Virtual Monitoring Method for Photovoltaic Power Stations Based on Digital Twin Technology

Abstract

The present invention provides a virtual monitoring method and system for a photovoltaic power station based on digital twin technology. By using digital twin technology, virtual monitoring and alarming of the photovoltaic power station are realized. Through the virtual monitoring platform, operation and maintenance personnel can grasp the operation status of the power station in real time, discover and handle abnormal situations in a timely manner, and improve the operation and maintenance efficiency. Through virtual monitoring and alarming, the number of on-site inspections and manual interventions can be reduced, and the operation and maintenance costs can be lowered. By using Momo AI for the monitoring, alarming, analysis and management of the virtual model, comprehensive and real-time monitoring of various elements and behaviors in the virtual environment can be achieved, and alarms can be issued in a timely manner when abnormalities or potential risks are detected. By using Momo AI for the monitoring, alarming, analysis and management of the virtual model, efficient, accurate and real-time monitoring and alarming functions can be realized, providing a strong guarantee for the safety and stability of the virtual environment, and realizing intelligent, virtual and unmanned monitoring of the photovoltaic power station.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins, and in particular to a virtual monitoring method for a photovoltaic power station based on digital twin technology, a virtual monitoring system for a photovoltaic power station based on digital twin technology, an electronic device, and a computer-readable storage medium. Background Art

[0002] Photovoltaic power station monitoring is to connect devices such as inverters, bus coupler boxes, irradiance meters, weather meters, and electric meters in a photovoltaic power station through data lines, use a photovoltaic power station data collector to collect data of these devices, and upload the data to a network server or a local computer through methods such as GPRS, Ethernet, and WIFI, so that users can view relevant data on the Internet or a local computer, facilitating power station management personnel and users to view and manage the operation data of the photovoltaic power station.

[0003] The traditional methods for photovoltaic power station monitoring mainly include manual inspection and setting up a server on-site for monitoring. Although they can achieve a certain effect of photovoltaic power station monitoring, they each have their own deficiencies:

[0004] 1. The disadvantage of the manual inspection method is that it relies on a large amount of human resources. Especially for large-scale photovoltaic power stations, the inspection and maintenance work is heavy and time-consuming, increasing the operation cost of the enterprise and restricting the improvement of operation and maintenance efficiency. In addition, it is difficult to detect potential equipment failures in real time during manual inspection, which may lead to a decline in equipment performance and even more serious consequences, thus affecting the overall power generation efficiency and economic benefits of the power station.

[0005] 2. For the method of setting up a server on-site for monitoring, its disadvantages are that the monitoring cost is relatively high, users need to remember the network address of each power station server and set up a username and password, and the management is rather troublesome. At the same time, there are certain limitations in data transmission for this method. It takes a certain amount of time to wait to view the data, and the client needs to be continuously upgraded to improve functions, and the settings are also rather cumbersome.

[0006] 3. With the development of technology, photovoltaic power station monitoring should also develop towards remote monitoring and intelligentization to improve monitoring efficiency and accuracy and reduce operation and maintenance costs. However, the current monitoring mode of photovoltaic power stations is mainly traditional, and AI monitoring is only applied in a few core places, unable to achieve specified, fast, comprehensive monitoring analysis and early warning, lacking an intelligent and broad development prospect. Summary of the Invention

[0007] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0008] On the one hand, a virtual monitoring method for a photovoltaic power station based on digital twin technology is provided, which is implemented based on a digital twin platform for a photovoltaic power station. The digital twin platform for the photovoltaic power station includes a data acquisition layer, a data processing layer, a digital twin model layer, and a virtual monitoring platform layer, where:

[0009] The data acquisition layer: is used to collect the status data of each element in the photovoltaic power station in real time and transmit it to the data processing layer, where the elements include people, objects, and behaviors located in the photovoltaic power station;

[0010] The data processing layer: is used to receive the status data from the data acquisition layer, perform cleaning, verification, and storage, and use big data analysis technology to process and analyze the collected data, extract the corresponding three-dimensional feature data from the status information of each element, and upload it to the digital twin model layer;

[0011] The digital twin model layer: is used to build a digital twin model of the photovoltaic power station based on the three-dimensional feature data through digital twin technology, obtain a digital twin model of the photovoltaic power station, and classify and save the digital twin model data sets of each element in the digital twin model of the photovoltaic power station;

[0012] The virtual monitoring platform layer: is used to visually display the digital twin model data sets of the digital twin model of the photovoltaic power station and its target management objects in each element; and, adopt a multi-modal AI model: Momo AI, perform multi-modal monitoring on each element of the digital twin model of the photovoltaic power station, and when an abnormal situation is monitored, automatically trigger an alarm mechanism, generate and send a corresponding alarm signal to the handheld inspection terminal of the operation and maintenance personnel;

[0013] The management layer: is used to select target management objects from each element and perform visual management and multi-modal monitoring on the target management objects;

[0014] The method includes:

[0015] S1. Establish a virtual monitoring task for the photovoltaic power station and select target management objects from each element;

[0016] S2. Collect the digital twin model data sets of the target management objects in the digital twin model of the photovoltaic power station in real time to obtain a target detection data set;

[0017] S3. Traverse and identify the target detection data set through Momo AI, and judge whether there is abnormal data that triggers the alarm mechanism in the target detection data set: if so, generate an alarm signal corresponding to the target management object; otherwise, continue to monitor;

[0018] S4. Through Momo AI, track the context data set of the abnormal data that appears, and send the obtained context data set together with the alarm signal to the inspection terminal.

[0019] Preferably, in S2, the digital twin model data set of the target management object in the photovoltaic power station twin model is collected in real time to obtain a target detection data set, including:

[0020] Collect the three-dimensional feature data of each element in real time;

[0021] Based on the data set mapping relationship between the entity model and the virtual model, perform data mapping calculations on the three-dimensional feature data of each element, and update the digital twin model data set of each element in the photovoltaic power station twin model according to the calculation results;

[0022] Traverse the digital twin model data sets before and after the update of each element, and mark the elements whose digital twin model data sets have data changes to obtain an element set S;

[0023] Judge whether the target management object exists in the element set S:

[0024] If it exists, extract the updated digital twin model data set of the target management object to obtain the target detection data set;

[0025] If it does not exist, continue to maintain the update monitoring.

