Digital twin system and method for wind turbines

Abstract

The present disclosure provides a digital twin system and method for a wind turbine. The system includes: a data acquisition module configured to acquire configuration parameters and operation data of the wind turbine, wherein the configuration parameters include the sensor configuration of the wind turbine, and the operation data includes sensor data; a digital twin module configured to perform adaptive configuration on an initial digital model according to the type of sensor determined by the sensor configuration and / or sensor data, wherein the digital model of the corresponding wind turbine is constructed by cutting the initial digital model according to the type of sensor to achieve adaptive configuration; and an operation control module configured to control the operation state of the wind turbine according to the operation state of the wind turbine calculated by the digital model of the wind turbine.

Description

Technical Field

[0001] The present disclosure relates to the field of wind power generation, and more specifically, to a digital twin system and method for a wind turbine. Background Art

[0002] In recent years, the customized sensor configuration of wind turbines has become more and more abundant, but sometimes due to installation or cost restrictions, many variables of interest cannot be equipped with corresponding sensors. Faced with different sensor configurations, the topological structure of the wind turbine digital model usually established is single and difficult to adjust and expand, so it is impossible to achieve the corresponding simulation accuracy and granularity according to different needs. Summary of the invention

[0003] Through digital twinning, virtual displacement and load sensors distributed throughout the wind turbine are built to save the number of actual sensor installations and hardware costs. The simulation model calculates the system's comprehensive dynamic variables in real time (including some variables that are not equipped with sensors at the wind farm site or are difficult to measure, such as blade loads, main shaft loads, yaw parameters, tower loads, blade and tower deformations, blade deformation energy, and blade swing energy ratio, etc.).

[0004] The digital twin provides the whole machine operating status and the displacement and load of each key component, providing more dimensional data for the design, control, operation and maintenance, fault prediction and life assessment of the unit.

[0005] According to one aspect of the present disclosure, a digital twin system of a wind turbine is provided, characterized in that the system comprises: a data acquisition module, configured to acquire configuration parameters and operating data of the wind turbine, the configuration parameters comprising sensor configuration of the wind turbine, and the operating data comprising sensor data; a digital twin module, configured to perform adaptive configuration on an initial digital model according to a type of sensor determined by the sensor configuration and / or sensor data, wherein a corresponding digital model of the wind turbine is constructed by trimming the initial digital model according to the type of sensor to achieve the adaptive configuration; and an operation control module, configured to control the operating state of the wind turbine calculated according to the digital model of the wind turbine.

[0006] The sensor data includes at least one of wind parameter data, blade root load data, and tower inclination angle data.

[0007] The digital twin module is also configured to: based on the sensor data including wind parameter data, adaptively configure the initial digital model according to the wind parameter data; or based on the sensor data not including wind parameter data, perform preliminary data conversion processing on the sensor data through a preliminary data conversion module, and adaptively configure the initial digital model according to the processed sensor data.

[0008] The data preliminary conversion module is configured as follows: based on the sensor data including blade root load data, in a three-dimensional rectangular coordinate system, force component data in three coordinate directions are fitted according to the bending moment data in the first and second coordinate directions in the blade root load, and the bending moment data in the third coordinate direction is obtained according to the conversion of the pitch current, pitch voltage and wind turbine speed in the controller data, all the bending moment data and force component data are converted from the blade root coordinate system to the hub coordinate system to obtain processed sensor data; and based on the sensor data including tower inclination data, the tower inclination data is converted into tower load data according to the tower deformation principle as the processed sensor data.

[0009] The digital twin module includes: multiple functional modules and a data sharing module for realizing various topological architectures of digital twins, and the functional modules in the digital twin module adopt a mutually decoupled modular form to exchange data through the data sharing module.

[0010] The configuration parameters also include model parameters of the wind turbine, the initial digital model establishes a tree topology framework according to the model parameters, and trimming the initial digital model includes: the tree topology framework trims connection nodes of the tree topology framework based on the sensor configuration and / or sensor data.

[0011] The tree topology framework includes subsystem blocks corresponding to various parts of the wind turbine. The subsystem blocks are composed of elements related to the parts and connections between the elements. The connection nodes are located between the subsystem blocks and between the elements in the subsystem blocks.

[0012] The regulation of the operation regulation module includes at least one of health detection, fault warning and auxiliary control.

[0013] The system further comprises a communication module, and the communication module is used for receiving controller data and sensor data in real time in a wired or wireless manner.

[0014] According to one aspect of the present disclosure, a digital twin method for a wind turbine is provided, the method comprising: collecting configuration parameters and operating data of the wind turbine, the configuration parameters comprising sensor configuration of the wind turbine, and the operating data comprising sensor data; performing adaptive configuration on an initial digital model according to a type of sensor determined by the sensor configuration and / or the sensor data, wherein a corresponding digital model of the wind turbine is constructed by trimming the initial digital model according to the type of the sensor to achieve adaptive configuration; and regulating the operating state of the wind turbine calculated according to the digital model of the wind turbine.

