Data management system for electric power capacity increasing site

Abstract

The invention relates to the technical field of digital and intelligent management of an electric power system, and discloses a data management system for an electric power capacity increasing site. According to the system, a collaborative architecture comprising a field equipment layer, an edge intelligent layer, a platform core layer and an application service layer is constructed, and multi-source heterogeneous data collection, edge side standardized packaging, platform side deep treatment and health degree dynamic evaluation and scenarized service packaging based on health degree scores are executed in sequence; and a complete data quality closed-loop management and control process is formed. The technical problems of data islands, quality out-of-control, processing lag, business disjunction and the like in a traditional scheme are effectively solved, knowing and controllability of data quality, high efficiency and accuracy of business collaboration and continuous optimization of system efficiency are achieved, and the method has the advantages of being high in data fusion degree, high in quality credibility, accurate in business enabling, good in system self-adaption and the like. The method is suitable for power line capacity increasing, equipment reconstruction sites, power grid intelligent operation and maintenance and other scenes.

Description

Technical Field

[0001] This invention relates to the field of digital and intelligent management technology of power systems, and discloses a data management system for power capacity expansion on-site. Background Technology

[0002] Power grid capacity expansion and renovation projects are crucial for ensuring power grid reliability and meeting the demands of load growth. During this process, comprehensive, accurate, and real-time monitoring of multi-source data, including equipment status, construction progress, and environmental parameters, is fundamental to achieving transparent project management and safe, efficient operation. Currently, in existing technological practices, data management at power grid expansion sites primarily relies on the following methods: First, deploying isolated specialized monitoring systems, such as dynamic capacity expansion calculation systems for transmission lines and online monitoring systems, to collect specific equipment status data; second, combining traditional SCADA systems with manual recording methods to manage broader on-site information, such as construction progress and inspection results; and third, utilizing preliminary data storage platforms or project workflow management software to attempt data storage and workflow approval.

[0003] However, during the development of this invention, it was discovered that existing technical solutions have significant shortcomings when dealing with complex and dynamic capacity expansion scenarios. Each professional system operates independently, with varying data standards and communication protocols, forming robust "data silos." This prevents the integration of status data, business processes, and spatial information, making it difficult to construct a unified on-site situation view. Furthermore, the quality of raw data collected on-site is inconsistent, with issues such as missing data and anomalies. Existing systems lack intrinsic assessment and repair mechanisms for data quality, and directly inputting low-quality data into advanced applications poses decision-making risks. In addition, the process from data collection to decision-making is lengthy and lacks timeliness, failing to meet the real-time response requirements of scenarios such as on-site safety monitoring. Moreover, data presentation is disconnected from specific on-site business roles, failing to proactively empower frontline operations.

[0004] While the aforementioned solutions have achieved certain results in specific areas, they generally face the dilemma of "data integration and quality being mutually exclusive" and "global situational awareness and real-time response being difficult to reconcile." The industry lacks a closed-loop management system that can fundamentally break down data silos, achieve knowable and controllable data quality, and transform high-quality data into business insights in real time. Therefore, there is an urgent need for an innovative data management method and system that can simultaneously solve core problems such as data silos, low quality, processing delays, and business disconnect, providing core support for the safe, efficient, and intelligent management of power capacity expansion sites. Summary of the Invention

[0005] This invention discloses a data management system for power capacity expansion sites. By constructing a collaborative architecture comprising a field device layer, an edge intelligence layer, a platform core layer, and an application service layer, the system enables unified access and standardized governance of multi-source heterogeneous data, dynamic assessment and controllable data quality, and scenario-based intelligent services based on health scores. This system significantly improves the transparency, operational efficiency, and decision-making security of power capacity expansion site management, substantially reduces the systemic risks caused by data silos, low quality, and processing delays in traditional solutions, and effectively addresses the prominent problems in existing technologies such as isolated system operation, data disconnect from business operations, and limited performance of advanced applications due to unreliable data.

[0006] To achieve the above objectives, the present invention provides a data management system for power capacity expansion sites, comprising: The field equipment layer is deployed at the power capacity expansion site to collect multi-source heterogeneous raw data from the power capacity expansion site. The edge intelligence layer is communicatively connected to the field device layer and is used to perform preliminary processing and standardized encapsulation of the multi-source heterogeneous raw data. The platform core layer, which is communicatively connected to the edge intelligence layer, includes: The data access and governance module is used to receive data processed by the edge intelligence layer and perform data cleaning and association with advanced business tags; The dynamic health assessment engine, connected to the data access and governance module, is used to calculate a dynamic health score in real time for the data after data cleaning and business tag association. A unified data foundation, connected to the dynamic health assessment engine, is used to store data with the health score attached; The data service module, connected to the unified data base, is used to provide a data service interface; The application service layer communicates with the data service interface of the data service module and is used to obtain data from the unified data base through the data service module based on the health score, and provide scenario-based data services to different user roles or third-party systems.

