Water-power engineering digital asset transfer method and system based on BIM (Building Information Modeling)

Abstract

The invention discloses a BIM-based hydroelectric engineering digital asset transfer method and system, relates to the field of hydroelectric engineering digital asset transfer, and constructs semantic association holographic assets through deep fusion of BIM, GIS, IoT, documents and other multi-source heterogeneous data through a knowledge graph, so as to thoroughly break through information islands and improve the transfer efficiency of hydroelectric engineering digital assets. Driving automatic association and conversion of design, construction and operation and maintenance data based on the mapping rule base, and generating a standardized full-life-cycle asset mapping matrix; quantitative quality diagnosis and a multi-objective optimization algorithm are innovatively introduced, an optimal repair strategy for balancing quality, cost and time can be dynamically generated according to objective evaluation results and operation and maintenance business requirements, finally, accurate data repair and knowledge graph updating are performed through a credibility evaluation mechanism, and a complete quality improvement closed loop is formed. And the integrity, the consistency and the service availability of the transferred data are systematically guaranteed.

Description

Technical Field

[0001] This application relates to the field of digital asset transfer in hydropower projects, and in particular to a BIM-based method and system for digital asset transfer in hydropower projects. Background Technology

[0002] The rapid development of digital technologies, including BIM (Building Information Modeling) which provides a 3D model framework for the entire lifecycle management of engineering projects, the integration of the Internet of Things (IoT) and big data to enable real-time monitoring and intelligent data analysis of engineering equipment, and the trends of cloud computing and platform-based management driving the construction of unified data management platforms, have prompted the government and industry to introduce a series of policies and standards to improve the management level of hydropower projects. These policies explicitly require the realization of intelligent 3D design and digital handover. Under these circumstances, the development of digital asset handover methods and systems for hydropower projects has become an inevitable choice to meet the needs of industry development and break through traditional limitations.

[0003] Existing technologies suffer from problems such as insufficient attention from participating units, loss of original data, non-standard archiving, and serious data silos, resulting in low handover efficiency and poor data availability during the operation and maintenance phase. As engineering projects continue to expand in scale and become increasingly complex, existing technologies face numerous challenges in traditional asset transfer methods. A large amount of design, construction, and equipment data is scattered across different carriers and departments, forming information silos. Data integrity and availability are greatly compromised, and centralized transfer models consume a lot of manpower. Summary of the Invention

[0004] The purpose of this invention is to provide a BIM-based digital asset transfer method and system for hydropower projects to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a BIM-based digital asset transfer system for hydropower projects, comprising: Heterogeneous data aggregation is performed on the BIM model, GIS geographic information, IoT sensor data and engineering documents of the hydropower project to obtain the holographic data asset of the hydropower project; Based on the hydropower project asset classification system, the holographic data assets are mapped throughout their entire lifecycle from design to construction to operation and maintenance, resulting in the asset mapping matrix of the hydropower project. The integrity, consistency, and accuracy of the data in the asset mapping matrix are evaluated from multiple dimensions to obtain a data quality assessment report for the hydropower project. Based on the data quality assessment report and operation and maintenance requirements, the handover strategy of the hydropower project is dynamically optimized to obtain the optimal handover strategy of the hydropower project. Based on the optimal handover strategy, the defective data in the holographic data asset is precisely repaired to obtain the enhanced data asset of the hydropower project.

[0006] In the preferred embodiment of this solution, the multi-source data fusion module is executed as follows: Semantic features are extracted from the BIM model of the hydropower project to obtain the structured geometric data of the hydropower project; Spatial topology analysis is performed on the GIS geographic information to obtain the geospatial data of the hydropower project; The IoT sensor data is subjected to time-series feature extraction and outlier filtering to obtain the equipment operation data of the hydropower project. Key information is identified and relationships are constructed from the engineering documents to obtain unstructured document data of the hydropower project; Based on knowledge graph technology, semantic association is performed on the structured geometric data, the geospatial data, the equipment operation data, and the unstructured document data to obtain the holographic data asset of the hydropower project.