[0026] Preferably, in S3, through Momo AI, traverse and identify the target detection data set, and judge whether there is abnormal data that triggers the alarm mechanism in the target detection data set, including:

[0027] Input the target detection data set of each target management object into the preset Momo AI anomaly detection model on the virtual monitoring platform layer;

[0028] Through the Momo AI anomaly detection model, traverse and identify the target detection data sets of each target management object, and judge whether there is abnormal data that triggers the alarm mechanism in the target detection data set;

[0029] Among them, the generation method of the Momo AI anomaly detection model includes:

[0030] Collect and preprocess the abnormal action data of each element in the photovoltaic power station, including image, video or text data;

[0031] Perform feature engineering on the abnormal operation data of each element, use the multimodal algorithm in Momo AI to adaptively identify and extract the abnormal operation features in the abnormal operation data of each element, and construct a feature set composed of the abnormal operation features of several elements;

[0032] Divide the feature set into a training set and a validation set according to a preset ratio;

[0033] Input the training set into the preset Momo AI for feature training and learning to construct a Momo AI anomaly detection model;

[0034] Use the validation set to verify the recognition performance of the Momo AI anomaly detection model:

[0035] If the verification passes, deploy the Momo AI anomaly detection model on the virtual monitoring platform layer, adjust the parameters and put it into application;

[0036] If the verification fails, repeat the above steps to reconstruct the Momo AI anomaly detection model.

[0037] Preferably, when performing feature engineering, it further includes:

[0038] Collect voice data / images describing the abnormal operation data of each element;

[0039] Parse the voice data / images and obtain the corresponding abnormal operation description text;

[0040] Use the multimodal algorithm in Momo AI to adaptively identify and extract the description information about the abnormal operations of each element in the abnormal operation description text;

[0041] Label the description information on the abnormal operation features.

[0042] On the other hand, a virtual monitoring system for a photovoltaic power station based on digital twin technology is provided. The virtual monitoring system for a photovoltaic power station based on digital twin technology is used to implement the above-mentioned virtual monitoring method for a photovoltaic power station based on digital twin technology. The system includes:

[0043] A management terminal, which is used to establish a virtual monitoring task for a photovoltaic power station and select a target management object from each element;

[0044] A virtual monitoring platform is used to collect in real time the digital twin model data set of the target management object in the twin model of the photovoltaic power station to obtain a target detection data set; and, through Momo AI, traverse and identify the target detection data set to determine whether there is abnormal data that triggers the alarm mechanism in the target detection data set: if so, generate an alarm signal corresponding to the target management object; otherwise, continue monitoring; and, through Momo AI, perform context data set tracking on the abnormal data that appears, and send the tracked context data set together with the alarm signal to the patrol inspection terminal;

[0045] A patrol inspection terminal is used to receive and display the context data set and the alarm signal;

[0046] The management end and the patrol inspection terminal are respectively communicatively connected to the virtual monitoring platform.

[0047] On the other hand, an electronic device is provided, which includes: a processor; a memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, any one of the methods in the above-mentioned virtual monitoring method of a photovoltaic power station based on digital twin technology is implemented.

[0048] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement any one of the methods in the above-mentioned virtual monitoring method of a photovoltaic power station based on digital twin technology.

[0049] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0050] The present invention utilizes digital twin technology to realize virtual monitoring and alarm of a photovoltaic power station, and has the following advantages:

[0051] Improve operation and maintenance efficiency: Through the virtual monitoring platform, operation and maintenance personnel can master the operation status of the power station in real time, discover and handle abnormal situations in time, and improve operation and maintenance efficiency.

[0052] Reduce operation and maintenance costs: Through virtual monitoring and alarm, the number of on-site patrol inspections and manual interventions can be reduced, and operation and maintenance costs can be reduced.

[0053] Optimize operation strategies: Based on the analysis results of the digital twin model, the operation strategies of the power station can be optimized, and power generation efficiency and equipment utilization rate can be improved.

[0054] This solution can be widely applied to the monitoring and management of various photovoltaic power stations, providing strong support for the intelligent and efficient operation of the power stations. By using Momo AI for the monitoring, alarm analysis, and management of virtual models, it is possible to achieve comprehensive and real-time monitoring of various elements and behaviors in the virtual environment, and issue alarms in a timely manner when anomalies or potential risks are detected. By using Momo AI for the monitoring, alarm analysis, and management of virtual models, it is possible to achieve efficient, accurate, and real-time monitoring and alarm functions, providing strong guarantee for the safety and stability of the virtual environment, and realizing the intelligent, virtual, and unmanned monitoring of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0056] Figure 1 FIG. 1 is a schematic structural diagram of a digital twin platform for a photovoltaic power station provided by an embodiment of the present invention;

[0057] Figure 2 FIG. 2 is a flowchart of a virtual monitoring method for a photovoltaic power station based on digital twin technology provided by an embodiment of the present invention;

[0058] Figure 3 FIG. 3 is a schematic diagram of the construction process of a Momo AI anomaly detection model provided by an embodiment of the present invention;

[0059] Figure 4 FIG. 4 is a block diagram of a virtual monitoring system for a photovoltaic power station based on digital twin technology provided by an embodiment of the present invention;

[0060] Figure 5 FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] The following will describe the technical solutions in the present invention with reference to the drawings.

[0062] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "exemplary" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0063] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, their intended meanings are the same. "Of", "corresponding", and "corresponding to" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, their intended meanings are the same.

[0064] In the embodiments of the present invention, sometimes subscripts such as W1 may be miswritten as non-subscript forms such as W1. When the difference is not emphasized, their intended meanings are the same.

[0065] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0066] The embodiments of the present invention provide a virtual monitoring method for a photovoltaic power station based on digital twin technology. This method can be implemented by an electronic device, which can be a terminal or a server.

[0067] Multi-modal AI Model: Introduction to Momo AI

[0068] Momo AI is a set of multi-modal AI models. Its greatest feature is that it not only has the ability to process images and text, but also can interact with the environment by pointing to specific objects. This pointing function enables Momo AI to have stronger application potential in both the physical world and the virtual world.

