation data of the power station within a preset historical period, including operation data under different external environmental conditions, different operating conditions, and different fault conditions. Combined with the aerodynamic principles, mechanical transmission principles, electrical control principles, electrochemical principles, and electromagnetic principles of the unit (such as the optical focusing principle of the concentrator, the energy conversion principle of the steam turbine, and the aerodynamic principle of the wind turbine), the operating behavior of the unit under normal and abnormal conditions is determined (such as the power curve of the wind turbine at different wind speeds, the operating conditions under extreme weather conditions, the parameter changes during equipment failure, the stress conditions of the blades, and the parameter change rules under fault conditions, the relationship between solar radiation intensity in different seasons and time periods and the operating parameters of the power station), and the actual operating characteristic parameters are obtained.

[0073] Use simulation software such as ANSYS and Fluent to set simulation test parameters. When setting simulation test parameters, refer to the key indicators in the power plant operation technical standards and specifications, combine them with actual operating characteristic parameters, incorporate known basic operating parameters (such as physical parameters under standard atmospheric conditions), and fully consider characteristic parameters under known abnormal operating conditions (such as the sudden changes in pressure and temperature when the collector tube leaks) to ensure the comprehensiveness and accuracy of the simulation parameters. For normal operating conditions, set the operating parameter changes within the normal range to simulate the operation of the power plant equipment under normal operating conditions. For abnormal operating conditions, set special conditions such as sudden changes in environmental parameters and equipment failures to simulate the power plant's operational response under extreme conditions.

[0074] Based on the simulation test parameters, simulation tests were run to generate simulation data covering all characteristic parameters of the power plant's operating data. The simulation results were then recorded and analyzed in detail. During the simulation process, the simulation parameters and model settings were continuously optimized to improve the accuracy and reliability of the simulation results. For example, not only were the normal operating conditions of the CSP plant simulated under different combinations of solar irradiance, ambient temperature, and wind speed, but the plant's response under abnormal conditions such as collector tube leakage, concentrator failure, and excessive heat loss from the thermal storage system were also simulated. This resulted in more complete simulation operation data.

[0075] 105. Use comparison algorithms and error assessment models to compare actual operation data with simulated operation data to determine the error analysis results.

[0076] Import actual operation data and simulated operation data into data analysis software, such as Python's data analysis library Pandas, NumPy, and the machine learning framework Scikit-learn. Use data comparison algorithms and error assessment models to compare the actual data collected in real time with the simulated data parameter by parameter, from temperature, pressure to power, flow, etc., to verify the accuracy of the digital model and calculate the errors and deviations between the actual data and the simulated data.

[0077] For example, the accuracy of the model in different parameters is evaluated by calculating indicators such as the root mean square error (RMSE) and mean absolute error (MAE). Parameters and model parts with large errors are analyzed in depth to identify the causes of the errors, such as unreasonable model assumptions, inaccurate parameter settings, and the influence of data noise. If the power generation predicted by the model does not match the actual power generation, the model is corrected and optimized using machine learning algorithms. Using deep learning algorithms, through training with large amounts of real-world and simulation data, model parameters are dynamically adjusted, such as adjusting the coefficients in the thermal efficiency model and optimizing the heat transfer parameters of the heat storage model. The model is continuously iterated and optimized based on the accuracy verification results until a digital model that accurately reflects the actual operating status of the solar thermal power station is obtained.

[0078] 106. Based on the error analysis results, the model parameters of the initial digital model are optimized in combination with the machine learning algorithm to obtain a refined digital model.

[0079] Using the error analysis results as training samples, deep learning model training is performed, such as convolutional neural networks (CNN), recurrent neural networks (RNN), and LSTM (long short-term memory networks), to dynamically adjust and optimize model parameters. During the training process, the model weights and biases are continuously updated through the backpropagation algorithm, controlling the model to learn the difference patterns between actual operation data and simulated operation data. Through the difference patterns, the model parameters of the initial digital model are optimized. After multiple iterative training, when the model error index reaches the set accuracy requirements, the model optimization is considered complete, and the final refined digital model is obtained. During the model optimization process, the experience and knowledge of domain experts are combined to manually intervene and adjust the model to improve the model's interpretability and practicality.

[0080] The refined digital model supports the creation of arbitrary HTML5 UI elements on web pages, such as controlling solar radiation intensity through a slider to intuitively demonstrate its impact on power plant operations. It provides a three-dimensional scene lens scheduling function, allowing users to freely switch perspectives, from a high-altitude bird's-eye view of the entire concentrating field to a close-up observation of the details of the collector tubes. It has a POI point drawing function to mark the location and operating parameters of key equipment. It supports a path drawing function to simulate the flow path of the heat transfer medium in the pipeline. It also implements a thermal map drawing function to intuitively display the temperature distribution in different areas of the power plant.