[0007] In the preferred embodiment of this solution, the asset mapping module is executed as follows: A classification system for hydropower engineering assets is established, which includes four major categories: hydraulic structures, electromechanical equipment, metal structure equipment, and auxiliary facilities. For each of the four categories, establish a mapping rule base between design parameters, construction records, and operation and maintenance requirements; Based on the mapping rule base, the design phase data in the holographic data asset is extended to the construction phase to obtain construction enhancement data. Based on the mapping rule base, the construction enhancement data is adapted to the operation and maintenance requirements to obtain operation and maintenance ready data; The operation and maintenance ready data is associated and integrated with the mapping rule base to form the asset mapping matrix of the hydropower project.

[0008] In the preferred embodiment of this solution, the quality diagnosis module is executed as follows: Missing information is detected in the key asset information of the asset mapping matrix to obtain the integrity index of the key asset information. Conflict analysis is performed on the cross-system data in the asset mapping matrix to obtain the consistency index of the cross-system data; The accuracy of the spatial geometric data in the asset mapping matrix is ​​verified to obtain the accuracy index of the spatial geometric data; Based on the handover standards for hydropower projects, the integrity index, consistency index, and accuracy index are weighted and calculated to obtain the comprehensive quality score of the hydropower project. Based on the comparison results between the comprehensive quality score and the preset threshold, a data quality assessment report for the hydropower project is generated.

[0009] In the preferred embodiment of this scheme, the strategy optimization module is executed as follows: By analyzing the problem distribution in the data quality assessment report, a set of data quality shortcomings is obtained; Obtain the business needs characteristics of the hydropower project operation and maintenance department, including equipment monitoring needs, maintenance needs, and safety management needs; Based on the data quality bottleneck set and the business requirement characteristics, an objective function for optimizing the handover strategy is constructed: F(S) = λ1·Q(S) + λ2·C(S) + λ3·T(S), where F(S) is the comprehensive score of the handover strategy S, λ1, λ2, and λ3 are weight coefficients, Q(S) is the data quality item, C(S) is the cost item, and T(S) is the time item. The handover strategy corresponding to the highest comprehensive score is selected as the optimal handover strategy.

[0010] In the preferred embodiment of this solution, the targeted repair module is executed as follows: The repair instructions in the optimal handover strategy are parsed to obtain a list of data items to be repaired; For each item in the list of data items to be repaired, determine its data source channel and acquisition priority; Based on the data source channels and the acquisition priority, incremental collection of defective data in the holographic data assets is performed to obtain the original repair data. The original repair data is evaluated for credibility, and credible repair data with a credibility level higher than a preset threshold is selected. The trusted repair data is then fused and updated with the holographic data asset to obtain the enhanced data asset of the hydropower project.

[0011] To achieve the above objectives, the present invention also provides the following technical solution: a BIM-based digital asset transfer method for hydropower projects, comprising the following steps: Heterogeneous data aggregation is performed on the BIM model, GIS geographic information, IoT sensor data and engineering documents of the hydropower project to obtain the holographic data asset of the hydropower project; Based on the hydropower project asset classification system, the holographic data assets are mapped throughout their entire lifecycle from design to construction to operation and maintenance, resulting in the asset mapping matrix of the hydropower project. The integrity, consistency, and accuracy of the data in the asset mapping matrix are evaluated from multiple dimensions to obtain a data quality assessment report for the hydropower project. Based on the data quality assessment report and operation and maintenance requirements, the handover strategy of the hydropower project is dynamically optimized to obtain the optimal handover strategy of the hydropower project. Based on the optimal handover strategy, the defective data in the holographic data asset is precisely repaired to obtain the enhanced data asset of the hydropower project.