[0069] In terms of architecture, Momo AI adopts an efficient data training method, preferentially using more accurate and detailed image descriptions to train the model. This strategy avoids the common AI "hallucination" problem, that is, incorrectly generating inaccurate information. Through the pointing function, Momo AI can identify objects and transmit their information to users in a more intuitive way, such as pointing out the objects in a picture and converting them into structured data in JSON format.

[0070] Compared with other AI models, the significant difference and innovation of Momo AI lie in its multi-modal interaction ability. Many large AI models mainly focus on the processing of single modalities such as images or text, while Momo AI can handle the complex relationship between images and text and perform well in multi-modal tasks. In visual-language evaluation tasks, the performance of Momo AI is on a par with current top closed-source models such as GPT-4 and Gemini 1.5 Pro, and even exceeds them in some scenarios.

[0071] In addition, the model size of Momo AI is relatively small, but its performance in multiple fields far exceeds that of its competitors which are ten times its size. This benefits from its innovative data training strategy and the attention to high-quality data sets. In contrast, other large multi-modal language models are usually trained on huge data sets containing billions of image and text samples and may contain trillions of parameters. Momo AI, on the other hand, is trained on a smaller and more "carefully curated" data set, achieving better performance.

[0072] The advantages of Momo AI are also reflected in its practical applications. Its multi-modal capabilities enable Momo AI to be widely applied in multiple practical scenarios, such as virtual assistant systems, augmented reality, and the robotics field. In virtual assistant systems, Momo AI can help users complete various tasks through its multi-modal interaction capabilities, such as ordering drinks or identifying items in pictures. In augmented reality applications, Momo AI can be combined with AR devices to provide a vision-based enhanced interaction experience. In the robotics field, Momo AI can help robots more accurately identify and manipulate objects through its powerful visual understanding capabilities.

[0073] Momo AI mainly integrates AI algorithms of two modalities, image processing and text processing, and has the ability to interact with the environment through "pointing". This pointing function is actually a special interaction modality. Specifically, it includes:

[0074] 1. Image processing algorithm: enables Momo AI to recognize and understand visual content, including objects, scenes, etc. This is a very crucial part of multi-modal AI because visual information is one of the most intuitive and richest sources of information in human-machine interaction.

[0075] 2. Text processing algorithm: enables Momo AI to understand and generate text information, thus enabling language interaction with users. The text processing algorithm plays an important role in multi-modal AI, enabling the machine to understand and respond to users' text instructions or queries.

[0076] 3. Pointing algorithm: This is an innovation of Momo AI. It can point to a specific object in visual content. Through this pointing function, Momo AI can not only identify objects but also interact with the environment more intuitively. This algorithm actually combines image processing and interaction technologies, providing a unique interaction method for Momo AI.

[0077] Different image processing algorithms or text processing algorithms, etc., can be customized by users or optimized and upgraded on the algorithm model architecture of omoAI. Existing image or text processing algorithms include:

[0078] Image processing algorithms mainly include the following types:

[0079] Filtering (smoothing, noise reduction): Such as mean filtering, median filtering, Gaussian filtering, etc., which are used to remove noise in the image or smooth the image.

[0080] Edge sharpening: Such as Sobel operator, Laplace operator, Prewitt operator, etc., which are used to enhance the edge information in the image.

[0081] Image segmentation: Such as threshold segmentation, boundary-based segmentation, Hough transform, region-based segmentation, etc., which are used to divide the image into several regions with specific properties.

[0082] Geometric transformation: Such as image rotation, translation, mirroring, etc., which are used to change the spatial position or shape of the image.

[0083] Feature extraction: Such as Blob analysis, corner detection, contour extraction, etc., which are used to extract useful feature information from the image.

[0084] Image enhancement: Such as histogram equalization, contrast enhancement, etc., which are used to improve the visual effect of the image.

[0085] Image matching: Such as template matching, search matching, etc., which are used to find regions similar to a specific template in the image.

[0086] Text processing algorithms mainly include the following types:

[0087] Word segmentation: Divide the text into words, phrases or other meaningful elements.

[0088] Stop word removal: Remove common and less meaningful words, such as "the", "is", "in", etc.

[0089] Stemming and lemmatization: Restore the vocabulary to its basic form or the form in the dictionary, such as restoring "running" to "run".

[0090] Part-of-speech tagging: Tag the part of speech of each word in the text, such as noun, verb, etc.

[0091] Named entity recognition (NER): Identify entities in the text, such as person names, locations, organizations, etc.

[0092] Sentiment analysis: Judge the sentiment tendency of the text, such as positive, negative or neutral.

[0093] Topic modeling: Extract topic information from the text for understanding and organizing text data.

[0094] Momo AI integrates various modal algorithms and can perform adaptive recognition on data such as images and texts and extract corresponding image and text features.

[0095] In the present invention, for a photovoltaic power station, digital twin virtual monitoring technology and a multi-modal AI model: MomoAI are utilized to realize multi-modal intelligent supervision of abnormal behaviors of the photovoltaic power station in a virtual model scenario. It can use Momo AI for monitoring alarm analysis and management of the virtual model, can achieve comprehensive and real-time monitoring of various elements and behaviors in the virtual environment, and issue alarms in a timely manner when detecting abnormalities or potential risks.

[0096] Such as Figure 1 shown, this method needs to be implemented based on a digital twin platform of a photovoltaic power station. The digital twin platform of the photovoltaic power station includes a data acquisition layer, a data processing layer, a digital twin model layer, and a virtual monitoring platform layer, where:

[0097] The data acquisition layer: is used to collect the status data of each element in the photovoltaic power station in real time and transmit it to the data processing layer. Among them, the elements include people, objects, and behaviors located in the photovoltaic power station;

[0098] The data processing layer: is used to receive the status data from the data acquisition layer, perform cleaning, verification, and storage, and use big data analysis technology to process and analyze the collected data, extract corresponding three-dimensional feature data from the status information of each element, and upload it to the digital twin model layer;

[0099] The digital twin model layer: is used to construct a digital twin model of the photovoltaic power station through digital twin technology based on the three-dimensional feature data, obtain a digital twin model of the photovoltaic power station, and classify and save the digital twin model data sets of each element in the digital twin model of the photovoltaic power station;

[0100] The virtual monitoring platform layer: is used to visually display the digital twin model data sets of the digital twin model of the photovoltaic power station and its target management objects in each element; and, use a multi-modal AI model: Momo AI, to perform multi-modal monitoring on each element of the digital twin model of the photovoltaic power station. When an abnormal situation is monitored, the alarm mechanism is automatically triggered, and corresponding alarm signals are generated and sent to the handheld inspection terminals of the operation and maintenance personnel;

[0101] The management layer: is used to select target management objects from each element and perform visual management and multi-modal monitoring on the target management objects.