[0007] Preferably, the field equipment layer includes condition monitoring sensors, smart meters, and mobile inspection terminals.

[0008] Preferably, the edge intelligence layer includes an edge intelligence sensing terminal; The edge intelligent sensing terminal is configured to perform the following operations: The multi-source heterogeneous raw data is parsed using multiple protocols to extract valid data; The effective data is encapsulated using a pre-defined standard data metadata model, the encapsulation including adding at least spatiotemporal tags and basic business tags to the effective data; The packaged valid data is checked for data rationality, and an instantaneous warning is generated when the packaged valid data exceeds a preset reasonable range.

[0009] Preferably, the data access and governance module includes: A data access gateway is used to receive standardized, encapsulated data streams from the edge intelligence layer. The data governance and activation engine, connected to the data access gateway, is used to perform data cleaning, data repair, and advanced business tag association on the received data stream.

[0010] Preferably, the health assessment engine is configured to calculate the health score using at least one of the following dimensions of the assessment data: Completeness is used to assess whether data is continuous and without missing parts; Reasonableness is used to assess whether the values ​​included in the data are within a predefined range of physical or business feasibility. Consistency is used to assess whether data is logically consistent with related data of the same type or in the environment. Timeliness is used to assess whether the delay from data collection to processing completion exceeds a preset timeliness threshold.

[0011] Preferably, the application service layer includes: A scenario-based service encapsulation engine is used to obtain data from the unified data foundation according to different user roles and business scenarios, and to intelligently process the health score of the data as the core logic to encapsulate it into a data service package. The intelligent processing includes at least one of the following methods: dynamically adjusting the content of the data service package based on the health score, identifying the credibility of the data in the data service package based on the health score, or filtering out the data in the data service package based on the health score.

[0012] Preferably, the scenario-based service encapsulation engine is configured to encapsulate inspection data service packages for on-site inspection personnel; The scenario-based service encapsulation engine dynamically prioritizes the devices to be inspected in the data service package based on the real-time health score of the device data.

[0013] Preferably, the scenario-based service encapsulation engine is configured to encapsulate project dashboard data service packages for project managers; The scenario-based service encapsulation engine associates and identifies the data health score with the key performance indicators in the project cockpit data service package.

[0014] Preferably, the scenario-based service encapsulation engine is configured to encapsulate data service packages for the control center or dynamically expanding computing system; The scenario-based service encapsulation engine selects data from the unified data base based on the condition that the health score is higher than a preset threshold, and then encapsulates it into the data service package.

[0015] Preferably, the application service layer also includes: A data visualization platform is used to graphically display the data service packages output by the scenario-based service encapsulation engine; The data visualization platform is configured to present the health score of the data in the data service package in a visual form.

[0016] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention include at least the following: This invention addresses the systemic challenges of data silos, uncontrollable quality, and weak business empowerment inherent in traditional solutions by constructing a layered architecture and closed-loop data flow that integrates "edge-platform-application." Through standardized encapsulation and instantaneous alerts at the edge intelligence layer, initial data organization and real-time assurance are achieved at the source. Data governance and dynamic health assessment at the platform core layer establish a unified and reliable data foundation, making data quality knowable and quantifiable. Scenario-based encapsulation at the application service layer precisely transforms high-quality data into "ready-to-use" service packages that drive business decisions. This system achieves end-to-end empowerment from chaotic data to intelligent business, significantly improving on-site operational efficiency, management decision accuracy, and system adaptive optimization capabilities. Simultaneously, it greatly reduces the risks to power grid operation caused by unreliable data, providing a high-value, evolvable overall solution for the digital management of power capacity expansion projects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the hierarchical architecture of the system of the present invention; Figure 2 This is a schematic diagram of the core components of the edge intelligence layer in the system of the present invention; Figure 3 This is a schematic diagram of the overall architecture of the system of the present invention; Figure 4 This is a flowchart illustrating the working logic of the dynamic health assessment engine in the system of this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] In this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0021] Example 1 As can be seen from the above background technology, in the field of digital and intelligent management of power systems, achieving unified access, high-quality governance and precise business empowerment of all elements of data at the capacity expansion site is the core foundation for improving engineering management efficiency and power grid operation safety. However, existing technologies that rely on a combination of isolated professional systems and manual recording, while achieving the collection and recording of specific business data to a certain extent, suffer from systemic defects such as robust data silos, uncontrollable quality, delayed response, and disconnect from business operations. They cannot guarantee data comprehensiveness while simultaneously ensuring quality reliability and real-time service, making it difficult to support on-site safety management and intelligent operation and maintenance scenarios with stringent requirements for data credibility and real-time decision-making. While some independent optimization solutions for data storage or process approval have improved certain aspects (such as online processes or data persistence), their technical architecture fails to achieve end-to-end quality closed-loop collaborative control from data collection to business empowerment. This results in significant shortcomings in management efficiency, including low data integration, weak quality reliability, poor accuracy in business empowerment, and insufficient system adaptability. The existing data support capabilities are significantly inferior to the high-standard management requirements of modern power capacity expansion projects, and cannot meet the application needs of high-value scenarios such as large-scale complex on-site operations, efficient cross-departmental collaboration, and the intelligent evolution of the power grid.