[0015] The sensor data includes at least one of wind parameter data, blade root load data, and tower inclination angle data.

[0016] The method also includes: based on the fact that the sensor data includes wind parameter data, adaptively configuring the initial digital twin model according to the wind parameter data; or based on the fact that the sensor data does not include wind parameter data, performing preliminary data conversion processing on the sensor data through a preliminary data conversion module, and adaptively configuring the initial digital twin model according to the processed sensor data.

[0017] The method also includes: based on the sensor data including blade root load data, in a three-dimensional rectangular coordinate system, fitting force component data in three coordinate directions according to the bending moment data in the first coordinate and second coordinate directions in the blade root load, and obtaining the bending moment data in the third coordinate direction according to the conversion of the pitch current, pitch voltage and wind turbine speed in the controller data, converting all the bending moment data and force component data from the blade root coordinate system to the hub coordinate system to obtain processed sensor data; and based on the sensor data including tower inclination data, converting the tower inclination data into tower load data according to the tower deformation principle as the processed sensor data.

[0018] The configuration parameters also include model parameters of the wind turbine, the initial digital model establishes a tree topology framework according to the model parameters, and trimming the initial digital model includes: the tree topology framework trims connection nodes of the tree topology framework based on the sensor configuration and / or sensor data.

[0019] The tree topology framework includes subsystem blocks corresponding to various parts of the wind turbine. The subsystem blocks are composed of elements related to the parts and connections between the elements. The connection nodes are located between the subsystem blocks and between the elements in the subsystem blocks.

[0020] According to one aspect of the present disclosure, a computer-readable storage medium storing a computer program is provided. When the computer program is executed by a processor, the digital twin method of the wind turbine as described above is implemented.

[0021] According to one aspect of the present disclosure, a computer device is provided, comprising: a processor; and a memory storing a computer program, wherein when the computer program is executed by the processor, the digital twin method of the wind turbine as described above is implemented.

[0022] The digital twin of the wind turbine disclosed in the present invention establishes a tree topology architecture including multiple subsystems, so that the digital twin of the wind turbine is not restricted by the sensor configuration. At the same time, the digital twin of the present invention fully considers the aeroelastic coupling effect and the rigid-flexible dynamic characteristics of the whole machine, and can be customized according to site conditions and requirements. Adaptive tailoring of the digital model can be achieved within the digital twin to cover a full range of different scenarios.

[0023] The digital model of the wind turbine in the present disclosure is modular, and the bottom layer of the model realizes various topological structures through a rich unit library, and expands different simulation accuracy and granularity according to different needs. The digital model has high solving efficiency and can also achieve real-time response in the tailored model that does not rely on wind parameters.

[0024] The wind parameters in this disclosure use radar wind measurement or cabin wind correction, or other sensor data configured on site as the input of the model. The PLC master control data is directly connected to the digital twin model in real time to avoid introducing deviations. At the same time, the project encrypts and platform-based transmission of design data and operation data, and the security of data access is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other aspects, features and advantages of the present disclosure will be more clearly understood from the following combined drawings and detailed description, in which:

[0026] Figure 1 is a block diagram of a digital twin system of a wind turbine according to an embodiment of the present disclosure.

[0027] Figure 2 4 is a block diagram of a hardware platform of a digital twin system of a wind turbine according to an embodiment of the present disclosure.

[0028] Figure 3 is a block diagram of a digital twin module of a wind turbine according to an embodiment.

[0029] Figure 4 is a block diagram of a data preliminary conversion module according to an embodiment.

[0030] Figure 5is a system block diagram of a digital twin module according to an embodiment.

[0031] Figure 6 is a schematic diagram of the structure of subsystems and blocks of a tree topology according to an embodiment.

[0032] Figure 7 is a schematic diagram of a tree topology architecture of a digital model according to an embodiment.

[0033] Figure 8 It is the aerodynamic calculation process based on the BEM model.

[0034] Fig. 9 It is the hydrodynamic calculation process.

[0035] Fig.10 is a block diagram of a digital twin method of a wind turbine according to an embodiment. DETAILED DESCRIPTION

[0036] The following specific embodiments are provided to help the reader gain a comprehensive understanding of the methods, devices and / or systems described herein. However, after understanding the disclosure of the present application, various modifications, modifications and equivalents of the methods, devices and / or systems described herein will be apparent. For example, the order of operations described herein is merely an example and is not limited to the order set forth herein, but in addition to the operations that must occur in a specific order, changes that will be apparent after understanding the disclosure of the present application may be made. In addition, in order to improve clarity and brevity, descriptions of features known in the art may be omitted. In order to enable those skilled in the art to better understand the present disclosure, specific embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings.