[0012] Compared with the prior art, the beneficial effects of the present invention are: This invention constructs an automated pipeline that integrates data aggregation, correlation mapping, quality assessment, strategy optimization, and precise repair. Its core advantages are: through knowledge graph-driven semantic association, it integrates multi-source heterogeneous data such as BIM, GIS, IoT, and documents into organic "holographic data assets," breaking down information silos; based on a mapping rule base, it achieves standardized integration and lifecycle management of design, construction, and operation and maintenance data, forming a traceable asset mapping matrix; it innovatively introduces quantitative quality diagnosis and multi-objective strategy optimization algorithms, which can dynamically generate optimal repair strategies that balance cost, time, and quality based on objective assessment results and operation and maintenance business needs; and finally, through a credibility assessment mechanism, it conducts targeted collection and fusion updates of defective data, forming a complete system from data integration and quality control to intelligent optimization closed loop, systematically ensuring the high quality, high availability, and business fit of digital handover results. Attached Figure Description

[0013] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of module connections according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the connection steps in an embodiment of the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] Please see Figure 1This invention provides a BIM-based digital asset transfer system for hydropower projects, which includes a multi-source data fusion module, an asset mapping module, a quality diagnosis module, a strategy optimization module, and a targeted repair module. The multi-source data fusion module is connected to the asset mapping module, the asset mapping module is connected to the quality diagnosis module, the quality diagnosis module is connected to the strategy optimization module, and the strategy optimization module is connected to the targeted repair module. The multi-source data fusion module is used to aggregate heterogeneous data from the hydropower project's BIM model, GIS geographic information, IoT sensor data, and engineering documents to obtain the hydropower project's holographic data assets. Furthermore, the specific execution method of the multi-source data fusion module is as follows: Semantic features are extracted from the BIM model of the hydropower project to obtain the structured geometric data of the hydropower project; Spatial topology analysis is performed on the GIS geographic information to obtain the geospatial data of the hydropower project; The IoT sensor data is subjected to time-series feature extraction and outlier filtering to obtain the equipment operation data of the hydropower project. Key information is identified and relationships are constructed from the engineering documents to obtain unstructured document data of the hydropower project; Based on knowledge graph technology, semantic association is performed on the structured geometric data, the geospatial data, the equipment operation data, and the unstructured document data to obtain the holographic data asset of the hydropower project.

[0017] BIM models are not simply 3D graphics. Their corresponding internal components (such as dam bodies, generator casings, and pressure steel pipes) have been assigned semantic information such as classification codes, material properties, and functional parameters according to industry standards (such as IFC). This step directly reads and extracts this predefined semantic information by parsing the internal data structure of the BIM file. For example, the system identifies a 3D entity as a hydro-generator unit (coded) and extracts its geometric dimensions (length, width, height, volume), material (model), and design performance parameters (rated power, speed). The extracted results are organized into a structured data table with components as basic units and attached attribute lists, forming structured geometric data. This ensures that the physical and functional attributes of the asset are preserved in a machine-readable manner from the design phase.

[0018] GIS data provides information such as the location, topography, and watershed of the project in the real geographic coordinate system. The core of this step is to analyze spatial relationships. The system obtains the absolute coordinates (latitude, longitude, and elevation) of hydraulic structures (such as power plants and dams) and analyzes their relative topological relationships. For example, the system uses latitude and longitude data to determine that the entrance point A of the water diversion tunnel and the surge tank point B are spatially connected; the power plant C is located on the bank of the river channel D. These topological relationships, such as connections and locations, together with the coordinate data of the hydraulic structures themselves, constitute geospatial data.

[0019] IoT sensors generate readings arranged in chronological order (time-series data), such as vibration, temperature, pressure, and flow. Time-series feature extraction refers to calculating characteristic values ​​that characterize the device's operating status from these continuous raw readings. For example, for a vibration signal within one minute, its peak value and dominant frequency are extracted; for temperature data within a day, its daily average, maximum value, and fluctuation range are calculated. Outlier filtering is based on engineering common sense or historical normal data ranges (thresholds) to automatically remove obviously erroneous readings (such as extreme values ​​exceeding the range caused by momentary sensor malfunctions). After this step, the messy raw signals are transformed into clean, representative equipment operating data that directly reflects the device's health and operating condition.

