AI-enhancement-based real-time hybrid test method and system for aerodynamic load of floating fan

Abstract

The invention discloses a floating fan aerodynamic load real-time mixing test method and system based on AI enhancement, and the method comprises the steps: calculating the six-degree-of-freedom motion information of a floating foundation through a numerical calculation model based on a real-time floating foundation kinetic equation; the method comprises the following steps: carrying a reduced-scale fan model on a six-degree-of-freedom motion platform, placing the six-degree-of-freedom motion platform on a wind tunnel atmospheric boundary layer, controlling the six-degree-of-freedom motion platform based on floating foundation six-degree-of-freedom motion information, driving the reduced-scale fan model to move, generating an aerodynamic load in a simulated wind environment, measuring an original load signal, and correcting the original load signal. Synchronously recording the actual pose of the six-degree-of-freedom platform; and AI correction is carried out on the corrected load signal and the actual pose of the six-degree-of-freedom platform to obtain a net aerodynamic load, the net aerodynamic load is fed back to the numerical calculation model, and closed-loop updating is carried out to realize coupling circulation. According to the method, the problem of interaction between numerical values and physical boundaries is solved, and the test precision of the large floating fan under the complex environment load can be remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the field of floating wind power technology and relates to a real-time hybrid test method and system for aerodynamic loads of floating wind turbines based on AI enhancement. The method is mainly used for high-precision verification of the full coupling of pneumatics, servo, hydrodynamics and mooring of large floating wind turbines under different working conditions. Background Art

[0002] Floating wind turbines are a key technology for the development of offshore wind power in deepwater areas, but their complex coupled dynamic characteristics (aerodynamics-servo-hydrodynamics-mooring) pose a huge challenge to traditional experimental methods. In the field of floating wind turbine design and analysis, existing numerical simulation methods are difficult to take into account both aerodynamic-hydrodynamic coupled response and large-scale time-domain response analysis. Using only numerical simulation methods, it is difficult to interpret the complex multi-physics characteristics of offshore wind power at different spatial and temporal scales. With the rapid development of offshore wind power, wind turbine design has gradually become larger and more complex. The bending-torsion coupling effect of the long and flexible blades of large wind turbines, the axial expansion effect under large deformation, blade flutter, and the negative damping effect within the impeller surface have become more significant. These effects lead to problems such as structural fatigue and increased difficulty in servo control. It is necessary to more accurately obtain the aerodynamic loads of the wind turbine and consider the aeroelastic response characteristics of the wind turbine. Design methods based on engineering experience and predictive numerical tools need to be continuously calibrated based on experimental data to ensure their reliability and effectiveness. Full-scale experiments are not feasible due to experimental conditions and cost constraints. Therefore, accurate and reliable wind tunnel experiments on large-scale wind turbine models can not only calibrate wind turbine parameters, but also further improve the reliability of the design.

[0003] The current wind tunnel test technology for scaled models of large wind turbines still has many shortcomings. Although pure physical model tests can reflect the real environment, they are limited by the scale ratio effect, and the aerodynamic load simulation is distorted. The current mainstream hybrid test methods mostly use one-way coupling, that is, only the numerically calculated load is applied to the physical model for simple numerical calculation verification. A real-time feedback loop of the physical response is not established, resulting in the inability to dynamically correct the hydrodynamic model. In addition, the calculation of aerodynamic loads in existing technologies mostly relies on direct measurement of six-component force sensors, but sensor noise and six-degree-of-freedom platform response delays will lead to load decoupling errors, which cannot meet high-precision requirements.

[0004] Based on the above considerations, there is an urgent need to develop a bidirectional real-time coupled hybrid test method to dynamically modify the numerical model through the corrected physical response data, break through the bottleneck of scale effect and nonlinear load simulation, and provide a highly reliable test verification method for the design of large floating wind turbines. Summary of the Invention

[0005] To address the existing challenges of one-way coupling, which cannot be corrected in real time, and traditional HIL hardware delays that can cause distortion in aerodynamic load measurement, this paper provides an AI-enhanced real-time hybrid test method and system for aerodynamic loads on floating wind turbines. This method offers greater accuracy in multi-physics field verification of large floating wind turbines, and more efficient iterative optimization.

