Wind power plant three-dimensional modeling data visualization analysis method and related device

Through three-dimensional modeling and computational fluid dynamics simulation, combined with machine learning and reinforcement learning, the problem of insufficient data management and analysis capabilities of wind farms is solved, efficient data management and intelligent operation and maintenance of wind farms are realized, and power generation efficiency is improved. Unit life.

CN119066976APending Publication Date: 2024-12-03PENGLAI WIND POWER BRANCH OF HUANENG SHANDONG POWER GENERATION CO LTD +1
View PDF 0 Cites 5 Cited by

Patent Information

Application Number
CN202411202876.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the construction, operation and maintenance management of wind farms, there are problems such as dispersed data sources, extensive management methods, insufficient analysis capabilities, lack of three-dimensional expression and intelligent decision-making methods, the degree of data visualization is not high, and data security and mutual trust need to be improved.

Method used

Using three-dimensional modeling technology to build a terrain model of the wind farm, simulating the wind flow field through calculation fluid dynamics, combining machine learning and reinforcement learning algorithms, generate three-dimensional visual scenes of the wind farm, predict power generation and health status, optimize operation strategies, and use The drone obtains high-precision terrain data, the OPC UA communication protocol ensures real-time data transmission, and edge computing devices perform local pre-processing.

Benefits of technology

It realizes efficient data acquisition and management of wind farms, improves data quality and timeliness, enhances spatial positioning capabilities, optimizes power generation efficiency and unit life, provides accurate fault warning and maintenance plans, and improves the intelligence of wind farms. Operation and maintenance level.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066976A_ABST
    Figure CN119066976A_ABST
Patent Text Reader

Abstract

The invention discloses a wind power plant three-dimensional modeling data visualization analysis method and a related device. The method comprises the following steps: acquiring geographic information data and meteorological data of a wind power plant; constructing a three-dimensional terrain model of the wind power plant by using the obtained geographic information data; acquiring operation state data of the wind turbine generator, performing parametric modeling on the wind turbine generator by using the acquired operation state data, and simulating a wind flow field of the wind power plant through a computational fluid dynamics method in combination with the meteorological data to obtain a wind flow field simulation result; generating a three-dimensional visual scene of the wind power plant based on the three-dimensional terrain model and the wind flow field simulation result; and analyzing the acquired operation state data, predicting the generating capacity and the health state of the wind turbine generator, and generating an operation strategy. According to the method, the refinement, automation and intelligence level of full-life-cycle management of the wind power plant is improved, cost reduction and efficiency improvement are achieved, and the method has important value for high-quality development of the wind power industry.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation project management, and in particular relates to a wind farm three-dimensional modeling data visualization analysis method and related devices. Background Art

[0002] As a clean and renewable form of energy, wind power plays an increasingly important role in global energy transformation and climate change response. With the continuous advancement of wind power technology and the continuous decline in costs, the global wind power industry has developed rapidly. As the core carrier for the development and utilization of wind energy resources, wind farms have continued to expand in scale and increase in number. In order to achieve efficient construction, intelligent operation and maintenance, and refined management of wind farms, digitalization and informatization of wind farms have become an inevitable trend.

[0003] At present, the construction, operation and maintenance management of wind farms mainly adopts traditional methods, and there are widespread problems such as scattered data sources, extensive management methods and insufficient analysis capabilities. Specifically, wind farms involve multi-source heterogeneous data such as geography, meteorology, and unit status. Traditional data collection methods are difficult to achieve real-time, accurate and comprehensive data; secondly, the planning and design of wind farms mainly rely on two-dimensional plane drawings, lacking three-dimensional stereoscopic expression of the whole scene, and poor intuitiveness and spatial positioning capabilities; thirdly, in terms of wind turbine modeling and performance simulation, most of them use simplified data models and statistical methods, which are difficult to accurately depict the complex structure and nonlinear characteristics of wind turbines. The production and operation management of wind farms mainly relies on manual experience, and lacks intelligent analysis and decision-making methods in power generation prediction and unit fault diagnosis. Finally, the visualization level of wind farm management is not high, mostly based on two-dimensional interfaces, and the immersion and interactivity need to be strengthened. At the same time, there is a lack of a unified and standardized data sharing mechanism between wind farms, and data security and mutual trust need to be improved. Summary of the invention

