A three-dimensional digital twin driven wind farm full life cycle visual operation system
By combining 3D digital twin models with blockchain technology, the problems of data isolation and high security risks in wind farm management systems have been solved, realizing closed-loop data management and virtual-real interaction throughout the entire lifecycle, thereby improving the operational efficiency and security of wind farms.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-26
- Publication Date
- 2026-06-23
AI Technical Summary
Existing wind farm management systems suffer from isolated data, inability to achieve dynamic flow and closed-loop management, inability to achieve real-time mapping between physical and virtual models, lack of fault chain reaction simulation and early warning capabilities, low decommissioning and dismantling efficiency and high safety risks, easy tampering of data evidence and difficulty in tracing responsibility, and are unable to meet the needs of high-quality development in the wind power industry.
By integrating multi-source heterogeneous data with a 3D digital twin model, a 1:1 high-precision virtual model is constructed to realize dynamic data flow and closed-loop management throughout the entire lifecycle. Combined with the linkage module of the entire lifecycle stage, the visualization operation interaction module, the intelligent adaptation and driving module, and the security and responsibility traceability module, it supports virtual and real interactive operation and rapid problem location. Blockchain technology is used to realize data storage and hierarchical permission management.
It has achieved closed-loop data management throughout the entire life cycle of wind farms, improved operational efficiency, reduced economic losses and safety risks, ensured the resource utilization of decommissioned equipment, and adapted to the management and control needs of wind farms of different types and sizes.
Smart Images
Figure CN122264984A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of wind farm management, specifically to a three-dimensional digital twin-driven visualization operation system for the entire lifecycle of a wind farm. Background Technology
[0002] Wind power generation has become a core component, and the scale and layout of wind farm construction continue to expand. Refined and intelligent management throughout the entire life cycle has become a core requirement for the industry's development. Wind farm operation covers four core stages, each generating heterogeneous data from multiple sources, including equipment, environment, geography, and the electricity market. The management requirements for different types of wind farms, such as those in mountainous or offshore areas, differ significantly. Furthermore, the need for resource utilization and improved dismantling efficiency after the decommissioning of wind power equipment is becoming increasingly urgent, placing higher demands on data interoperability and stage-by-stage coordination across the entire chain.
[0003] Existing wind farm management systems have significant technical shortcomings. Most systems focus only on a single operational phase, creating isolated information silos that prevent dynamic data flow and closed-loop management throughout the entire lifecycle. Furthermore, data transmission lacks prioritization, leading to delays in core decision-making data. The absence of a 1:1 high-precision 3D digital twin model hinders real-time mapping between physical and virtual models, making multi-scenario simulation and prediction, as well as virtual-physical interactive operations, limiting the accuracy of control and decision-making efficiency.
[0004] Traditional management systems also suffer from numerous operational pain points. Fault prediction only targets single components and lacks the ability to simulate and warn of fault chain reactions, which can easily lead to systemic equipment problems. The decommissioning and dismantling process lacks advance rehearsals and tool compatibility verification procedures, making on-site operations prone to problems such as tool incompatibility and unreasonable paths, resulting in low dismantling efficiency and high safety risks. In addition, data storage uses traditional methods, which are easily tampered with and make it difficult to achieve reverse accountability. When problems occur, it is impossible to quickly identify the responsible party, which cannot meet the high-quality development needs of the wind power industry. Summary of the Invention
[0005] Based on this, the purpose of this invention is to provide a three-dimensional digital twin-driven wind farm full life cycle visualization operation system to solve the technical problems of isolated data at each stage and inability to achieve dynamic flow and closed-loop management in general wind farm management systems.
[0006] To achieve the above objectives, the present invention provides the following technical solution: a three-dimensional digital twin-driven wind farm full lifecycle visualization operation system, comprising:
[0007] The three-dimensional digital twin model construction module is used to integrate multi-source heterogeneous data to construct a 1:1 high-precision virtual model of a wind farm. The multi-source heterogeneous data includes equipment life cycle parameters, environmental perception data, electricity market data, geospatial data, decommissioning and dismantling interface parameters reserved in the design stage, and equipment recyclable marking data recorded in the construction stage.
[0008] The full life cycle stage linkage module covers four core stages of wind farm design and planning, construction, operation and maintenance, and decommissioning. It enables dynamic data flow at each stage and allows for advance matching of decommissioning needs during the design stage and synchronous recording of relevant recycling information during the construction stage.
[0009] The visualization and interactive module enables real-time mapping between the physical wind farm and the virtual model, multi-scenario simulation and prediction, and supports virtual-real interactive operation and rapid problem location based on the three-dimensional digital twin model.
[0010] The intelligent adaptation and driving module, through a real-time data synchronization mechanism, AI intelligent optimization algorithm, and wind farm type self-learning adaptation function, enables dynamic adjustment and precise control of the entire life cycle of wind farms under different scenarios.
[0011] The security and accountability module uses blockchain technology to achieve full lifecycle data storage, sets up a hierarchical permission management mechanism, and supports reverse tracing of abnormal operations.
[0012] In the above technical solution, five modules work together to achieve full life-cycle management and control of wind farms, build a 1:1 high-precision virtual model, connect the four-stage data flow, realize virtual-real mapping and intelligent adaptation, and ensure data security and accountability through blockchain notarization and hierarchical permissions, thus solving the pain points of traditional management information silos.