[0020] Design drawings, construction logs, acceptance reports, equipment manuals, and other documents are unstructured documents containing a mixture of text, images, and tables. Key information identification utilizes keyword matching, layout analysis, and simple natural language processing techniques to locate and extract core information from these documents. For example, from a "Hydrogen Turbine Factory Test Report," key fields such as equipment number, test date, and efficiency can be identified and extracted. Relationship building involves establishing two types of links for the extracted information: first, links to specific assets (e.g., binding the equipment number in this report to the corresponding turbine generator component ID in the BIM model); second, links to relevant events or data (e.g., establishing a time association between the test date in this report and the operational data collected by IoT sensors on that day). Through this step, fragmented document content is transformed into unstructured document data with clear asset ownership and contextual relationships.

[0021] Knowledge graphs are a technology that uses graphs to represent and store knowledge. In this step, the system treats the data obtained in the first four steps as entities (e.g., No. 1 turbine, No. 7 dam section, vibration data on October 26, 2023, turbine factory test report) and relationships (e.g., belonging to, located at, collected at… time, recorded at). The system automatically or semi-automatically constructs these entities and relationships, ultimately forming a vast, interconnected network—a holographic data asset. For example, in this graph, it can be clearly seen that: No. 1 turbine (BIM entity) is located within the main plant (GIS entity), its vibration characteristic value on October 26, 2023 (IoT entity) is normal, the relevant factory test report (document entity) concludes as qualified, and the report was issued by XX manufacturing plant (external entity). This solves the data silo problem, making asset data an organic whole.

[0022] The asset mapping module is used to perform full lifecycle mapping of the holographic data assets based on the hydropower project asset classification system, from design to construction to operation and maintenance, to obtain the asset mapping matrix of the hydropower project. Furthermore, the specific execution method of the asset mapping module is as follows: A classification system for hydropower engineering assets is established, which includes four major categories: hydraulic structures, electromechanical equipment, metal structure equipment, and auxiliary facilities. For each of the four categories, establish a mapping rule base between design parameters, construction records, and operation and maintenance requirements; Based on the mapping rule base, the design phase data in the holographic data asset is extended to the construction phase to obtain construction enhancement data. Based on the mapping rule base, the construction enhancement data is adapted to the operation and maintenance requirements to obtain operation and maintenance ready data; The operation and maintenance ready data is associated and integrated with the mapping rule base to form the asset mapping matrix of the hydropower project.

[0023] Based on known hydropower industry standards, the system pre-defines a tree-like classification structure. For example, the root directory is hydropower engineering assets, and the first-level subcategories are hydraulic structures (dams, water diversion systems, etc.), electromechanical equipment (turbines, generators, transformers, etc.), etc. Each asset in the system must belong to a specific category within this system, which is the foundation for all subsequent mapping, querying, and management.

[0024] For each type of asset, the system pre-defines a set of rules that clearly specify the parameters of concern during the design phase (such as design head), the information that needs to be recorded and verified during the construction phase (such as the actual pump model installed and concrete pouring records), and the information that needs to be monitored and used during the operation and maintenance phase (such as recommended maintenance cycles and bearing temperature measurement points that need to be monitored in real time). For example, for the main transformer, the rule base defines that the rated capacity of the design parameter should be mapped to the nameplate capacity in the delivery acceptance form of the construction record, and further linked to the calculation basis of the load rate monitoring alarm threshold for operation and maintenance needs.

[0025] The system scans holographic data assets, primarily from the design phase (such as BIM design model attributes). Based on the rule base, it automatically reserves or links fields that should be filled in the construction phase for these data. For example, if there is a gate component in the BIM, the rule base indicates that the actual number of anti-corrosion coating layers and the installation quality images of the sealing strip need to be recorded during the construction phase. The system then creates these two fields in the gate's data structure and attempts to automatically fill them from the integrated construction logs, acceptance images, and other document data. If they are not found, they are marked as to be supplemented. This process generates construction augmentation data, which contains richer dimensions of construction period information than the original design data.

[0026] Based on the operational requirements defined in the rule base, the system performs format conversion, unit unification, redundancy removal, and key information highlighting on the construction enhancement data. For example, a part on a design drawing may be identified by part number A-007, while the procurement of maintenance spare parts requires the use of manufacturer spare part code P-8877. The rule base defines this mapping relationship, and the system automatically replaces it accordingly. At the same time, the system reorganizes the data according to the data templates commonly used in the operation and maintenance system (such as asset cards and equipment ledgers) to ensure that the generated data meets the direct import requirements of the operation and maintenance system in terms of content, format, and granularity, i.e., operation and maintenance ready data.

