Data maintenance management method and device based on three-dimensional digital twinborn model

Abstract

The invention provides a data maintenance management method and device for a three-dimensional digital twin model, and the method comprises the steps: collecting the operation state data of a physical entity in real time through Internet of Things equipment, and carrying out the data preprocessing operation of the operation state data; according to the parameter information of the physical entity, constructing a corresponding three-dimensional digital twinborn model, and fusing the preprocessed real-time operation state data with the three-dimensional digital twinborn model; and based on the three-dimensional digital twinborn model, analyzing the acquired data by using a configured machine algorithm, and generating a decision support report based on an analysis result. The invention aims to realize data maintenance and management of the three-dimensional digital twin model of the physical entity by utilizing technologies such as the Internet of Things, data mining and machine learning. Decision support is provided by collecting data of physical entities in real time and performing data analysis and model establishment and updating.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a data maintenance and management method based on a three-dimensional digital twin model. Background Art

[0002] 3D digital twin model: 3D digital twin model is an important part of digital twin technology. It uses advanced modeling technology and digital means to accurately map and simulate physical entities in three-dimensional space. Specifically, the 3D digital twin model uses a variety of technical means such as geometric modeling, physical modeling, and behavioral modeling to construct a virtual copy that is highly similar or even completely identical to the physical entity. This virtual copy not only contains basic information such as the geometric shape and structural characteristics of the physical entity, but also integrates multi-dimensional information such as the physical entity's operating data, environmental parameters, and material properties, thereby achieving comprehensive, real-time, and dynamic reflection and prediction of the physical entity.

[0003] Compared with traditional data maintenance and management methods, data maintenance and management through three-dimensional digital twin models can significantly reduce labor costs and improve the efficiency of data maintenance and management.

[0004] However, existing technologies have many problems in data maintenance and management of 3D digital twin models of physical entities, including insufficient real-time and accuracy of data collection, limited data analysis and model update capabilities, weak data security and privacy protection, poor visualization and decision support, and lack of continuously optimized data maintenance and management methods. These problems limit the effectiveness and value of digital twin models in practical applications. Summary of the invention

[0005] The technical problem to be solved by the present invention is how to improve the quality, security and availability of data to provide stronger support for decision-making; in view of this, the present invention provides a data maintenance management method and device based on a three-dimensional digital twin model.

[0006] The technical solution adopted by the present invention is a data maintenance and management method based on a three-dimensional digital twin model, comprising:

[0007] Step S1, collecting the operation status data of the physical entity in real time through the Internet of Things device, and performing data preprocessing operations on the operation status data;

[0008] Step S2, constructing a corresponding three-dimensional digital twin model according to the parameter information of the physical entity, and fusing the preprocessed real-time operating status data with the three-dimensional digital twin model;

[0009] Step S3, based on the three-dimensional digital twin model, use the configured machine algorithm to analyze the collected data, and generate a decision support report based on the analysis results. The decision support report includes equipment maintenance suggestions, energy consumption optimization plans, and safety hazard inspections.

[0010] In one embodiment, the method further comprises:

[0011] Step S4: Visualize the real-time operation status data and the decision support report.

[0012] In one embodiment, in step S1, the operating status data includes:

[0013] Temperature, humidity, voltage, current, device status.

[0014] In one embodiment, in step S1, the preprocessing operation includes:

[0015] Data cleaning: remove noise, fill missing values, and delete duplicate data.

[0016] In one embodiment, in step S2, the parameter information includes:

[0017] The structure, size and layout of the physical entity.

[0018] In one embodiment, step S3 specifically includes:

[0019] Analyze the collected data using the configuration algorithm to extract the information and rules represented by the data, where the analysis includes: equipment operation trend prediction, fault warning, and energy efficiency evaluation;

[0020] Based on the analysis results, a decision support report is generated.

[0021] In one embodiment, the configuration algorithm specifically includes one or more of the following:

[0022] Random forest, support vector machine, gradient boosting machine, convolutional neural network, recurrent neural network, long short-term memory network.