[0013] The multi-source heterogeneous data also includes dynamically assigned tags based on data priority, specifically:
[0014] The system automatically identifies the current stage of the wind farm's entire life cycle and assigns dynamic priorities to various types of data. In the design and planning stage, terrain data and decommissioning and dismantling interface parameters are given the highest priority. In the construction stage, installation accuracy data and equipment recyclability markings are given the highest priority. In the operation and maintenance scheduling stage, equipment operating status data and electricity price data in the electricity market are given the highest priority. In the decommissioning and disposal stage, recycling price data and dismantling path data are given the highest priority.
[0015] During data transmission and processing, the real-time performance of the highest priority data is guaranteed, while low priority data is transmitted in batches using compression to reduce network load while ensuring that core decision-making data is transmitted without delay.
[0016] In the above technical solution, data priorities are dynamically allocated according to the wind power scenario to ensure the real-time nature of core decision-making data. Low-priority data is compressed and transmitted in batches, which reduces network load and ensures zero latency for core data, thereby improving data processing and transmission efficiency.
[0017] The 3D digital twin model construction module includes a BIM submodule, a GIS submodule, a decommissioning and dismantling pre-simulation submodule, and a real-time calibration submodule. The decommissioning and dismantling pre-simulation submodule also has a virtual adaptation function for dismantling tools, specifically:
[0018] Import the 3D model and operating parameters of mainstream dismantling equipment, including tool size, load-bearing capacity, and operating radius;
[0019] During the pre-disassembly process, the compatibility between the imported disassembly equipment and the wind farm equipment components is automatically verified. If there are compatibility issues such as tools being unable to reach the parts or insufficient load-bearing capacity, the disassembly sequence is automatically adjusted or alternative disassembly equipment is recommended. The compatibility conflict locations are highlighted in the three-dimensional digital twin model.
[0020] Simultaneously, the GIS submodule is linked to update the feasibility of the recycling transportation channel for the adapted dismantling equipment.
[0021] In the above technical solution, a twin model is constructed using multiple sub-modules. The virtual adaptation of the disassembly tool can automatically verify compatibility, adjust the disassembly order, highlight conflicting locations, and link with GIS to verify accessibility, thereby avoiding disassembly problems in advance and improving the accuracy of decommissioning and disassembly rehearsals.
[0022] The operation and maintenance scheduling phase of the full lifecycle stage linkage module also includes a dynamic scheduling function for maintenance resources, specifically:
[0023] By combining AI fault prediction results, real-time location data of maintenance personnel, tool inventory status data, and traffic data, the optimal maintenance dispatch plan can be automatically generated.
[0024] If multiple devices are at risk of failure at the same time, they are sorted according to the urgency of the failure, maintenance cost, and the impact on power generation, and resources are prioritized to handle high-priority maintenance tasks.
[0025] During maintenance, maintenance progress data is synchronized to the three-dimensional digital twin model in real time. If maintenance delay occurs, power generation scheduling adjustments are automatically triggered to reduce economic losses.
[0026] In the above technical solution, dynamic scheduling of maintenance resources can automatically generate the optimal dispatch plan, sort faults by weight, synchronize maintenance progress and dynamically adjust power generation scheduling, and minimize the economic and power generation losses caused by maintenance delays.
[0027] The visualization and interactive module includes a spatial visualization layer, a temporal visualization layer, a performance visualization layer, and a virtual-real interaction layer. The virtual-real interaction layer also features a virtual rollback function for operational errors, specifically:
[0028] When performing equipment start-up, shutdown, and parameter adjustment operations on a three-dimensional digital twin model, the system first simulates the operation results and displays the possible impacts of the operation, including changes in power generation and fluctuations in equipment load.
[0029] If the simulation results pose a safety risk or economic loss, a one-click rollback operation is supported, and the equipment in the physical wind farm will not execute the erroneous instruction.
[0030] All virtual operation records are automatically synchronized to the security and accountability module.
[0031] In the above technical solution, the four-layer visualization architecture realizes deep interaction between the virtual and real worlds. The virtual rollback of operation errors can first simulate the impact of the operation, and the risk scenario can be rolled back with one click. The physical device does not execute the wrong instructions, and the virtual operation record is stored as evidence, thus avoiding operational safety and economic risks.
[0032] The intelligent adaptation driving module includes a data synchronization unit, an AI optimization unit, and a type self-learning adaptation unit. The type self-learning adaptation unit also has the function of transferring experience across different types of wind farms, specifically:
[0033] Automatically extract operational data characteristics and optimization decision-making experience from different types of wind farms to build an experience knowledge base. The wind farm types include mountain wind farms, offshore wind farms, and plain wind farms.
[0034] When a new wind farm of a certain type is connected, in addition to automatically adjusting the parameters of the AI intelligent optimization algorithm, successful cases of similar scenarios are matched from the experience knowledge base to assist in optimization decision-making. The assistance in optimization decision-making includes transferring the anti-corrosion maintenance experience of offshore wind farms to high-humidity mountain wind farms.
[0035] The operation data of newly added wind farms are synchronously and reversely updated to the experience knowledge base, enabling continuous iteration of self-learning capabilities.