[0022] Therefore, this application provides a data management system for power capacity expansion sites, such as... Figure 1, Figure 2 , Figure 3 and Figure 3 As shown, the system physically consists of a field device layer, an edge intelligence layer, a platform core layer, and an application service layer, with components within each layer interconnected through clearly defined communication links.

[0023] The status monitoring sensors, smart meters, and mobile inspection terminals at the field equipment layer establish communication connections with the edge intelligent sensing terminals at the edge intelligence layer via industrial fieldbus or IoT protocols, responsible for collecting and uploading multi-source heterogeneous raw data. The edge intelligent sensing terminals then establish communication connections with the data access gateway at the platform core layer via mobile communication networks or enterprise intranets, uploading the data streams that have undergone preliminary processing and standardized packaging. Within the platform core layer, the data access gateway is directly connected to the data governance and activation engine, responsible for sending the data streams in for deep cleaning and repair; the processing results of the data governance and activation engine are sent to the connected dynamic health assessment engine for real-time quantitative scoring of data quality; the assessed data is then stored in a unified data base directly connected to the dynamic health assessment engine; the data service module is connected to the unified data base, serving as the system's sole external data outlet. The application service layer's scenario-based service encapsulation engine connects with the data service module. The scenario-based service encapsulation engine retrieves data from the unified data foundation by calling the application programming interface provided by the data service module. The processing results of the scenario-based service encapsulation engine are directly output to the data visualization platform that collaborates with it for graphical display. At the same time, it provides data services to third-party systems through the interfaces encapsulated by the data service module.

[0024] System working principle and workflow After the system starts up, its complete workflow and the core functions of each module are as follows: The field equipment layer is responsible for collecting multi-source heterogeneous raw data at the lowest level. Status monitoring sensors (such as conductor temperature sensors and micro-weather stations) capture equipment operating status and environmental parameters; smart meters collect electrical quantity data such as current, voltage, and power; and mobile inspection terminals are used for manual entry of inspection records, capturing on-site images, and reporting personnel location information via GPS / BeiDou modules.

[0025] This raw data enters the edge intelligent sensing terminal at the edge intelligence layer via the communication link. The terminal first performs multi-protocol parsing, identifying and converting device data from different manufacturers and using different protocols, extracting valid physical quantity data values. Next, it performs standardized encapsulation, attaching at least spatiotemporal tags (precise GPS coordinates and millisecond-level timestamps) and basic business-related tags (such as the associated capacity expansion project and device ID) to the valid data using a pre-defined standard data metadata model. This achieves unified identification at the data source, laying the foundation for breaking down data silos. Finally, it performs lightweight health assessment and instantaneous alarms, checking the reasonableness of the encapsulated data (e.g., determining if the temperature value is within the physically feasible range of -50°C to 150°C). If a significant data anomaly or communication interruption is detected, a warning is immediately generated locally and pushed to on-site personnel, achieving a millisecond-level safety response.

[0026] The standard data stream, processed at the edge layer, enters the platform's core layer through the data access gateway. As the system entry point, the data access gateway is responsible for receiving data uploaded from all edge terminals with high concurrency and high reliability. The data is then fed into the data governance and activation engine, which performs in-depth processing: its data cleaning and repair functions employ intelligent algorithms based on spatiotemporal correlation (e.g., for missing temperature data, spatial interpolation estimation is performed using data from the same line, adjacent towers, and simultaneous moments), and it identifies and corrects abnormal data; its business tag association function dynamically adds richer business tags (such as "construction phase" or "critical section line") to the data according to preset business rules, deeply binding the data with business processes.