[0004] In order to solve one of the above technical defects, the present invention provides a wind farm three-dimensional modeling data visualization analysis method and related devices. In order to achieve the above purpose, the present invention adopts the following technical solutions to achieve it:

[0005] In a first aspect, a method for visualizing and analyzing three-dimensional modeling data of a wind farm is provided, comprising:

[0006] Obtain geographic information data and meteorological data of wind farms;

[0007] Using the acquired geographic information data, construct a three-dimensional terrain model of the wind farm;

[0008] Acquire the operating status data of the wind turbine generator set, perform parameterized modeling on the wind turbine generator set using the acquired operating status data, and simulate the wind flow field of the wind farm by a computational fluid dynamics method in combination with the meteorological data to obtain a wind flow field simulation result;

[0009] Generate a three-dimensional visualization scene of the wind farm based on the three-dimensional terrain model and the wind flow field simulation results;

[0010] The acquired operating status data is analyzed to predict the power generation and health status of the wind turbine generator set and generate an operating strategy.

[0011] Furthermore, the acquisition of geographic information data and meteorological data of the wind farm specifically includes:

[0012] Use drones equipped with high-resolution cameras and lidar to take aerial photos and scan wind farms to obtain high-precision terrain images and point cloud data;

[0013] The acquired terrain image and point cloud data are registered, filtered and segmented to generate a digital terrain model and a digital surface model of the wind farm.

[0014] Furthermore, the obtaining of wind turbine operating status data specifically includes:

[0015] By connecting with the SCADA system of the wind turbine, the power, speed, blade pitch angle and nacelle yaw angle operating parameters of the wind turbine are collected in real time using the OPC UA communication protocol, and the data is stored in a time series database;

[0016] By deploying vibration and oil condition monitoring sensors on wind turbines, data reflecting the health status of wind turbines can be obtained and pre-processed locally through edge computing devices.

[0017] Furthermore, the step of performing parameterized modeling on the wind turbine generator set includes:

[0018] According to the design parameters of the wind turbine, three-dimensional geometric modeling is performed on the tower, nacelle, blades and key components of the pitch system of the wind turbine;

[0019] The material properties and motion characteristics of the tower, nacelle, blades and pitch system components of the wind turbine are parametrically defined to construct a multi-body dynamics model of the wind turbine;

[0020] The multi-body dynamics model of the wind turbine generator set is associated with its corresponding geographical coordinates to form an overall three-dimensional model of the wind farm.

[0021] Furthermore, the simulating the wind flow field of the wind farm by means of computational fluid dynamics method specifically includes:

[0022] Obtaining meteorological data of the area where the wind farm is located, including wind speed, wind direction, temperature and air pressure, etc., using computational fluid dynamics software to perform three-dimensional modeling of the wind farm, and setting boundary conditions such as terrain and atmospheric boundary layer;

[0023] The meteorological data are used as initial conditions and driving conditions for simulation, and the Navier-Stokes equations are solved to obtain the flow field information of wind speed, wind direction and turbulence intensity inside and around the wind farm.

[0024] Furthermore, generating a three-dimensional visualization scene of the wind farm based on the three-dimensional terrain model and the wind flow field simulation result specifically includes:

[0025] The wind farm's 3D terrain model, wind turbine model, wind flow field simulation results and other data are integrated to build the overall virtual environment of the wind farm;

[0026] Develop a WebGL-based 3D visualization engine to achieve grid rendering and streaming of large-scale terrain data;

[0027] Perform real-time animation simulation of the operating status of wind turbines, and visualize wind speed, wind direction, etc. based on wind flow field data.

