Wind turbine blade resin flow prediction method and system based on digital twinning

Abstract

The application provides a wind power blade resin flow prediction method and system based on digital twinning, relates to the technical field of digital twinning, and comprises the following steps: obtaining multi-source detection historical data about a to-be-detected wind power blade mold, and determining a historical resin front position and a historical resin advancing speed; creating a three-dimensional resin model based on the geometric size of the to-be-detected wind power blade mold, introducing resin material parameters and resin process parameters to simulate a resin flow process, combining temperature state parameters, and constructing an initial resin flow model; inputting the multi-source detection historical data into the initial resin flow model to generate a prediction center reflection wavelength sequence and a prediction temperature change sequence, and correcting parameters of the initial resin flow model based on the difference between the historical center reflection wavelength sequence and the historical temperature change sequence, so that a target resin flow model is obtained; and inputting multi-source detection real-time data of the to-be-detected wind power blade mold into the target resin flow model to generate corresponding resin state parameters.

Description

Technical Field

[0001] This invention relates to the field of digital twin technology, and in particular to a method and system for predicting resin flow in wind turbine blades based on digital twins. Background Technology

[0002] With the rapid development of the wind power industry and the increasing trend towards larger wind turbines, the size of wind turbine blades is constantly increasing, making their structural reliability and manufacturing quality increasingly important for the overall performance and service life of the turbine. In wind turbines, blades are key structural components, and their manufacturing quality directly affects the power generation efficiency and service life of the unit. Currently, blade manufacturing mainly employs vacuum injection molding, which guides resin into the fiber preform through vacuum negative pressure to achieve efficient molding. However, the injection process requires high-level process control; uneven resin flow can easily cause irreversible defects such as dry spots and porosity, affecting the final structural performance. Therefore, real-time monitoring of the resin flow status is crucial for achieving quality control during the blade molding process.

[0003] However, data acquired solely from the sensors themselves is insufficient for deep perception and intelligent control of the complex infill process. The infill process involves multi-physics coupling problems such as fluid dynamics, heat and mass transfer, and chemical reactions, exhibiting significant nonlinearity, time-varying characteristics, and local uncertainties. Traditional data acquisition and process control suffer from problems such as "data silos," "lack of system modeling," and "response lag," failing to meet the needs of intelligent wind turbine blade manufacturing and hindering the realization of visualized monitoring, dynamic prediction, intelligent optimization, and closed-loop feedback of the infill process. Summary of the Invention

[0004] In view of this, the present invention proposes a method and system for predicting resin flow in wind turbine blades based on digital twins.

[0005] The technical solution of this invention is implemented as follows: The first aspect of this invention provides a method for predicting resin flow in wind turbine blades based on digital twins, comprising: The system acquires multi-source historical detection data about the mold of the wind turbine blade under test, and determines the historical resin leading edge position and historical resin propulsion speed of the mold based on the multi-source historical detection data. The multi-source historical detection data includes the historical center reflection wavelength sequence detected by the fiber Bragg grating sensor and the historical temperature change sequence detected by the temperature sensing unit. A three-dimensional resin model is created based on the geometric dimensions of the wind turbine blade mold to be tested. Resin material parameters and resin process parameters are introduced into the three-dimensional resin model to simulate the resin flow process. Combined with temperature state parameters, an initial resin flow model is constructed. The multi-source detection historical data is input into the initial resin flow model to generate the predicted front position and predicted propulsion velocity. The parameters of the initial resin flow model are then corrected based on the first difference between the predicted front position and the historical resin front position and the second difference between the predicted propulsion velocity and the historical resin propulsion velocity to obtain the target resin flow model. The multi-source real-time detection data of the wind turbine blade mold under test is input into the target resin flow model to generate corresponding resin state parameters; the resin state parameters include the current resin front position, resin propulsion speed, temperature distribution and curing state.

[0006] Based on the above technical solutions, preferably, the acquisition of multi-source detection historical data about the wind turbine blade mold under test includes: A unified timestamp is added to the data collected by the fiber Bragg grating sensor and the temperature sensing unit to obtain the corresponding time-series data; The time-series data is interpolated or resampled to map the time-series data with different sampling frequencies onto the same time axis, forming synchronized multi-source detection historical data.