[0036] In the above technical solution, multiple units achieve intelligent adaptation, cross-type experience transfer can build an experience knowledge base, new electric fields match similar cases and iterative algorithms, data reverse updates the knowledge base, realize self-learning iteration, and adapt to the management and control needs of different types of wind farms.
[0037] The AI fault prediction algorithm also has a fault chain reaction simulation function, specifically:
[0038] Based on the mechanical structure and electrical connections of wind farm equipment, a fault propagation model is constructed.
[0039] When a single component malfunction is detected, the fault propagation model automatically simulates the chain of problems that the malfunction may cause. These chain of problems include gearbox failure leading to generator overload and blade damage affecting wind speed capture efficiency.
[0040] The performance visualization layer displays the fault propagation path in the form of a dynamic flowchart, provides early warning of cascading risk points, and coordinates with the dynamic scheduling function of maintenance resources to prioritize the protection of critical propagation nodes.
[0041] In the above technical solution, fault chain reaction simulation can construct a fault propagation model, predict the chain problem of single-point anomaly, visualize the propagation path, warn of risk points and coordinate resource scheduling, protect critical nodes in advance, and prevent the fault from escalating.
[0042] The decommissioning and disposal phase of the full life-cycle linkage module also includes a material traceability and secondary utilization matching module. This module also has dynamic assessment and negotiation assistance functions for recycling value, specifically:
[0043] Based on data on equipment material composition, real-time market price, and equipment wear and tear recorded using blockchain technology, the benchmark value for recycling retired equipment can be calculated in real time.
[0044] Automatically capture transaction prices in the secondary market for similar equipment and the price range of recycling companies, and generate price comparison charts;
[0045] It provides recommendations for the lowest acceptable price and the optimal negotiation strategy for recycling negotiations, while also identifying key parameters that affect recycling value, including metal purity and component integrity.
[0046] In the above technical solution, the material traceability and secondary utilization module can dynamically assess the recycling value, capture market prices to generate comparison charts, provide negotiation floor prices and strategies, mark key influencing parameters, and help maximize the residual value of decommissioned equipment and improve the efficiency of recycling negotiations.
[0047] The safety and accountability traceability module also has an emergency permission temporary upgrade function, specifically:
[0048] In the event of extreme weather or sudden equipment failure, authorized personnel may apply for temporary escalation of operating privileges, which include adjusting key operating parameters and initiating emergency shutdown procedures.
[0049] Permission application information is automatically synchronized to multi-level approval nodes, supporting rapid approval on mobile devices. At the same time, blockchain technology records permission upgrade time, applicant information, and operation content in real time.
[0050] Once the emergency is resolved, the operating permissions are automatically restored to their original level, and all temporary operation records are archived separately for easy traceability and auditing later.
[0051] In the above technical solution, the emergency permission temporary upgrade supports rapid application and mobile approval in emergency situations. The entire operation is recorded by blockchain. Permissions are automatically restored after the emergency is resolved, and the operation is archived separately, balancing emergency response efficiency and accountability.
[0052] The visual operation interaction module also supports one-click report generation, which also has cross-stage problem correlation analysis capabilities, specifically:
[0053] Automatically identify related issues at different stages of the entire life cycle, including the relationship between dismantling difficulties in the decommissioning stage and unreasonable interface reservations in the design and planning stage, as well as installation deviations in the construction stage;
[0054] The generated summary report displays the problem propagation path in the form of a correlation graph and quantifies the impact weight of the problem at each stage;
[0055] Based on the correlation analysis results, cross-stage optimization suggestions are automatically generated. These suggestions include adjusting interface standards in the design and planning stage and standardizing installation processes in the construction stage, forming a continuous improvement loop throughout the entire lifecycle.
[0056] In the above technical solution, one-click report generation can analyze cross-stage issues, the graph shows the problem transmission path and quantifies the weight, automatically generates optimization suggestions, forms a closed loop of continuous improvement throughout the entire life cycle, and promotes the iterative improvement of wind farm management level.
[0057] In summary, the present invention has the following main advantages: The three-dimensional digital twin-driven wind farm full life cycle visualization operation system provided by the present invention effectively solves the pain points of traditional wind farm management, such as information silos and inaccurate control. The system integrates multi-source heterogeneous data to construct a 1:1 high-precision twin model, realizes dynamic allocation of data priorities, breaks down data barriers in the four stages of design, construction, operation and maintenance, and decommissioning, and forms a closed loop of data and stage linkage throughout the entire life cycle. Relying on the visualization interaction module, it completes real-time mapping between virtual and real, multi-scenario simulation, and virtual rollback of operational errors. Combined with the intelligent adaptation driving module, it realizes AI optimization and cross-type... This system facilitates the transfer of wind farm experience, adapts to different management and control needs, leverages blockchain technology for end-to-end data storage, and employs tiered access control to ensure dynamic adjustment of emergency permissions and accountability. It also features fault cascading warnings, intelligent scheduling of maintenance resources, pre-decommissioning and dismantling simulations, dynamic assessment of recycling value, and cross-stage problem correlation analysis. This enables visualized, intelligent, and precise management and control of the entire wind farm lifecycle, forming a continuous improvement loop that significantly enhances operational efficiency, reduces economic losses and safety risks, ensures the resource utilization of decommissioned equipment, and allows for industrial-scale promotion of the technical solution, adapting to the management and control needs of wind farms of different types and sizes. Attached Figure Description
[0058] Figure 1 This is a flowchart of the system modules of the present invention. Detailed Implementation
[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.