[0027] An asset mapping matrix is ​​a structured data table or relational model. Its rows are specific asset instances (such as Unit 1), and its columns are key attribute fields that span the entire lifecycle of design, construction, and operation and maintenance. Each cell stores the operation and maintenance readiness value of the asset in that field and associates it with its data source (which BIM attribute, which construction record) and the mapping rules applied.

[0028] It should be noted that the O&M readiness value is a rule-driven numerical conversion and standardization. For example, for the "generator rated power" attribute, the original BIM model might store it as "550000000W" (watts). During the handover of O&M, this power value needs to be converted to "megawatts (MW)" and retained to two decimal places. The system automatically performs the calculation and formatting: 550,000,000 W / 1,000,000 = 550.00 MW. Therefore, the O&M readiness value written to the corresponding cell in the asset mapping matrix is ​​"550.00MW".

[0029] The quality diagnosis module is used to conduct multi-dimensional assessments of the data integrity, consistency, and accuracy in the asset mapping matrix, and to obtain a data quality assessment report for the hydropower project.

[0030] Furthermore, the specific execution method of the quality diagnosis module is as follows: Missing information is detected in the key asset information of the asset mapping matrix to obtain the integrity index of the key asset information. Conflict analysis is performed on the cross-system data in the asset mapping matrix to obtain the consistency index of the cross-system data; The accuracy of the spatial geometric data in the asset mapping matrix is ​​verified to obtain the accuracy index of the spatial geometric data; Based on the handover standards for hydropower projects, the integrity index, consistency index, and accuracy index are weighted and calculated to obtain the comprehensive quality score of the hydropower project. Based on the comparison results between the comprehensive quality score and the preset threshold, a data quality assessment report for the hydropower project is generated.

[0031] Based on a predefined list of key asset information (such as the factory serial number of major equipment and the concrete strength grade of important structures), the system traverses each asset record in the asset mapping matrix, checks whether each key field required in the list has a valid value (not empty, not marked as to be supplemented), counts the number and proportion of missing fields, and calculates a quantitative completeness index (e.g., 0-100 points) by combining the importance weight of the fields.

[0032] The system automatically performs cross-validation. For example, it checks the rated oil pressure of the same speed governor. The BIM design parameters show 6.3 MPa, the equipment manufacturer's certificate shows 6.5 MPa, and the commissioning report shows 6.4 MPa. The system will identify this numerical conflict. Similarly, it checks spatial consistency, such as whether the installation location of a pipeline valve (from the construction survey record) is near the connection point of its corresponding pipeline in the BIM model. By comparing the descriptions of the same fact from different data sources, the system counts the number and severity of conflicts, quantifies the number and severity of conflicts, and calculates a consistency index.

[0033] The accuracy of the two main aspects is verified: Absolute accuracy: The asset coordinates after BIM / GIS integration are compared with the coordinates of high-precision as-built survey control points to calculate the positional deviation.

[0034] Relative accuracy: Check the rationality of the spatial relationship between assets. For example, check whether the outlet of the tailrace pipe is indeed geometrically connected to the inlet of the tailrace channel and the dimensions match. Compare the deviation value with the allowable tolerance range of the project to calculate the accuracy index.

[0035] The system has a pre-set transfer quality standard for goods, which assigns different weights to three indicators: integrity, consistency, and accuracy. The system combines the three sub-indicators into a comprehensive quality score according to a weighted calculation formula.

[0036] The system compares the calculated overall quality score with a preset pass threshold (e.g., 80 points). If the score is greater than the pass threshold, the system automatically generates a structured data quality assessment report. This report includes consistency indicators, completeness indicators, accuracy indicators, and an overall quality score, as well as a list of all detected issues. For example, missing data detection found that the model field of the #3 main transformer cooler was empty; conflict analysis found that the wall thickness data of the #1 pressure steel pipe was inconsistent between the drawings and the material book.