[0006] The technical solution adopted in the present invention is as follows:

[0007] A real-time hybrid test method for aerodynamic loads of a floating wind turbine based on AI enhancement includes the following steps:

[0008] Based on the real-time floating foundation dynamic equations, a numerical calculation model is used to simulate the floating body's six-degree-of-freedom motion, wave loads, and mooring system response, and calculate the floating foundation's six-degree-of-freedom motion information;

[0009] A scaled wind turbine model is mounted on a six-degree-of-freedom motion platform and placed in the atmospheric boundary layer of a wind tunnel. The six-degree-of-freedom motion information of the floating foundation is used to obtain position and posture instructions to control the six-degree-of-freedom motion platform, drive the scaled wind turbine model to move, generate aerodynamic loads in a simulated wind environment, measure the original load signals and make corrections, and simultaneously record the actual position and posture of the six-degree-of-freedom platform.

[0010] AI correction is performed on the corrected load signal and the actual position of the six-degree-of-freedom platform. The net aerodynamic load is obtained based on the correction result, and the net aerodynamic load is fed back to the numerical calculation model, and a closed-loop update is implemented to realize the coupling cycle.

[0011] Furthermore, the wave load includes hydrodynamic load and hydrostatic restoring force. The hydrodynamic load is composed of radiation force, viscous force and diffraction force. The hydrostatic restoring force is solved using a linearized model. The mooring system adopts a lumped mass model and solves the mooring tension through real-time integration.

[0012] Furthermore, the scaled wind turbine model tower base is provided with a six-component force sensor to measure the original load signal, and the nacelle is provided with an acceleration sensor to measure the hub center height acceleration, and the original load signal is corrected according to the hub center height acceleration.

[0013] Furthermore, the AI ​​correction includes noise suppression on the corrected load signal and delay compensation on the actual posture of the six-degree-of-freedom platform.

[0014] Furthermore, the noise suppression step specifically includes: decomposing the modified load signal by using wavelet packet transform, automatically identifying the noise dominant frequency band and applying adaptive threshold filtering to obtain a noise-reduced load signal.

[0015] Furthermore, the specific steps of the delay compensation include: inputting the actual posture sequence of the six-degree-of-freedom platform, learning the motion characteristics of the six-degree-of-freedom motion platform based on the LSTM network model, and outputting the compensated posture of the six-degree-of-freedom platform.

[0016] Furthermore, obtaining the net aerodynamic load according to the correction result specifically includes: calculating the compensation force according to the compensation posture of the six-degree-of-freedom platform, and calculating the net aerodynamic load according to the load signal after noise reduction of the compensation force.

[0017] An AI-enhanced real-time hybrid test system for aerodynamic loads on floating wind turbines, used to implement the above method, includes:

[0018] Numerical subsystem: used to simulate the six-degree-of-freedom motion of the floating body, wave loads and mooring system response based on the real-time floating foundation dynamic equations using numerical calculation models, calculate the six-degree-of-freedom motion information of the floating foundation, and generate posture instructions based on the six-degree-of-freedom motion information of the floating foundation;

[0019] Physics subsystem: Used to mount the scaled wind turbine model on a six-degree-of-freedom motion platform and place it in the wind tunnel's atmospheric boundary layer. The six-degree-of-freedom motion platform is controlled according to position and posture commands to drive the scaled wind turbine model to move. It generates aerodynamic loads in a simulated wind environment, measures and corrects the raw load signals, and simultaneously records the actual position and posture of the six-degree-of-freedom platform.

[0020] AI correction module: used to perform AI correction on the corrected load signal and the actual position of the six-degree-of-freedom platform, obtain the net aerodynamic load based on the correction result, feed the net aerodynamic load back to the numerical calculation model, and implement a closed-loop update to achieve a coupled cycle.

[0021] A computer device, comprising:

[0022] one or more processors;

[0023] a memory for storing one or more programs;

[0024] When the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned AI-enhanced real-time hybrid test method for aerodynamic loads of floating wind turbines.

[0025] A computer-readable storage medium storing computer instructions, when the computer instructions are executed by one or more processors, causes the one or more processors to perform the steps in the above method.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The AI-enhanced real-time hybrid test method and system for aerodynamic loads of floating wind turbines provided by the present invention can be used for high-precision verification of the full coupling of pneumatics, servo, hydrodynamics and mooring of floating wind turbines under different working conditions, and to build a fully closed-loop bidirectional coupling system, that is, to establish a bidirectional real-time feedback channel of "numerical instructions → physical execution" and "physical response → numerical model correction", dynamically iterate to convergence, break through the limitations of traditional one-way coupling, and significantly improve the test fidelity; AI correction solves the problems of sensor noise and hardware delay, decouples the aerodynamic load and continuously reduces the RMSE, significantly improving the data credibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 1 is a flow chart of a method in an embodiment of the present invention.