[0060] The embodiments of the present invention will now be described.
[0061] A three-dimensional digital twin-driven wind farm full life cycle visualization operation system, as shown in the figure, includes a three-dimensional digital twin model construction module, which is used to integrate multi-source heterogeneous data to construct a 1:1 high-precision virtual model of the wind farm, realizing accurate mapping between the physical wind farm and the virtual wind farm.
[0062] The multi-source heterogeneous data includes:
[0063] Equipment lifecycle parameters, including design parameters, factory parameters, operating parameters, and loss parameters for equipment such as fans, towers, transformer substations, and cables;
[0064] Environmental perception data, including wind speed, wind direction, temperature, humidity, altitude, geological data, and disaster early warning data;
[0065] Electricity market data, including real-time electricity prices, trading rules, grid connection requirements, and power generation indicators;
[0066] Geospatial data, including topography, site boundaries, transportation routes, and pipeline network layout;
[0067] The decomposition interface parameters reserved during the design phase include the disassembly lifting points, splitting interfaces, and reserved dimensions for disassembly and assembly space.
[0068] Equipment recyclability tagging data recorded during the construction phase, including recyclable component identification, material type, and recycling priority tagging.
[0069] The three-dimensional digital twin model construction module further includes a BIM sub-module, a GIS sub-module, a decommissioning and dismantling pre-simulation sub-module, and a real-time calibration sub-module.
[0070] The decommissioning and dismantling pre-rehearsal submodule has a virtual adaptation function for dismantling tools, specifically implemented as follows:
[0071] Import the 3D model and operating parameters of mainstream dismantling equipment. The operating parameters include tool dimensions, rated load capacity, operating radius, and rotation range.
[0072] When rehearsing the disassembly process of the whole machine or components in a virtual environment, the system automatically verifies the compatibility of the imported disassembly equipment with the wind farm equipment components. If there are compatibility issues such as tools being unable to reach, insufficient load-bearing capacity, or interference with the work space, the system automatically optimizes and adjusts the disassembly sequence or recommends alternative disassembly equipment to the operators. The system also marks the compatibility conflict locations in the three-dimensional digital twin model with highlighted color marks and warning boxes.
[0073] The GIS submodule is synchronized and linked to verify the feasibility of dismantling equipment and transport vehicles after adaptation, taking into account the site's road width, load-bearing capacity, turning radius, and height restrictions, and the dismantling and transport routes are updated synchronously.
[0074] This system features a full lifecycle phase linkage module, covering four core phases: wind farm design and planning, construction, operation and maintenance, and decommissioning. This enables real-time data exchange and dynamic flow across all phases, forming a closed-loop data chain from design to decommissioning.
[0075] During the design and planning phase, the requirements for decommissioning, dismantling, and recycling should be embedded in advance, and standardized dismantling interfaces and recyclable marking rules should be reserved.
[0076] During the construction phase, data such as equipment installation accuracy, component material, and recyclability are collected and entered simultaneously to provide basic data for subsequent decommissioning and disposal.
[0077] During the operation and maintenance scheduling phase, real-time data on operation, maintenance, and faults are collected to optimize design and construction standards.
[0078] During the decommissioning and disposal phase, dismantling, recycling, and residual value assessment are completed based on full lifecycle data, forming a closed-loop data system for each phase.
[0079] The full lifecycle stage linkage module also includes a dynamic scheduling function for maintenance resources during the operation and maintenance scheduling phase, specifically:
[0080] The system integrates AI fault prediction results, real-time location data of maintenance personnel, inventory status data of maintenance tools and spare parts, and on-site traffic data. Through path optimization and task allocation algorithms, it automatically generates the optimal maintenance dispatch plan.
[0081] When multiple devices simultaneously issue fault warnings or experience faults, a comprehensive ranking model is established based on the urgency of the fault, maintenance costs, and the impact on power generation. Priority is given to dispatching manpower, tools, and spare parts resources to handle high-priority maintenance tasks.
[0082] During maintenance, data such as maintenance progress, replaced parts, and causes of failures are synchronized to the three-dimensional digital twin model in real time. If maintenance delays occur due to personnel delays or lack of spare parts, the system will automatically trigger power generation scheduling adjustment strategies to reduce power generation losses and economic losses.
[0083] The full life-cycle stage linkage module also includes a material traceability and secondary utilization matching module in the decommissioning and disposal stage, and has dynamic assessment and negotiation assistance functions for recycling value:
[0084] Based on blockchain-based evidence of equipment material composition, service life, wear and tear, and maintenance records, combined with real-time price data from the second-hand market for scrap metal and parts, the benchmark value for recycling retired equipment and components can be calculated in real time.
[0085] The system automatically captures secondary market transaction prices of similar decommissioned equipment and official price ranges from multiple recycling companies, generating price comparison trend charts;
[0086] It provides optimal negotiation suggestions for recycling negotiations, such as the lowest acceptable floor price and a phased disposal strategy, while marking key parameters that affect recycling value, such as metal purity, core component integrity rate, and remanufacturability rate.