[0037] The strategy optimization module is used to dynamically optimize the handover strategy of the hydropower project based on the data quality assessment report and operation and maintenance requirements characteristics, so as to obtain the optimal handover strategy of the hydropower project. Furthermore, the specific execution method of the strategy optimization module is as follows: By analyzing the problem distribution in the data quality assessment report, a set of data quality shortcomings is obtained; Obtain the business needs characteristics of the hydropower project operation and maintenance department, including equipment monitoring needs, maintenance needs, and safety management needs; Based on the data quality bottleneck set and the business requirement characteristics, an objective function for optimizing the handover strategy is constructed: F(S) = λ1·Q(S) + λ2·C(S) + λ3·T(S), where F(S) is the comprehensive score of the handover strategy S, λ1, λ2, and λ3 are weight coefficients, Q(S) is the data quality item, C(S) is the cost item, and T(S) is the time item. The handover strategy corresponding to the highest comprehensive score is selected as the optimal handover strategy.

[0038] The system categorizes quality assessment reports by problem type (missing, conflicting, insufficient accuracy), asset category (mechanical and electrical, metal and structural), and severity level. For example, metal and structural equipment asset documents are severely missing, and mechanical and electrical equipment parameter conflicts are concentrated. The severity level is obtained by matching the comprehensive quality score with the comprehensive quality score range corresponding to the preset severity level.

[0039] The business needs characteristics of the hydropower project operation and maintenance department are obtained. These business needs characteristics include equipment monitoring needs, maintenance needs, and safety management needs. The equipment monitoring needs, maintenance needs, and safety management needs correspond to different weights of quality, cost, and time. Here, S represents a specific handover strategy, which defines which data to repair first, to what extent to repair it, and what methods to use for repair (such as automatic data entry, manual verification, and on-site retesting). Q(S) represents the expected improvement in data quality (predicted overall quality score) after implementing the strategy. C(S) represents the estimated cost (human resources, outsourcing, etc.) required to implement the strategy. T(S) represents the estimated time cost required to implement the strategy. λ1, λ2, and λ3 are adjustable weight coefficients.

[0040] The targeted repair module is used to accurately repair the defective data in the holographic data asset based on the optimal handover strategy, so as to obtain the enhanced data asset of the hydropower project. Furthermore, the specific execution method of the targeted repair module is as follows: The repair instructions in the optimal handover strategy are parsed to obtain a list of data items to be repaired; For each item in the list of data items to be repaired, determine its data source channel; Based on the data source channels, incremental data collection is performed on the defective data in the holographic data assets to obtain the original repair data; The original repair data is evaluated for credibility, and credible repair data with a credibility level higher than a preset threshold is selected. The trusted repair data is then fused and updated with the holographic data asset to obtain the enhanced data asset of the hydropower project.

[0041] The optimal handover strategy is internally parsed into a series of specific, executable task instructions. The system transforms these instructions into a clear list of data items to be repaired. Each item in the list specifies in detail: which asset and which attribute has a problem (e.g., #2 water pump, bearing temperature historical data missing from August 1-10, 2023), what standard needs to be met (e.g., need to supplement the daily average), and the suggested repair method (e.g., extract from the SCADA system historical database backup).

[0042] Based on the asset type and the nature of the problem, the system matches the most likely data source for each item to be repaired. For example, missing equipment models are first obtained from the electronic data sheet (EDD) provided by the equipment supplier; secondly, paper packing slips are scanned for OCR recognition; and finally, the on-site engineer is contacted for confirmation.

[0043] For sources that can be accessed automatically (such as databases and EDD files), queries and extractions are performed directly. For sources that require manual intervention (such as scanning of paper documents and on-site inquiries), work orders are generated and pushed to relevant personnel. Newly collected data used to fill defects is called raw repair data.