[0029] Figure 2 Schematic diagram of the physical subsystem principle in an embodiment of the present invention.

[0030] Figure 3 Schematic diagram of the numerical subsystem principle in an embodiment of the present invention.

[0031] Figure 4 Schematic diagram of the AI ​​correction module in an embodiment of the present invention.

[0032] Figure 5 Schematic diagram of the noise suppression processing unit in an embodiment of the present invention.

[0033] Figure 6 Schematic diagram of the delay compensation unit in an embodiment of the present invention.

[0034] Figure 7 This is a comparison chart of the dynamic response differences of the floating wind turbine platform under surge (Surge) based on the AI-enhanced real-time hybrid test method for aerodynamic loads of floating wind turbines (HIL-AI) in an embodiment of the present invention and the FAST numerical model. DETAILED DESCRIPTION

[0035] The technical solution of the present invention will be further explained in detail below with reference to the accompanying drawings and specific embodiments.

[0036] A real-time hybrid test method for aerodynamic loads of a floating wind turbine based on AI enhancement includes the following steps:

[0037] Based on the real-time dynamic equations of the floating foundation, a numerical calculation model is used to simulate the floating body's six-degree-of-freedom motion, wave loads, and mooring system response, and calculate the floating foundation's six-degree-of-freedom motion information. The wave loads include hydrodynamic loads and hydrostatic restoring forces, which are composed of radiation, viscous, and diffraction forces. The hydrostatic restoring forces are solved using a linearized model. The mooring system uses a lumped mass model, and the mooring tension is solved through real-time integration.

[0038] A scaled wind turbine model was mounted on a six-degree-of-freedom motion platform and placed in the wind tunnel's atmospheric boundary layer. The six-degree-of-freedom motion information from the floating foundation was used to obtain positional commands to control the six-degree-of-freedom motion platform, driving the scaled wind turbine model and generating aerodynamic loads in a simulated wind environment. A six-component force sensor was installed at the tower base of the scaled wind turbine model to measure the raw load signal, and an accelerometer was installed in the nacelle to measure the hub center height acceleration. The raw load signal was corrected based on the hub center height acceleration, and the actual position of the six-degree-of-freedom platform was simultaneously recorded.

[0039] AI correction is performed on the corrected load signal and the actual position of the six-degree-of-freedom platform. The net aerodynamic load is obtained based on the correction result, and the net aerodynamic load is fed back to the numerical calculation model, and a closed-loop update is implemented to realize the coupling cycle.

[0040] The AI ​​correction includes noise suppression of the corrected load signal and delay compensation of the actual posture of the six-degree-of-freedom platform. The specific steps of noise suppression include: decomposing the corrected load signal using wavelet packet transform, automatically identifying the dominant frequency band of noise and applying adaptive threshold filtering to obtain a noise-reduced load signal. The specific steps of delay compensation include: inputting the actual posture sequence of the six-degree-of-freedom platform, learning the motion characteristics of the six-degree-of-freedom motion platform based on the LSTM network model, and outputting the compensated posture of the six-degree-of-freedom platform to offset the response lag of the six-degree-of-freedom platform. The compensation force is then calculated based on the compensated posture of the six-degree-of-freedom platform, and the net aerodynamic load is calculated based on the load signal after noise reduction due to the compensation force.

[0041] In another embodiment of the present invention, a real-time hybrid test system for aerodynamic loads of floating wind turbines based on AI enhancement is provided for implementing the above method. The flow chart is as follows: Figure 1 The system includes a numerical subsystem, a physical subsystem, and an AI correction module. During initialization, the numerical subsystem uses a numerical calculation model to simulate the six-degree-of-freedom motion of the floating body, wave loads, and mooring system response, solves the six-degree-of-freedom dynamic equations of the floating foundation in real time, outputs the six-degree-of-freedom motion information of the floating foundation, and generates the six-degree-of-freedom platform posture command q s .

[0042] The six-degree-of-freedom dynamic equation of the floating foundation is:

[0043]

[0044] Among them, F hst is the hydrostatic restoring force, F moor is the mooring tension, F hydro is the hydrodynamic load, F aero is the net aerodynamic load.