[0028] Furthermore, the acquired operating status data is analyzed to predict the power generation and health status of the wind turbine and generate an operating strategy, which specifically includes:

[0029] The machine learning algorithm is used to train the historical operation data of wind turbines to establish a nonlinear mapping relationship between meteorological parameters such as wind speed and wind direction and the power generation of wind turbines;

[0030] Based on the meteorological forecast data of the wind farm, the machine learning model is used to make a rolling forecast of the power generation of the wind turbines in the future;

[0031] Perform feature extraction and anomaly detection on the vibration, oil quality and other status monitoring data of wind turbines to evaluate the current health status of wind turbines and predict their remaining service life;

[0032] Based on the three-dimensional model of the wind farm and historical operation data, the reinforcement learning algorithm is used to optimize the wind turbine's pitch, frequency, yaw and other control strategies;

[0033] According to the changes in meteorological conditions such as wind speed and wind direction, the coordinated operation mode of each wind turbine is adaptively adjusted to improve the overall power generation efficiency of the wind farm;

[0034] According to the health status prediction results of wind turbines, a predictive maintenance plan is formulated to reasonably arrange the maintenance time and spare parts replacement cycle of wind turbines.

[0035] In a second aspect, a wind farm three-dimensional modeling data visualization analysis system is provided, comprising:

[0036] The data acquisition module is used to integrate the design parameters, operation data and historical fault data of wind turbines and build a knowledge graph in the field of wind turbines;

[0037] Data acquisition module, used to obtain geographic information data and meteorological data of the wind farm, as well as wind turbine operating status data;

[0038] Model building module, used to build a three-dimensional terrain model of the wind farm;

[0039] A scene generation module is used to generate a three-dimensional visualization scene of a wind farm;

[0040] An analysis module, used for analyzing the acquired operation status data;

[0041] Prediction module, used to predict the power generation and health status of wind turbines;

[0042] The operation strategy module is used for predictive maintenance planning and rationally arranges the maintenance time and spare parts replacement cycle of wind turbines.

[0043] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein when the processor executes the computer program, the steps of the wind farm three-dimensional modeling data visualization analysis method as described in any one of the above items are implemented.

[0044] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for visualizing and analyzing three-dimensional modeling data of a wind farm as described in any one of the above items is implemented.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. This method uses three-dimensional modeling technology to construct a three-dimensional terrain model of the wind farm, which can intuitively present the terrain features, machine site layout, wind resource distribution, etc. of the wind farm in a three-dimensional way, provide accurate data support for the optimization of wind farm site selection and micro-site selection, and has strong spatial positioning capabilities, which improves the visual management level of wind farm engineering construction; secondly, by obtaining the operating status data of the wind turbine set, the wind turbine set is parametrically modeled using the acquired operating status data, which improves the digitalization and automation level of wind farm construction and operation and maintenance, and realizes the efficient acquisition and integrated management of all wind farm data, reduces the manual input of data collection and processing, and improves the data quality, timeliness, accuracy and comprehensiveness; finally, the acquired operating status data is analyzed to predict the power generation and health status of the wind turbine set and generate an operating strategy, which overcomes the unfavorable factors such as the strong intermittent and random nature of wind power output, provides new ideas for wind power prediction and power grid dispatching, optimizes the group control of the unit through reinforcement learning, and seeks the best balance between power generation efficiency and unit life.

[0047] 2. By introducing drones to obtain high-precision terrain images and point cloud data, efficient acquisition and fusion management of all wind farm data is achieved, reducing the manual input of data collection and processing, and improving data quality and timeliness. Based on the generated digital terrain model and digital surface model, terrain parameters such as slope, aspect, and roughness can be analyzed to provide a scientific basis for wind farm wind energy resource assessment, wind turbine layout optimization, etc., to achieve automatic identification and measurement of buildings, roads, vegetation, etc. in wind farms, and improve the automation level of wind farm management.