[0007] Based on the above technical solutions, preferably, the historical center reflection wavelength sequence includes a first center reflection wavelength sequence and a second center reflection wavelength sequence; the step of determining the historical resin leading edge position and historical resin propulsion speed of the wind turbine blade mold under test based on the multi-source detection historical data includes: The distinction threshold is determined based on the first central reflection wavelength sequence when resin impregnation has not occurred; The second historical center reflection wavelength sequence at the time of resin impregnation is processed by first-order difference processing. The moment when the reflection wavelength at the measuring point first exceeds the distinction threshold is determined as the impregnation moment, and the resin impregnation time sequence corresponding to multiple measuring points is obtained. The historical resin front position and the historical resin propagation speed are determined based on the positional distance relationship of multiple measuring points and the resin impregnation time series.

[0008] Based on the above technical solutions, preferably, the determination of the historical resin front position and the historical resin propagation speed based on the positional distance relationship of multiple measuring points and the resin impregnation time series includes: Obtain the first and second immersion times corresponding to the latest two adjacent measuring points that are immersed and those that are not yet immersed, respectively. The historical resin front position and the historical resin propulsion speed are determined based on the first coordinate of the latest immersed measuring point, the second coordinate of the adjacent measuring point that has not yet been immersed, the first immersion time, the second immersion time, and the current time.

[0009] Based on the above technical solutions, preferably, the step of introducing resin material parameters and resin process parameters into the three-dimensional resin model to simulate the resin flow process, and combining temperature state parameters to construct an initial resin flow model, includes: By incorporating temperature state parameters into the curing kinetics model, the degree of resin curing at multiple temperature values ​​is determined, and a resin curing degree function is constructed. Resin material parameters and resin process parameters are introduced into the three-dimensional resin model to simulate the resin flow process, and the resin curing degree function is used for optimization to obtain an initial resin flow model.

[0010] Based on the above technical solutions, preferably, the step of correcting the parameters of the initial resin flow model based on the first difference between the predicted front position and the historical resin front position and the second difference between the predicted propulsion velocity and the historical resin propulsion velocity to obtain the target resin flow model includes: If the first difference is greater than the first threshold, or the second difference is greater than the second threshold, the permeability parameters of the initial resin flow model are corrected based on the first difference and the second difference to obtain the target resin flow model.

[0011] Based on the above technical solutions, preferably, the target resin flow model includes multiple sub-models set in different sub-regions; the step of correcting the permeability parameters of the initial resin flow model based on the first difference and the second difference to obtain the target resin flow model includes: When the resin front enters the target sub-region, the permeability parameters of the sub-model corresponding to the target sub-region are corrected based on the first difference and the second difference; the target sub-region is any one of multiple sub-regions.

[0012] Furthermore, a second aspect of the present invention provides a wind turbine blade resin flow prediction system based on digital twins, comprising: a data acquisition module, a model creation module, a model correction module, and a parameter prediction module; wherein, The data acquisition module is configured to acquire multi-source detection historical data about the wind turbine blade mold under test, and determine the historical resin leading edge position and historical resin propulsion speed of the wind turbine blade mold under test based on the multi-source detection historical data; the multi-source detection historical data includes the historical center reflection wavelength sequence detected by the fiber Bragg grating sensor and the historical temperature change sequence detected by the temperature sensing unit. The model creation module is configured to create a three-dimensional resin model based on the geometric dimensions of the wind turbine blade mold to be tested, and to introduce resin material parameters and resin process parameters into the three-dimensional resin model to simulate the resin flow process. Combined with temperature state parameters, an initial resin flow model is constructed. The model correction module is configured to input the multi-source detection historical data into the initial resin flow model to generate a predicted front position and a predicted propulsion velocity, and to correct the parameters of the initial resin flow model based on a first difference between the predicted front position and the historical resin front position and a second difference between the predicted propulsion velocity and the historical resin propulsion velocity, so as to obtain a target resin flow model. The parameter prediction module is configured to input the multi-source real-time detection data of the wind turbine blade mold under test into the target resin flow model to generate corresponding resin state parameters; the resin state parameters include the current resin front position, resin propulsion speed, temperature distribution and curing state.