[0037] Definition of technical terms

[0038] Digital twin: A digital analysis method that uses physical models, sensor update data, and operation history data to integrate multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, complete mapping in virtual space, and thus reflect the data of the entire life cycle of the corresponding physical equipment.

[0039] Mechanism model: An accurate mathematical model established based on the internal mechanism of an object or production process or the transfer mechanism of material flow. The mathematical model of an object or process is obtained based on the mass balance equation, energy balance equation, momentum balance equation, phase balance equation, certain physical property equations, chemical reaction laws, basic circuit laws, etc.

[0040] Multibody Dynamic System: (MBDS) is a system composed of entities (rigid / flexible) or links, which are connected to each other by joints that restrict their relative motion. It is generally used to study the motion laws of multibody systems composed of rigid / flexible bodies.

[0041] Figure 1 is a block diagram of a digital twin system of a wind turbine according to an embodiment of the present disclosure.

[0042] Reference Figure 1 According to an embodiment of the present disclosure, the digital twin system of a wind turbine includes: a data acquisition module 100 , a digital twin module 200 and an operation control module 300 .

[0043] The data collection module 100 is configured to collect configuration parameters and operation data of the wind turbine.

[0044] The configuration parameters include the sensor configuration of the wind turbine, and the operation data include the sensor data. Optionally, the sensor configuration includes configuration information such as the type of sensor equipped with the wind turbine, and the sensor data may include at least one of wind parameter data, blade root load data, and tower inclination data. The data acquisition module 100 may directly obtain the type information of the sensor through the sensor configuration in the configuration parameters, or may indirectly analyze and obtain the type information of the sensor through the sensor data in the operation data.

[0045] The digital twin module 200 is configured to perform adaptive configuration on the initial digital model (the initial digital model refers to the whole machine simulation model for the full set of configuration parameters and operating data of the wind turbine) according to the type of sensor determined by the sensor configuration and / or sensor data. The digital model of the corresponding wind turbine can be constructed by cutting the initial digital model according to the type of sensor to achieve the adaptive configuration (for example, the digital model of the corresponding wind turbine may include one or more of the blade subsystem, the pitch subsystem, the transmission chain subsystem, and the nacelle yaw subsystem). The digital twin system of the wind turbine disclosed in the present invention may include an initial digital model based on the model parameters. The digital twin module 200 can adaptively configure the initial digital model according to the type of sensor determined by the configuration parameters and operating data collected by the data acquisition module 100. The adaptive configuration can cut the corresponding module in the initial digital model that matches the type of sensor to obtain a digital model that is adapted to the sensor type.

[0046] The operation control module 300 is configured to control the operation state of the wind turbine according to the operation state of the wind turbine calculated by the digital model of the wind turbine. Based on the digital model adapted to the sensor type, the digital model can perform real-time simulation calculation on the operation state of the wind turbine, and the operation control module 300 controls the execution of the wind turbine through the simulated dynamic response in the calculation result, etc. The control may include at least one of health detection, fault warning and auxiliary control, but is not limited to this. For example, the wind turbine digital twin system in this embodiment can be used as a virtual load and deformation sensor, so the operation control module 300 can obtain the load and deformation operation data of key components based on the calculation results of the simulation calculation, and perform auxiliary control and fault warning. Through the output of the overall digital twin, the actual load-bearing capacity of the wind turbine entity at various sites can be accumulated to establish an actual load database. The embodiment of the present disclosure can conveniently obtain a load time series with real-time response, and the established system and method can be applied in operation and maintenance and life prediction, which needs to be combined with wind prediction and further application of wind-load relationship mechanism.

[0047] Digital models based on traditional industrial software are generally used in the design and finalization stage of products, and it is difficult to achieve real-time calculations that match the site. However, the digital model of the wind turbine disclosed in the present invention can be used for real-time fault warning and auxiliary control on site. The digital twin system according to the embodiment of the present invention can adapt to different configurations of on-site sensors, batch configuration for different wind farms and models, and solve the security issues of design data and operation data at the same time, and can be applied on a large scale in various wind farms.

[0048] In addition, the digital twin system also includes a communication module, the communication module includes an application program interface, and the communication module is used to receive controller data and sensor data in real time in a wired or wireless manner. The digital twin system also includes a storage module, which includes: a real-time database for storing controller data and sensor data in real time; and a configuration information database for storing model parameter data and sensor configuration parameters.