[0087] This system includes a visual operation and interaction module, which realizes real-time data mapping between physical wind farms and virtual models based on a 3D digital twin model, multi-scenario simulation and prediction, and supports virtual-real linkage operation, rapid location of equipment and fault points, scene roaming and indicator query.
[0088] The visualization and interactive module includes a spatial visualization layer, a temporal visualization layer, a performance visualization layer, and a virtual-real interaction layer.
[0089] Spatial visualization layer: Displays the three-dimensional layout of the wind farm, equipment locations, and site environment;
[0090] Time visualization layer: supports full lifecycle historical backtracking, real-time monitoring, and future trend prediction;
[0091] Performance visualization layer: Displays core performance indicators such as power generation, load, efficiency, and failure probability;
[0092] Virtual-Real Interaction Layer: Supports direct execution of simulation operations such as control, debugging, maintenance, and disassembly on the virtual model, which are then synchronously mapped to the physical system after confirmation.
[0093] The virtual-real interaction layer has a virtual rollback function for operational errors, specifically:
[0094] Before performing operations such as equipment start-up and shutdown, parameter adjustment, and mode switching on the three-dimensional digital twin model, the system first performs virtual simulation and outputs the predicted results of changes in power generation, equipment load fluctuations, grid impact, and safety risks after the operation.
[0095] If the simulation results indicate equipment safety risks, a significant reduction in power generation, or economic losses, the system allows operators to roll back the virtual operation with a single click. The corresponding equipment in the physical wind farm will not receive or execute the erroneous instruction.
[0096] All virtual operations, simulation results, and rollback records are automatically synchronized to the security and accountability module, forming a triple protection mechanism of simulation, confirmation, and execution.
[0097] The visual operation interaction module also supports one-click report generation and has cross-stage problem correlation analysis capabilities:
[0098] The system automatically identifies and associates transitive problems at different stages of the entire life cycle. For example, difficulties in dismantling and low recycling efficiency during the decommissioning and disposal stage are directly related to unreasonable dismantling interface reservations during the design and planning stage and installation accuracy deviations during the construction stage.
[0099] The generated operation and maintenance reports, decommissioning assessment reports, and rectification reports will display the problem propagation path in the form of a correlation graph, and quantify the impact weight of problems at each stage of design, construction, operation and maintenance, and decommissioning.
[0100] Based on the correlation analysis results, cross-stage optimization suggestions are automatically generated, such as adjusting the interface standards in the design stage, standardizing the installation accuracy in the construction stage, and optimizing the maintenance strategy in the operation and maintenance stage, forming a closed loop of continuous improvement throughout the entire life cycle.
[0101] This system includes an intelligent adaptation and driving module, which uses a real-time data synchronization mechanism, AI intelligent optimization algorithm, and wind farm type self-learning adaptation function to achieve dynamic adjustment and precise control of the entire life cycle process of wind farms of different terrains, sizes, and types.
[0102] The intelligent adaptation driver module specifically includes a data synchronization unit, an AI optimization unit, and a type self-learning adaptation unit.
[0103] Among them, the type self-learning adaptation unit has the function of cross-type wind farm experience transfer, which is implemented as follows:
[0104] The system automatically extracts operational data characteristics, fault patterns, maintenance strategies, and optimization decision-making experience from different types of wind farms, such as mountain wind farms, offshore wind farms, and plain wind farms, and builds a standardized wind farm experience knowledge base.
[0105] When a new wind farm of a certain type is connected, the system automatically identifies the site type and operation characteristics, adaptively adjusts the weight and parameters of the AI intelligent optimization algorithm, and matches successful cases of similar scenarios from the experience knowledge base to realize experience transfer and reuse.
[0106] The actual operation data, optimization effects, and fault records of newly added wind farms are synchronously updated to the experience knowledge base, enabling continuous iteration of self-learning capabilities.
[0107] This system includes a safety and accountability traceability module, which uses blockchain technology to immutably store data on the design, construction, operation and maintenance, and decommissioning of wind farms throughout their entire lifecycle. It also sets up a hierarchical access control mechanism, with different roles having different viewing, operation, and management permissions. Furthermore, it supports reverse tracing of abnormal operations, fault causes, and responsible parties.
[0108] The safety and accountability traceability module also has an emergency permission temporary upgrade function, specifically implemented as follows:
[0109] In the event of emergencies such as typhoons, rainstorms, extreme temperatures, sudden equipment failures, or fires, authorized management personnel may apply for temporary enhancement of operating privileges. The scope of privileges includes adjusting key operating parameters, initiating group control emergency shutdown, switching power supply modes, and performing emergency evacuation operations.
[0110] Permission application information is automatically pushed to multi-level approval nodes, supporting fast approval on PC and mobile devices. The blockchain synchronously records the permission upgrade time, applicant, approver, operation content, and operation time.
[0111] Once the emergency is resolved, the system automatically restores the operating permissions to their original level, and all temporary permission operation records are archived and stored separately for subsequent auditing, accountability tracing, and incident analysis.