[0027] The data, after undergoing in-depth processing, is fed into the dynamic health assessment engine. This is the core algorithm module of the system, which calculates a dynamically changing health score (0-100 points) for each data point in real time. The assessment process covers four precise dimensions: completeness (assessing whether the data sequence is continuous and without missing data); reasonableness (assessing whether the data values ​​are within a predefined physical or business feasible range); consistency (assessing whether the data is logically consistent with related similar or environmental data (e.g., whether its trend conforms to the changing patterns of ambient temperature and load current); and timeliness (assessing whether the delay from data collection to data storage exceeds a preset threshold). Based on the data's comprehensive performance across these dimensions, the engine outputs an objective quality score.

[0028] All evaluated data, along with its health score, is stored in a unified data infrastructure. This infrastructure serves as the single, trusted data source for the entire system, centrally storing all high-quality data. The data service module acts as a unified data export channel, providing standardized and secure data service interfaces (APIs) to the outside world.

[0029] At the application service layer, the scenario-based service encapsulation engine retrieves data from the unified data foundation through the data service module's interface. The engine's core function is to intelligently process data health scores as the core logic, based on different user roles and business scenarios, and encapsulate them into "ready-to-use data service packages." This intelligent processing manifests in several ways: dynamically adjusting the content of the data service package based on the health score (e.g., dynamically prioritizing equipment to be inspected when generating task packages for inspection personnel); identifying the reliability of data within the data service package based on the health score (e.g., marking low-health data as a yellow warning in the project manager's dashboard); or filtering data within the data service package based on the health score (e.g., selecting only key data with a health score higher than 90 when encapsulating data packets for a dynamically expanding computing system).

[0030] These service packages are ultimately presented to users in a graphical way (such as a dashboard or map heatmap) through a data visualization platform, which is configured to simultaneously present the health score of the data; at the same time, they are also provided to third-party systems through standardized interfaces to empower a wider range of business applications.

[0031] The entire system forms an intelligent closed loop. Feedback from third-party systems or users on the effectiveness of the system (such as "the calculation results of certain data have a high degree of consistency") can be fed back to the dynamic health assessment engine to optimize its assessment model; the optimized model or strategy (such as a more accurate reasonableness threshold) can then be used as an optimization strategy to be sent back to the edge intelligent sensing terminal to improve its local processing capabilities, thereby achieving continuous self-evolution of "the more data is used, the better it becomes, and the more the system is used, the smarter it becomes".

[0032] It is important to note that in this system, the business information executed by the edge intelligence layer and the platform core layer is interconnected, and there is a clear division of labor and a progressive collaborative relationship in terms of hierarchy, depth, and purpose: At the edge intelligence layer, the basic business association tag focuses on the fundamental identity binding and source tracing of data. It attaches the most fundamental business identity to the data through pre-defined static or quasi-static information (such as "to which capacity expansion project ID" and "device unique ID") in the data metadata model, aiming to initially break down data silos and solve the basic questions of "who owns the data and from which business link does it come?" This process pursues efficiency and standardization, laying a unified identity foundation for subsequent processing.

[0033] At the platform's core layer, the aforementioned business tag association focuses on enriching the deep semantics of data and dynamically binding it to context. Building upon the identity provided at the edge layer, it leverages the platform's global data view and sophisticated business rule engine to dynamically attach more business-insightful advanced tags (such as "construction phase," "critical section," and "safety warning level") to the data. This aims to address the advanced question of "what does the data mean and what is its importance in the current business context," thereby achieving deep coupling and intelligent activation of data and business processes.

[0034] Together, these two elements constitute a complete business chain from "data identity identification" to "business semantic empowerment," which is a key and continuous step in the system's transformation of data from raw signals to intelligent service assets.

[0035] Through the aforementioned collaborative architecture and closed-loop workflow, the following significant benefits have been achieved: First, data quality has become knowable, controllable, and improveable. By assigning a dynamic health score to each piece of data, downstream advanced applications can make quality-based decisions, fundamentally ensuring the reliability of calculation results. Second, information silos have been completely broken down. Through standardized data meta-models and unified governance processes, a "unified data fact" has been constructed across businesses and roles, greatly improving collaborative efficiency. Third, the accuracy and efficiency of on-site operations have been significantly improved. Through scenario-based service encapsulation, a shift from "people seeking tasks" to "tasks seeking people" has been achieved, enabling data to proactively empower business operations. Finally, the system has formed a self-evolving closed loop of "data-driven optimization," with its overall performance continuously improving during use, possessing long-term viability, and providing a high-value, evolvable overall solution for the digital management of power capacity expansion sites.