[0045] like Figure 3 As shown in Figure 1, the external forces acting on the 6DOF platform consist of three components: hydrostatic restoring force, mooring force, and hydrodynamic load. The hydrostatic restoring force is generated by the balance between buoyancy and gravity, and is solved using a linearized model. The mooring force uses a lumped mass model to discretize the mooring cable. By coupling the solution with the platform dynamics model, the dynamic response of the anchor chain is calculated in real time to obtain the mooring tension. The hydrodynamic load consists of radiation force, viscous force, and diffraction force, and is calculated as follows:

[0046] F hydro =F rad +F visc +F diff

[0047] Among them, F rad is the radiation force, obtained by solving the platform velocity and delay matrix; F visc is the viscous force, which is calculated using semi-empirical formulas such as the Morrison equation; F diff To calculate the diffraction force, the frequency domain transfer function is obtained by pre-simulating the three-dimensional panel method, and then solved in real time by combining the wave power spectrum density. Figure 2 As shown in the figure, the physical subsystem uses a scaled wind turbine model to place it in the atmospheric boundary layer of the wind tunnel, and uses a six-degree-of-freedom platform to send the posture command q s The aerodynamic load is generated in the wind tunnel by converting the spatial motion of the scaled wind turbine model into a six-component force sensor at the tower base of the scaled wind turbine model to measure the original load signal F. bal , an acceleration sensor is installed in the scaled wind turbine model cabin to measure the hub center height acceleration a hub Due to the weight limit of the nacelle mechanical structure, in most cases the mass of the scaled model blade-hub-nacelle will exceed the theoretical value of the scaled calculation, which will introduce additional inertia force into the structural load and require inertia force correction. The corrected tower base six-component load signal The calculation method is:

[0048]

[0049] in, It is the original load signal measured by the six-component force sensor on the tower base. is the corrected tower base six-component load signal, is the hub center height acceleration vector, M model and M0 are the actual inertia tensor of the scaled wind turbine model and the theoretical inertia tensor calculated based on the scaled prototype, respectively.

[0050] The actual position q of the six-degree-of-freedom platform is recorded synchronously, and the read data is transmitted to the AI ​​correction module.

[0051] like Figure 4The figure shows the principle diagram of AI correction module. AI correction module adopts multi-source data fusion to synchronously receive the corrected load signal read by the physical subsystem. And the actual position q of the six-degree-of-freedom platform, and then the corrected load signal is corrected by the noise suppression unit Perform wavelet packet decomposition, automatically identify the noise-dominant frequency band, and apply adaptive threshold filtering to obtain the de-noised load signal; use the delay compensation unit based on the LSTM network to predict the displacement of the future Δt time, generate compensation posture instructions to compensate for the response lag of the six-degree-of-freedom platform, and obtain the compensation posture of the six-degree-of-freedom platform.

[0052] Figure 5 The figure shows the principle diagram of the noise suppression processing unit in this embodiment. The noise suppression processing uses wavelet packet transform to transform the modified load signal Decompose into 32 sub-bands and obtain the coefficient C of each band i (t) (i = 1, 2, ..., 32); automatically identify the noise-dominant frequency band and calculate the energy proportion of each frequency band:

[0053]

[0054] Among them, C i (t) is the wavelet packet coefficient sequence of the ith sub-band, C k (t) is the coefficient sequence of the kth sub-band after wavelet packet decomposition.

[0055] Sort the frequency bands from high to low and perform energy accumulation Among them, m is the frequency band number of the cumulative cutoff (accumulated from the front to the back to the mth frequency band), j is the frequency band traversal index (the number after sorting from high to low frequency), E j is the energy proportion of the jth frequency band after sorting.

[0056] When E cum When (m)>η, the first m high-frequency bands are determined to be noise-dominated bands (η is the energy accumulation threshold, which can be adaptively adjusted according to the signal characteristics); adaptive threshold filtering is performed on the noise-dominated bands (threshold σ is the noise standard deviation, N is the signal length); output the load signal after noise reduction F bal_clean .

[0057] Figure 6 The schematic diagram of the delay compensation unit in this embodiment shows a working mechanism of the delay compensation unit based on LSTM, which is used for response lag compensation of the six-degree-of-freedom platform. The LSTM network model receives a historical pose sequence [q t-2Δt ,qt-Δt ,q t ] as input, the platform motion features are learned through the LS TM network model to predict the future position at t+Δt Where Δt is dynamically determined by the platform response delay characteristics.