[0023] Another aspect of the present invention further provides a data maintenance and management device based on a three-dimensional digital twin model, comprising:

[0024] A collection unit, configured to collect the operation status data of the physical entity in real time through the Internet of Things device, and perform data preprocessing operations on the operation status data;

[0025] A construction unit configured to construct a corresponding three-dimensional digital twin model according to parameter information of the physical entity, and fuse the preprocessed real-time operating status data with the three-dimensional digital twin model;

[0026] The decision-making unit is configured to analyze the collected data based on the three-dimensional digital twin model using a configured machine algorithm, and generate a decision support report based on the analysis results. The decision support report includes equipment maintenance recommendations, energy consumption optimization plans, and safety hazard inspections.

[0027] Another aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the data maintenance and management method based on the three-dimensional digital twin model as described in any one of the above items are implemented.

[0028] Another aspect of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the data maintenance and management method based on the three-dimensional digital twin model as described in any of the above items are implemented.

[0029] Compared with the prior art, the present invention has at least the following advantages:

[0030] The technical solution of the present invention aims to realize the data maintenance and management of the three-dimensional digital twin model of the physical entity by using the Internet of Things, data mining, machine learning and other technologies. By collecting the data of the physical entity in real time, performing data analysis and model establishment and updating, providing decision support and visual display, and continuously optimizing and improving the data maintenance and management methods, the quality, security and availability of the data can be improved, providing more powerful support for decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of a data maintenance and management method based on a three-dimensional digital twin model according to an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of the composition of a data maintenance and management device based on a three-dimensional digital twin model according to an embodiment of the present invention;

[0033] Figure 3 The figure is a schematic diagram of the composition of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose, the present invention is described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0035] Unless otherwise defined, all terms (including technical terms and scientific terms) used in this article have the same meaning as commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that terms (such as terms defined in commonly used dictionaries) should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless explicitly defined in this article.

[0036] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0037] An embodiment of the present invention provides a data maintenance and management method based on a three-dimensional digital twin model, comprising:

[0038] Step S1, collecting the operation status data of the physical entity in real time through the Internet of Things device, and performing data preprocessing operations on the operation status data;

[0039] Step S2, constructing a corresponding three-dimensional digital twin model according to the parameter information of the physical entity, and fusing the preprocessed real-time operating status data with the three-dimensional digital twin model;

[0040] Step S3, based on the three-dimensional digital twin model, use the configured machine algorithm to analyze the collected data, and generate a decision support report based on the analysis results. The decision support report includes equipment maintenance suggestions, energy consumption optimization plans, and safety hazard inspections.

[0041] refer to Figure 1 , the method provided in this embodiment will be described in detail step by step below.

[0042] In this embodiment, before step S1, it is usually necessary to perform demand analysis and system planning, which specifically includes the following steps:

[0043] 1. Determine the requirements: First, the functions and performance indicators that the system needs to achieve must be clearly defined based on actual requirements, including but not limited to: accuracy requirements for 3D models, real-time data collection, data processing capabilities, response time for abnormal alarms, and user-friendly interface, etc.

[0044] 2. System planning: Based on the results of demand analysis, carry out system planning, including: determine the system architecture, clarify the functions and interfaces of each component. Select the appropriate technology stack, such as WebGL, HTML5, JavaScript, etc., to support 3D visualization and front-end interaction. Design a data storage solution to ensure the integrity, security and accessibility of the data. Plan the data processing process, including data collection, cleaning, analysis, modeling and other steps.

[0045] Step S1, collecting the operating status data of the physical entity in real time through the Internet of Things device, and performing data preprocessing operations on the operating status data.

[0046] The specific process includes the following:

[0047] 1. Data collection: Real-time collection of operating status data of physical entities through various data sources such as Internet of Things (IoT) devices, sensors, cameras, etc. These data include but are not limited to temperature, humidity, voltage, current, equipment status, etc.

[0048] 2. Data preprocessing: The collected raw data may contain noise, redundancy, missing data, etc., and preprocessing is required to improve data quality.

[0049] The preprocessing steps may include, for example: Data cleaning: removing noise, filling missing values, deleting duplicate data, etc. Data conversion: converting data in different formats and units into a unified format and standard units. Data compression: compressing the 3D model data to reduce storage space and transmission bandwidth requirements.