[0048] 3. The OPC UA communication protocol ensures real-time, efficient and secure data transmission, allowing wind farm managers to understand the operating status of wind turbines in real time; vibration and oil status monitoring sensors can capture the health status information of wind turbines in real time. After local pre-processing by edge computing devices, potential faults can be quickly identified and early warnings can be issued, providing maintenance personnel with accurate fault location and cause information, thereby reducing fault downtime.

[0049] 4. Through 3D geometric modeling, the geometric shape and size of each component of the wind turbine can be intuitively displayed, which is convenient for designers to verify and optimize the design, ensure that the design of the wind turbine meets the performance requirements, and reduce design errors and defects. The multi-body dynamics model can simulate the dynamic behavior of the wind turbine in the real environment, including the response of the wind turbine under wind load, the interaction between various components, etc., and can accurately analyze and predict the performance of the wind turbine, providing a scientific basis for the operation and maintenance of the wind farm.

[0050] 5. Through wind farm simulation, the wind speed, wind direction and turbulence intensity distribution inside and around the wind farm can be accurately predicted, providing a scientific basis for the design of the wind farm, helping to optimize the layout of wind turbines and improve the power generation efficiency and economic benefits of the wind farm.

[0051] 6. By integrating multi-dimensional data such as terrain, wind turbines and wind flow fields into the virtual environment, the overall layout and operating status of the wind farm can be intuitively displayed, which is convenient for wind farm managers and decision makers to quickly understand the overall situation of the wind farm and provide support for decision-making. WebGL technology enables efficient rendering of large-scale terrain data on the Web side. Through grid rendering and streaming technology, it can ensure efficient loading and rendering of data while maintaining visual quality.

[0052] 7. By establishing a nonlinear mapping relationship between meteorological parameters such as wind speed and wind direction and the power generation of wind turbines through machine learning algorithms, the power generation of wind turbines in the future can be predicted more accurately, allowing wind farm managers to formulate power generation plans and scheduling strategies in advance and optimize resource allocation; feature extraction and anomaly detection of vibration, oil quality and other status monitoring data of wind turbines can more accurately evaluate the current health status of wind turbines and predict their remaining service life, so as to detect potential faults in time, formulate targeted maintenance plans, reduce failure rates, and extend the service life of wind turbines. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0054] Figure 1 A flow chart of the wind farm three-dimensional modeling data visualization analysis method provided by the present invention;

[0055] Figure 2 This is a schematic diagram of data collection and preprocessing in the wind farm three-dimensional modeling data visualization analysis method provided by the present invention.

[0056] Figure 3 A schematic diagram of three-dimensional modeling and simulation in the three-dimensional modeling data visualization analysis method for a wind farm provided by the present invention;

[0057] Figure 4 A visualization and interaction schematic diagram is provided in the wind farm three-dimensional modeling data visualization analysis method provided by the present invention;

[0058] Figure 5A schematic diagram of data analysis and decision making in the wind farm three-dimensional modeling data visualization analysis method provided by the present invention;

[0059] Figure 6 A schematic diagram of data security and sharing in the wind farm three-dimensional modeling data visualization analysis method provided by the present invention;

[0060] Figure 7 Schematic diagram of the wind farm three-dimensional modeling data visualization analysis system provided by the present invention;

[0061] Figure 8 This is a practical engineering solution diagram for the wind farm three-dimensional modeling data visualization analysis system provided by the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0063] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0065] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0066] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0067] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0068] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0069] The embodiment of the present invention provides a wind farm three-dimensional modeling data visualization analysis method and related devices.

[0070] like Figure 1 As shown, in a first aspect, an embodiment of the present invention provides a method for visualizing and analyzing three-dimensional modeling data of a wind farm, comprising:

[0071] S101. Obtain geographic information data and meteorological data of the wind farm; illustratively, use a drone equipped with a high-resolution camera and a laser radar to take aerial photos and scan the wind farm to obtain high-precision terrain images and point cloud data; the high-resolution camera carried by the drone can be Sony RX1R II, with a resolution of 42 million pixels; the laser radar can be Velodyne VLP-16, with a range of 100m and an accuracy of ±3cm to take aerial photos and scan the wind farm to obtain high-precision images and point cloud data of the wind farm; then align, filter and segment the acquired terrain images and point cloud data to generate a digital terrain model and digital surface model of the wind farm. In the process of obtaining meteorological data, it is necessary to deploy automatic weather stations around the wind farm to obtain measured data of meteorological parameters such as wind speed, wind direction, temperature and air pressure around the wind farm, and obtain numerical forecast data for the area where the wind farm is located in the future from the meteorological department.