[0049] The digital twin system can be deployed in the integrated auxiliary controller on the unit side, and a real-time protocol is used to establish a connection within the digital twin platform, such as ethercat, Canopen, powerlink, etc. There is no problem of data transmission delay, and the minimum delay can achieve the collection cycle of field data, which is generally 20ms. At the same time, the platform directly collects 20ms data for processing and calculation, ensuring real-time performance while also ensuring the realization of key load information in the digital twin model. The degree of simulation can be improved by not introducing errors in wind parameters and controller signals. At the same time, the use of real-time protocols and other methods to improve real-time performance can expand the scope of application of digital twins. For example, based on radar or wind parameter correction and direct call of real-time PLC main controller parameters, the errors of external parameters obtained by calculation can be avoided. At the same time, the dynamic response of the whole machine at key frequencies is fully considered for the 20ms collection cycle, and the accuracy of load extremes and fatigue loads is improved.

[0050] Figure 2 4 is a block diagram of a hardware platform of a digital twin system of a wind turbine according to an embodiment of the present disclosure.

[0051] Reference Figure 2 According to the embodiment of the present invention, the hardware platform of the digital twin system of the wind turbine mainly includes a host computer module, a system management module, a data push module, a data acquisition module, a data interface module, a time series database module, a configuration information database module, a digital twin virtual space (i.e., digital model) module and a business module.

[0052] The processing of the hardware platform of the digital twin system of the wind turbine according to the embodiment of the present disclosure includes:

[0053] Pre-adding configuration parameters of the wind turbine generator to the configuration information database through the system management module, the configuration parameters including the model parameters of the wind turbine generator and the on-site sensor configuration;

[0054] From the perspective of data types, the data acquisition module collects data from the field controller (for example, the master PLC) and sensor data and stores them in the time series database. The real-time data required in the digital twin virtual space of the wind turbine is transmitted to the data interface module through the bus according to the time interval required by the real-time requirements (for example, 0.02s or 1s). Some non-real-time data will be transferred from the time series database to the data interface. The call of controller parameters can be changed from PLC real-time data to simulation controller (controller DLL file and parameter file);

[0055] The specific contents of the data collected by the data acquisition module include: blade root load, main shaft load, tower load, tower inclination data, wind parameters (including cabin wind and radar wind), impeller azimuth, variable pitch system state quantity, motor speed, converter torque and other control quantities and state quantities, but are not limited thereto, and can be the full set and subset of the above variable ranges;

[0056] According to the signal analyzed by the data interface, the digital twin virtual space performs adaptive configuration, initialization and dynamic calculation on the digital model according to the specific machine model parameters and sensor configuration on site. The calculation results are returned to the data interface and stored in the time series database through the data interface. Among them, the calculation results are the dynamic response results of the digital model, including the load, deformation and state quantity of key components;

[0057] The calculation results are sent to the business module at the same time, and the business module performs fault warning, health assessment and auxiliary control through the integration of data. In addition, according to the embodiment, the control instructions of the business module can be transmitted to the controller (for example, the main control PLC). And according to the embodiment, the data in the business module can be pushed to the host computer through the data push module for users to view and use.

[0058] Optionally, the hardware platform of the digital twin system can be replaced with an edge cloud computing model, etc., but is not limited to this.

[0059] Figure 3 is a block diagram of a digital twin module of a wind turbine according to an embodiment.

[0060] Reference Figure 3 According to an embodiment of the present disclosure, the digital twin module of a wind turbine may include an automatic conversion and encryption module 310, an automatic judgment module 320, a preliminary data conversion module 330, a wind reconstruction module 340, a model adaptive matching module 350 and a model operation module 360.

[0061] According to an embodiment of the present disclosure, the automatic judgment module 320 can determine whether the parsed data contains wind parameter (cabin wind or radar wind) data. If it contains wind parameters, it enters the wind reconstruction module 340; if it does not contain wind parameters, it directly enters the data preliminary conversion module 330.

[0062] The automatic conversion and encryption module 310 can parse the unit model configuration file transmitted from the configuration database via the interactive interface, and automatically convert it into the configuration parameter file format used by the digital twin model solver and encrypt it. The sensor data may include at least one of wind parameter data, blade root load data, and tower inclination data. The unit parameter file may include the structure, material, electrical characteristics, field identification parameters, etc. of key components. The digital twin module can initialize parameters according to the unit parameter file to build the topological framework of the digital model. The platform-based transmission of model parameters and operating data ensures the security of data access.

[0063] The model adaptive matching module 350 can match the complete topological framework of the digital model according to the data or wind file generated by the preliminary data conversion, and tailor the topological framework to customize the design for the usage scenario.

[0064] The model operation module 360 ​​can perform model operation based on the output of the model adaptive matching module 350 and output a dynamic response result.