[0050] Step S2: construct a corresponding three-dimensional digital twin model based on the parameter information of the physical entity, and fuse the preprocessed real-time operating status data with the three-dimensional digital twin model.

[0051] The specific process includes the following:

[0052] 1. Model design: Design a three-dimensional digital twin model based on the structure, size, layout and other information of the physical entity. The model must be highly realistic and interactive, and accurately reflect the appearance and internal structure of the physical entity.

[0053] 2. Model construction: Use 3D modeling software (such as Blender, 3ds Max, etc.) or automated modeling tools to build a 3D digital twin model based on design drawings and measured data. The model must include the geometric shape, location information, attribute data, etc. of the equipment.

[0054] 3. Data fusion: Fuse the pre-processed real-time data with the 3D model to achieve dynamic visualization of the data. It is necessary to ensure the real-time update of the data and the synchronous rendering of the model so that users can understand the operating status of the physical entity in real time.

[0055] In this embodiment, the process of designing a three-dimensional digital twin model based on the structure, size, layout and other information of the physical entity can be implemented by the following method:

[0056] Preliminary preparation and demand analysis:

[0057] First, it is necessary to collect relevant information about the physical entity, including but not limited to design drawings, measured data, equipment manuals, operation and maintenance records, etc. These materials will provide basic data for subsequent 3D modeling.

[0058] After collecting enough information, it is necessary to conduct an in-depth analysis of the modeling requirements. This includes determining the purpose of the model, the required accuracy, the display method, the interactive function, etc. For example, if the model is used for operation and maintenance management, then the maintainability of the equipment and the location of the wearing parts need to be focused on; if the model is used for training, then the interactivity of the model and the demonstration of the operation process need to be emphasized.

[0059] Based on the results of the demand analysis, a detailed modeling plan needs to be developed. This includes determining the modeling tools, assigning modeling tasks, developing a schedule, budgeting resources, etc. The modeling plan needs to fully consider the team's capabilities, time limits, and budget constraints.

[0060] 3D modeling process:

[0061] Establish a basic model: Based on the design drawings and measured data of the physical entity, start to establish a basic 3D model. This includes creating the geometric shape of the object, defining the size and proportion of the object, setting the material and texture of the object, etc. During the modeling process, it is necessary to ensure the accuracy and authenticity of the model for subsequent data fusion and visualization.

[0062] Add details and attributes: After the basic model is established, more details and attributes need to be added. This includes the internal structure of the equipment, connectors, identification plates, etc. At the same time, attribute data needs to be added to the model, such as the name, model, manufacturer, installation date, etc. of the equipment. The addition of these details and attributes will make the model richer and more specific, and improve its practical value.

[0063] Optimize model performance: Since 3D models may contain a large amount of data and complex structures, the model needs to be optimized to improve its performance. This includes reducing the number of polygons, optimizing textures and materials, using level of detail (LOD) technology, etc. Through optimization, you can ensure that the model has a smooth rendering speed and low memory usage at runtime.

[0064] Conduct model testing: After the model is built, it needs to be fully tested to ensure that it meets the requirements of the requirements specification. The test content includes but is not limited to the accuracy, completeness, interactivity, performance, etc. of the model. If any problems or defects are found, they need to be repaired and improved in a timely manner.

[0065] Data fusion and visualization

[0066] Data preprocessing: Before integrating real-time data with the 3D model, data preprocessing is required, including data cleaning (removing noise, filling missing values, etc.), data conversion (converting data in different formats and units into a unified format and standard units), and data compression (reducing storage space and transmission bandwidth requirements).

[0067] Data and model fusion: After preprocessing, real-time data needs to be fused with the 3D model. This includes mapping the sensor data to the corresponding part of the model to achieve dynamic visualization of the data. For example, the data of the temperature sensor can be mapped to the surface of the device to show the temperature change in the form of color or animation.

