Digital twin energy management method and system based on artificial intelligence algorithm

Abstract

The invention relates to the technical field of energy management visualization, in particular to a digital twinborn energy management method based on an artificial intelligence algorithm, which comprises the following steps of: acquiring data from energy production to consumption links by adopting a sensor and an external system, verifying and optimizing, and obtaining a digital twinborn energy management result; constructing a virtual mirror image model capable of reflecting the state of the physical system in real time; an interaction function is designed, and a visual interaction scene is realized; and displaying the data in a scene in an overlapping manner, feeding back an interaction result, detecting energy consumption abnormity by using an algorithm, generating early warning information, inputting the information into a physical system for execution, feeding back a result, and obtaining an optimized digital twin energy management module. The method solves the problems that the quality of data acquisition and processing in the link from energy production to consumption is poor, a real-time precise digital twinborn model is difficult to construct, visual interaction is not visual, energy consumption abnormity cannot be detected in time, an effective regulation and control strategy cannot be generated in time, and then the energy management efficiency and quality are affected.

Description

Technical Field

[0001] This invention belongs to the field of energy management visualization technology, specifically relating to a digital twin energy management method and system based on artificial intelligence algorithms. Background Technology

[0002] In the field of energy management visualization technology, the entire energy production and consumption process involves numerous complex and interconnected systems and devices. Traditional energy management models rely primarily on manual data collection and decentralized monitoring equipment. This approach is not only inefficient but also struggles to guarantee data integrity and accuracy, making it difficult to comprehensively and in real-time grasp the dynamic information of each stage of the energy system. Due to the diverse and inconsistent quality of data sources, there is a significant amount of noise and outliers. Furthermore, the lack of effective integration of information from different data sources hinders accurate analysis and decision-making regarding the energy system. Simultaneously, the lack of models that can accurately reflect the physical system's state in real-time limits the monitoring and prediction capabilities of the energy system, making it impossible to promptly identify potential problems and take effective countermeasures. In terms of visualization, traditional energy management displays are mostly two-dimensional charts or simple interfaces, failing to intuitively present the spatial distribution and complex relationships of the energy system. Users struggle to grasp the overall system operation, resulting in a poor interactive experience and hindering users from quickly obtaining key information and making decisions. Moreover, existing energy management systems are inadequate in detecting energy consumption anomalies and regulating equipment. They often fail to detect energy consumption anomalies in a timely manner, and even when detected, it is difficult to quickly generate scientifically sound control strategies, leading to energy waste or low system efficiency. With the growth of energy demand and the increasing complexity of energy structures, higher demands are being placed on energy management. Digital twin technology offers new ideas and methods for solving these problems. By constructing a digital twin model of the energy system and integrating multi-source data, it enables visualized interaction and intelligent control, effectively improving the precision and intelligence of energy management and ensuring the safe, efficient, and stable operation of the energy system.

[0003] Existing technologies suffer from inefficient and inaccurate data acquisition and processing, difficulty in constructing digital twin models that accurately reflect the state of physical systems in real time, poor visualization and interaction effects, and inability to detect energy consumption anomalies in a timely and effective manner and generate reasonable control strategies. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides a digital twin energy management method and system based on artificial intelligence algorithms. This method solves problems such as poor data acquisition and processing quality in the energy production and consumption stages, difficulty in constructing real-time and accurate digital twin models, unintuitive visualization and interaction, and the inability to promptly detect energy consumption anomalies and generate effective control strategies, thereby affecting energy management efficiency and quality. To achieve the above objectives, this invention adopts the following technical solution:

[0005] The aforementioned digital twin energy management method based on artificial intelligence algorithms includes the following steps: acquiring data from energy production to consumption using sensors and external systems; removing noise and outliers through cleaning; fusing information from different data sources; labeling the data to obtain a preprocessed dataset; extracting key features from the preprocessed data; selecting appropriate artificial intelligence algorithms to construct a digital twin model; and constructing a virtual mirror model that reflects the real-time state of the physical system through verification and optimization; integrating geographic information with the digital twin model to construct a 3D model of the equipment; rendering the scene; mapping system data to the 3D model; designing interactive functions; realizing a visualized interactive scene; receiving user commands through an interactive interface; retrieving related data from the model and database based on the commands; overlaying the data in the scene and providing feedback on the interactive results to obtain an interactive data display; using algorithms to detect energy consumption anomalies and generate early warning information; combining rules to generate equipment control strategies; inputting these strategies into the physical system for execution and providing feedback on the results to obtain an optimized digital twin energy management module.

[0006] Furthermore, the process of acquiring data from energy production to consumption using sensors and external systems, removing noise and outliers through cleaning, fusing information from different data sources, and labeling the data to obtain a preprocessed dataset includes the following steps: acquiring data from energy production sources to consumption using sensors and external systems, including power sensors and electrical parameter sensors, and external systems including energy management systems and meteorological systems; accurately removing noise and outliers from the data by setting reasonable thresholds and algorithms to ensure data accuracy; integrating energy information from different data sources and with varying formats using data fusion algorithms; and meticulously labeling the data according to its characteristics and uses to obtain a complete and standardized preprocessed dataset.

[0007] Furthermore, the process of extracting key features from preprocessed data, selecting appropriate artificial intelligence algorithms to construct a digital twin model, and building a virtual mirror model that can reflect the real-time state of the physical system through verification and optimization includes the following steps: using feature analysis methods to extract key features from the preprocessed data, including equipment power, frequency, and temperature parameters; selecting Long Short-Term Memory networks and Convolutional Neural Networks to construct a digital twin model framework based on data characteristics and modeling requirements; adjusting and optimizing model parameters by inputting test data into the model and comparing the output results with the actual physical system state; and obtaining a virtual mirror model that reflects the real-time operating state of the physical system after verification and optimization.

[0008] Furthermore, the integration of geographic information with digital twin models to construct a 3D model of the equipment, render the scene, map system data to the 3D model, and design interactive functions to realize a visualized interactive scene includes the following steps: using a geographic information module to obtain the geographical location information of the energy system equipment; extracting the appearance and structural features of the equipment using 3D modeling software to construct a 3D model of the equipment; deeply integrating the geographic information with the constructed digital twin model to determine the spatial location of the equipment in the virtual scene; using a rendering engine to render the scene with lighting and materials to enhance realism; mapping the real-time operating data and status data of the energy system to the corresponding parts of the 3D model, and designing interactive functions such as mouse clicks, zooming, and rotation to enable users to interact with the scene and obtain a visualized interactive scene for human-computer interaction.

[0009] Furthermore, the process of receiving user commands through an interactive interface, retrieving relevant data from the model and database based on the commands, overlaying the data onto the scene, and providing feedback on the interaction results to obtain interactive data display includes the following steps: Building a user operation platform using interactive interface design technology; receiving user input commands in real time through the interactive interface, including specifying a target area and selecting a device; extracting relevant operating parameters from the digital twin model based on the received commands, and obtaining historical data and device information from the database; integrating and processing the extracted data, and overlaying it onto the corresponding position in the 3D visualization scene in the form of intuitive charts and numerical values; waiting for the display to complete, and providing feedback on the interactive operation results to the user, allowing the user to clearly understand the operation results and obtain a complete and clear interactive data display interface.

[0010] Furthermore, the process of using algorithms to detect energy consumption anomalies and generate early warning information, combining rules to generate equipment control strategies, inputting these strategies into the physical system for execution, and feeding back the results to obtain an optimized digital twin energy management module includes the following steps: constructing an energy consumption anomaly detection model using machine learning algorithms; extracting characteristic parameters of equipment energy consumption for comparative analysis by real-time monitoring of energy system data streams to accurately identify energy consumption anomalies and generate early warning information; generating targeted equipment control strategies based on preset energy management optimization rules, combined with the anomaly type and the current operating status of the system; inputting the generated control strategies into the physical energy system for execution, while continuously collecting actual operating data after system execution; feeding back the execution results to the digital twin model for verification and optimization; and obtaining the digital twin energy management module through iterative adjustments.