[0065] For example, the digital twin module constructed as above can include wind parameter data based on the sensor data, and adaptively configure the initial digital model according to the wind parameter data; or based on the sensor data not including wind parameter data, the sensor data is processed by the data preliminary conversion module, and the initial digital model is adaptively configured according to the processed sensor data. Optionally, if the sensor data includes wind parameters, the complete topological framework is used and the external load is aerodynamic force. If the sensor data does not include wind parameters but only includes blade root loads, the blade subsystem is cut from the topological framework and the external load is changed to blade root loads. If the sensor data does not include wind parameters but only includes tower top loads, the blade subsystem, pitch subsystem, transmission chain subsystem and cabin yaw subsystem are cut from the topological framework and the external load is changed to tower top loads, etc. In addition, the offshore unit may include hydrodynamic parameters.

[0066] Before the digital model is operated, the adaptively configured model is initialized to keep the state of the digital model consistent with the measured data. The relevant state quantities, control quantities and load input quantities in the digital model are updated once every fixed time step (the time step is set according to the real-time requirements of the system), and a dynamic response iteration is performed, and the dynamic response results (for example, the operating quantity of the unit, the load and displacement data of each key component) are transmitted back to the interactive interface.

[0067] This embodiment can solve the problem that the simulation degree of the digital twin model of the wind turbine is restricted due to the great uncertainty of the wind parameters measured on site, and the control system interface problem caused by the wind parameter data format and the differences in software and hardware.

[0068] Figure 4is a block diagram of a data preliminary conversion module according to an embodiment.

[0069] Reference Figure 4 According to the embodiment, the data preliminary conversion module can perform corresponding data conversion based on different sensor configurations. The data preliminary conversion module can fit the force component data in three coordinate directions according to the bending moment data in the first and second coordinate directions in the blade root load in a three-dimensional rectangular coordinate system based on the sensor data including blade root load data, and obtain the bending moment data in the third coordinate direction according to the conversion of the pitch current, pitch voltage and wind turbine speed in the controller data, and convert all the bending moment data and force component data from the blade root coordinate system to the hub coordinate system to obtain the processed sensor data; and based on the sensor data including tower inclination data, the tower inclination data is converted into tower load data according to the tower deformation principle as the processed sensor data.

[0070] For example, when the sensor includes a blade root load, the preliminary data conversion module fits the force components of the blade root load in three directions according to the blade root force component fitting coefficients of the model in the configured model database and the flapping and swing torques of the blade root. The blade root force component fitting coefficient is adapted offline through the deformation principle of the blade and is pre-configured into the model database. Then, combined with the pitch angle position and the impeller azimuth position, the blade root or rotating hub load is converted to a fixed coordinate system. If the sensor includes a tower inclination sensor, the preliminary data conversion module converts it into a tower load according to the deformation principle of the tower. The sensor is not limited to this, and the processing of the preliminary data conversion module is not limited to this.

[0071] Figure 5 is a system block diagram of a digital twin module according to an embodiment.

[0072] The digital twin module may include multiple functional modules and data sharing modules for realizing various topological architectures of the digital twin, and the various functional modules in the digital twin module adopt a mutually decoupled modular form to exchange data through the data sharing module.

[0073] According to the embodiment, the architecture for realizing the digital twin of the whole machine can realize the initial configuration input and calling by calling the module. Each system adopts a modular design. The modules of each system can interact with each other through the data sharing module. The modification and update of each module will not affect other modules. The interface between the calling module satisfies the operation of the complete model with radar wind / cabin wind as input conditions and calling the simulation controller file. The external interface can meet the operation of the tailored model and the operation of the complete model for accessing the on-site real-time control parameters. The modules are decoupled from each other and transmit data through the data sharing module. This modular system architecture is easy to expand and is also convenient for tailoring different modules to meet various scene calls and functional requirements.

[0074] According to the embodiment, the digital twin module can accept information such as an external configuration file parsed by the calling module through an interface; the wind module can parse the three-dimensional turbulent wind file data or turbulent wind settings, and construct a three-dimensional wind field based on the inflow angle and wind shear coefficient, and give the wind speed information in all directions of the impeller surface and the grid points in the external specific area, and pass the data to the data sharing module; the MBDS model of the wind turbine is established based on the tree system topology architecture.

[0075] Figure 6 is a schematic diagram of the structure of subsystems and blocks of a tree topology according to an embodiment.

[0076] Figure 7 is a schematic diagram of a tree topology architecture of a digital model according to an embodiment.

[0077] Reference Figure 6 and Figure 7 , the digital model establishes a tree topology framework according to the model parameters, and trimming the initial digital model may include: the tree topology framework trims the connection nodes of the tree topology framework based on the sensor configuration and / or the adaptive configuration of the sensor data. In this case, the configuration parameters of the wind turbine include the model parameters of the wind turbine. The tree topology framework includes subsystem blocks corresponding to various parts of the wind turbine, and the subsystem blocks are composed of elements related to the parts and connections between the elements, and the connection nodes are located between the subsystem blocks and between the elements in the subsystem blocks.