[0068] Visualization interface design: In order to display the 3D digital twin model and data analysis results, an intuitive and easy-to-use visualization interface needs to be designed. The interface design needs to fully consider the user's usage habits and needs, and provide interactive operations such as zooming, panning, and rotating, so that users can observe the model and data from different angles.

[0069] Real-time data display and interaction: In the visualization interface, the operating status data of the physical entity needs to be displayed in real time, and the key indicators of the equipment need to be intuitively reflected through colors, icons, animations, etc. At the same time, the interface needs to support user interaction operations, such as clicking on the device to view detailed information and dragging the slider to adjust the viewing angle.

[0070] Model maintenance and updates:

[0071] Regular model inspection: In order to ensure the accuracy and real-time performance of the 3D digital twin model, the model needs to be inspected regularly. This includes checking the integrity of the model, the accuracy of the data, and the performance of the model. If any problems or anomalies are found, they need to be repaired and updated in a timely manner.

[0072] Model update and upgrade: As the physical entity changes and upgrades, the 3D digital twin model needs to be updated and upgraded accordingly. This includes adding or removing equipment, adjusting equipment layout, updating equipment properties, etc. At the same time, the model needs to be optimized and improved to improve its performance and usability.

[0073] Data security and privacy protection: During model maintenance and updating, special attention should be paid to data security and privacy protection. This includes ensuring that the collected data is not illegally accessed or leaked, and preventing malicious attacks and virus intrusions. To this end, it is necessary to establish a complete data security and privacy protection mechanism, such as data encryption storage, access rights control, and audit log recording.

[0074] System testing and deployment:

[0075] Integration testing: After the 3D digital twin model is designed, integration testing is required to ensure that the model can work properly with other components of the system. The test content includes but is not limited to the model's loading speed, rendering effect, interactive functions, and accuracy of data analysis.

[0076] User acceptance test: In order to ensure that the 3D digital twin model meets user needs, users need to be invited to conduct acceptance tests. Users will evaluate and test the model based on actual usage scenarios and needs, and put forward improvement opinions and suggestions. The model needs to be further optimized and improved based on user feedback.

[0077] System deployment and training: After the test is passed, the 3D digital twin model needs to be deployed to the production environment and necessary configuration and optimization needs to be performed. At the same time, system usage training is also required for operation and maintenance personnel to help them quickly master the system's operation methods and functional features. The training content includes but is not limited to model viewing methods, interactive operations, data analysis, and abnormal alarm processing.

[0078] Continuous optimization and iteration:

[0079] User feedback collection: After the 3D digital twin model is put into use, it is necessary to continuously collect user feedback and usage experience. This includes user evaluation and suggestions on model satisfaction, functional requirements, performance, etc. By collecting user feedback, we can continuously discover problems and deficiencies in the model and provide direction for subsequent optimization and iteration.

[0080] Model performance monitoring: In order to ensure the stable operation and efficient performance of the 3D digital twin model, the performance of the model needs to be continuously monitored. This includes monitoring indicators such as the model's rendering speed, memory usage, and CPU usage, and promptly discovering and resolving performance bottlenecks. Through performance monitoring, it can be ensured that the model has good performance and user experience in actual use.

[0081] Iterative optimization and upgrade: Based on user feedback and performance monitoring results, the 3D digital twin model needs to be iteratively optimized and upgraded. This includes fixing known issues, adding new features, optimizing performance, etc. Through continuous iterative optimization and upgrade, the practical value and user experience of the model can be continuously improved to meet the ever-changing needs and expectations of users.

[0082] Step S3: Based on the three-dimensional digital twin model, the collected data is analyzed using the configured machine algorithm, and a decision support report is generated based on the analysis results.

[0083] The specific processing flow includes:

[0084] 1. Data mining and analysis: Use data mining and machine learning algorithms to conduct in-depth analysis of the collected data and extract valuable information and patterns. The analysis content includes but is not limited to: equipment operation trend prediction, fault warning, energy efficiency evaluation, etc.

[0085] 2. Decision support: Based on the analysis results, a decision support report is generated to provide scientific decision-making basis for operation and maintenance personnel. The report content includes but is not limited to: equipment maintenance suggestions, energy consumption optimization solutions, safety hazard inspections, etc.