[0011] The second aspect of this invention provides a digital twin energy management system based on artificial intelligence algorithms. This system includes the following modules: a multi-source data acquisition and preprocessing module, used to acquire data from energy production to consumption from sensors and external systems, remove noise and outliers through cleaning, fuse information from different data sources, and label the data to obtain a preprocessed dataset; a digital twin module, used to extract key features from the preprocessed data, select appropriate artificial intelligence algorithms to construct a digital twin model, and through verification and optimization, construct a virtual mirror model that can reflect the real-time state of the physical system; a 3D scene generation module, used to integrate geographic information with the digital twin model, construct a 3D model of the equipment, render the scene, map system data to the 3D model, design interactive functions, and realize a visualized interactive scene; a user interaction module, used to receive user commands through an interactive interface, retrieve related data from the model and database according to the commands, overlay the data in the scene, and provide feedback on the interaction results to obtain an interactive data display; and an early warning and control module, used to use algorithms to detect abnormal energy consumption and generate early warning information, combine rules to generate equipment control strategies, input them into the physical system for execution, and provide feedback on the results to obtain an optimized digital twin energy management module.

[0012] A third aspect of the present invention provides a digital twin energy management device based on an artificial intelligence algorithm, the digital twin energy management device based on an artificial intelligence algorithm including a memory and at least one processor, the memory storing instructions; the at least one processor calling the instructions in the memory to cause the digital twin energy management device based on an artificial intelligence algorithm to perform the steps of the digital twin energy management method based on an artificial intelligence algorithm as described in any of the preceding claims.

[0013] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions, characterized in that, when executed by a processor, the instructions implement the steps of the digital twin energy management method based on an artificial intelligence algorithm as described in any one of the preceding claims.

[0014] In the technical solution provided by this invention, data from energy production to consumption is acquired using sensors and external systems. Noise and outliers are removed through cleaning, and information from different data sources is integrated and labeled to obtain a preprocessed dataset. Key features of the preprocessed data are extracted, and a suitable artificial intelligence algorithm is selected to construct a digital twin model. Through verification and optimization, a virtual mirror model that can reflect the real-time state of the physical system is constructed. Geographic information is integrated with the digital twin model to construct a 3D model of the equipment, render the scene, map system data to the 3D model, and design interactive functions to realize a visualized interactive scene. User commands are received through the interactive interface, and related data is retrieved from the model and database according to the commands. The data is overlaid and displayed in the scene, and the interactive results are fed back, resulting in an interactive data display. Algorithms are used to detect energy consumption anomalies and generate early warning information. Combined with rules, equipment control strategies are generated, input into the physical system for execution, and the results are fed back, resulting in an optimized digital twin energy management module. This invention solves the problems of poor data acquisition and processing quality in the energy production to consumption process, difficulty in constructing real-time and accurate digital twin models, unintuitive visualization interaction, and inability to detect energy consumption anomalies and generate effective control strategies in a timely manner, thus affecting the efficiency and quality of energy management. Attached Figure Description

[0015] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention.

[0016] Figure 1 This is a schematic diagram of the first embodiment of a digital twin energy management method based on artificial intelligence algorithms in this invention.

[0017] Figure 2 This is a schematic diagram of a second embodiment of a digital twin energy management method based on artificial intelligence algorithms in this invention.

[0018] Figure 3 This is a schematic diagram of a third embodiment of a digital twin energy management method based on artificial intelligence algorithms in this invention.

[0019] Figure 4 This is a schematic diagram of the fourth embodiment of a digital twin energy management method based on artificial intelligence algorithms in this invention.