[0102] The steps of constructing a virtual model (digital twin model) corresponding to the entity using digital twin technology will not be elaborated here. The steps of constructing a virtual model using three-dimensional feature data (such as extracting the corresponding three-dimensional action and posture features of a person from the three-dimensional point cloud data of the person in the scene and constructing the corresponding three-dimensional posture model; or collecting three-dimensional data of the equipment in the scene and extracting the corresponding three-dimensional feature data) can refer to the following solution:

[0103] 1. Data collection and preprocessing

[0104] Data collection:

[0105] Use devices such as drones, lidar (LiDAR), and 3D scanners to perform high-precision scanning and measurement on the photovoltaic power station to obtain the original three-dimensional point cloud data.

[0106] At the same time, collect the status information of each element in the photovoltaic power station (such as solar panels, inverters, brackets, etc.), including but not limited to temperature, voltage, current, power, etc.

[0107] Data preprocessing:

[0108] Perform denoising, registration, segmentation, etc. on the original three-dimensional point cloud data to extract clear and accurate three-dimensional features.

[0109] Clean, calibrate, and format the status information to ensure the accuracy and consistency of the data.

[0110] 2. Three-dimensional feature data extraction

[0111] Feature recognition:

[0112] Use three-dimensional image processing algorithms (such as edge detection, surface fitting, etc.) to extract the three-dimensional features of each element in the photovoltaic power station from the preprocessed three-dimensional point cloud data, such as shape, size, position, etc.

[0113] Feature data conversion:

[0114] Convert the extracted three-dimensional features into digital data formats, such as coordinate points, vectors, polygons, etc., for subsequent processing and analysis.

[0115] 3. Data upload and integration

[0116] Data upload:

[0117] Upload the extracted three-dimensional feature data and status information to the data storage system in the digital twin model layer.

[0118] Data integration:

[0119] In the digital twin model layer, the three-dimensional feature data and status information are integrated to form a three-dimensional feature dataset containing complete information.

[0120] 4. Digital twin model construction

[0121] ‌Model initialization‌:

[0122] Based on the 3D feature data set, a preliminary digital twin model of the PV power station is constructed using 3D modeling software (such as AutoCAD, SolidWorks, etc.) or a digital twin platform.

[0123] ‌Model refinement‌:

[0124] According to the detailed information of the 3D feature data, the preliminary model is refined, including adding textures, adjusting colors, setting animations, etc., to more realistically reflect the actual situation of the photovoltaic power station.

[0125] ‌Model Validation‌:

[0126] The accuracy and reliability of the digital twin model are ensured by comparison and verification with the actual photovoltaic power station.

[0127] 5. Classification and data management

[0128] ‌Save by Category‌:

[0129] The various elements in the constructed photovoltaic station twin model (such as solar panel model, inverter model, administrator or technician model of each workstation (for posture recognition), etc.) are classified and saved to facilitate subsequent management and query.

[0130] ‌Data Management‌:

[0131] Establish a complete data management mechanism, including data backup, data update, data access permission control, etc., to ensure the security and availability of the digital twin model data set.

[0132] 6. Continuous optimization and iteration

[0133] ‌Real-time monitoring and feedback‌:

[0134] Use digital twin models to conduct real-time monitoring and simulation analysis of photovoltaic power stations to promptly identify and solve problems.

[0135] ‌Model update and iteration‌:

[0136] According to the actual changes in photovoltaic power stations and the emergence of new technologies, the digital twin model is updated and iterated regularly to maintain the advancement and accuracy of the model.

[0137] Through the above steps, the digital twin model of the photovoltaic power station can be constructed by using big data analysis technology and digital twin technology, and the extraction of three-dimensional feature data and the management of the model can be realized. This will provide strong support for the operation, maintenance and management of the photovoltaic power station.

[0138] This solution uses digital twin technology, combined with Internet of Things, big data analysis and visualization technology, to build a virtual monitoring platform corresponding to the real photovoltaic power station. The platform can collect the operation data of each device in the power station in real time, simulate and analyze through the digital twin model, and realize the comprehensive monitoring and abnormal alarm of the power station operation status.

[0139] (1) The system architecture is as follows:

[0140] 1. Data acquisition layer:

[0141] Install various sensors and intelligent meters, such as inverter output power sensors, busbar box current and voltage sensors, irradiance meters, meteorological instruments, electricity meters, etc., to collect the operation data of each device in the power station in real time.

[0142] The data acquisition device transmits the collected data to the data processing center by wired or wireless means.

[0143] 2. Data processing layer:

[0144] The data processing center receives the data from the data acquisition layer, and performs cleaning, verification and storage.

[0145] Using big data analysis technology, process and analyze the collected data, extract useful information, and provide data support for the virtual monitoring platform.

[0146] 3. Digital twin model layer:

[0147] Based on the integration of physical models, sensor updates, historical and real-time data, build a digital twin model of the photovoltaic power station.

[0148] The digital twin model can reflect the operation status of each device in the power station in real time, including the working status of the inverter, the current and voltage of the busbar box, irradiance intensity, meteorological conditions, power generation, etc.

[0149] 4. Virtual monitoring platform layer:

[0150] Provide a user-friendly interface to display the digital twin model of the photovoltaic power station (referred to as the photovoltaic power station twin model), and display the operation status and key parameters of each device in real time.