[0036] Example 2 Based on the system architecture described in Embodiment 1, this embodiment will combine a typical "dynamic capacity expansion monitoring of transmission lines" scenario to elaborate in detail the collaborative workflow and data processing details of the edge intelligent sensing terminal and the internal modules of the platform core layer in the system, so as to further illustrate the specific implementation of the present invention.

[0037] Please see Figure 2 , Figure 3 and Figure 4The workflow of this embodiment begins with data acquisition and edge preprocessing. Assume that on a 110kV capacity expansion line, condition monitoring sensors (such as conductor temperature sensors) and micro-weather stations (collecting ambient temperature and wind speed) deployed on the towers collect raw data at 1-minute intervals and transmit the data to the local edge intelligent sensing terminal via a LoRa wireless network. The terminal immediately initiates the edge processing flow: first, its multi-protocol parsing module is activated, automatically identifying and parsing heterogeneous data formats from sensors from different manufacturers (such as parsing Modbus and IEC 104 protocols respectively), accurately extracting valid data such as conductor temperature, ambient temperature, and wind speed. Subsequently, the standardized encapsulation module, based on a preset standard data metadata model, adds four core metadata elements to each valid data entry: a spatiotemporal tag (the tower's precise GPS coordinates and the millisecond-level timestamp of data acquisition), a lineage tag (the unique ID and model of the source device), an initial health tag (an initial score preset based on the historical reliability of the sensor model, such as 85 points), and an advanced business association tag (such as associating it with the "XX110kV Capacity Expansion Project" and "Dynamic Capacity Expansion Monitoring" business phases). After encapsulation, the lightweight health assessment module performs instantaneous judgment on the data, performing data rationality checks, such as determining whether the conductor temperature value is within a preset reasonable range (such as -20℃ to 120℃). If a temperature data point is found to instantly jump to 150℃, the terminal will immediately trigger an audible and visual alarm locally and push an instantaneous warning to the on-site inspection personnel's APP via the mobile network, achieving a millisecond-level response to safety hazards.

[0038] The standard data stream, having completed edge preprocessing, enters the platform's core layer via the 5G network and data access gateway. On the platform side, the data governance and activation engine first performs deep cleaning of the data. If conductor temperature data is missing at a certain moment due to transient communication interference, the engine doesn't simply fill it with data from the previous moment. Instead, it activates its intelligent data repair function: automatically querying temperature data for the same line, adjacent towers, and at the same time, and using a Kriging spatial interpolation algorithm based on spatiotemporal correlation to estimate and generate repaired values. Simultaneously, the engine performs business tag association, dynamically attaching advanced business tags such as "critical section" and "dynamic capacity expansion under monitoring" to this batch of line data.

[0039] The processed data is then fed into a dynamic health assessment engine for precise quality scoring. This engine performs a multi-dimensional evaluation of the received conductor temperature data (see...). Figure 4In terms of completeness, the system checks whether data points are continuous and without missing data points over the past hour; in terms of reasonableness, it determines whether the values ​​are within a reasonable expected range (e.g., 0℃ to 80℃); in terms of consistency, it analyzes whether the trend of change conforms to the conductor heat balance equation with changes in ambient temperature and load current; and in terms of timeliness, it verifies whether the total delay from data collection to completion of treatment and storage is less than the preset threshold of 3 seconds. The engine integrates the performance across all dimensions and, through a weighted scoring model, calculates a health score of 92 for the conductor temperature data.

[0040] The score, along with the data, is stored in a unified data base. When the dynamic capacity expansion calculation system initiates a data request, the scenario-based service encapsulation engine retrieves the data from the base through the data service module's interface. Based on preset rules ("only provide data with a health score > 90 for the dynamic capacity expansion system"), the engine automatically filters out conductor temperature data with a health score of 92, along with load current and ambient wind speed data from the same batch that meet health standards. This data is packaged into a "high-reliability dynamic capacity expansion input data package" and pushed to the dynamic capacity expansion calculation system in real time via a standard API interface. Simultaneously, the data visualization platform clearly displays the line's real-time current carrying capacity, key point temperature, and its corresponding health score (92) on the project manager's dashboard interface in a dashboard format. When the score falls below a threshold (e.g., 90), the corresponding area on the interface changes color as a warning.