[0044] The system performs automated evaluation using a multi-source data confidence assessment model: Source authority: Different sources are pre-classified (e.g., original equipment manufacturer data > third-party test reports > construction team records) and given different base scores; Time freshness: The closer the time of data generation or collection is to the present, the higher its freshness score; Consistency verification: The new data is compared with the existing, verified related data (for example, the newly added motor power value should be compared with the value marked on the electrical schematic diagram and the value in the contract technical parameter table of the same motor). The higher the consistency, the higher the score. The system performs a weighted summation of the scores from these three dimensions, Cdata = W1*Sa + W2*Sf + W3*Sc, to obtain the overall credibility Cdata. Only data with Cdata higher than a preset threshold (such as 0.8) is adopted as credible repair data.

[0045] The system will select reliable repair data and update the original holographic data asset knowledge graph. For example, in the missing position of the vibration test report, a vibration test report will be added to obtain the enhanced data asset after the knowledge graph is updated.

[0046] To achieve the above objectives, the present invention also provides the following technical solution: a BIM-based digital asset transfer method for hydropower projects, comprising the following steps: Heterogeneous data aggregation is performed on the BIM model, GIS geographic information, IoT sensor data and engineering documents of the hydropower project to obtain the holographic data asset of the hydropower project; Based on the hydropower project asset classification system, the holographic data assets are mapped throughout their entire lifecycle from design to construction to operation and maintenance, resulting in the asset mapping matrix of the hydropower project. The integrity, consistency, and accuracy of the data in the asset mapping matrix are evaluated from multiple dimensions to obtain a data quality assessment report for the hydropower project. Based on the data quality assessment report and operation and maintenance requirements, the handover strategy of the hydropower project is dynamically optimized to obtain the optimal handover strategy of the hydropower project. Based on the optimal handover strategy, the defective data in the holographic data asset is precisely repaired to obtain the enhanced data asset of the hydropower project.

[0047] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A BIM-based digital asset transfer system for hydropower projects, characterized in that: include: Multi-source data fusion module: used to aggregate heterogeneous data from hydropower project BIM model, GIS geographic information, IoT sensor data and engineering documents to obtain holographic data assets of the hydropower project; Asset mapping module: Based on the hydropower project asset classification system, it performs full lifecycle mapping of the holographic data assets from design to construction to operation and maintenance, and obtains the asset mapping matrix of the hydropower project; Quality Diagnosis Module: Used to conduct multi-dimensional assessments of the data integrity, consistency, and accuracy in the asset mapping matrix, and to obtain a data quality assessment report for the hydropower project; Strategy optimization module: Based on the data quality assessment report and operation and maintenance requirements, it dynamically optimizes the handover strategy of the hydropower project to obtain the optimal handover strategy of the hydropower project; Targeted Repair Module: Based on the optimal handover strategy, this module is used to accurately repair defective data in the holographic data asset to obtain the enhanced data asset of the hydropower project.

2. The BIM-based digital asset transfer system for hydropower projects according to claim 1, characterized in that: The specific execution method of the multi-source data fusion module is as follows: Semantic features are extracted from the BIM model of the hydropower project to obtain the structured geometric data of the hydropower project; Spatial topology analysis is performed on the GIS geographic information to obtain the geospatial data of the hydropower project; The IoT sensor data is subjected to time-series feature extraction and outlier filtering to obtain the equipment operation data of the hydropower project. Key information is identified and relationships are constructed from the engineering documents to obtain unstructured document data of the hydropower project; Based on knowledge graph technology, semantic association is performed on the structured geometric data, the geospatial data, the equipment operation data, and the unstructured document data to obtain the holographic data asset of the hydropower project.

3. The BIM-based digital asset transfer system for hydropower projects according to claim 1, characterized in that: The specific execution method of the asset mapping module is as follows: Construct a classification system for hydropower engineering assets, which includes four major categories: hydraulic structures, electromechanical equipment, metal structure equipment, and auxiliary facilities. For each of the four categories, establish a mapping rule base between design parameters, construction records, and operation and maintenance requirements; Based on the mapping rule base, the design phase data in the holographic data asset is extended to the construction phase to obtain construction enhancement data; Based on the mapping rule base, the construction enhancement data is adapted to the operation and maintenance requirements to obtain operation and maintenance ready data; The operation and maintenance ready data is associated and integrated with the mapping rule base to form the asset mapping matrix of the hydropower project.