[0058] The core processing of the LSTM network model includes three key steps:

[0059] First, the gate mechanism is calculated, the forget gate f t =σ(W f ·[h t-1 ,q t ]+b f Determines the proportion of historical information retained (0 = completely forgotten, 1 = completely retained), where σ is the Sigmoid activation function, W f is the weight matrix of the forget gate (f is a special parameter indicating that this parameter belongs to the forget gate), h t-1 is the hidden state at the previous moment, q t is the actual position input vector of the six-degree-of-freedom platform at the current moment, b f is the bias vector of the forget gate; vector input gate i t =σ(W i ·[h t-1 ,q t ]+b i ) controls the degree of updating of new information, where W i is the weight matrix of the vector input gate (i is a special parameter indicating that the parameter belongs to the vector input gate), b i Bias vector for the vector input gate; candidate state Where tanh is the hyperbolic tangent activation function, W c is the weight matrix of the candidate state (c is a special parameter indicating that the parameter belongs to the candidate state), b c is the bias vector of the candidate state. Next is the state update, cell state where f t is the forget gate of the current time step, C t-1 is the cell state at the previous time step, i t is the input step of the current time step, is the candidate cell state of the current time step; fuses historical and current information, output gate o t =σ(W o ·[h t-1 ,q t ]+b o ) adjust the output ratio, W o is the weight matrix of the output gate, o is a dedicated parameter indicating that the parameter belongs to the output gate), b ois the bias vector of the output gate; hidden state Generate the current moment output (including compressed memory information), where o t is the output gate of the current time step, C t is the cell state at the current time step; the loop processes three time steps (t-2Δt→t-Δt→t), where Δt is the time step, and the final output h t 、C t Save as a new initial state for prediction calculations in subsequent time steps, and finally get the predicted pose The calculation formula is as follows:

[0060]

[0061] Where g is a nonlinear activation function, W out is the weight matrix of the output layer (usually a two-dimensional matrix), h t To represent the hidden state of the current time step, b out is the bias vector (one-dimensional vector). Finally, the compensated pose is obtained Passed to the fusion processor.

[0062] The load is decoupled and calculated, and the six-degree-of-freedom platform compensation posture is obtained using the delay compensation unit Calculate compensation force Where [M] t is the inertia tensor matrix of the scaled wind turbine model, is the acceleration vector of the six-degree-of-freedom platform compensation posture, [K] t is the gravity stiffness matrix of the scaled wind turbine model. The noise-reduced load signal F is obtained by combining the noise suppression unit. bal_clean , extract the net aerodynamic load F aero =F bal_clean -F corr ; The net aerodynamic load F aero Feedback to the numerical subsystem, re-solve the platform dynamic equations, and complete the real-time coupling cycle. s The calculation formula is as follows:

[0063]

[0064] Among them, q s =[x,y,z,ρ,θ,σ] T (x is surge, y is sway, z is heave, ρ is roll, θ is pitch, θ is yaw), F hst is the hydrostatic restoring force, F moor is the mooring tension, F hydro is the hydrodynamic load, F aero is the net aerodynamic load.

[0065] Figure 7 To verify the consistency between the method of the present invention (HIL-AI) and FAST simulation in the dynamic response of surge. By comparing the power spectral density (PSD) of the platform motion under the Operational sea condition (Hs = 7.10 m, Tp = 12.10 s), it is shown that this method can reproduce the wave-dominated dynamic characteristics with high precision. It can be seen from the image that in the low-frequency band (f < 0.01 Hz), the PSD curves of the coupled calculation method (red line) and the numerical simulation (blue line) coincide highly near the natural frequency of the platform surge, and the peak position and amplitude error are less than 5%. This coupled calculation method can accurately reproduce the low-frequency coupling dynamics; in the mid-frequency band (0.1 Hz < f < 0.3 Hz), the trends of the two curves are similar, and the difference in PSD amplitude is less than 10%. Especially near the main wave frequency, the energy matches well, which proves that this coupled calculation method can accurately simulate the linear response under wave excitation and verifies the rationality of HIL-AI.

[0066] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0068] These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0070] The above description is only a preferred embodiment of the present invention. Although the present invention has been disclosed as a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can use the above disclosed methods and technical contents to make many possible changes and modifications to the technical solution of the present invention without departing from the scope of the technical solution of the present invention, or modify it into an equivalent embodiment with equivalent changes. Therefore, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of protection of the technical solution of the present invention.