[0013] More preferably, a third aspect of the present invention provides an electronic device including a processor and a memory; the memory has a computer program stored thereon, wherein the computer program, when executed by the processor, implements the wind turbine blade resin flow prediction method based on digital twins as described in the first aspect.

[0014] More preferably, a fourth aspect of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the wind turbine blade resin flow prediction method based on digital twins as described in the first aspect.

[0015] The method and system for predicting resin flow in wind turbine blades based on digital twins of the present invention have the following advantages over the prior art: 1. By retrieving historical resin front position and propulsion speed from historical data and combining this with real-time data to predict the current state, dynamic monitoring of the entire resin infusion cycle from flow to curing is achieved, overcoming the shortcomings of traditional methods that only focus on local parameters. A three-dimensional model is created based on the mold geometry, and resin material and process parameters are introduced to simulate the resin flow process. By integrating temperature state parameters, the influence of heat and mass transfer on the flow is further considered, constructing a multi-physics coupled initial model. The model parameters are dynamically corrected using the difference between historical data and model prediction results, forming a closed-loop feedback mechanism of data-driven, model optimization, and prediction verification. This achieves comprehensive, full-process synchronous mapping of the infusion process, greatly improving prediction accuracy and response speed.

[0016] 2. Temperature parameters are introduced into the curing kinetics model to construct a resin curing degree function, which quantifies the degree of resin curing at different temperatures. This function is then used to optimize the three-dimensional resin flow model. By introducing the time dimension through the curing degree function, i.e., the curing degree changes over time, the full-cycle behavior of the resin from flow to curing is simulated. The differences in curing degree caused by temperature gradients within the mold are identified, thereby more accurately predicting changes in resin flow and improving the accuracy and reliability of the prediction results.

[0017] 3. The mold is divided into multiple sub-regions, each independently modeled and assigned permeability parameters. When the resin front enters a target sub-region, only the parameters of that region are corrected, avoiding global model correction issues and improving the accuracy of local flow simulation. By correcting the permeability through differential feedback, local flow anomalies can be captured in real time, ensuring that the model is highly consistent with the actual physical process and reducing the impact of differences in resin flow resistance in different regions. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for predicting resin flow in wind turbine blades based on digital twins, provided in an embodiment of the present invention. Figure 2 A schematic diagram of a wind turbine blade resin flow prediction system based on digital twin provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] In some embodiments, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating a method for predicting resin flow in wind turbine blades based on digital twins, provided by an embodiment of the present invention. The method for predicting resin flow in wind turbine blades based on digital twins provided by the present invention includes: S110, acquire multi-source detection historical data about the wind turbine blade mold to be tested, and determine the historical resin leading edge position and historical resin propulsion speed of the wind turbine blade mold to be tested based on the multi-source detection historical data; the multi-source detection historical data includes the historical center reflection wavelength sequence detected by the fiber Bragg grating sensor and the historical temperature change sequence detected by the temperature sensing unit.

[0022] In this embodiment, multiple fiber Bragg grating sensors can be embedded along the main resin flow direction in areas where resin flow behavior differs significantly, such as the main beam area, web area, and front and rear edges of the mold. Multiple grating measurement points distributed along the flow direction are also set to form a continuous sensing of the resin front advancement process. In areas with large local thickness changes or where temperature rise is prone to occur, temperature sensing units are set to supplement the temperature monitoring during the curing exothermic process, thereby obtaining sufficient multi-source detection historical data.

[0023] In some embodiments, acquiring multi-source testing historical data about the wind turbine blade mold under test includes: A unified timestamp is added to the data collected by the fiber Bragg grating sensor and the temperature sensing unit to obtain the corresponding time-series data; Interpolation or resampling is performed on the time series data to map time series data with different sampling frequencies onto the same time axis, forming synchronized multi-source detection historical data.

[0024] In this embodiment, historical data from multi-source detection is organized and managed hierarchically and uniformly. By analyzing the temporal correlation of data from different measurement points on the same optical fiber, the position and propulsion velocity of the resin flow front are determined. Simultaneously, combined with the temperature variation characteristics of different regions, spatially correlated input data is provided for state inversion in the subsequent digital twin model. Here, a highly efficient timestamp-based synchronization algorithm is employed to ensure data consistency and synchronization between different modules, effectively preventing data inconsistencies caused by network latency or transmission errors.