[0078] like Figure 6 , a tree topology can be used to build an MBDS model, which includes a variety of different subsystems, each of which can be built using one or more different subsystem blocks, and each subsystem block can include fixed configuration attributes (basic components). Through the established unit library, the subsystem blocks can select basic components from the unit library for assembly. This architecture can be applied to various topologies.

[0079] The basic components in the subsystem block may include: near and far connection points, including position, mass, and inertia information, and the mass inertia can be 0; connection relationships, including fixed connections, elastic damping connections, rotational connections, gear connections, and other various connection methods, among which rotational connections can introduce external control inputs (speed, displacement, torque); elements, including rigid bodies, flexible body unit models (Eulerbeam, Timoshenkobeam, IGA, etc.), super units, contact units, etc. as the main body of the subsystem block; applied external loads, including centralized and distributed loading of forces and torques; coordinate transformations, including translation vectors or rotation matrices. Figure 6 In the subsystem block, the solid line box represents the necessary attributes, and the dashed line box represents the optional attributes. Based on such a rich unit library model architecture, it can be easily combined into any topology structure to meet the simulation requirements of different granularity and dimensions.

[0080] Reference Figure 7 This modular construction method based on the unit library of the tree topology architecture can be applied to various topology architectures. The topology can be tailored based on the connection between each subsystem or the connection within the subsystem to meet various needs in the field of wind turbine digital twins. In addition, the main topology can add branches, such as the transfer function (first order or second order) of the electrical system or actuator, and the passive uncoupled sub-model (adding the load output of the subsystem drive mechanism, etc. on the basis of the trunk), but it is not limited to this.

[0081] The tree topology architecture can adaptively and quickly tailor different signals collected by field sensors to facilitate customized application scenarios, thereby meeting different needs and realizing large-scale application of digital twin models. At the same time, the modeling method and complexity of the sub-model can be easily adjusted according to needs.

[0082] Figure 8 It is the aerodynamic calculation process based on the BEM model.

[0083] The aerodynamic calculation module calculates the aerodynamic force based on the inflow wind speed information and the structural node information. The fan aeroelastic model established in the embodiment of the present disclosure fully considers the aerodynamic characteristics of the fan and the coupling characteristics of the rigid-flexible body dynamics of the whole machine. The embodiment of the present disclosure adopts a mechanism model based on the aeroelastic theory, but is not limited to this. It can also be replaced by a data and mechanism fusion model, for example, according to the field measured data, the relevant parameters in the model are corrected by mathematical methods.

[0084] The calculation of aerodynamic force can adopt the existing mature theories such as blade element momentum (BEM) model, lift line model and free vortex, and the relevant description is omitted here. Figure 8The typical process of calculating aerodynamics based on the BEM model is given, including the BEM calculation main model, dynamic inflow model, oblique wake model, blade tip stall model, etc. The embodiment of the present disclosure can also be replaced by lift line theory or free vortex theory based on the BEM model plus correction calculation. Digital twins can establish a tree topology based on aeroelastic theory and rigid-flexible body dynamics theory, which can highly reflect the aerodynamic and dynamic characteristics of the whole machine. The overall accuracy difference of key loads is within 5%, which can obtain on-site attention at low cost but does not measure specific loads and operating data.

[0085] Fig. 9 It is the hydrodynamic calculation process.

[0086] Optionally, if it is an offshore unit, it is necessary to solve the hydrodynamic forces on the supporting structure through a hydrodynamic calculation module.

[0087] According to IEC specifications, offshore wind turbines must consider hydrodynamics. Hydrodynamic calculations include wave simulation and wave force calculations. Different design conditions require different wave models. Generally, it is necessary to simulate irregular waves, which are generated by superimposing linear waves. In some cases, it is necessary to add constrained waves to simulate extreme waves, which is achieved by adding a periodic stream function wave to the irregular wave background. The calculation of wave force mainly uses the mature Morison wave force formula in engineering, and the force of waves on structures is calculated by superimposing the drag force related to the water particle velocity and the inertial force related to the water particle acceleration.

[0088] If other types of external loads are included, other external load calculation modules can be added. For example, calculation of external loads caused by friction torque and various motor drive torques can also be included.

[0089] If the digital twin model of the wind turbine needs to call the simulation controller file for solving, the API call is implemented through the control module; the sensor data and controller data are introduced through the external interface to prepare for the adaptive tailoring of the digital model; the output information of each module is defined in the output module, such as the unit operation volume, the displacement and load of key components, etc.; the overall model assembly, solver setting, initialization and dynamic solution setting are implemented through the system module; the calling module triggers the run command and calls the solver module to solve the dynamic response of the digital twin model of the wind turbine; after the calculation is completed, the results are output according to the set time interval and step size, and can also be directly transferred to the database from the external interface as needed.