Claims

1. A real-time hybrid test method for aerodynamic loads of floating wind turbines based on AI enhancement, characterized in that: The following steps are involved: Based on the real-time floating foundation dynamic equations, a numerical calculation model is used to simulate the floating body's six-degree-of-freedom motion, wave loads, and mooring system response, and calculate the floating foundation's six-degree-of-freedom motion information; A scaled wind turbine model is mounted on a six-degree-of-freedom motion platform and placed in the atmospheric boundary layer of a wind tunnel. The six-degree-of-freedom motion information of the floating foundation is used to obtain position and posture instructions to control the six-degree-of-freedom motion platform, drive the scaled wind turbine model to move, generate aerodynamic loads in a simulated wind environment, measure the original load signals and make corrections, and simultaneously record the actual position and posture of the six-degree-of-freedom platform. AI correction is performed on the corrected load signal and the actual position of the six-degree-of-freedom platform. The net aerodynamic load is obtained based on the correction result, and the net aerodynamic load is fed back to the numerical calculation model, and a closed-loop update is implemented to realize the coupling cycle.

2. The AI-enhanced real-time hybrid test method for floating wind turbine aerodynamic loads according to claim 1 is characterized in that: The wave load includes hydrodynamic load and hydrostatic restoring force. The hydrodynamic load is composed of radiation force, viscous force and diffraction force. The hydrostatic restoring force is solved using a linearized model. The mooring system adopts a lumped mass model and solves the mooring tension through real-time integration.

3. The AI-enhanced real-time hybrid test method for floating wind turbine aerodynamic loads according to claim 1 is characterized in that: The scaled wind turbine model tower base is provided with a six-component force sensor to measure the original load signal, and the nacelle is provided with an acceleration sensor to measure the hub center height acceleration, and the original load signal is corrected according to the hub center height acceleration.

4. The AI-enhanced real-time hybrid test method for floating wind turbine aerodynamic loads according to claim 1 is characterized in that: The AI ​​correction includes noise suppression on the corrected load signal and delay compensation on the actual posture of the six-degree-of-freedom platform.

5. The AI-enhanced real-time hybrid test method for floating wind turbine aerodynamic loads according to claim 4 is characterized in that: The specific steps of noise suppression include: decomposing the modified load signal by using wavelet packet transform, automatically identifying the noise dominant frequency band and applying adaptive threshold filtering to obtain the load signal after noise reduction.

6. The AI-enhanced real-time hybrid test method for floating wind turbine aerodynamic loads according to claim 5 is characterized in that: The specific steps of the delay compensation include: inputting the actual posture sequence of the six-degree-of-freedom platform, learning the motion characteristics of the six-degree-of-freedom motion platform based on the LSTM network model, and outputting the compensated posture of the six-degree-of-freedom platform.

7. The AI-enhanced real-time hybrid test method for floating wind turbine aerodynamic loads according to claim 6 is characterized in that: Obtaining the net aerodynamic load according to the correction result specifically includes: calculating the compensation force according to the compensation posture of the six-degree-of-freedom platform, and calculating the net aerodynamic load according to the load signal after noise reduction of the compensation force.

8. A real-time hybrid test system for aerodynamic loads of floating wind turbines based on AI enhancement, characterized in that: The method for implementing any one of claims 1 to 7 comprises: Numerical subsystem: used to simulate the six-degree-of-freedom motion of the floating body, wave loads and mooring system response based on the real-time floating foundation dynamic equations using numerical calculation models, calculate the six-degree-of-freedom motion information of the floating foundation, and generate posture instructions based on the six-degree-of-freedom motion information of the floating foundation; Physics subsystem: Used to mount the scaled wind turbine model on a six-degree-of-freedom motion platform and place it in the wind tunnel's atmospheric boundary layer. The six-degree-of-freedom motion platform is controlled according to position and posture commands to drive the scaled wind turbine model to move. It generates aerodynamic loads in a simulated wind environment, measures and corrects the raw load signals, and simultaneously records the actual position and posture of the six-degree-of-freedom platform. AI correction module: used to perform AI correction on the corrected load signal and the actual position of the six-degree-of-freedom platform, obtain the net aerodynamic load based on the correction result, feed the net aerodynamic load back to the numerical calculation model, and implement a closed-loop update to achieve a coupled cycle.

9. A computer device, characterized in that: The computer device comprises: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the AI-enhanced real-time hybrid test method for aerodynamic loads of a floating wind turbine as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed by one or more processors, the one or more processors are caused to execute the steps of the method according to any one of claims 1 to 7.

Images