[0151] Adopt a multimodal AI model (abbreviation: "Momo AI") to conduct multimodal monitoring on the twin model of the photovoltaic power station, comprehensively monitor the operation status of the power station, including real-time monitoring of parameters such as power generation, equipment temperature, voltage, and current.

[0152] When an abnormal situation is detected, the alarm mechanism is automatically triggered to remind the operation and maintenance personnel through means such as sound, light, and pop-up windows.

[0153] (2) Function implementation

[0154] 1. Real-time data collection and transmission:

[0155] Utilize Internet of Things technology to achieve real-time collection and transmission of data of each device in the power station.

[0156] Ensure the accuracy and real-time nature of the data, providing a reliable data source for the virtual monitoring platform.

[0157] 2. Digital twin model construction:

[0158] Based on the physical structure and equipment layout of the power station, construct a three-dimensional digital twin model.

[0159] Map the collected data to the digital twin model in real time to achieve virtual reproduction of the operation status of the power station.

[0160] 3. Virtual operation monitoring:

[0161] On the virtual monitoring platform, the operation status and key parameters of each device in the power station are displayed in real time.

[0162] Support comprehensive monitoring of the operation status of the power station, including real-time monitoring of parameters such as power generation, equipment temperature, voltage, and current.

[0163] Provide a graphical interface to display data in the form of charts, curves, etc., enabling operation and maintenance personnel to quickly understand the operation situation of the power station.

[0164] 4. Abnormal alarm and fault diagnosis:

[0165] When an abnormal situation is detected, the alarm mechanism is automatically triggered to remind the operation and maintenance personnel through means such as sound, light, and pop-up windows.

[0166] Provide fault diagnosis suggestions to help operation and maintenance personnel quickly locate the cause of the problem and take corresponding measures for handling.

[0167] Therefore, the present invention utilizes Momo AI for monitoring, alarm analysis, and management of the virtual model, which can achieve comprehensive and real-time monitoring of various elements and behaviors in the virtual environment, and issue an alarm in a timely manner when an abnormality or potential risk is detected. Specifically:

[0168] First, Momo AI has powerful multi-modal processing capabilities and can process various types of data such as images, videos, and texts simultaneously. In virtual model monitoring, Momo AI can comprehensively perceive the state of the virtual world by analyzing visual information (such as human actions, object positions, etc.) and text information (such as system logs, user inputs, etc.) in the virtual environment.

[0169] Next, Momo AI uses advanced deep learning and machine learning algorithms to perform real-time analysis and processing on the collected data. It can identify abnormal behaviors or potential risks in the virtual environment, such as abnormal actions of people, abnormal movements of objects, abnormal changes in system parameters, etc. These abnormalities may be internal problems in the virtual world or caused by external attacks or failures.

[0170] Once Momo AI detects an abnormality, it will immediately trigger an alarm mechanism. The alarm mechanism can include various forms of notifications, such as sound alerts, pop-up warnings, email notifications, etc., to ensure that monitoring personnel can quickly learn about and respond to abnormal situations. At the same time, Momo AI can also provide detailed information and context about the occurrence of the abnormality to help monitoring personnel quickly locate the problem and take corresponding handling measures.

[0171] In addition, Momo AI also has the ability to self-learn and optimize. It can gradually improve the accuracy of identifying abnormal behaviors and the alarm response speed by continuously analyzing and processing data in the virtual environment. This enables Momo AI to better adapt to the changes and developments of the virtual environment and provide continuous support and improvement for monitoring alarm analysis management.

[0172] In summary, using Momo AI for monitoring alarm analysis management of virtual models can achieve efficient, accurate, and real-time monitoring and alarm functions, providing strong guarantees for the safety and stability of the virtual environment.

[0173] As Figure 2 shown, it is a flowchart of the virtual monitoring method for a photovoltaic power station based on digital twin technology, and the processing flow of this method can include the following steps:

[0174] S1. Establish a virtual monitoring task for the photovoltaic power station and select target management objects from each element;

[0175] S2. Real-time collect the digital twin model data set of the target management object in the twin model of the photovoltaic power station to obtain a target detection data set;

[0176] S3. Through Momo AI, traverse and identify the target detection dataset, and determine whether there is abnormal data in the target detection dataset that triggers the alarm mechanism: If so, generate an alarm signal corresponding to the target management object; otherwise, continue to monitor.

[0177] S4. Through Momo AI, track the context dataset of the abnormal data that appears, and send the tracked context dataset together with the alarm signal to the patrol terminal.

[0178] Because using Momo AI for monitoring, alarm analysis and management of virtual models can achieve comprehensive and real-time monitoring of various elements and behaviors in the virtual environment, and send alarms in a timely manner when abnormalities or potential risks are detected. Therefore, in the present invention, an administrator can pre-construct a virtual monitoring task for a photovoltaic power station, and the task can include:

[0179] Elements to be monitored;

[0180] Core elements in each monitored element, and used as the target management object;

[0181] Monitoring content and corresponding alarm mechanisms;

[0182] Monitoring signal routing addresses and distribution schemes for patrol administrators, etc.

[0183] The core element can be specified by the administrator. For example, the abnormal supervision of the virtual models of inverters and their administrators includes the abnormal monitoring of human behaviors and the abnormal monitoring of the position status or movement behaviors of objects (for example, for the assembly / repair and inspection actions of inverter accessories, Momo AI can identify whether their assembly / repair and inspection actions are qualified. Momo AI will receive training on the abnormal action data of the assembly / repair and inspection actions of the inverter accessories in the early stage; the same applies to others).

[0184] Subsequently, when applied on the platform, data of each element (physical model) is collected in real time and processed based on dataset mapping to dynamically update the digital twin model datasets of each element in the twin model of the photovoltaic power station in real time.

[0185] The multi-modal AI model: Momo AI, can perform virtual monitoring on each element in the virtual scene, monitor abnormal behaviors in the virtual scene for data such as action feature images, voices, or texts of the virtual model, and achieve remote supervision and management. When multi-modal monitoring of each element is performed in the twin model of the photovoltaic power station, when an abnormal situation is monitored, the alarm mechanism is automatically triggered, and corresponding alarm signals are generated and sent to the handheld patrol terminals of the operation and maintenance personnel.