[0112] In this system, the multi-source heterogeneous data is also configured with dynamic data priority assignment labels, specifically implemented as follows:
[0113] The system automatically identifies the current stage of the wind farm's life cycle and assigns corresponding dynamic priorities to different types of data, prioritizing the real-time performance of core data.
[0114] In the data transmission and processing stage, priority is given to ensuring low-latency and high-real-time transmission and processing of the highest priority data; low priority data is compressed in batches and uploaded on a timed basis to reduce network bandwidth load and system computing power consumption.
[0115] This system utilizes AI fault prediction algorithms to simulate fault chain reactions.
[0116] Based on the mechanical structure connection relationships, electrical topology relationships, and control logic relationships of wind farm equipment, a fault propagation model at the equipment, component, and part levels is constructed.
[0117] When the system detects an anomaly in a single component or an early warning of a fault, it automatically simulates the chain of faults that the anomaly may trigger through a fault propagation model.
[0118] The performance visualization layer displays the fault propagation path and risk level in the form of dynamic flowcharts and topology diagrams, provides early warning of key points of cascading risks, and links with the dynamic scheduling function of maintenance resources to prioritize the scheduling of resources to protect and deal with key nodes of fault propagation, thereby preventing the fault from escalating.
[0119] This embodiment uses a 50MW coastal mountain wind farm as the application object, with a total of 25 2MW doubly-fed wind turbine generators. The site is located in a coastal mountainous terrain with high humidity and high salt fog. The wind farm's full life cycle visualization operation system driven by the three-dimensional digital twin described in this invention is used to complete the closed-loop management of the entire life cycle from design and planning, construction, operation and maintenance scheduling, and decommissioning. The collaborative operation process of each module of the system is as follows:
[0120] I. Operation during the design and planning phase
[0121] 3D digital twin model construction
[0122] The system integrates terrain data, geological data, and wind turbine design parameters through BIM and GIS sub-modules to build a 1:1 high-precision 3D virtual model of the wind farm; the decommissioning and dismantling pre-simulation sub-module imports the dismantling parameters of blades, gearboxes, and towers in advance, reserves standardized dismantling lifting points and dismantling space interfaces, and synchronously enters the decommissioning and dismantling interface parameters.
[0123] Data priority is dynamically allocated.
[0124] The system recognizes that it is currently in the design and planning stage, and automatically sets the terrain data and decommissioning interface parameters as the highest priority to ensure that the design modeling data is processed without delay, while other auxiliary data is transmitted in batches.
[0125] Full life cycle pre-planning
[0126] The full life cycle linkage module embeds decommissioning and recycling requirements during the design phase, marking the types of recyclable components and material composition for each wind turbine, forming basic data for "designing for decommissioning".
[0127] II. Operation during the construction phase
[0128] Construction data synchronous entry
[0129] Construction workers can use mobile devices to upload data on wind turbine installation accuracy, tower docking deviation, and equipment recyclability markings to the system in real time, and the data is synchronized to the three-dimensional digital twin model.
[0130] Disassembly tool virtual adaptation verification
[0131] The decommissioning and dismantling pre-simulation submodule imports 3D models of dismantling equipment such as a 350t truck crane and blade-specific clamps, automatically verifies the lifting operation radius and load-bearing adaptability, discovers blind spots in the original design site, automatically adjusts the dismantling site and lifting sequence, and links with the GIS submodule to verify the access conditions of the construction road, outputting the optimal construction and decommissioning compatible solution.
[0132] Data Priority Adjustment
[0133] The system switches to the construction phase data priority, setting installation accuracy data and equipment recyclability tag data as the highest priority to ensure real-time synchronization of key construction data.
[0134] III. Operation and Maintenance Scheduling Phase
[0135] Intelligent adaptation and experience transfer
[0136] The intelligent adaptation and driving module identifies this site as a coastal mountain wind farm, transfers experience in high salt spray corrosion prevention and maintenance of offshore wind farms from the experience knowledge base, and automatically adjusts the AI optimization algorithm parameters to optimize the corrosion prevention and maintenance strategies for towers and electrical cabinets.
[0137] AI Fault Prediction and Chain Reaction Simulation
[0138] The system detected an abnormal rise in the oil temperature of the #12 wind turbine gearbox. It simulated the chain risk of gearbox failure → generator overload → power grid fluctuation through a fault propagation model, and dynamically displayed the fault propagation path in the performance visualization layer to provide early warning of key risk nodes.
[0139] Maintain dynamic resource scheduling
[0140] The system automatically generates the optimal dispatch plan by combining the location of maintenance personnel, spare parts inventory, and traffic conditions; due to the high weight of the power generation impact of the #12 wind turbine failure, maintenance resources are prioritized for disposal, and the maintenance progress is synchronized to the 3D model in real time.
[0141] Visual interaction and virtual rollback operation
[0142] The maintenance personnel attempted to adjust the operating parameters of wind turbine #12 on the virtual model. The system first simulated the operation results and predicted the risk of equipment overload. The maintenance personnel rolled back the virtual operation with one click. The physical wind turbine did not execute the instruction, and all simulation records were synchronized to the blockchain for evidence storage.