[0025] In some embodiments, the historical center reflection wavelength sequence includes a first center reflection wavelength sequence and a second center reflection wavelength sequence; determining the historical resin leading edge position and historical resin propulsion speed of the wind turbine blade mold under test based on multi-source detection historical data includes: The distinction threshold is determined based on the first central reflection wavelength sequence when resin impregnation has not occurred; The second historical center reflection wavelength sequence at the time of resin impregnation is processed by first-order difference, and the moment when the reflection wavelength at the measuring point first exceeds the discrimination threshold is determined as the impregnation moment, thus obtaining the resin impregnation time sequence corresponding to multiple measuring points. The historical resin front position and historical resin propagation speed were determined based on the positional distance relationship of multiple measuring points and the resin impregnation time series.

[0026] For example, each piece of collected data is appended with a unique timestamp. And by using interpolation or resampling, data with different sampling frequencies are mapped to the same time axis to form a synchronized dataset: ; in, Indicates the first At time 1, the fiber Bragg grating (FBG) measurement points are The reflected wavelength, Indicates the first Temperature values ​​at each temperature measuring point.

[0027] When the resin front reaches a certain FBG measurement point, the thermo-mechanical-optical coupling environment changes abruptly due to the change in the medium surrounding the fiber from air to resin, resulting in a significant change in the grating reflection wavelength. First-order differential processing is performed on the FBG wavelength sequence:

[0028] ; when Exceeding the preset threshold At that time, the resin front is determined to be at time [time missing]. Reaching the location of the measuring point: ; This yields the resin wetting time series for each measuring point: .

[0029] Select a time interval during which no resin impregnation occurred: ; Perform a first-order difference on the wavelength sequence within this time period: ; The standard deviation is used as the statistical characteristic of this difference series: ; in, This represents the number of sampling points.

[0030] The discrimination threshold is defined as a multiple of the standard deviation: ,like Select .

[0031] The arrival time of the resin front at each measuring point can be obtained from the above. The FBG wavelength sequence was processed by first-order difference to obtain Given a distinguishing threshold The arrival time is the moment when the condition is first met. ; exist It continues to be established internally.

[0032] This results in a set of discrete data points: and discrete Transform into a continuous frontier function .

[0033] In some embodiments, determining the historical resin front position and historical resin propagation speed based on the positional distance relationship of multiple measuring points and the resin wetting time series includes: Obtain the first and second immersion times corresponding to the latest two adjacent measuring points that are immersed and those that are not yet immersed, respectively. The historical resin front position and historical resin propagation speed are determined based on the first coordinate of the latest wetted measuring point, the second coordinate of the adjacent measuring point that has not yet been wetted, the first wetting time, the second wetting time, and the current time.

[0034] In this embodiment, at any time The resin front is located between two adjacent measuring points that have just been wetted and those that have not yet been wetted.

[0035] Set at time satisfy: This indicates that the resin front is at and between.

[0036] The leading edge position is obtained through linear interpolation: ; in, It is the first The coordinates of each measuring point in the main flow direction of the mold.

[0037] Based on the spatial coordinates of each FBG measurement point With corresponding soaking time Construct the state variables of the resin flow front propulsion velocity: ; Simultaneously, the internal temperature field state quantity of the mold is constructed by combining temperature sensor data. This forms the set of state variables used as input for the initial resin flow model: ; in, Indicates the position of the resin front.

[0038] S120: A three-dimensional resin model is created based on the geometric dimensions of the wind turbine blade mold to be tested. Resin material parameters and resin process parameters are introduced into the three-dimensional resin model to simulate the resin flow process. Combined with temperature state parameters, an initial resin flow model is constructed.

[0039] In some embodiments, resin material parameters and resin process parameters are introduced into the three-dimensional resin model to simulate the resin flow process. Combined with temperature state parameters, an initial resin flow model is constructed, including: By incorporating temperature state parameters into the curing kinetics model, the degree of resin curing at multiple temperature values ​​is determined, and a resin curing degree function is constructed. Resin material parameters and resin process parameters are introduced into a three-dimensional resin model to simulate the resin flow process, and the resin curing degree function is used for optimization to obtain an initial resin flow model.