4. The BIM-based digital asset transfer system for hydropower projects according to claim 1, characterized in that: The specific execution method of the quality diagnosis module is as follows: Missing information is detected in the key asset information of the asset mapping matrix to obtain the integrity index of the key asset information. Conflict analysis is performed on the cross-system data in the asset mapping matrix to obtain the consistency index of the cross-system data; The accuracy of the spatial geometric data in the asset mapping matrix is ​​verified to obtain the accuracy index of the spatial geometric data; Based on the handover standards for hydropower projects, the integrity index, consistency index, and accuracy index are weighted and calculated to obtain the comprehensive quality score of the hydropower project. Based on the comparison between the comprehensive quality score and the preset threshold, a data quality assessment report for the hydropower project is generated.

5. A BIM-based digital asset transfer system for hydropower projects according to claim 1, characterized in that: The specific execution method of the strategy optimization module is as follows: By analyzing the problem distribution in the data quality assessment report, a set of data quality shortcomings is obtained; Obtain the business needs characteristics of the hydropower project operation and maintenance department, including equipment monitoring needs, maintenance needs, and safety management needs; Based on the data quality bottleneck set and the business requirement characteristics, an objective function for optimizing the handover strategy is constructed: F(S) = λ1·Q(S) + λ2·C(S) + λ3·T(S), where F(S) is the comprehensive score of the handover strategy S, λ1, λ2, and λ3 are weight coefficients, Q(S) is the data quality item, C(S) is the cost item, and T(S) is the time item. The handover strategy corresponding to the highest comprehensive score is selected as the optimal handover strategy.

6. A BIM-based digital asset transfer system for hydropower projects according to claim 1, characterized in that: The specific execution method of the targeted repair module is as follows: The repair instructions in the optimal handover strategy are parsed to obtain a list of data items to be repaired; For each item in the list of data items to be repaired, determine its data source channel; Based on the data source channels, incremental data collection is performed on the defective data in the holographic data assets to obtain the original repair data; The original repair data is evaluated for credibility, and credible repair data with a credibility level higher than a preset threshold is selected. The trusted repair data is then fused and updated with the holographic data asset to obtain the enhanced data asset of the hydropower project.

7. A BIM-based digital asset transfer system for hydropower projects according to claim 6, characterized in that: The specific execution method of the targeted repair module is as follows: A multi-source data confidence assessment model is constructed, which includes three dimensions: source authority, time freshness, and consistency verification. The source of the original repair data is evaluated for its authority, resulting in a source authority score. The difference between the acquisition time of the original repaired data and the current time is calculated to obtain a time freshness score; The original repair data is compared with the surrounding related data to obtain a consistency verification score. Based on the source authority score, the time freshness score, and the consistency verification score, the overall credibility of the original repair data is calculated. Cdata = W1·Sa + W2·Sf + w3·Sc, where Cdata is the overall credibility, WI, W2, and W3 are the weight coefficients of the corresponding source authority score, time freshness score, and time freshness score, respectively, Sa is the source authority score, Sf is the time freshness score, and Sc is the consistency verification score. The original repair data with an overall credibility Cdata higher than the preset threshold is recorded as credible repair data.

8. A BIM-based digital asset transfer method for hydropower projects, applied to the BIM-based digital asset transfer system for hydropower projects as described in any one of claims 1-7, characterized in that: include: Heterogeneous data aggregation is performed on the BIM model, GIS geographic information, IoT sensor data and engineering documents of the hydropower project to obtain the holographic data asset of the hydropower project; Based on the hydropower project asset classification system, the holographic data assets are mapped throughout their entire lifecycle from design to construction to operation and maintenance, resulting in the asset mapping matrix of the hydropower project. The integrity, consistency, and accuracy of the data in the asset mapping matrix are evaluated from multiple dimensions to obtain a data quality assessment report for the hydropower project. Based on the data quality assessment report and operation and maintenance requirements, the handover strategy of the hydropower project is dynamically optimized to obtain the optimal handover strategy of the hydropower project. Based on the optimal handover strategy, the defective data in the holographic data asset is precisely repaired to obtain the enhanced data asset of the hydropower project.

Images