[0143] Emergency privileges temporarily upgraded
[0144] When a typhoon is issued as an extreme weather warning, the site manager applies for an emergency upgrade of permissions, which is quickly approved via mobile device, and the emergency shutdown procedure for all wind turbines on site is initiated. The entire process of the permission upgrade is recorded by blockchain, including the time and content of the operation. The permissions are automatically restored after the typhoon is over.
[0145] Data priority switching
[0146] During the operation and maintenance phase, equipment operating status data and real-time electricity price data are given the highest priority to ensure zero delay in power generation scheduling and fault monitoring data.
[0147] IV. Operation during the Decommissioning and Disposal Phase
[0148] Full process rehearsal of decommissioning and dismantling
[0149] The system calls upon the disassembly interfaces and recyclable marking data retained during the design and construction phases, and uses a 3D model to fully simulate the disassembly process of the entire machine, automatically matching the optimal disassembly equipment and transportation route.
[0150] Dynamic assessment of recycling value and negotiation assistance
[0151] The safety and responsibility traceability module uses blockchain to retrieve material and loss data throughout the equipment's lifecycle, combines it with real-time recycling market prices, automatically calculates the benchmark value for recycling decommissioned wind turbines, generates a comparison chart of quotations from multiple recycling companies, and provides a negotiation floor price and disposal strategy.
[0152] Data Priority Adjustment
[0153] During the decommissioning phase, recycling price data and dismantling route data will be given the highest priority to ensure efficient operation of residual value assessment and dismantling scheduling.
[0154] V. Cross-stage report generation and closed-loop optimization
[0155] The system automatically correlates and analyzes the data through a one-click report generation function: the low efficiency of dismantling and retiring some wind turbines at this site is due to installation deviations during the construction phase and insufficient precision of interface reservations during the design phase.
[0156] The system uses a correlation graph to show the problem propagation path, quantifies the impact weight of each stage, and outputs optimization suggestions: improve the accuracy of subsequent project design interfaces, standardize construction and installation error control, and form a closed loop of continuous improvement throughout the entire life cycle.
[0157] This comprehensive embodiment fully verifies all the core functions of the system, including full lifecycle data closed loop, 3D twin visualization, AI intelligent adaptation, blockchain traceability, fault chain early warning, virtual operation rollback, and decommissioning value assessment. The technical solution can be stably implemented and industrially promoted.
[0158] Although embodiments of the present invention have been shown and described, these specific embodiments are merely explanations of the invention and are not intended to limit it. The specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. After reading this specification, those skilled in the art may make modifications, substitutions, and variations to the embodiments as needed without departing from the principles and spirit of the invention, but such modifications, substitutions, and variations are protected by patent law as long as they are within the scope of the claims of the present invention.
Claims
1. A three-dimensional digital twin-driven wind farm full lifecycle visualization operation system, characterized in that, include: The three-dimensional digital twin model construction module is used to integrate multi-source heterogeneous data to construct a 1:1 high-precision virtual model of a wind farm. The multi-source heterogeneous data includes equipment life cycle parameters, environmental perception data, electricity market data, geospatial data, decommissioning and dismantling interface parameters reserved in the design stage, and equipment recyclable marking data recorded in the construction stage. The full life cycle stage linkage module covers four core stages of wind farm design and planning, construction, operation and maintenance, and decommissioning. It enables dynamic data flow at each stage and allows for advance matching of decommissioning needs during the design stage and synchronous recording of relevant recycling information during the construction stage. The visualization and interactive module enables real-time mapping between the physical wind farm and the virtual model, multi-scenario simulation and prediction, and supports virtual-real interactive operation and rapid problem location based on the three-dimensional digital twin model. The intelligent adaptation and driving module, through a real-time data synchronization mechanism, AI intelligent optimization algorithm, and wind farm type self-learning adaptation function, enables dynamic adjustment and precise control of the entire life cycle of wind farms under different scenarios. The security and accountability module uses blockchain technology to achieve full lifecycle data storage, sets up a hierarchical permission management mechanism, and supports reverse tracing of abnormal operations.
2. The three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 1, characterized in that: The multi-source heterogeneous data also includes dynamically assigned tags based on data priority, specifically: The system automatically identifies the current stage of the wind farm's entire life cycle and assigns dynamic priorities to various types of data. In the design and planning stage, terrain data and decommissioning and dismantling interface parameters are given the highest priority. In the construction stage, installation accuracy data and equipment recyclability markings are given the highest priority. In the operation and maintenance scheduling stage, equipment operating status data and electricity price data in the electricity market are given the highest priority. In the decommissioning and disposal stage, recycling price data and dismantling path data are given the highest priority. During data transmission and processing, the real-time performance of the highest priority data is guaranteed, while low priority data is transmitted in batches using compression to reduce network load while ensuring that core decision-making data is transmitted without delay.
3. The three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 1, characterized in that: The 3D digital twin model construction module includes a BIM submodule, a GIS submodule, a decommissioning and dismantling pre-simulation submodule, and a real-time calibration submodule. The decommissioning and dismantling pre-simulation submodule also has a virtual adaptation function for dismantling tools, specifically: Import the 3D model and operating parameters of mainstream dismantling equipment, including tool size, load-bearing capacity, and operating radius; During the pre-disassembly process, the compatibility between the imported disassembly equipment and the wind farm equipment components is automatically verified. If there are compatibility issues such as tools being unable to reach the parts or insufficient load-bearing capacity, the disassembly sequence is automatically adjusted or alternative disassembly equipment is recommended. The compatibility conflict locations are highlighted in the three-dimensional digital twin model. Simultaneously, the GIS submodule is linked to update the feasibility of the recycling transportation channel for the adapted dismantling equipment.