[0072] S102: construct a three-dimensional terrain model of the wind farm using the acquired geographic information data; illustratively, Figure 2 As shown in the figure, the acquired geographic information data is preprocessed by cleaning, verification, and spatiotemporal alignment, and stored and managed in a unified data format. Distributed message queues such as Kafka are used to achieve real-time data aggregation and subscription distribution. Finally, the processed geographic information data is used to build a three-dimensional terrain model of the wind farm, as shown in the figure. Figure 3As shown in the figure, the image and point cloud data of the wind farm are imported into 3D modeling software (such as Autodesk InfraWorks, Bentley Context Capture, etc.), and a high-precision 3D terrain model is generated through aerial triangulation, texture mapping and other technologies. The model is simplified and multi-level of detail (LOD) processing is performed to meet the display and calculation requirements in different scenarios.

[0073] S103, obtaining the operating status data of the wind turbine, using the obtained operating status data to perform parametric modeling on the wind turbine, and combining the meteorological data, simulating the wind flow field of the wind farm by computational fluid dynamics method, and obtaining the wind flow field simulation result; illustratively, by docking with the SCADA system of the wind turbine, the power, speed, blade pitch angle and nacelle yaw angle operating parameters of the wind turbine are collected in real time by OPC UA communication protocol, and the data are stored in the time series database; at the same time, by deploying vibration and oil status monitoring sensors on key components of the wind turbine (such as blades, gearboxes and generators), data reflecting the health status of the wind turbine is obtained, and local data preprocessing and feature extraction are performed through edge computing devices (such as NVIDIA Jetson Nano). According to the design parameters of the wind turbine (such as blade length, tower height, rated power, etc.), three-dimensional geometric modeling (such as SolidWorks, CATIA, etc.) is performed on the tower, nacelle, blades and key components of the pitch system of the wind turbine; and the constraints and degrees of freedom between the components are defined through assembly relationships to form a multi-body dynamic model of the wind turbine.

[0074] Assume that the lift L and drag D of the wind turbine blade can be expressed as:

[0075]

[0076] Among them, ρ is air density, V is incoming wind speed, S is the windward area of ​​the blade, C L and C D They are the lift coefficient and drag coefficient respectively, which are related to the blade model and angle of attack.

[0077] Finally, computational fluid dynamics (CFD) software (such as ANSYS Fluent, OpenFOAM, etc.) is used to perform numerical simulation of the wind farm. First, the three-dimensional terrain and wind turbine layout of the wind farm are discretized to generate a grid model suitable for CFD solution; then the calculation parameters such as the atmospheric boundary layer and turbulence model are set, and meteorological data are used as initial and boundary conditions; finally, the unsteady Navier-Stokes equations are solved to obtain flow field information such as wind speed, wind direction, and turbulence intensity inside and around the wind farm.

[0078] Reynolds stress τ in turbulence models ijThe Boussinesq hypothesis is usually adopted, that is:

[0079]

[0080] Among them, μ t is the turbulent viscosity, S ij is the strain rate tensor, k is the turbulent kinetic energy, δ ij is the Kronecker symbol.