[0040] In this embodiment, the resin flow process can be described using an equivalent seepage model, the basic form of which is: ; In the formula, This refers to the equivalent permeability, corresponding to the resin process parameters. This refers to the resin viscosity, corresponding to the resin material parameters. This represents the pressure gradient.

[0041] Based on temperature state variables The degree of resin curing function was calculated using a curing kinetic model. : ; This is a temperature-dependent reaction rate constant that varies with temperature.

[0042] ; in, This is the pre-exponential factor, i.e., the frequency factor. As the apparent activation energy, This is the gas constant, which is 8.314 J / (mol·K). This refers to absolute temperature.

[0043] During the simulation, the curing state dynamically affects the resistance to resin flow; therefore, it is necessary to incorporate the resin curing degree function. Coupled with an equivalent seepage model, this allows for more accurate prediction of resin flow variations. On one hand, in the twin model simulating resin flow in the wind turbine blade mold under test—the initial resin flow model—the temperature state quantity... It will affect the curing reaction rate Resin curing degree function By adjusting the resin's flowability through feedback, the resin flow simulation is made more closely resemble real-world working conditions. On the other hand, flow parameters, such as permeability, are adjusted through the degree of cure. This, in turn, affects the speed of advancement at the front, achieving a two-way coupling effect.

[0044] Penetration It can be represented as: ; in, It is a curing correction factor, indicating that the higher the degree of curing, the worse the fluidity.

[0045] S130, input the multi-source detection historical data into the initial resin flow model to generate the predicted front position and predicted propulsion velocity, and correct the parameters of the initial resin flow model based on the first difference between the predicted front position and the historical resin front position and the second difference between the predicted propulsion velocity and the historical resin propulsion velocity to obtain the target resin flow model.

[0046] In some embodiments, the parameters of the initial resin flow model are corrected based on a first difference between the predicted resin front position and the historical resin front position, and a second difference between the predicted propulsion velocity and the historical resin propulsion velocity, to obtain a target resin flow model, including: If the first difference is greater than the first threshold, or the second difference is greater than the second threshold, the permeability parameters of the initial resin flow model are corrected based on the first and second differences to obtain the target resin flow model.

[0047] Taking the first difference corresponding to the position of the resin front as an example, calculate the first difference of the resin front at the current time. ,in, This represents the frontier position predicted by the model.

[0048] If the first difference Exceeding the preset threshold The flow parameters in the model are then corrected using the following formula. : ; in, The correction coefficient represents the adjustment range of the control parameters.

[0049] Through continuous calibration, the model can be dynamically adjusted based on measured data, thereby improving prediction accuracy and ensuring that the simulation results better match actual working conditions. The principle of using the second difference to correct the permeability parameters of the initial resin flow model is the same as that of the first difference, and will not be repeated here.

[0050] In some embodiments, the target resin flow model includes multiple sub-models disposed in different sub-regions; the permeability parameters of the initial resin flow model are corrected based on a first difference and a second difference to obtain the target resin flow model, including: When the resin front enters the target sub-region, the permeability parameters of the sub-model corresponding to the target sub-region are corrected based on the first difference and the second difference; the target sub-region can be any one of multiple sub-regions.

[0051] In this embodiment, the mold is divided into multiple target sub-regions. Each target sub-region has an independent sub-model. The calculation of that sub-model is only triggered when the resin front enters a target sub-region or when the FBG sensor data in that region changes significantly. For example, if the resin front position... Reach the target sub-region This will trigger an update of the twin model for that region:

[0052] ; For target sub-regions that have not yet been updated, the calculation results from the previous time step are used to avoid unnecessary computation and resource waste. This mechanism not only improves real-time performance but also allows for flexible adjustment of the calculation frequency for different working conditions in different regions of the mold, ensuring that efficiency is improved without compromising accuracy.

[0053] S140 inputs the multi-source real-time detection data of the wind turbine blade mold to be tested into the target resin flow model to generate the corresponding resin state parameters; the resin state parameters include the current resin front position, resin propulsion speed, temperature distribution and curing state.