[0081] Furthermore, a Bayesian optimization algorithm can be introduced to globally optimize model parameters. Bayesian optimization constructs a surrogate model of the objective function (such as a Gaussian process model) and continuously updates the surrogate model based on collected data. This intelligently selects the next optimal parameter combination for testing, finding the optimal model parameters within a relatively small number of trials and improving the model's accuracy and generalization capabilities. A model performance evaluation index system can also be established. In addition to commonly used indicators such as root mean square error (RMSE) and mean absolute error (MAE), some indicators closely related to the actual operation of the power plant are also introduced, such as power generation forecast accuracy and equipment fault warning accuracy. By comprehensively evaluating these indicators, the model's performance can be comprehensively measured, providing more accurate guidance for model optimization and improvement.

[0082] The model is regularly retrained and updated. As power plants and equipment operate longer, more actual operating data is accumulated. This new data is used to retrain the deep learning model, adapting it to factors such as aging power plant equipment and environmental changes, maintaining its accuracy and reliability.

[0083] Furthermore, based on the above-mentioned embodiment, this embodiment also includes: constructing a user-friendly interactive interface for visualizing the power plant model and presenting parameters in real time, facilitating user interaction and operational control. The interface design, based on responsive principles, ensures a good user experience on terminal devices of different sizes (such as desktop computers, tablets, and mobile phones). It displays the overall layout of the power plant and the operating status of the equipment in a three-dimensional visualization, and displays various key operating parameters in real time, such as generated power, speed, temperature, wind direction, and irradiation intensity.

[0084] The system receives user instructions and uses them to change the 3D visualization display style and key operating parameters. For example, users can freely rotate and scale the model using a mouse, keyboard, or touch. Parameters are displayed in real time, using various formats, such as charts and numbers, to present power plant operating parameters. User interaction and operational control are also enabled, allowing users to send commands through the interface to adjust simulation parameters and query historical data. Furthermore, it supports multilingual switching to meet the needs of users in different regions. It also offers personalized customization, allowing users to customize the interface layout and display content based on their usage habits and needs.

[0085] Furthermore, this embodiment also includes: establishing a user authority management mechanism according to different user roles; based on the user authority management mechanism, combined with multi-level protection, matching different operation permissions for users, and based on different operation permissions, pushing operation logs to corresponding personnel for security warning protection.

[0086] Specifically, multi-factor authentication technology is used to manage user permissions and ensure system security and data confidentiality. For example, administrators have the highest permissions and can modify models and configure systems, while ordinary operations and maintenance personnel can only view data and perform simple operations. Multi-layered security protection technologies, including firewalls, intrusion detection systems (IDS), and data encryption, can also be used to prevent external attacks and data leaks. At the same time, the refined digital model is regularly maintained and updated. Based on the actual situation of the power plant's equipment modifications, operational strategy adjustments, and other factors, the model parameters and structure are adjusted in a timely manner to ensure the model's accuracy and effectiveness, and to accurately reflect the power plant's latest operating status.

[0087] System operation logs and fault alarm mechanisms can also be established to record system operations and operating conditions in real time. When an abnormality occurs, an alarm message is issued immediately so that operation and maintenance personnel can handle it promptly. For example, by analyzing data such as server resource utilization and network traffic, it is possible to predict whether the server is likely to be overloaded or attacked by a network, so that appropriate measures can be taken in advance to prevent it and ensure the stable operation of the system.

[0088] The refined digital model obtained by the modeling method of the present invention has the following advantages:

[0089] (1) High-precision modeling: Through oblique photography and manual modeling technology, high-precision modeling of power station equipment is achieved to meet the needs of equipment disassembly, animation production, etc.

[0090] (2) Real-time data monitoring: Through the access of SCADA system and sensor data, real-time simulation and monitoring of equipment operating status can be achieved.

[0091] (3) Efficient interaction: Provides rich API interfaces and functional effects, supports complex 3D scene operations and efficient data display.

[0092] (4) Cross-platform compatibility: supports a variety of terminal devices and browsers to ensure high-quality access and smooth operation of the system.

[0093] Based on the same general inventive concept, the present invention also protects a digital and refined modeling system for a power plant. The digital and refined modeling system for a power plant described below and the digital and refined modeling method for a power plant described above can refer to each other.