[0081] S104, based on the three-dimensional terrain model and the wind flow field simulation results, generate a three-dimensional visualization scene of the wind farm; illustratively, Figure 4 As shown in the figure, a virtual environment of a wind farm is constructed in a game engine (such as Unity 3D, Unreal Engine, etc.), and the three-dimensional terrain model, wind turbine model, wind flow field simulation results and other data of the wind farm are integrated, and then imported into the scene after scaling at a certain ratio, and rendering parameters such as lighting, materials, and special effects are set to construct the overall virtual environment of the wind farm to achieve realistic visual effects. Secondly, a three-dimensional visualization engine based on WebGL is developed to realize grid rendering and streaming of large-scale terrain data, perform real-time animation simulation of the operating status of wind turbines, and visualize wind speed, wind direction, etc. according to wind flow field data. In addition, for large-scale terrain data and dynamic flow field data in the three-dimensional scene of the wind farm, spatial segmentation, frustum culling, multi-level details (LOD) and other technologies are used to optimize the rendering process to improve the display efficiency and smoothness of the scene. At the same time, the parallel computing capability of the GPU is utilized to realize hardware accelerated rendering of terrain, turbines, wind flow fields, etc. through graphics APIs such as OpenGL and DirectX. Finally, the human-computer interaction function of the wind farm 3D visualization system is developed to support multiple interaction methods such as mouse, keyboard and touch screen. Users can control the translation, rotation, zoom and other operations of the perspective through the keyboard and mouse to realize free browsing of the scene; through gesture operations on the touch screen, the selection and query of units, wind flow fields, etc. can be realized; through interface elements such as menus and buttons, switching and control between different functional modules can be realized.

[0082] S105, analyzing the acquired operating status data, predicting the power generation and health status of the wind turbine, and generating an operating strategy; illustratively, Figure 5As shown in the figure, a machine learning algorithm (such as support vector machine SVM, random forest RF and long short-term memory network LSTM, etc.) is used to establish a wind turbine power generation prediction model, and the historical operation data of the wind turbine is trained to establish a nonlinear mapping relationship between meteorological parameters such as wind speed and wind direction and wind turbine power generation; the input features of the model (such as wind speed, wind direction, temperature, air pressure, etc.) are determined by feature selection methods, and grid search, cross-validation and other methods are used to optimize the model's hyperparameters. After the model training is completed, according to the meteorological forecast data of the wind farm, the machine learning model is used to make a rolling forecast of the wind turbine power generation in the future, providing a basis for the optimal scheduling of the wind farm.

[0083] Assume that the relationship between the output power P of the wind turbine generator and the wind speed v is:

[0084]

[0085] Among them, v i 、v r 、v o are the cut-in wind speed, rated wind speed and cut-out wind speed respectively, R is the rotor radius, C p is the wind energy utilization coefficient, P r is the rated power.

[0086] The vibration, oil and other state monitoring data of the wind turbine are subjected to feature extraction and anomaly detection to evaluate the current health status of the wind turbine and predict its remaining service life. Specifically, the SCADA data and state monitoring data of the wind turbine are subjected to feature engineering processing to extract key indicators reflecting the health status of the unit (such as vibration amplitude, spectrum characteristics, oil contamination, etc.). Secondly, unsupervised learning algorithms such as one-class support vector machine (One-Class SVM) and isolation forest (Isolation Forest) are used to perform anomaly detection and fault diagnosis on the health status of the wind turbine, and a prediction model for the remaining service life of the wind turbine is established based on historical maintenance data. Subsequently, based on the three-dimensional model of the wind farm and historical operation data, the control strategies of the wind turbine such as variable pitch, variable frequency, and yaw are optimized using reinforcement learning algorithms. According to the changes in meteorological conditions such as wind speed and wind direction, the coordinated operation mode of each wind turbine is adaptively adjusted to improve the overall power generation efficiency of the wind farm. According to the prediction results of the health status of the wind turbine, a predictive maintenance plan is formulated to reasonably arrange the maintenance time and spare parts replacement cycle of the wind turbine.

[0087] In addition, if Figure 6As shown in the figure, this method also builds a wind farm data sharing platform based on a consortium chain (such as Hyperledger Fabric) to encrypt and store the operation data and wind resource data of wind turbines, and realizes the secure sharing and transaction of data through smart contracts and access control strategies. It uses the characteristics of blockchain such as immutability and traceability to ensure the authenticity and credibility of wind power data flowing between all parties in the industrial chain, and promote the collaborative innovation and development of the wind power industry. Finally, the privacy protection mechanism of Federated Learning is adopted to realize the data fusion calculation between different wind farms without directly sharing the original data. Each wind farm uses its own data to train the machine learning model locally, and exchanges gradient information through encrypted communication protocols, which protects data privacy while improving the generalization performance of the model.