[0054] Here, multi-source real-time detection data from the wind turbine blade mold under test is input into the target resin flow model to generate corresponding resin state parameters, enabling automatic determination of the resin front arrival time and resin propulsion speed. If a monitoring point fails to detect a resin wetting signal for an extended period or the resin front propulsion speed is significantly lower than expected, a stagnation warning is triggered, indicating potential risks of dry spots or insufficient local penetration.

[0055] In some embodiments, please refer to Figure 2 , Figure 2 This is a schematic diagram of a wind turbine blade resin flow prediction system based on digital twins, provided in an embodiment of the present invention. The present invention provides a wind turbine blade resin flow prediction system 200 based on digital twins, comprising: a data acquisition module 210, a model creation module 220, a model correction module 230, and a parameter prediction module 240; wherein,

[0056] The data acquisition module 210 is configured to acquire multi-source detection historical data about the wind turbine blade mold under test, and determine the historical resin leading edge position and historical resin propulsion speed of the wind turbine blade mold under test based on the multi-source detection historical data; the multi-source detection historical data includes the historical center reflection wavelength sequence detected by the fiber Bragg grating sensor and the historical temperature change sequence detected by the temperature sensing unit. The model creation module 220 is configured to create a three-dimensional resin model based on the geometric dimensions of the wind turbine blade mold to be tested, and to introduce resin material parameters and resin process parameters into the three-dimensional resin model to simulate the resin flow process. Combined with temperature state parameters, an initial resin flow model is constructed. The model correction module 230 is configured to input multi-source detection historical data into the initial resin flow model to generate the predicted front position and predicted propulsion velocity, and to correct the parameters of the initial resin flow model based on the first difference between the predicted front position and the historical resin front position and the second difference between the predicted propulsion velocity and the historical resin propulsion velocity, so as to obtain the target resin flow model. The parameter prediction module 240 is configured to input the multi-source detection real-time data of the wind turbine blade mold under test into the target resin flow model to generate the corresponding resin state parameters. The resin state parameters include the current resin front position, resin propulsion speed, temperature distribution and curing state.

[0057] In some embodiments, the data acquisition module 210 is specifically configured as follows: A unified timestamp is added to the data collected by the fiber Bragg grating sensor and the temperature sensing unit to obtain the corresponding time-series data; Interpolation or resampling is performed on the time series data to map time series data with different sampling frequencies onto the same time axis, forming synchronized multi-source detection historical data.

[0058] In some embodiments, the historical center reflection wavelength sequence includes a first center reflection wavelength sequence and a second center reflection wavelength sequence; the data acquisition module 210 is specifically configured as follows: The distinction threshold is determined based on the first central reflection wavelength sequence when resin impregnation has not occurred; The second historical center reflection wavelength sequence at the time of resin impregnation is processed by first-order difference, and the moment when the reflection wavelength at the measuring point first exceeds the discrimination threshold is determined as the impregnation moment, thus obtaining the resin impregnation time sequence corresponding to multiple measuring points. The historical resin front position and historical resin propagation speed were determined based on the positional distance relationship of multiple measuring points and the resin impregnation time series.

[0059] In some embodiments, the data acquisition module 210 is specifically configured as follows: Obtain the first and second immersion times corresponding to the latest two adjacent measuring points that are immersed and those that are not yet immersed, respectively. The historical resin front position and historical resin propagation speed are determined based on the first coordinate of the latest wetted measuring point, the second coordinate of the adjacent measuring point that has not yet been wetted, the first wetting time, the second wetting time, and the current time.

[0060] In some embodiments, the model creation module 220 is configured as follows: By incorporating temperature state parameters into the curing kinetics model, the degree of resin curing at multiple temperature values ​​is determined, and a resin curing degree function is constructed. Resin material parameters and resin process parameters are introduced into a three-dimensional resin model to simulate the resin flow process, and the resin curing degree function is used for optimization to obtain an initial resin flow model.

[0061] In some embodiments, the model correction module 230 is specifically configured to include: If the first difference is greater than the first threshold, or the second difference is greater than the second threshold, the permeability parameters of the initial resin flow model are corrected based on the first and second differences to obtain the target resin flow model.