[0086] In this embodiment, how to use data mining and machine learning algorithms to conduct in-depth analysis of the collected data and extract valuable information and rules can be achieved by the following methods:

[0087] Data preprocessing and preparation:

[0088] Data collection and integration: First, data needs to be collected from various data sources such as sensors, equipment logs, and operation and maintenance records. These data may exist in different formats, frequencies, and qualities, so they need to be integrated and cleaned. During the integration process, the integrity and consistency of the data must be ensured, and duplicate, erroneous, or irrelevant data must be removed.

[0089] Data cleaning and conversion: Data cleaning is a key step in preprocessing, including noise removal, missing value filling, smoothing, etc. For missing values, interpolation, regression or other methods can be used for estimation and filling. At the same time, data in different formats need to be converted into a unified format for subsequent analysis.

[0090] Feature selection and extraction: Before data analysis, meaningful features need to be extracted from the original data. Feature selection is based on the understanding of the business and data, and selects features that have an impact on the analysis target. Feature extraction is to calculate new features such as mean, variance, maximum, minimum, etc. from the original data through mathematical transformation or statistical methods.

[0091] Data Mining and Pattern Recognition:

[0092] Association rule mining: Association rule mining is used to discover frequent item sets and association rules in data. In equipment operation and maintenance data, the relationship between equipment failure and certain operating parameters can be mined to provide a basis for fault warning. For example, if a certain device is found to frequently fail under specific operating parameters, the corresponding warning rules can be set.

[0093] Cluster analysis: Cluster analysis is to divide data into multiple groups or clusters, so that the data similarity within the same cluster is high, while the data similarity between different clusters is low. In the equipment energy efficiency evaluation, cluster analysis can be used to divide the equipment into different energy efficiency levels so as to formulate targeted optimization measures.

[0094] Classification and prediction: Classification is the division of data into predetermined categories or labels. In equipment failure warning, classification algorithms can be used to classify equipment status and determine whether the equipment is in a faulty state. Prediction is to build models based on historical data to predict future trends. For example, time series analysis or machine learning algorithms can be used to predict the operating trend and remaining life of equipment.

[0095] Machine Learning Algorithm Applications:

[0096] Algorithm selection and training: Select the appropriate machine learning algorithm based on the analysis objectives and data characteristics. Common algorithms include decision trees, random forests, support vector machines, neural networks, etc. Use the selected algorithm to train the data to obtain a prediction model or classifier.

[0097] Model evaluation and optimization: Evaluate the trained model to check its accuracy, stability, and generalization ability. You can use cross-validation, accuracy, recall, and other indicators for evaluation. If the model performance is poor, you need to optimize it, such as adjusting algorithm parameters, increasing the number of features, changing the model structure, etc.

[0098] Real-time prediction and update: Deploy the trained model to the production environment for real-time prediction and update. Real-time prediction can promptly detect equipment failures or abnormal operation, and provide timely processing suggestions for operation and maintenance personnel. At the same time, the model needs to be updated regularly to adapt to changes in equipment status and environment.

[0099] Fault warning and energy efficiency assessment:

[0100] Fault warning mechanism: Based on the analysis results of data mining and machine learning algorithms, a fault warning mechanism is established. When the equipment operation status is abnormal or close to the fault threshold, the system automatically sends out a warning signal to notify the operation and maintenance personnel to handle it in time. The warning signal can be in the form of SMS, email, APP push, etc.

[0101] Energy efficiency evaluation and optimization suggestions: Evaluate the energy efficiency of equipment and identify equipment and links with low energy efficiency. Based on the evaluation results, put forward targeted optimization suggestions, such as adjusting operating parameters, replacing high-efficiency components, improving process flow, etc. By implementing optimization measures, the energy efficiency level of equipment can be improved and energy consumption costs can be reduced.

[0102] Visual display and interaction:

[0103] Visual design: In order to intuitively display data analysis results and equipment status, a visual interface needs to be designed. The interface should be concise and clear, and can clearly display key indicators and trends. Visual display can be performed in the form of charts, dashboards, maps, etc.