[0020] Figure 5 This is a schematic diagram of the fifth embodiment of a digital twin energy management method based on artificial intelligence algorithms in this invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0022] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0023] A digital twin energy management method based on artificial intelligence algorithms, such as Figure 1 As shown, the process includes the following steps: acquiring data from energy production to consumption using sensors and external systems; removing noise and outliers through cleaning; fusing information from different data sources; labeling the data to obtain a preprocessed dataset; extracting key features from the preprocessed data; selecting appropriate artificial intelligence algorithms to construct a digital twin model; and through verification and optimization, constructing a virtual mirror model that can reflect the real-time state of the physical system; integrating geographic information with the digital twin model to construct a 3D model of the equipment; rendering the scene; mapping system data to the 3D model; designing interactive functions; realizing a visualized interactive scene; receiving user commands through the interactive interface; retrieving related data from the model and database based on the commands; overlaying the data in the scene and providing feedback on the interactive results to obtain an interactive data display; using algorithms to detect energy consumption anomalies and generate early warning information; combining rules to generate equipment control strategies; inputting these strategies into the physical system for execution and providing feedback on the results to obtain an optimized digital twin energy management module.

[0024] like Figure 2 As shown, in this embodiment, sensors and external systems are used to acquire data from energy production to consumption. The sensors include power sensors and electrical parameter sensors, and the external systems include energy management systems and meteorological systems. By setting reasonable thresholds and algorithms, noise and outliers in the data are accurately removed to ensure data accuracy. Energy information from different data sources and with different formats is integrated using data fusion algorithms. The data is meticulously labeled according to its characteristics and uses to obtain a complete and standardized preprocessed dataset.

[0025] Data from all stages of the energy process is acquired using multiple sensors and external systems, resulting in a wide and comprehensive information source. By setting reasonable thresholds and employing algorithms to remove noise and outliers, the accuracy and reliability of the data are greatly improved, providing a solid foundation for subsequent analysis. Data fusion algorithms are used to integrate energy information from different sources and formats, breaking down data barriers and achieving efficient data aggregation. The preprocessed dataset, formed after detailed data annotation, is complete and standardized, facilitating rapid retrieval and utilization, effectively improving data processing efficiency and providing strong support for precise energy management decisions.

[0026] like Figure 3 As shown, in this embodiment, a feature analysis method is used to extract key features from the preprocessed data. These key features include device power, frequency, and temperature parameters. Based on the data characteristics and modeling requirements, a long short-term memory network and a convolutional neural network are selected to construct a digital twin model framework. By inputting test data into the model and comparing the output results with the actual physical system state, the model parameters are adjusted and optimized. After verification and optimization, a virtual mirror model that reflects the real-time operating state of the physical system is obtained.

[0027] Feature analysis was employed to accurately extract key characteristics such as equipment power, frequency, and temperature, capturing the core elements of energy system operation and providing a precise basis for model construction. A digital twin model framework was constructed using Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs), fully leveraging the advantages of both algorithms to enhance the model's ability to handle complex data. Parameters were optimized by inputting test data and comparing the output with the actual state, ensuring the model closely matches the physical system. The resulting virtual mirror model accurately reflects the operating status of the physical system in real time, providing reliable support for energy system monitoring, prediction, and decision-making, and facilitating efficient energy management.

[0028] like Figure 4 As shown, in this embodiment, a geographic information module is used to obtain the geographic location information of the energy system equipment. The appearance and structural features of the equipment are extracted using 3D modeling software to construct a 3D model of the equipment. The geographic information is deeply integrated with the constructed digital twin model to determine the spatial location of the equipment in the virtual scene. A rendering engine is used to render the scene with lighting and materials to enhance the realism. The real-time operation data and status data of the energy system are mapped to the corresponding parts of the 3D model. Interactive functions such as mouse click, zoom, and rotation are designed to allow users to interact with the scene and obtain a visual interactive scene for human-computer interaction.