[0062] In some embodiments, the model correction module 230 is specifically configured as follows: When the resin front enters the target sub-region, the permeability parameters of the sub-model corresponding to the target sub-region are corrected based on the first difference and the second difference; the target sub-region can be any one of multiple sub-regions.

[0063] It should be noted that the wind turbine blade resin flow prediction system based on digital twins provided in this application embodiment and the wind turbine blade resin flow prediction method based on digital twins provided in this application embodiment are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned wind turbine blade resin flow prediction method based on digital twins, and the repeated parts will not be described again.

[0064] In some embodiments, please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 300 provided in this application includes a processor 310 and a memory 320; the memory 320 stores a computer program, wherein the computer program, when executed by the processor, implements the aforementioned method for predicting resin flow in wind turbine blades based on digital twins.

[0065] Specifically, processor 310 may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. Processor 310 may also include onboard memory for caching purposes. Processor 310 may be a single processing unit or multiple processing units for performing different actions of the method flow according to embodiments of this application.

[0066] The memory 320 may be any medium capable of containing, storing, transmitting, propagating, or transmitting instructions. For example, the memory 320 may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, apparatuses, or propagation media. Specific examples of the memory 320 include: magnetic storage devices such as magnetic tape or hard disk drives (HDDs); optical storage devices such as optical discs (CD-ROMs); and may also be random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0067] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the aforementioned method for predicting resin flow in wind turbine blades based on digital twins. This computer-readable medium may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into that device / apparatus / system. The aforementioned computer-readable medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0068] According to embodiments of this application, a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, optical fiber, radio frequency signals, etc., or any suitable combination thereof.

[0069] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application. Therefore, the scope of this application should not be limited to the above embodiments, but should be defined not only by the appended claims, but also by their equivalents. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the protection scope of this invention.

Claims

1. A method for predicting resin flow in wind turbine blades based on digital twins, characterized in that, include: The system acquires multi-source historical detection data about the mold of the wind turbine blade under test, and determines the historical resin leading edge position and historical resin propulsion speed of the mold based on the multi-source historical detection data. The multi-source historical detection data includes the historical center reflection wavelength sequence detected by the fiber Bragg grating sensor and the historical temperature change sequence detected by the temperature sensing unit. A three-dimensional resin model is created based on the geometric dimensions of the wind turbine blade mold to be tested. Resin material parameters and resin process parameters are introduced into the three-dimensional resin model to simulate the resin flow process. Combined with temperature state parameters, an initial resin flow model is constructed. The multi-source detection historical data is input into the initial resin flow model to generate the predicted front position and predicted propulsion velocity. The parameters of the initial resin flow model are then corrected based on the first difference between the predicted front position and the historical resin front position and the second difference between the predicted propulsion velocity and the historical resin propulsion velocity to obtain the target resin flow model. The multi-source real-time detection data of the wind turbine blade mold under test is input into the target resin flow model to generate corresponding resin state parameters; the resin state parameters include the current resin front position, resin propulsion speed, temperature distribution and curing state.

2. The method for predicting resin flow in wind turbine blades based on digital twins as described in claim 1, characterized in that, The acquisition of multi-source historical testing data on the wind turbine blade mold under test includes: A unified timestamp is added to the data collected by the fiber Bragg grating sensor and the temperature sensing unit to obtain the corresponding time-series data; The time-series data is interpolated or resampled to map the time-series data with different sampling frequencies onto the same time axis, forming synchronized multi-source detection historical data.

3. The method for predicting resin flow in wind turbine blades based on digital twins as described in claim 1, characterized in that, The historical center reflection wavelength sequence includes a first center reflection wavelength sequence and a second center reflection wavelength sequence; determining the historical resin leading edge position and historical resin propulsion speed of the wind turbine blade mold under test based on the multi-source detection historical data includes: The distinction threshold is determined based on the first central reflection wavelength sequence when resin impregnation has not occurred; The second historical center reflection wavelength sequence at the time of resin impregnation is processed by first-order difference processing. The moment when the reflection wavelength at the measuring point first exceeds the distinction threshold is determined as the impregnation moment, and the resin impregnation time sequence corresponding to multiple measuring points is obtained. The historical resin front position and the historical resin propagation speed are determined based on the positional distance relationship of multiple measuring points and the resin impregnation time series.