[0041] This embodiment demonstrates, through the detailed process described above, how the system achieves end-to-end transformation from raw data to high-reliability business services, and reflects the synergy between edge real-time response and platform deep intelligence, as well as the core role of data health in ensuring the reliability of advanced applications.

[0042] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0043] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0044] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A data management system for power capacity expansion sites, characterized in that, The system includes: The field equipment layer is deployed at the power capacity expansion site to collect multi-source heterogeneous raw data from the power capacity expansion site. The edge intelligence layer is communicatively connected to the field device layer and is used to perform preliminary processing and standardized encapsulation of the multi-source heterogeneous raw data. The platform core layer, which is communicatively connected to the edge intelligence layer, includes: The data access and governance module is used to receive data processed by the edge intelligence layer and perform data cleaning and association with advanced business tags; The dynamic health assessment engine, connected to the data access and governance module, is used to calculate a dynamic health score in real time for the data after data cleaning and business tag association. A unified data foundation, connected to the dynamic health assessment engine, is used to store data with the health score attached; The data service module, connected to the unified data base, is used to provide a data service interface; The application service layer communicates with the data service interface of the data service module and is used to obtain data from the unified data base through the data service module based on the health score, and provide scenario-based data services to different user roles or third-party systems.

2. The data management system for power capacity expansion sites according to claim 1, characterized in that, The field equipment layer includes condition monitoring sensors, smart meters, and mobile inspection terminals.

3. The data management system for power capacity expansion sites according to claim 1, characterized in that, The edge intelligence layer includes an edge intelligence sensing terminal; The edge intelligent sensing terminal is configured to perform the following operations: The multi-source heterogeneous raw data is parsed using multiple protocols to extract valid data; The effective data is encapsulated using a pre-defined standard data metadata model, the encapsulation including adding at least spatiotemporal tags and basic business tags to the effective data; The packaged valid data is checked for data rationality, and an instantaneous warning is generated when the packaged valid data exceeds a preset reasonable range.

4. The data management system for power capacity expansion sites according to claim 1, characterized in that, The data access and governance module includes: A data access gateway is used to receive standardized, encapsulated data streams from the edge intelligence layer. The data governance and activation engine, connected to the data access gateway, is used to perform data cleaning, data repair, and advanced business tag association on the received data stream.

5. The data management system for power capacity expansion sites according to claim 1, characterized in that, The health assessment engine is configured to calculate the health score using at least one of the following dimensions of the assessment data: Completeness is used to assess whether data is continuous and without missing parts; Reasonableness is used to assess whether the values ​​included in the data are within a predefined range of physical or business feasibility. Consistency is used to assess whether data is logically consistent with related data of the same type or in the environment. Timeliness is used to assess whether the delay from data collection to processing completion exceeds a preset timeliness threshold.

6. The data management system for power capacity expansion sites according to claim 1, characterized in that, The application service layer includes: A scenario-based service encapsulation engine is used to obtain data from the unified data foundation through the data service module according to different user roles and business scenarios, and to intelligently process the health score of the data as the core logic to encapsulate it into a data service package. The intelligent processing includes at least one of the following methods: dynamically adjusting the content of the data service package based on the health score, identifying the credibility of the data in the data service package based on the health score, or filtering out the data in the data service package based on the health score.

7. The data management system for power capacity expansion sites according to claim 6, characterized in that, The scenario-based service encapsulation engine is configured to encapsulate inspection data service packages for on-site inspection personnel. The scenario-based service encapsulation engine dynamically prioritizes the devices to be inspected in the data service package based on the real-time health score of the device data.

8. The data management system for power capacity expansion sites according to claim 6, characterized in that, The scenario-based service encapsulation engine is configured to encapsulate project cockpit data service packages for project managers. The scenario-based service encapsulation engine associates and identifies the data health score with the key performance indicators in the project cockpit data service package.

9. The data management system for power capacity expansion sites according to claim 6, characterized in that, The scenario-based service encapsulation engine is configured to encapsulate data service packages for the control center or dynamically expanding computing system. The scenario-based service encapsulation engine selects data from the unified data base based on the condition that the health score is higher than a preset threshold, and then encapsulates it into the data service package.

10. The data management system for power capacity expansion on-site according to claim 6, characterized in that, The application service layer also includes: A data visualization platform is used to graphically display the data service packages output by the scenario-based service encapsulation engine; The data visualization platform is configured to present the health score of the data in the data service package in a visual form.

Images