[0088] In the second aspect, a wind farm three-dimensional modeling data visualization analysis system is provided, such as Figure 7 As shown, including:

[0089] The data acquisition module is used to integrate the design parameters, operation data and historical fault data of wind turbines and build a knowledge graph in the field of wind turbines;

[0090] Data acquisition module, used to obtain geographic information data and meteorological data of the wind farm, as well as wind turbine operating status data;

[0091] Model building module, used to build a three-dimensional terrain model of the wind farm;

[0092] A scene generation module is used to generate a three-dimensional visualization scene of a wind farm;

[0093] An analysis module, used for analyzing the acquired operation status data;

[0094] Prediction module, used to predict the power generation and health status of wind turbines;

[0095] The operation strategy module is used for predictive maintenance planning and rationally arranges the maintenance time and spare parts replacement cycle of wind turbines.

[0096] In terms of system software architecture design, such as Figure 8As shown in the figure, the system adopts a software architecture with front-end and back-end separation in specific engineering practice. The front-end uses frameworks such as Vue.js for user interface development, and the back-end uses Spring Boot, Flask, etc. to build RESTful API services. At the same time, containerization technologies such as Docker and Kubernetes are used to achieve rapid deployment and elastic scaling of the system, improving the reliability and scalability of the system. In terms of hardware system integration, IoT devices such as sensors and edge computing nodes are deployed on key equipment such as wind turbines and meteorological towers. Real-time data transmission and remote monitoring are achieved through communication technologies such as industrial Ethernet and 5G. At the same time, network security measures such as virtual private networks (VPNs) and firewalls are used to ensure the confidentiality and integrity of wind farm data transmission.

[0097] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein the processor implements the steps of the wind farm three-dimensional modeling data visualization analysis method as described above when executing the computer program.

[0098] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned wind farm three-dimensional modeling data visualization analysis method is implemented.

[0099] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

[0100] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0104] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A wind farm three-dimensional modeling data visualization analysis method, characterized in that: include: Obtain geographic information data and meteorological data of wind farms; Using the acquired geographic information data, construct a three-dimensional terrain model of the wind farm; Acquire the operating status data of the wind turbine generator set, perform parameterized modeling on the wind turbine generator set using the acquired operating status data, and simulate the wind flow field of the wind farm by a computational fluid dynamics method in combination with the meteorological data to obtain a wind flow field simulation result; Generate a three-dimensional visualization scene of the wind farm based on the three-dimensional terrain model and the wind flow field simulation results; The acquired operating status data is analyzed to predict the power generation and health status of the wind turbine generator set and generate an operating strategy.

2. The visualization analysis method according to claim 1, characterized in that: The acquisition of geographic information data and meteorological data of the wind farm specifically includes: Use drones equipped with high-resolution cameras and lidar to take aerial photos and scan wind farms to obtain high-precision terrain images and point cloud data; The acquired terrain image and point cloud data are registered, filtered and segmented to generate a digital terrain model and a digital surface model of the wind farm.

3. The visualization analysis method according to claim 1, characterized in that: The obtaining of wind turbine operating status data specifically includes: By connecting with the SCADA system of the wind turbine, the power, speed, blade pitch angle and nacelle yaw angle operating parameters of the wind turbine are collected in real time using the OPC UA communication protocol, and the data is stored in a time series database; By deploying vibration and oil condition monitoring sensors on wind turbines, data reflecting the health status of wind turbines can be obtained and pre-processed locally through edge computing devices.