4. The method for predicting resin flow in wind turbine blades based on digital twins as described in claim 3, characterized in that, The determination of the historical resin front position and the historical resin propagation speed based on the positional distance relationship of multiple measuring points and the resin impregnation time series includes: Obtain the first and second immersion times corresponding to the latest two adjacent measuring points that are immersed and those that are not yet immersed, respectively. The historical resin front position and the historical resin propulsion speed are determined based on the first coordinate of the latest immersed measuring point, the second coordinate of the adjacent measuring point that has not yet been immersed, the first immersion time, the second immersion time, and the current time.

5. The method for predicting resin flow in wind turbine blades based on digital twins as described in claim 1, characterized in that, The process of introducing resin material parameters and resin process parameters into the three-dimensional resin model to simulate the resin flow process, combined with temperature state parameters, constructs an initial resin flow model, including: By incorporating temperature state parameters into the curing kinetics model, the degree of resin curing at multiple temperature values ​​is determined, and a resin curing degree function is constructed. Resin material parameters and resin process parameters are introduced into the three-dimensional resin model to simulate the resin flow process, and the resin curing degree function is used for optimization to obtain an initial resin flow model.

6. The method for predicting resin flow in wind turbine blades based on digital twins as described in claim 1, characterized in that, The process of correcting the parameters of the initial resin flow model based on a first difference between the predicted resin front position and the historical resin front position, and a second difference between the predicted propulsion velocity and the historical resin propulsion velocity, to obtain the target resin flow model, includes: If the first difference is greater than the first threshold, or the second difference is greater than the second threshold, the permeability parameters of the initial resin flow model are corrected based on the first difference and the second difference to obtain the target resin flow model.

7. The method for predicting resin flow in wind turbine blades based on digital twins as described in claim 6, characterized in that, The target resin flow model includes multiple sub-models set in different sub-regions; The step of correcting the permeability parameters of the initial resin flow model based on the first difference and the second difference to obtain the target resin flow model includes: When the resin front enters the target sub-region, the permeability parameters of the sub-model corresponding to the target sub-region are corrected based on the first difference and the second difference; The target sub-region can be any one of multiple sub-regions.

8. A wind turbine blade resin flow prediction system based on digital twins, characterized in that, include: The system includes a data acquisition module, a model creation module, a model correction module, and a parameter prediction module; among which, The data acquisition module is configured to acquire multi-source detection historical data about the wind turbine blade mold under test, and determine the historical resin leading edge position and historical resin propulsion speed of the wind turbine blade mold under test based on the multi-source detection historical data; the multi-source detection historical data includes the historical center reflection wavelength sequence detected by the fiber Bragg grating sensor and the historical temperature change sequence detected by the temperature sensing unit. The model creation module is configured to create a three-dimensional resin model based on the geometric dimensions of the wind turbine blade mold to be tested, and to introduce resin material parameters and resin process parameters into the three-dimensional resin model to simulate the resin flow process. Combined with temperature state parameters, an initial resin flow model is constructed. The model correction module is configured to input the multi-source detection historical data into the initial resin flow model to generate a predicted front position and a predicted propulsion velocity, and to correct the parameters of the initial resin flow model based on a first difference between the predicted front position and the historical resin front position and a second difference between the predicted propulsion velocity and the historical resin propulsion velocity, so as to obtain a target resin flow model. The parameter prediction module is configured to input the multi-source real-time detection data of the wind turbine blade mold under test into the target resin flow model to generate corresponding resin state parameters; the resin state parameters include the current resin front position, resin propulsion speed, temperature distribution and curing state.

9. An electronic device comprising a processor and a memory; said memory storing a computer program, wherein, When executed by the processor, the computer program implements the method for predicting resin flow in wind turbine blades based on digital twins as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, It stores a computer program, wherein the computer program, when executed by a processor, implements the method for predicting resin flow in wind turbine blades based on digital twins as described in any one of claims 1 to 7.

Images