[0029] By leveraging a geographic information module to acquire equipment location information and combining it with 3D modeling software to accurately construct 3D models of the equipment, the system intuitively presents the equipment's appearance and structure. Deep integration of geographic information and digital twin models clarifies the precise spatial location of the equipment within the virtual scene, enhancing the scene's spatial plausibility. Utilizing a rendering engine for lighting and material rendering significantly improves the scene's realism and immersion. Real-time energy system data is mapped to the 3D model, and rich interactive functions are designed, allowing users to intuitively view data and interact with the scene.

[0030] like Figure 5 As shown, in this embodiment, an interactive interface design technology is used to build a user operation platform. The platform receives user input commands in real time through the interactive interface, including specifying a target area and selecting a device. Based on the received commands, relevant operating parameters are extracted from the digital twin model, and historical data and device information are obtained from the database. The extracted data is integrated and processed, and displayed in the corresponding position in the 3D visualization scene in the form of intuitive charts and values. After the display is completed, the results of the interactive operation are fed back to the user, so that the user can clearly understand the operation results and obtain a complete and clear interactive data display interface.

[0031] The user operation platform, built using interactive interface design technology, is convenient and user-friendly. It can receive user commands in real time regarding target area specification, device selection, and other tasks, meeting diverse operational needs. Based on these commands, it accurately extracts operating parameters from the digital twin model, as well as historical data and device information from the database, ensuring data comprehensiveness and accuracy. The integrated and processed data is then displayed in intuitive charts and numerical values ​​overlaid at corresponding locations in the 3D scene, allowing users to quickly obtain key information. Finally, timely feedback on the interaction results allows users to clearly understand the effectiveness of their operations, providing a complete, clear, and efficient interactive data display experience.

[0032] In this embodiment, a machine learning algorithm is used to construct an energy consumption anomaly detection model. By monitoring the energy system data stream in real time, the characteristic parameters of equipment energy consumption are extracted and compared for analysis to accurately identify energy consumption anomalies and generate early warning information. Based on preset energy management optimization rules, combined with the anomaly type and the current operating status of the system, a targeted equipment control strategy is generated. The generated control strategy is input into the physical energy system for execution, while continuously collecting the actual operating data after system execution. The execution results are fed back to the digital twin model for verification and optimization. After iterative adjustments, the digital twin energy management module is obtained.

[0033] An energy consumption anomaly detection model built using machine learning algorithms can monitor energy system data flow in real time, accurately extract and analyze equipment energy consumption characteristic parameters, quickly identify anomalies and generate early warnings, effectively avoiding energy waste and potential risks. Based on preset rules and anomaly conditions, targeted equipment control strategies are generated to ensure efficient system operation. These strategies are input into the physical system for execution and real-world data collection, then fed back to the digital twin model for verification and optimization. Through iterative adjustments, the model continuously aligns with reality. The resulting digital twin energy management module enables precise energy consumption control and intelligent system optimization, significantly improving the scientific rigor and effectiveness of energy management.

[0034] This invention also provides a digital twin energy management system based on artificial intelligence algorithms, comprising the following modules: a multi-source data acquisition and preprocessing module, used to acquire data from energy production to consumption from sensors and external systems, remove noise outliers by cleaning, integrate information from different data sources, and label the data to obtain a preprocessed dataset; a digital twin module, used to extract key features from the preprocessed data, select appropriate artificial intelligence algorithms to construct a digital twin model, and construct a virtual mirror model that can reflect the real-time state of the physical system through verification and optimization; a 3D scene generation module, used to integrate geographic information with the digital twin model, construct a 3D model of the equipment, render the scene, map system data to the 3D model, design interactive functions, and realize a visualized interactive scene; a user interaction module, used to receive user commands through an interactive interface, retrieve related data from the model and database according to the commands, overlay the data in the scene, and provide feedback on the interactive results to obtain an interactive data display; and an early warning and control module, used to use algorithms to detect abnormal energy consumption and generate early warning information, combine rules to generate equipment control strategies, input them into the physical system for execution, and provide feedback on the results to obtain an optimized digital twin energy management module.