4. The three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 1, characterized in that: The operation and maintenance scheduling phase of the full lifecycle stage linkage module also includes a dynamic scheduling function for maintenance resources, specifically: By combining AI fault prediction results, real-time location data of maintenance personnel, tool inventory status data, and traffic data, the optimal maintenance dispatch plan can be automatically generated. If multiple devices are at risk of failure at the same time, they are sorted according to the urgency of the failure, maintenance cost, and the impact on power generation, and resources are prioritized to handle high-priority maintenance tasks. During maintenance, maintenance progress data is synchronized to the three-dimensional digital twin model in real time. If maintenance delay occurs, power generation scheduling adjustments are automatically triggered to reduce economic losses.
5. The three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 1, characterized in that: The visualization and interactive module includes a spatial visualization layer, a temporal visualization layer, a performance visualization layer, and a virtual-real interaction layer. The virtual-real interaction layer also features a virtual rollback function for operational errors, specifically: When performing equipment start-up, shutdown, and parameter adjustment operations on a three-dimensional digital twin model, the system first simulates the operation results and displays the possible impacts of the operation, including changes in power generation and fluctuations in equipment load. If the simulation results pose a safety risk or economic loss, a one-click rollback operation is supported, and the equipment in the physical wind farm will not execute the erroneous instruction. All virtual operation records are automatically synchronized to the security and accountability module.
6. The three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 1, characterized in that: The intelligent adaptation driving module includes a data synchronization unit, an AI optimization unit, and a type self-learning adaptation unit. The type self-learning adaptation unit also has the function of transferring experience across different types of wind farms, specifically: Automatically extract operational data characteristics and optimization decision-making experience from different types of wind farms to build an experience knowledge base. The wind farm types include mountain wind farms, offshore wind farms, and plain wind farms. When a new wind farm of a certain type is connected, in addition to automatically adjusting the parameters of the AI intelligent optimization algorithm, successful cases of similar scenarios are matched from the experience knowledge base to assist in optimization decision-making. The assistance in optimization decision-making includes transferring the anti-corrosion maintenance experience of offshore wind farms to high-humidity mountain wind farms. The operation data of newly added wind farms are synchronously and reversely updated to the experience knowledge base, enabling continuous iteration of self-learning capabilities.
7. The three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 4, characterized in that: The AI fault prediction algorithm also has a fault chain reaction simulation function, specifically: Based on the mechanical structure and electrical connections of wind farm equipment, a fault propagation model is constructed. When a single component malfunction is detected, the fault propagation model automatically simulates the chain of problems that the malfunction may cause. These chain of problems include gearbox failure leading to generator overload and blade damage affecting wind speed capture efficiency. The performance visualization layer displays the fault propagation path in the form of a dynamic flowchart, provides early warning of cascading risk points, and coordinates with the dynamic scheduling function of maintenance resources to prioritize the protection of critical propagation nodes.
8. The three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 1, characterized in that: The decommissioning and disposal phase of the full life-cycle linkage module also includes a material traceability and secondary utilization matching module. This module also has dynamic assessment and negotiation assistance functions for recycling value, specifically: Based on data on equipment material composition, real-time market price, and equipment wear and tear recorded using blockchain technology, the benchmark value for recycling retired equipment can be calculated in real time. Automatically capture transaction prices in the secondary market for similar equipment and the price range of recycling companies, and generate price comparison charts; It provides recommendations for the lowest acceptable price and the optimal negotiation strategy for recycling negotiations, while also identifying key parameters that affect recycling value, including metal purity and component integrity.
9. The three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 1, characterized in that: The safety and accountability traceability module also has an emergency permission temporary upgrade function, specifically: In the event of extreme weather or sudden equipment failure, authorized personnel may apply for temporary escalation of operating privileges, which include adjusting key operating parameters and initiating emergency shutdown procedures. Permission application information is automatically synchronized to multi-level approval nodes, supporting rapid approval on mobile devices. At the same time, blockchain technology records permission upgrade time, applicant information, and operation content in real time. Once the emergency is resolved, the operating permissions are automatically restored to their original level, and all temporary operation records are archived separately for easy traceability and auditing later.
10. A three-dimensional digital twin-driven wind farm full life-cycle visualization operation system according to claim 5, characterized in that: The visual operation interaction module also supports one-click report generation, which also has cross-stage problem correlation analysis capabilities, specifically: Automatically identify related issues at different stages of the entire life cycle, including the relationship between dismantling difficulties in the decommissioning stage and unreasonable interface reservations in the design and planning stage, as well as installation deviations in the construction stage; The generated summary report displays the problem propagation path in the form of a correlation graph and quantifies the impact weight of the problem at each stage; Based on the correlation analysis results, cross-stage optimization suggestions are automatically generated. These suggestions include adjusting interface standards in the design and planning stage and standardizing installation processes in the construction stage, forming a continuous improvement loop throughout the entire lifecycle.