[0094] Figure 3 It is a structural diagram of the power plant digital refined modeling system provided in this embodiment.

[0095] like Figure 3 As shown, this embodiment provides a power plant digital refined modeling system, including:

[0096] Modeling module 301 is used to perform surveying and modeling of the power station using external image data of the power station in combination with a digital elevation model, and to perform manual modeling of the power station using internal image data of the power station, construction drawings, and a building information model in combination with the principle of disassembly; and to construct an initial digital model based on the results of the surveying and modeling and the results of the manual modeling;

[0097] The acquisition module 302 is used to collect the actual operation data of the power station in real time using the detection device and the SCADA system;

[0098] The simulation module 303 is used to perform a simulation experiment using the initial digital model based on the simulation experiment parameters to obtain simulation operation data;

[0099] A comparison module 304 is used to compare the actual operation data with the simulated operation data using a comparison algorithm and an error assessment model to determine an error analysis result;

[0100] The optimization module 305 is used to optimize the model parameters of the initial digital model based on the error analysis results in combination with the machine learning algorithm to obtain a refined digital model.

[0101] Figure 4 Schematic diagram of the structure of the electronic device provided in this embodiment.

[0102] like Figure 4 As shown, the electronic device may include: a processor (processor) 410, a communication interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call the logic instructions in the memory 430 to execute the digital refined modeling method of the power station, which includes: using the external image data of the power station in combination with the digital elevation model to survey and model the power station, and using the internal image data, construction drawings and building information model of the power station in combination with the principle of disassembly to manually model the power station; constructing an initial digital model based on the results of the surveying and modeling and the results of the manual modeling; using the detection device and the SCADA system to collect the actual operation data of the power station in real time; based on the simulation experiment parameters, using the initial digital model to conduct a simulation experiment to obtain simulation operation data; using a comparison algorithm and an error evaluation model to compare the actual operation data with the simulated operation data to determine the error analysis results; based on the error analysis results, combining the machine learning algorithm to optimize the model parameters of the initial digital model to obtain a refined digital model.

[0103] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0104] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the digital and refined modeling method of the power station provided by the above methods, the method including: using the external image data of the power station, combined with the digital elevation model, to survey and model the power station, and using the internal image data, construction drawings and building information model of the power station, combined with the principle of disassembly, to manually model the power station; constructing an initial digital model based on the results of the surveying and modeling and the results of the manual modeling; using a detection device and a SCADA system to collect the actual operation data of the power station in real time; based on simulation experiment parameters, using the initial digital model to perform simulation experiments to obtain simulation operation data; using a comparison algorithm and an error evaluation model to compare the actual operation data with the simulation operation data to determine the error analysis results; based on the error analysis results, combining a machine learning algorithm to optimize the model parameters of the initial digital model to obtain a refined digital model.

[0105] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the digital refined modeling method of a power station provided by the above-mentioned methods, the method comprising: using the external image data of the power station in combination with a digital elevation model to survey and model the power station, and using the internal image data, construction drawings and building information model of the power station in combination with the principle of disassembly to manually model the power station; constructing an initial digital model based on the results of the surveying and modeling and the results of the manual modeling; using a detection device and a SCADA system to collect the actual operation data of the power station in real time; based on simulation experiment parameters, using the initial digital model to conduct a simulation experiment to obtain simulation operation data; using a comparison algorithm and an error evaluation model to compare the actual operation data with the simulation operation data to determine an error analysis result; based on the error analysis result, optimizing the model parameters of the initial digital model in combination with a machine learning algorithm to obtain a refined digital model.

[0106] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0107] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A digital and refined modeling method for a power station, characterized by: include: The power station was surveyed and modeled using external image data of the power station in combination with a digital elevation model. The power station was also manually modeled using internal image data of the power station, construction drawings, and a building information model in combination with the principle of disassembly. constructing an initial digital model based on the results of the surveying and mapping modeling and the results of the manual modeling; Using detection devices and a SCADA system to collect actual operating data of the power station in real time; Based on the simulation experiment parameters, a simulation experiment is performed using the initial digital model to obtain simulation operation data; Using a comparison algorithm and an error assessment model, the actual operation data and the simulated operation data are compared to determine an error analysis result; Based on the error analysis results, the model parameters of the initial digital model are optimized in combination with a machine learning algorithm to obtain a refined digital model.