[0035] The multi-source data acquisition and preprocessing module ensures comprehensive and accurate data, laying a solid foundation for system operation. The digital twin module constructs a virtual mirror model that accurately reflects the physical system's state in real time, facilitating efficient monitoring and decision-making. The 3D scene generation module enables visual interaction, enhancing users' intuitive understanding of the energy system. The user interaction module facilitates user operation and information retrieval, enhancing the user experience. The early warning and control module can promptly detect energy consumption anomalies and generate control strategies, ensuring stable system operation. The collaboration of these modules comprehensively improves the efficiency and quality of energy management.

[0036] This invention also provides a digital twin energy management device based on artificial intelligence algorithms. This device may further include one or more power supplies, one or more wired or wireless network interfaces, one or more input / output interfaces, and / or one or more operating systems, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that the structure of the artificial intelligence-based digital twin energy management device does not constitute a limitation on the computer device provided by this invention, and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0037] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the various steps of the digital twin energy management method based on artificial intelligence algorithms provided in the above embodiments.

[0038] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital twin energy management method based on artificial intelligence algorithms, characterized in that, The digital twin energy management method based on artificial intelligence algorithms includes the following steps: Data from energy production to consumption is acquired using sensors and external systems. Noise and outliers are removed by cleaning, information from different data sources is integrated, and the data is labeled to obtain a preprocessed dataset. Extract key features from preprocessed data, select appropriate artificial intelligence algorithms to build a digital twin model, and through verification and optimization, build a virtual mirror model that can reflect the state of the physical system in real time; By integrating geographic information with digital twin models, constructing 3D models of equipment, rendering scenes, mapping system data to 3D models, designing interactive functions, and realizing visualized interactive scenes; The system receives user commands through an interactive interface, retrieves relevant data from the model and database according to the commands, overlays the data in the scene, and provides feedback on the interaction results to obtain interactive data display. Algorithms are used to detect abnormal energy consumption and generate early warning information. Combined with rules, equipment control strategies are generated, which are then input into the physical system for execution and feedback is provided to obtain an optimized digital twin energy management module.

2. The digital twin energy management method based on artificial intelligence algorithms according to claim 1, characterized in that, The process involves acquiring data from energy production to consumption using sensors and external systems, cleaning and removing noise and outliers, fusing information from different data sources, and labeling the data to obtain a preprocessed dataset. This includes the following steps: Data from energy production to consumption is acquired using sensors and external systems. The sensors include power sensors and electrical parameter sensors, and the external systems include energy management systems and meteorological systems. By setting reasonable thresholds and algorithms, noise and outliers in the data can be accurately removed to ensure data accuracy. Energy information from different data sources and in different formats is integrated using data fusion algorithms; Detailed annotations are performed based on data characteristics and intended use to obtain a complete and standardized preprocessed dataset.

3. The digital twin energy management method based on artificial intelligence algorithms according to claim 1, characterized in that, The process of extracting key features from preprocessed data, selecting appropriate artificial intelligence algorithms to construct a digital twin model, and then verifying and optimizing the model to build a virtual mirror model that can reflect the real-time state of the physical system includes the following steps: Feature analysis is used to extract key features from preprocessed data, including equipment power, frequency, and temperature parameters. Based on the data characteristics and modeling requirements, Long Short-Term Memory Networks and Convolutional Neural Networks were selected to construct the digital twin model framework; By inputting test data into the model and comparing the output results with the actual physical system state, the model parameters are adjusted and optimized. After verification and optimization, a virtual mirror model that reflects the real-time operating status of the physical system was obtained.