4. The visualization analysis method according to claim 1, characterized in that: The step of performing parameterized modeling on the wind turbine generator set comprises: According to the design parameters of the wind turbine, three-dimensional geometric modeling is performed on the tower, nacelle, blades and key components of the pitch system of the wind turbine; The material properties and motion characteristics of the tower, nacelle, blades and pitch system components of the wind turbine are parametrically defined to construct a multi-body dynamics model of the wind turbine; The multi-body dynamics model of the wind turbine generator set is associated with its corresponding geographical coordinates to form an overall three-dimensional model of the wind farm.

5. The visualization analysis method according to claim 1, characterized in that: The simulation of the wind flow field of the wind farm by the computational fluid dynamics method specifically includes: Obtaining meteorological data of the area where the wind farm is located, including wind speed, wind direction, temperature and air pressure, etc., using computational fluid dynamics software to perform three-dimensional modeling of the wind farm, and setting boundary conditions such as terrain and atmospheric boundary layer; The meteorological data are used as initial conditions and driving conditions for simulation, and the Navier-Stokes equations are solved to obtain the flow field information of wind speed, wind direction and turbulence intensity inside and around the wind farm.

6. The visualization analysis method according to claim 1, characterized in that: The generating of a three-dimensional visualization scene of the wind farm based on the three-dimensional terrain model and the wind flow field simulation result specifically includes: The wind farm's 3D terrain model, wind turbine model, wind flow field simulation results and other data are integrated to build the overall virtual environment of the wind farm; Develop a WebGL-based 3D visualization engine to achieve grid rendering and streaming of large-scale terrain data; Perform real-time animation simulation of the operating status of wind turbines, and visualize wind speed, wind direction, etc. based on wind flow field data.

7. The visualization analysis method according to claim 1, characterized in that: Analyze the acquired operating status data, predict the power generation and health status of the wind turbine, and generate an operating strategy, specifically including: The machine learning algorithm is used to train the historical operation data of wind turbines to establish a nonlinear mapping relationship between meteorological parameters such as wind speed and wind direction and the power generation of wind turbines; Based on the meteorological forecast data of the wind farm, the machine learning model is used to make a rolling forecast of the power generation of the wind turbines in the future; Perform feature extraction and anomaly detection on the vibration, oil quality and other status monitoring data of wind turbines to evaluate the current health status of wind turbines and predict their remaining service life; Based on the three-dimensional model of the wind farm and historical operation data, the reinforcement learning algorithm is used to optimize the wind turbine's pitch, frequency, yaw and other control strategies; According to the changes in meteorological conditions such as wind speed and wind direction, the coordinated operation mode of each wind turbine is adaptively adjusted to improve the overall power generation efficiency of the wind farm; According to the health status prediction results of wind turbines, a predictive maintenance plan is formulated to reasonably arrange the maintenance time and spare parts replacement cycle of wind turbines.

8. A wind farm three-dimensional modeling data visualization analysis system, characterized in that: include: The data acquisition module is used to integrate the design parameters, operation data and historical fault data of wind turbines and build a knowledge graph in the field of wind turbines; Data acquisition module, used to obtain geographic information data and meteorological data of the wind farm, as well as wind turbine operating status data; Model building module, used to build a three-dimensional terrain model of the wind farm; A scene generation module is used to generate a three-dimensional visualization scene of a wind farm; An analysis module, used for analyzing the acquired operation status data; Prediction module, used to predict the power generation and health status of wind turbines; The operation strategy module is used for predictive maintenance planning and rationally arranges the maintenance time and spare parts replacement cycle of wind turbines.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable in the processor, wherein the processor implements the steps of the wind farm three-dimensional modeling data visualization analysis method as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for visualizing and analyzing three-dimensional modeling data of a wind farm according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Supervision method and device for distributed power equipment

    CN120165496A

  • A method and apparatus for monitoring distributed power equipment

    CN120165496B

  • Low-altitude meteorological digital twinborn reconstruction method based on three-dimensional entity data modeling

    CN120930555A

  • Real-time three-dimensional visualization system of wind power plant

    CN121010703A

  • A real-time three-dimensional visualization system for a wind power plant

    CN121010703B