[0104] Implementation of interactive functions: The visualization interface should support user interactive operations, such as zooming, panning, filtering, etc. Users can view data in different time periods, switch views of different devices or indicators, etc. through interactive operations. Interactive functions can improve user participation and usage experience.

[0105] Real-time data update and display: The visualization interface needs to display the latest data and analysis results in real time. This requires the ability to process and update data in real time and push the updated results to the front end for display. Through real-time data update and display, users can understand the equipment status and operation trends in a timely manner.

[0106] System Integration and Deployment:

[0107] Integration with other systems: The data maintenance management system of the 3D digital twin model needs to be integrated with other systems, such as equipment monitoring system, operation and maintenance management system, etc. Through system integration, data sharing and interaction can be achieved, and the overall operation and maintenance efficiency and management level can be improved.

[0108] System deployment and configuration: Deploy the system to the production environment and perform necessary configuration and optimization. Ensure that the system can run stably and meet business needs. Perform regular maintenance and updates on the system to adapt to business development and environmental changes.

[0109] User training and support: Provide users with system training and support. The training content includes system function introduction, operation methods, data analysis skills, etc. Provide user manuals and online help documents for users to find and use at any time. At the same time, establish a user feedback mechanism to collect and process user feedback in a timely manner, and continuously improve and optimize the system.

[0110] Continuous optimization and iteration:

[0111] Improve data quality: Continuously optimize data collection and processing processes to improve data quality and accuracy. Clean and verify data regularly to ensure data integrity and consistency. By improving data quality, the accuracy and reliability of data analysis can be improved.

[0112] Algorithm model optimization: Continuously optimize and iterate the machine learning algorithm model. According to new data and business needs, adjust the algorithm parameters and structure to improve the prediction accuracy and generalization ability of the model. Through algorithm model optimization, the accuracy and practicality of fault warning and energy efficiency evaluation can be improved.

[0113] System performance monitoring and tuning: Continuously monitor and tune system performance. Pay attention to indicators such as system response time, throughput, and number of concurrent users, and promptly identify and resolve performance bottlenecks. Through system performance monitoring and tuning, you can ensure that the system can maintain a stable operating state under high load.

[0114] Step S4: Visualize the real-time operation status data and the decision support report.

[0115] 1. Visual interface design: Design an intuitive and easy-to-use visual interface to display the 3D digital twin model and data analysis results. The interface needs to support interactive operations such as zooming, panning, and rotating so that users can observe the model and data from different angles.

[0116] 2. Real-time data display: In the visual interface, the running status data of the physical entity is displayed in real time. Through colors, icons, animations, etc., the key indicators such as temperature, humidity, voltage, current, etc. of the equipment are intuitively reflected.

[0117] 3. Abnormal alarm and disposal: When abnormal data is detected, the alarm mechanism is triggered immediately to remind users through sound, pop-up windows, etc. At the same time, abnormal data details and disposal suggestions are provided to help users quickly locate the problem and take measures.

[0118] 4. User interaction and feedback: Support users to interact through the interface, such as clicking on the device to view detailed information, dragging the slider to adjust the viewing angle, etc. At the same time, collect user feedback and continuously optimize the interface design and function implementation.

[0119] Furthermore, this embodiment also involves the following contents:

[0120] 1) Model maintenance and optimization

[0121] 1. Model update: As the physical entity changes and upgrades, the 3D digital twin model needs to be updated regularly. Updates include but are not limited to: equipment addition and reduction, layout adjustment, property changes, etc.

[0122] 2. Performance optimization: In order to improve the system's operating efficiency and user experience, the 3D digital twin model needs to be optimized. Optimization measures include but are not limited to: model lightweight processing, rendering algorithm improvement, data transmission acceleration, etc.

[0123] 3. Data security and privacy protection: A comprehensive data security and privacy protection mechanism must be established to ensure that the collected data is not illegally accessed or leaked. Specific measures include but are not limited to: data encryption storage, access rights control, audit log recording, etc.