2. The power plant digital refined modeling method according to claim 1, characterized in that: The method of surveying and modeling the power station using the external image data of the power station in combination with the digital elevation model includes: Based on oblique photography, drones were used to conduct a full-scale scan of the power station's topography to obtain external image data; The external image data is imported into the 3D reconstruction software for surveying and mapping modeling, and a topographical and building geometric entity structure model that meets the digital elevation model standard is generated to complete the surveying and mapping modeling.

3. The power plant digital refined modeling method according to claim 1, characterized in that: The power station is manually modeled using the power station's internal image data, construction drawings, and building information models, combined with the principle of disassembly, including: Collect internal image data, construction drawings, and building information models of power plants; manually constructing the power station's internal mechanical structure, electrical components, piping systems, electrical wiring, external dimensions, and relationship to the surrounding environment based on the internal image data, construction drawings, and building information models; The internal mechanical structure, electrical components, piping system, electrical wiring, external dimensions, and relationship with the surrounding environment are input into 3ds Max. In combination with disassembly, a visual model of the internal structure is manually constructed to complete the manual modeling.

4. The power plant digital refined modeling method according to claim 1, characterized in that: The detection device and the SCADA system are used to collect the actual operation data of the power station in real time, including: Collect various power plant operation data through diverse sensors; Summarize the various operational data through the SCADA system and collect video surveillance images through cameras; The actual operation data of the power station is determined by combining the data summarized by the SCADA system and the video monitoring screen.

5. The power plant digital refined modeling method according to claim 1, characterized in that: The method of performing a simulation experiment based on the simulation experiment parameters and utilizing the initial digital model to obtain simulation operation data includes: Determine simulation test parameters based on various parameter thresholds in power plant operation technical standards and specifications, actual operation characteristic parameters, known basic operation parameters, and characteristic parameters under known abnormal operation conditions; Based on the simulation test parameters, a simulation test is run to generate simulation operation data covering all characteristic parameters of the power station operation data.

6. The power plant digital refined modeling method according to claim 5, characterized in that: Before determining the simulation test parameters based on various parameter thresholds in power plant operation technical standards and specifications, actual operation characteristic parameters, known basic operation parameters, and characteristic parameters under known abnormal operation conditions, the following steps are also included: Collect the accumulated operation data of the power station within a preset historical period, including operation data under different external environmental conditions, different operating conditions, and different fault conditions; Based on the operating data under the different external environmental conditions, different operating conditions, and different fault states, combined with the aerodynamic principles, electrochemical principles, electromagnetic principles, mechanical transmission principles, and electrical control principles of the unit, the operating behavior of the unit under normal and abnormal conditions is determined to obtain the actual operating characteristic parameters.

7. The power plant digital refined modeling method according to claim 1, characterized in that: The method of optimizing the model parameters of the initial digital model based on the error analysis results and combining a machine learning algorithm to obtain a refined digital model includes: Using the error analysis results as training samples, deep learning model training is performed; During the training process, the weights and biases of the model are continuously updated through a back-propagation algorithm to control the model to learn the difference pattern between the actual operation data and the simulated operation data; The parameters of the initial digital model are optimized through the difference pattern to obtain a refined digital model.

8. The method for digital and refined modeling of a power plant according to any one of claims 1 to 7, characterized in that: Also includes: Based on the responsive principle, the overall layout of the power station and the operating status of the equipment are displayed in a 3D visual manner, and various key operating parameters are displayed in real time; Receive user operation instructions, and change the display style of the three-dimensional visualization method and the switching of the various key operating parameters according to the operation instructions.

9. The method for digital and refined modeling of a power station according to any one of claims 1 to 7, characterized in that: Also includes: Establish user rights management mechanism based on different user roles; Based on the user authority management mechanism, combined with multi-level protection, different operation permissions are matched for users, and based on the different operation permissions, operation logs are pushed to corresponding personnel for security warning protection.

10. A digital and refined modeling system for a power station, characterized in that: include: The modeling module is used to survey and model the power station using the external image data of the power station in combination with the digital elevation model. The internal image data of the power station, construction drawings and building information model are used to manually model the power station in combination with the principle of disassembly. constructing an initial digital model based on the results of the surveying and mapping modeling and the results of the manual modeling; An acquisition module, for collecting actual operation data of the power station in real time using a detection device and a SCADA system; A simulation module, configured to perform a simulation experiment using the initial digital model based on simulation experiment parameters to obtain simulation operation data; A comparison module, configured to compare the actual operation data with the simulated operation data using a comparison algorithm and an error evaluation model to determine an error analysis result; The optimization module is used to optimize the model parameters of the initial digital model based on the error analysis results in combination with a machine learning algorithm to obtain a refined digital model.

Images