4. The digital twin energy management method based on artificial intelligence algorithms according to claim 1, characterized in that, The process of integrating geographic information with digital twin models to construct a 3D model of the device, rendering the scene, mapping system data to the 3D model, designing interactive functions, and realizing a visualized interactive scene includes the following steps: Geographic information modules are used to obtain the geographical location information of energy system equipment, and 3D modeling software is used to extract the appearance and structural features of the equipment to construct a 3D model of the equipment. By deeply integrating geographic information with the constructed digital twin model, the spatial location of the device in the virtual scene can be determined; The rendering engine is used to render the scene's lighting and materials, enhancing its realism; The real-time operation and status data of the energy system are mapped to the corresponding parts of the 3D model, and interactive functions such as mouse click, zoom and rotate are designed to enable users to interact with the scene and obtain a visualized interactive scene for human-computer interaction.

5. The digital twin energy management method based on artificial intelligence algorithms according to claim 1, characterized in that, The process of receiving user commands through an interactive interface, retrieving relevant data from the model and database based on the commands, overlaying the data onto the scene, and providing feedback on the interaction results to obtain interactive data display includes the following steps: A user operation platform is built using interactive interface design technology. The platform receives user input commands in real time through the interactive interface. These commands include specifying a target area and selecting a device. Based on the received instructions, relevant operating parameters are extracted from the digital twin model, and historical data and equipment information are obtained from the database; The extracted data is integrated and processed, and then displayed in the corresponding positions in the 3D visualization scene in the form of intuitive charts and numerical values. Once the display is complete, the results of the interactive operation will be fed back to the user, allowing the user to clearly understand the effectiveness of the operation and obtain a complete and clear interactive data display interface.

6. The digital twin energy management method based on artificial intelligence algorithms according to claim 1, characterized in that, The process of using algorithms to detect abnormal energy consumption and generate early warning information, combining this with rules to generate equipment control strategies, inputting these strategies into the physical system for execution, and providing feedback on the results, results in an optimized digital twin energy management module. This process includes the following steps: A machine learning algorithm is used to build an energy consumption anomaly detection model. By monitoring the energy system data stream in real time, the characteristic parameters of equipment energy consumption are extracted and compared and analyzed to accurately identify energy consumption anomalies and generate early warning information. Based on preset energy management optimization rules, and combined with the anomaly type and the current operating status of the system, a targeted equipment control strategy is generated; The generated control strategy is input into the physical energy system for execution, while the actual operating data after the system is executed is continuously collected; The execution results are fed back to the digital twin model for verification and optimization. After iterative adjustments, the digital twin energy management module is obtained.

7. A digital twin energy management system based on artificial intelligence algorithms, characterized in that, The digital twin energy management system based on artificial intelligence algorithms includes the following modules: The multi-source data acquisition and preprocessing module is used to acquire data from energy production to consumption from sensors and external systems. It removes noise and outliers by cleaning, integrates information from different data sources, and labels the data to obtain a preprocessed dataset. The digital twin module is used to extract key features from preprocessed data, select appropriate artificial intelligence algorithms to build a digital twin model, and through verification and optimization, build a virtual mirror model that can reflect the state of the physical system in real time. The 3D scene generation module is used to integrate geographic information with digital twin models, build 3D models of equipment, render scenes, map system data to 3D models, design interactive functions, and realize visualized interactive scenes. The user interaction module is used to receive user commands through the interactive interface, retrieve relevant data from the model and database according to the commands, overlay the data in the scene and provide feedback on the interaction results, thus obtaining interactive data display. The early warning and control module is used to detect abnormal energy consumption using algorithms, generate early warning information, combine rules to generate equipment control strategies, input them into the physical system for execution, and provide feedback on the results to obtain an optimized digital twin energy management module.

8. A digital twin energy management device based on artificial intelligence algorithms, characterized in that, The artificial intelligence-based digital twin energy management device includes a memory and at least one processor. The memory stores instructions, and the at least one processor invokes the instructions in the memory to cause the artificial intelligence-based digital twin energy management device to perform the steps of the artificial intelligence-based digital twin energy management method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the digital twin energy management method based on artificial intelligence algorithms as described in any one of claims 1-6.

Images