[0090] Fig.10 is a block diagram of a digital twin method of a wind turbine according to an embodiment.

[0091] Reference Fig.10According to an embodiment of the present disclosure, the digital twin method of a wind turbine includes: in step 101, collecting configuration parameters and operating data of the wind turbine, wherein the configuration parameters include the sensor configuration of the wind turbine, and the operating data include the sensor data. In step 102, adaptive configuration is performed on the initial digital model according to the type of sensor determined by the sensor configuration and / or the sensor data, and the digital model of the corresponding wind turbine is constructed by cutting the initial digital model according to the type of sensor to achieve adaptive configuration. In step 103, the operating state of the wind turbine is regulated according to the operating state of the wind turbine calculated by the digital model of the wind turbine.

[0092] According to an embodiment of the present disclosure, the sensor data includes at least one of wind parameter data, blade root load data, and tower inclination angle data.

[0093] The digital twin method according to an embodiment of the present disclosure may also be based on the fact that the sensor data includes wind parameter data, and the initial digital twin model is adaptively configured according to the wind parameter data; or based on the fact that the sensor data does not include wind parameter data, the sensor data is subjected to preliminary data conversion processing through a preliminary data conversion module, and the digital twin model is adaptively configured according to the processed sensor data.

[0094] The digital twin method according to the embodiment of the present disclosure may also be based on the sensor data including blade root load data, and in a three-dimensional rectangular coordinate system, fit the force component data in three coordinate directions according to the bending moment data in the first and second coordinate directions in the blade root load, and obtain the bending moment data in the third coordinate direction according to the conversion of the pitch current, pitch voltage and wind turbine speed in the controller data, and convert all the bending moment data and force component data from the blade root coordinate system to the hub coordinate system to obtain the processed sensor data; and based on the sensor data including tower inclination data, convert the tower inclination data into tower load data according to the tower deformation principle as the processed sensor data.

[0095] The configuration parameters include model parameters of the wind turbine, the initial digital model establishes a tree topology framework according to the model parameters, and trimming the initial digital model may include: the tree topology framework trims connection nodes of the tree topology framework based on the sensor configuration and / or sensor data.

[0096] The tree topology framework includes subsystem blocks corresponding to various parts of the wind turbine. The subsystem blocks are composed of elements related to the parts and connections between the elements. The connection nodes are located between the subsystem blocks and between the elements in the subsystem blocks.

[0097] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium storing a computer program is also provided. The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to execute a digital twin method of a wind turbine according to the present disclosure. The computer-readable recording medium is any data storage device that can store data read out by a computer system. Examples of computer-readable recording media include: read-only memory, random access memory, read-only optical disc, magnetic tape, floppy disk, optical data storage device, and carrier wave (such as data transmission over the Internet via a wired or wireless transmission path).

[0098] According to an exemplary embodiment of the present disclosure, a computer device is also provided. The computer device includes a processor and a memory. The memory is used to store a computer program. The computer program is executed by the processor so that the processor executes the computer program of the digital twin method of the wind turbine according to the present disclosure.

[0099] The digital twin system according to the embodiment of the present disclosure can adapt to different configurations of on-site sensors and be configured in batches for different wind farms and machine models. It has strong applicability, universal interfaces, real-time response, and high model solving efficiency. It can also solve the security issues of design data and operation data and can be applied on a large scale in various wind farms.

[0100] The specific implementation methods of the present disclosure have been described in detail above. Although some embodiments have been shown and described, those skilled in the art should understand that these embodiments may be modified and varied without departing from the principles and spirit of the present disclosure, the scope of which is defined by the claims and their equivalents. These modifications and variations should also be within the scope of protection of the claims of the present disclosure.

Claims

1. A digital twin system of a wind turbine, characterized in that: The system comprises: A data acquisition module is configured to acquire configuration parameters and operation data of the wind turbine, wherein the configuration parameters include sensor configuration of the wind turbine, and the operation data includes sensor data; A digital twin module is configured to perform adaptive configuration on the initial digital model according to the type of sensor determined by the sensor configuration and / or the sensor data, wherein the digital model of the corresponding wind turbine is constructed by tailoring the initial digital model according to the type of the sensor to achieve the adaptive configuration; an operation control module, configured to control the operation state of the wind turbine according to the operation state of the wind turbine calculated by the digital model of the wind turbine, Among them, the digital twin module is also configured to: perform preliminary data conversion processing on the sensor data through the data preliminary conversion module, and the data preliminary conversion module is configured to: based on the sensor data including blade root load data, in a three-dimensional rectangular coordinate system, fit the force component data in three coordinate directions according to the bending moment data in the first coordinate and second coordinate directions in the blade root load, and obtain the bending moment data in the third coordinate direction according to the conversion of the pitch current, pitch voltage and wind turbine speed in the controller data, and convert all the bending moment data and force component data from the blade root coordinate system to the hub coordinate system to obtain the processed sensor data.