[0186] Preferably, in step S2, the digital twin model data set of the target management object in the twin model of the photovoltaic power station is collected in real time to obtain a target detection data set, including:

[0187] Collect the three-dimensional feature data of each element in real time;

[0188] Based on the data set mapping relationship between the entity model and the virtual model, perform data mapping calculation on the three-dimensional feature data of each element, and update the digital twin model data set of each element in the twin model of the photovoltaic power station according to the calculation result;

[0189] Traverse the digital twin model data sets before and after the update of each element, and mark the elements whose digital twin model data sets have changed, to obtain an element set S;

[0190] Judge whether the target management object exists in the element set S:

[0191] If it exists, extract the updated digital twin model data set of the target management object to obtain the target detection data set;

[0192] If it does not exist, continue to maintain update monitoring.

[0193] Because the management terminal needs to perform Momo AI specified management on the target management object. Therefore, when the data of the virtual models of subsequent elements is updated, in order to avoid increasing the data operation and calculation pressure of Momo AI, the present invention first traverses and identifies the data set changes before and after the updated elements, judges and marks the elements with data changes, and aggregates the elements with data changes in the data set to obtain an element set S. Then, it is judged whether the element set S contains the element where the target management object is located. If there is a target management object corresponding to the element with data changes, the updated data set is extracted as the target detection data set to be detected; if not, the data change supervision of the model is continued. By the above method, it is avoided that the Momo AI model performs data detection on all elements, reducing its operation pressure and computing power cost.

[0194] Preferably, in step S3, through Momo AI, traverse and identify the target detection data set, and judge whether there is abnormal data triggering the alarm mechanism in the target detection data set, including:

[0195] Input the target detection data sets of each target management object into the preset Momo AI anomaly detection model on the virtual monitoring platform layer;

[0196] Through the Momo AI anomaly detection model, traverse and identify the target detection datasets of each of the target management objects, and determine whether there is abnormal data in the target detection datasets that triggers the alarm mechanism;

[0197] Among them, as Figure 3 shown, the method for generating the Momo AI anomaly detection model includes:

[0198] Collect the abnormal action data of each element in the photovoltaic power station and preprocess it, including image, video or text data;

[0199] Perform feature engineering on the abnormal action data of each element, use the multi-modal algorithm in Momo AI to adaptively identify and extract the abnormal action features in the abnormal action data of each element, and construct a feature set composed of the abnormal action features of several elements;

[0200] Divide the feature set into a training set and a validation set according to a preset ratio;

[0201] Input the training set into the preset Momo AI for feature training and learning to construct the Momo AI anomaly detection model;

[0202] Use the validation set to verify the recognition performance of the Momo AI anomaly detection model:

[0203] If the verification passes, deploy the Momo AI anomaly detection model on the virtual monitoring platform layer, adjust the parameters and put it into application;

[0204] If the verification fails, repeat the above steps to reconstruct the Momo AI anomaly detection model.

[0205] Because Momo AI has a multi-modal algorithm model, it can not only perform feature recognition of data, but also perform model training based on the extracted features to construct a corresponding anomaly detection model.

[0206] Here, it is possible to collect the abnormal action data of people, equipment or corresponding behaviors in the virtual scene, such as the abnormal operation action image of a certain accessory of the inverter by xx technicians, the fault operation data of the equipment, or the abnormal transportation trajectory data of a certain photovoltaic equipment such as a photovoltaic panel in the photovoltaic power station, etc.

[0207] Furthermore, the steps of using Momo AI to perform feature learning on the abnormal action data of people, objects or behaviors and constructing the Momo AI anomaly detection model can refer to the following content:

[0208] ‌Data collection and preprocessing‌:

[0209] Collect a dataset containing normal and abnormal actions. This data can include images, videos, text, or other forms of data.

[0210] Preprocess the data, including data cleaning, denoising, normalization, etc., to ensure data quality and make it suitable for feature learning.

[0211] Feature extraction:

[0212] Use Momo AI or its integrated feature extraction technology to extract useful features from the preprocessed data. These features should be able to reflect the essential attributes and regularities of the data.

[0213] Feature extraction may involve using deep learning algorithms such as convolutional neural networks (CNNs) to extract features from images or videos, or using text embedding models to extract features from text data.

[0214] Momo AI integrates multi-modal algorithm models, such as image algorithms, text algorithms, or machine learning algorithms such as CNNs and RNNs. Therefore, it can adaptively select the appropriate algorithm for each data type to perform feature recognition and extraction according to the data type. For example, for abnormal operation action images, CNN can be used to identify and extract abnormal action posture features.

[0215] Model training:

[0216] Select a suitable AI algorithm, such as an autoencoder, isolation forest, or deep learning-based model, for training the anomaly detection model.

[0217] Use the collected dataset to train the model. During training, the model will learn how to distinguish between normal and abnormal action data.

[0218] Adjust the model's parameters and perform multiple iterative trainings to improve the model's accuracy and generalization ability.

[0219] Model evaluation and optimization:

[0220] Use the validation set to evaluate the performance of the model, including metrics such as accuracy, recall, and F1 score. This is completed by the administrator.

[0221] Optimize the model based on the evaluation results, such as adjusting feature selection, improving the model structure, or adjusting training parameters.

[0222] Repeat the process of training, evaluation, and optimization until the model reaches a satisfactory performance level.

[0223] Deployment and application:

[0224] Deploy the trained Momo AI anomaly detection model to the virtual monitoring platform layer.

[0225] Use the model to perform real-time detection on new input data to identify abnormal actions.

[0226] Take corresponding measures according to the detection results, such as issuing an alarm, recording a log, or conducting further analysis.

[0227] Continuous improvement:

[0228] Collect new abnormal action data for continuously updating and optimizing the model.

[0229] Monitor the performance of the model and retrain or adjust it when necessary.

[0230] Explore new feature extraction and model training methods to further improve the accuracy and robustness of the model.