[0124] 2) System testing and deployment

[0125] 1. System testing: Before the system is officially launched, it is necessary to conduct a comprehensive test on the system. The test content includes but is not limited to: functional testing, performance testing, security testing, etc. Ensure that the system meets all requirements in the requirements specification.

[0126] 2. System deployment: After the test is passed, the system will be deployed to the production environment. During the deployment process, factors such as network configuration, load, and data security need to be considered to ensure that the system runs stably and meets actual business needs.

[0127] 3. User training and support: After deployment, system training is required for operation and maintenance personnel to help them quickly master the system's operation methods and functional features. At the same time, technical support and maintenance services are provided to ensure long-term stable operation of the system.

[0128] Compared with the prior art, this embodiment has at least the following effects:

[0129] 1) This embodiment designs a three-dimensional digital twin model based on the structure, size, layout and other information of the physical entity, thereby generating a three-dimensional digital twin model with a high consistency with the physical entity, thereby improving the accuracy of subsequent data management using the three-dimensional digital twin model.

[0130] 2) This embodiment uses data mining and machine learning algorithms to conduct in-depth analysis of the collected data to provide more accurate data and more efficient data provision for the three-dimensional digital twin model, thereby improving the real-time performance of data management using the three-dimensional digital twin model.

[0131] 3) This embodiment improves the usability of the data maintenance management system based on the three-dimensional digital twin model through the design of the visualization page.

[0132] 4) This embodiment continuously updates and upgrades the data maintenance management system based on the three-dimensional digital twin model through a feedback mechanism to meet the changes in physical entities and improve the applicability of the system.

[0133] In summary, the embodiment of the present invention proposes a data maintenance management method and system based on a three-dimensional digital twin model, which realizes efficient data collection, processing, analysis and visualization. By constructing a virtual model that corresponds one-to-one to the physical entity, the system can reflect the operating status and change trend of the physical entity in real time, and provide scientific decision-making basis and efficient operation and maintenance tools for operation and maintenance personnel; at the same time, the system is also highly scalable and customizable, and can meet the operation and maintenance management needs of different industries and fields. With the continuous advancement of technology and the continuous expansion of application scenarios, the data maintenance management system based on the three-dimensional digital twin model will play a more important role in the future.

[0134] The second embodiment of the present invention corresponds to the first embodiment, and can be referred to Figure 2 This embodiment introduces a data maintenance and management device based on a three-dimensional digital twin model, including the following components:

[0135] A collection unit, configured to collect the operation status data of the physical entity in real time through the Internet of Things device, and perform data preprocessing operations on the operation status data;

[0136] A construction unit configured to construct a corresponding three-dimensional digital twin model according to parameter information of the physical entity, and fuse the preprocessed real-time operating status data with the three-dimensional digital twin model;

[0137] The decision-making unit is configured to analyze the collected data based on the three-dimensional digital twin model using a configured machine algorithm, and generate a decision support report based on the analysis results. The decision support report includes equipment maintenance recommendations, energy consumption optimization plans, and safety hazard inspections.

[0138] In one embodiment, the device is further used for:

[0139] The real-time operating status data and the decision support report include visualization processing.

[0140] In this embodiment, the operating status data includes: temperature, humidity, voltage, current, and device status.

[0141] In this embodiment, the preprocessing operation includes: data cleaning: removing noise, filling missing values, and deleting duplicate data.

[0142] In this embodiment, the parameter information includes: the structure, size, and layout of the physical entity.

[0143] In this embodiment, the decision unit is specifically configured as follows:

[0144] Analyze the collected data using the configuration algorithm to extract the information and rules represented by the data, where the analysis includes: equipment operation trend prediction, fault warning, and energy efficiency evaluation;

[0145] Based on the analysis results, a decision support report is generated.

[0146] In this embodiment, the configuration algorithm specifically includes one or more of the following: random forest, support vector machine, gradient boosting machine, convolutional neural network, recurrent neural network, long short-term memory network.