2. The system according to claim 1, characterized in that The sensor data includes at least one of wind parameter data, blade root load data, and tower inclination angle data.

3. The system according to claim 2, characterized in that The digital twin module is also configured to: Based on the sensor data including wind parameter data, adaptively configuring the initial digital model according to the wind parameter data; or Based on the fact that the sensor data does not include wind parameter data, a preliminary data conversion module is used to perform preliminary data conversion processing on the sensor data, and the initial digital model is adaptively configured according to the processed sensor data.

4. The system according to claim 3, characterized in that The data preliminary conversion module is configured as follows: Based on the fact that the sensor data includes tower inclination data, the tower inclination data is converted into tower load data according to the tower deformation principle as processed sensor data.

5. The system according to claim 1, characterized in that The digital twin module includes: multiple functional modules and data sharing modules for realizing various topological architectures of digital twins, and The various functional modules in the digital twin module adopt a mutually decoupled modular form to exchange data through a data sharing module.

6. The system according to claim 1, characterized in that The configuration parameters also include the model parameters of the wind turbine. The initial digital model establishes a tree topology framework according to the aircraft model parameters, and trimming the initial digital model includes: the tree topology framework trims connection nodes of the tree topology framework based on the sensor configuration and / or sensor data.

7. The system according to claim 6, characterized in that The tree topology framework includes subsystem blocks corresponding to various parts of the wind turbine. The subsystem blocks are composed of elements related to the parts and connections between the elements. The connection nodes are located between the subsystem blocks and between the elements in the subsystem blocks.

8. The system according to any one of claims 1 to 7, characterized in that: The regulation of the operation regulation module includes at least one of health detection, fault warning and auxiliary control.

9. The system according to any one of claims 1 to 7, characterized in that: The system also includes a communication module, The communication module is used to receive controller data and sensor data in real time in a wired or wireless manner.

10. A digital twin method for a wind turbine, characterized in that: The method comprises: Collecting configuration parameters and operation data of the wind turbine, wherein the configuration parameters include sensor configuration of the wind turbine, and the operation data includes sensor data; Performing adaptive configuration on the initial digital model according to the type of sensor determined by the sensor configuration and / or the sensor data, wherein the digital model of the corresponding wind turbine is constructed by tailoring the initial digital model according to the type of the sensor to achieve the adaptive configuration; The operation state of the wind turbine is regulated according to the operation state of the wind turbine calculated by the digital model of the wind turbine, Among them, the sensor data is subjected to preliminary data conversion processing by a preliminary data conversion module, and based on the sensor data including blade root load data, in a three-dimensional rectangular coordinate system, force component data in three coordinate directions are fitted according to the bending moment data in the first coordinate and second coordinate directions in the blade root load, and the bending moment data in the third coordinate direction is obtained according to the conversion of the pitch current, pitch voltage and wind turbine speed in the controller data, and all the bending moment data and force component data are converted from the blade root coordinate system to the hub coordinate system to obtain the processed sensor data.

11. The method according to claim 10, characterized in that The sensor data includes at least one of wind parameter data, blade root load data, and tower inclination angle data.

12. The method according to claim 11, characterized in that The method further comprises: Based on the sensor data including wind parameter data, adaptively configuring the initial digital model according to the wind parameter data; or Based on the fact that the sensor data does not include wind parameter data, a preliminary data conversion module is used to perform preliminary data conversion processing on the sensor data, and the initial digital model is adaptively configured according to the processed sensor data.

13. The method according to claim 12, characterized in that The method further comprises: Based on the fact that the sensor data includes tower inclination data, the tower inclination data is converted into tower load data according to the tower deformation principle as processed sensor data.

14. The method according to claim 10, characterized in that The configuration parameters also include the model parameters of the wind turbine. The initial digital model establishes a tree topology framework according to the aircraft model parameters, and trimming the initial digital model includes: the tree topology framework trims connection nodes of the tree topology framework based on the sensor configuration and / or sensor data.

15. The method according to claim 14, characterized in that The tree topology framework includes subsystem blocks corresponding to various parts of the wind turbine. The subsystem blocks are composed of elements related to the parts and connections between the elements. The connection nodes are located between the subsystem blocks and between the elements in the subsystem blocks.

16. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the digital twin method for a wind turbine as claimed in any one of claims 10 to 15 is implemented.

17. A computer device, characterized in that: The computer device comprises: processor; A memory storing a computer program, which, when executed by a processor, implements the digital twin method for a wind turbine as claimed in any one of claims 10 to 15.

Images