[0231] Because Momo AI can use an optimized dataset to construct model training data, including:

[0232] Detailed image description: Describe abnormal actions through images (i.e., abnormal action annotations and explanatory information on the abnormal action diagram);

[0233] Voice description: Describe the image in detail through voice. This voice input usually contains more details to help the AI better understand and learn the content in the image. For example, for an abnormal operation action of a certain component of an inverter, the administrator can prepare corresponding voice data for explaining the abnormal operation. The voice needs to explain, for example, which points are prone to operation errors, what the action requirements are for each error position, and what the correction strategy for operation errors is; etc.

[0234] Through the enhanced training data, Momo AI can deeply understand the characteristic data of the abnormal action data of each element, thereby strengthening the accuracy of model training and learning.

[0235] Preferably, when performing feature engineering, it also includes:

[0236] Collect voice data / images describing the abnormal action data of each element;

[0237] Parse the voice data / images and obtain the corresponding text description of abnormal actions;

[0238] Use the multi-modal algorithm in Momo AI to adaptively identify and extract the description information about the abnormal actions of each element in the text description of abnormal actions;

[0239] Label the description information on the abnormal action features.

[0240] For the collection, analysis, recognition, and annotation of the description data of the abnormal operation data of each element, the following steps can be referred to:

[0241] First, collect the abnormal operation data:

[0242] For voice data, the voice information describing the abnormal operations of each element can be collected through the recording on the management side or the relevant application device program (such as the voice recording function of a smartphone).

[0243] For image data, a camera or a screenshot tool can be used to capture the image of each element in the abnormal operation state.

[0244] Next, analyze the voice / image data:

[0245] Voice data: Using speech recognition technology, the collected voice data is converted into text form. This step can be achieved with the help of existing speech recognition software or APIs, converting the description of abnormal operations in the voice into processable text information.

[0246] Image data: Through image recognition technology, each element in the image is recognized, and the features of abnormal operations are extracted. This usually involves steps such as image preprocessing, feature extraction, and classification, which can be completed using computer vision libraries or deep learning models.

[0247] Then, utilize the multi-modal algorithm in Momo AI:

[0248] Taking the text of the description of abnormal operations obtained from the analysis as input, the multi-modal algorithm in Momo AI is used for adaptive recognition. The multi-modal algorithm can comprehensively consider various information such as text, voice, and image, improving the accuracy and robustness of recognition.

[0249] Through algorithm processing, the specific description information about the abnormal operations of each element in the text is extracted, and this information will be used for subsequent annotation work.

[0250] Finally, label the description information on the abnormal operation features:

[0251] For image data, the extracted description information of abnormal operations can be labeled on the abnormal operation features of the corresponding elements in the form of text labels (the labeling position can be defaulted to the upper right corner). This can be achieved through image annotation tools or programming to ensure that the description information corresponds one-to-one with the abnormal operation features in the image.

[0252] For voice data, the text description obtained through parsing can also be marked on the abnormal action features of the corresponding elements. In this way, during subsequent use, the voice description of a specific abnormal action can be found by querying the database.

[0253] Through the above steps, the goal of collecting, parsing, identifying, and annotating the abnormal action data of each element can be achieved. Momo AI has multimodal algorithms that can extract descriptive information about abnormal actions from the parsed text, such as abnormal action correction strategies.

[0254] Therefore, by using Momo AI for the monitoring, alarm analysis, and management of virtual models, the present invention can achieve efficient, accurate, and real-time monitoring and alarm functions, providing a strong guarantee for the safety and stability of the virtual environment.

[0255] Figure 4 It is a block diagram of a virtual monitoring system for a photovoltaic power station based on digital twin technology shown according to an exemplary embodiment. This system is used for the virtual monitoring method of a photovoltaic power station based on digital twin technology. Refer to Figure 4 On the other hand, a virtual monitoring system for a photovoltaic power station based on digital twin technology is provided. The virtual monitoring system for a photovoltaic power station based on digital twin technology is used to implement the above-mentioned virtual monitoring method for a photovoltaic power station based on digital twin technology. The system includes:

[0256] A management terminal, which is used to establish a virtual monitoring task for the photovoltaic power station and select a target management object from each element;

[0257] A virtual monitoring platform, which is used to collect in real time the digital twin model data set of the target management object in the twin model of the photovoltaic power station to obtain a target detection data set; and, through Momo AI, traverse and identify the target detection data set to determine whether there is abnormal data that triggers the alarm mechanism in the target detection data set: if so, generate an alarm signal corresponding to the target management object; otherwise, continue monitoring; and, through Momo AI, perform context data set tracking on the abnormal data that appears, and send the tracked context data set together with the alarm signal to the patrol inspection terminal;

[0258] A patrol inspection terminal, which is used to receive and display the context data set and the alarm signal;

[0259] The management terminal and the patrol inspection terminal are respectively communicatively connected to the virtual monitoring platform.

[0260] For the interactive management functions between the management terminal and the patrol inspection terminal and the virtual monitoring platform respectively, please understand in combination with the above platform and method, and will not be elaborated here.

[0261] Figure 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As shown in Figure 5 , optionally, the electronic device 410 may include a first processor 2001.

[0262] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003.

[0263] Among them, the first processor 2001 is connected to the memory 2002 and the transceiver 2003, and may be connected through a communication bus.

[0264] Next, in combination with Figure 5 each component of the electronic device 410 will be specifically introduced:

[0265] Among them, the first processor 2001 is the control center of the electronic device 410, and may be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. For example: one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0266] Optionally, the first processor 2001 may execute various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0267] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 5 the CPU0 and CPU1 shown in

[0268] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 5 the first processor 2001 and the second processor 2004 shown in . Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, the processor may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0269] Among them, the memory 2002 is used to store the software program for implementing the solution of the present invention and is controlled by the first processor 2001 for execution. The specific implementation manner can refer to the above method embodiments and will not be elaborated here.

[0270] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently and is coupled to the first processor 2001 through the interface circuit ( Figure 5 not shown) of the electronic device 410. The embodiments of the present invention do not make specific limitations on this.

[0271] The transceiver 2003 is used to communicate with a network device or communicate with a terminal device.

[0272] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 not shown separately). Among them, the receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0273] Optionally, the transceiver 2003 may be integrated with the first processor 2001 or may exist independently and is coupled to the first processor 2001 through the interface circuit ( Figure 5 not shown) of the electronic device 410. The embodiments of the present invention do not make specific limitations on this.