[0147] A third embodiment of the present invention is an electronic device, such as Figure 3 As shown, it can be understood as a physical device, including a processor and a memory storing instructions executable by the processor. When the instructions are executed by the processor, the following operations are performed:

[0148] Step S1, collecting the operation status data of the physical entity in real time through the Internet of Things device, and performing data preprocessing operations on the operation status data;

[0149] Step S2, constructing a corresponding three-dimensional digital twin model according to the parameter information of the physical entity, and fusing the preprocessed real-time operating status data with the three-dimensional digital twin model;

[0150] Step S3, based on the three-dimensional digital twin model, use the configured machine algorithm to analyze the collected data, and generate a decision support report based on the analysis results. The decision support report includes equipment maintenance suggestions, energy consumption optimization plans, and safety hazard inspections.

[0151] Step S4: Visualize the real-time operation status data and the decision support report.

[0152] The fourth embodiment of the present invention, the process of the data maintenance management method based on the three-dimensional digital twin model of this embodiment is the same as the first, second or third embodiment, the difference is that, in engineering implementation, this embodiment can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the method of the present invention can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, disk, CD), including a number of instructions for a device to execute the method described in the embodiment of the present invention.

[0153] Through the description of the specific implementation methods, a deeper and more specific understanding of the technical means and effects adopted by the present invention to achieve the predetermined purpose should be obtained. However, the accompanying drawings are only for reference and illustration purposes and are not intended to limit the present invention.

Claims

1. A data maintenance and management method based on a three-dimensional digital twin model, characterized in that: include: Step S1, collecting the operation status data of the physical entity in real time through the Internet of Things device, and performing data preprocessing operations on the operation status data; Step S2, constructing a corresponding three-dimensional digital twin model according to the parameter information of the physical entity, and fusing the preprocessed real-time operating status data with the three-dimensional digital twin model; Step S3, based on the three-dimensional digital twin model, use the configured machine algorithm to analyze the collected data, and generate a decision support report based on the analysis results. The decision support report includes equipment maintenance suggestions, energy consumption optimization plans, and safety hazard inspections.

2. The data maintenance and management method based on the three-dimensional digital twin model according to claim 1 is characterized in that: The method further comprises: Step S4: Visualize the real-time operation status data and the decision support report.

3. The data maintenance and management method based on the three-dimensional digital twin model according to claim 1 is characterized in that: In step S1, the operating status data includes: Temperature, humidity, voltage, current, device status.

4. The data maintenance and management method based on the three-dimensional digital twin model according to claim 2 is characterized in that: In step S1, the preprocessing operation includes: Data cleaning: remove noise, fill missing values, and delete duplicate data.

5. The data maintenance and management method based on the three-dimensional digital twin model according to claim 1 is characterized in that: In step S2, the parameter information includes: The structure, size and layout of the physical entity.

6. The data maintenance and management method based on the three-dimensional digital twin model according to claim 5 is characterized in that: The step S3 specifically includes: Analyze the collected data using the configuration algorithm to extract the information and rules represented by the data, where the analysis includes: equipment operation trend prediction, fault warning, and energy efficiency evaluation; Based on the analysis results, a decision support report is generated.

7. The data maintenance and management method based on the three-dimensional digital twin model according to claim 6 is characterized in that: The configuration algorithm specifically includes one or more of the following: Random forest, support vector machine, gradient boosting machine, convolutional neural network, recurrent neural network, long short-term memory network.

8. A data maintenance and management device based on a three-dimensional digital twin model, characterized in that: include: A collection unit, configured to collect the operation status data of the physical entity in real time through the Internet of Things device, and perform data preprocessing operations on the operation status data; A construction unit configured to construct a corresponding three-dimensional digital twin model according to parameter information of the physical entity, and fuse the preprocessed real-time operating status data with the three-dimensional digital twin model; The decision-making unit is configured to analyze the collected data based on the three-dimensional digital twin model using a configured machine algorithm, and generate a decision support report based on the analysis results. The decision support report includes equipment maintenance recommendations, energy consumption optimization plans, and safety hazard inspections.

9. An electronic device, characterized in that: The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the data maintenance and management method based on the three-dimensional digital twin model as described in any one of claims 1 to 7 are implemented.

10. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the data maintenance and management method based on a three-dimensional digital twin model as described in any one of claims 1 to 7.

Images