[0274] It should be noted that Figure 5 the structure of the electronic device 410 shown in the figure does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0275] In addition, the technical effects of the electronic device 410 may refer to the technical effects of the virtual monitoring method for photovoltaic power stations based on digital twin technology described in the foregoing method embodiments, which will not be elaborated herein.

[0276] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0277] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0278] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0279] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0280] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0281] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0282] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0283] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, systems, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0284] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of systems or units can be electrical, mechanical, or other forms.

[0285] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0286] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0287] When the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0288] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A photovoltaic station virtual monitoring method based on digital twin technology, implemented based on a photovoltaic station digital twin platform, characterized in that: The photovoltaic station digital twin platform includes a data acquisition layer, a data processing layer, a digital twin model layer and a virtual monitoring platform layer, wherein: ‌Data Collection Layer‌: used to collect the status data of each element in the photovoltaic station in real time and transmit it to the data processing layer, where the elements include people, objects and behaviors in the photovoltaic station; ‌Data processing layer‌: used to receive the state data from the data acquisition layer, clean, verify and store it, and use big data analysis technology to process and analyze the collected data, extract the corresponding three-dimensional feature data from the state information of each element and upload it to the ‌digital twin model layer; ‌Digital twin model layer‌: used to construct a digital twin model of a photovoltaic power station through digital twin technology based on the three-dimensional feature data, obtain a photovoltaic station twin model, and classify and save the digital twin model data set of each element in the photovoltaic station twin model; ‌Virtual monitoring platform layer‌: used to visualize the digital twin model data set of the target management objects in the PV station twin model and its elements; and, using a multimodal AI model: Momo AI, to perform multimodal monitoring of each element of the PV station twin model. When an abnormal situation is monitored, the alarm mechanism is automatically triggered, and the corresponding alarm signal is generated and sent to the handheld inspection terminal of the operation and maintenance personnel; Management layer: used to select target management objects from various elements, and perform visual management and multi-modal monitoring on the target management objects; The method comprises: S1. Establish a virtual monitoring task for the photovoltaic station and select the target management object from each element; S2. Collecting the digital twin model data set of the target management object in the photovoltaic station twin model in real time to obtain a target detection data set; S3. Through Momo AI, traverse and identify the target detection data set, and determine whether abnormal data that triggers the alarm mechanism appears in the target detection data set: if so, generate an alarm signal corresponding to the target management object; otherwise, continue monitoring; S4. Through Momo AI, the context data set is tracked for the abnormal data that appears, and the context data set obtained by tracking is sent together with the alarm signal to the inspection terminal.

2. The photovoltaic station virtual monitoring method based on digital twin technology according to claim 1 is characterized in that: The step S2, collecting the digital twin model data set of the target management object in the photovoltaic station twin model in real time to obtain a target detection data set, includes: Collecting the three-dimensional feature data of each element in real time; Based on the data set mapping relationship between the physical model and the virtual model, data mapping calculation is performed on the three-dimensional feature data of each element, and the digital twin model data set of each element in the photovoltaic station twin model is updated according to the calculation result; Traversing the digital twin model data set before and after each element is updated, and marking the elements of the digital twin model data set that have data changes, to obtain an element set S; Determine whether the target management object exists in the element set S: If so, extract the updated digital twin model dataset of the target management object to obtain the target detection dataset; If it does not exist, continue to update monitoring.

3. The photovoltaic station virtual monitoring method based on digital twin technology according to claim 1 is characterized in that: S3, through Momo AI, traversing and identifying the target detection data set, and determining whether abnormal data that triggers an alarm mechanism appears in the target detection data set, includes: Inputting the target detection data set of each target management object into the Momo AI anomaly detection model preset on the virtual monitoring platform layer; Through the Momo AI anomaly detection model, the target detection data set of each target management object is traversed and identified to determine whether abnormal data that triggers an alarm mechanism appears in the target detection data set; The method for generating the Momo AI anomaly detection model includes: Collect and pre-process abnormal motion data of each element in the photovoltaic station, including image, video or text data; Perform feature engineering on the abnormal action data of each element, use the multimodal algorithm in Momo AI to adaptively identify and extract abnormal action features in the abnormal action data of each element, and construct a feature set consisting of the abnormal action features of several elements; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into the preset Momo AI, perform feature training and learning, and construct a Momo AI anomaly detection model; The recognition performance of the Momo AI anomaly detection model is verified using the validation set: If the verification is successful, the Momo AI anomaly detection model is deployed on the virtual monitoring platform layer and put into use after adjusting the parameters; If the verification fails, repeat the steps of "the method for generating the Momo AI anomaly detection model" above to rebuild the Momo AI anomaly detection model.

4. The photovoltaic station virtual monitoring method based on digital twin technology according to claim 3 is characterized in that: When performing feature engineering, it also includes: Collect voice data / images describing abnormal motion data of each element; Parsing the voice data / image and obtaining corresponding abnormal action description text; Using the multimodal algorithm in Momo AI, adaptively identify and extract the description information of the abnormal actions of each element in the abnormal action description text; The description information is marked on the abnormal action feature.

5. A photovoltaic station virtual monitoring system based on digital twin technology, wherein the photovoltaic station virtual monitoring system based on digital twin technology is used to implement the photovoltaic station virtual monitoring method based on digital twin technology as claimed in any one of claims 1 to 4, characterized in that: The system comprises: The management end is used to establish the virtual monitoring task of the photovoltaic station and select the target management object from each element; A virtual monitoring platform is used to collect the digital twin model data set of the target management object in the photovoltaic station twin model in real time to obtain a target detection data set; and, through Momo AI, traverse and identify the target detection data set to determine whether abnormal data that triggers an alarm mechanism appears in the target detection data set: if so, generate an alarm signal corresponding to the target management object; otherwise, continue monitoring; and, through Momo AI, perform context data set tracking on the abnormal data that appears, and send the context data set obtained by tracking together with the alarm signal to the inspection terminal; An inspection terminal, used for receiving and displaying the context data set and the alarm signal; The management terminal and the inspection terminal are respectively connected to the virtual monitoring platform for communication.

6. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 4.

Images