633 results about "Aerodynamics" patented technology

The invention discloses a tunnel fan energy-saving control method and system, a storage medium and a program product, and relates to the field of general control or regulation systems.The method comprises the steps that historical train flow data are obtained, and the predicted train flow of the next time period is obtained through calculation according to the historical train flow data; collecting real-time gas concentration data and wind speed and direction data; calculating a theoretical gas concentration increment based on an aerodynamic model, the predicted train flow, the real-time gas concentration data and the wind speed and direction data; calculating according to the theoretical gas concentration increment and a pollutant diffusion model to obtain a pollutant diffusion trend; determining a target section according to the pollutant diffusion trend and a preset gas concentration threshold value; according to the position information of the target section and the pollutant diffusion trend, the minimum starting number of tunnel fans and the corresponding minimum rotating speed are obtained through calculation; and generating a fan control instruction according to the minimum number of started fans and the minimum rotating speed. According to the method, the effect of reducing the energy consumption of the tunnel fan while the ventilation effect of the tunnel is maintained is achieved.

The invention discloses a method for measuring an attitude angle of a free throwing object in a wind tunnel test through a binocular system, and belongs to the field of aerodynamics tests based on a photogrammetry technology. Comprising the steps that a binocular system is arranged in a wind tunnel, and internal and external parameters of the binocular system are calibrated through a cross scale; reconstructing the surface mark points of the calibration plate by photogrammetry outside the wind tunnel and establishing a local coordinate system; placing a calibration plate in the wind tunnel, wherein each vector of a local coordinate system is parallel or vertical to an incoming vector, and calibrating a wind tunnel coordinate system by adopting a resection method; carrying out photogrammetry and initial pose installation on mark points on the surface of a thrown object; acquiring each state image of the thrown object and reconstructing the three-dimensional coordinates of the surface mark points; taking the attitude angle of the thrown object as 0 degree as a reference state, and comparing the rigid body transformation relationship between the blowing state point cloud and the reference state point cloud to obtain attitude angle data. Alignment of a wind tunnel coordinate system and a binocular system coordinate system can be achieved, limitation of the appearance of the thrown object is avoided, and attitude angle data of the thrown object are calculated in a non-contact and high-precision mode.

The present invention relates to a digital accompanying flight system for a launch vehicle based on real-time telemetry data, and a method. The system comprises a ballistic simulation model, a propulsion simulation model, a mass simulation model, an aerodynamics simulation model, an environment simulation model, a timing model, and a trigger correction model. The ballistic simulation model, the propulsion simulation model, the mass simulation model, the aerodynamics simulation model, and the environment simulation model synchronously perform simulation. On the basis of a preset flight sequence and real-time telemetry data, the timing model determines, at each simulation step length, whether a key timing action has occurred, and simulates the key timing action by adopting a discrete event message. On the basis of telemetry data of a launch vehicle which is obtained in real time, the trigger correction model determines whether the ballistic simulation model needs to be corrected, and when correction is needed, sends a correction message to the ballistic simulation model.

A method of using a computer implemented neural network for a simulation of aerodynamic performance of a technical object having a geometry, the method comprising: Training the neural network using a plurality of sets of encodings of pre-computed computational fluid dynamics, CFD, outputs, wherein the training is generated using inputs comprising: a geometry of at least one training technical object; spatial locations of input nodes of the neural network as node attributes; a relationship between the geometry of the at least one training technical object and the neural network input node locations; associated boundary conditions; operating conditions; and computed outputs comprising flow fields and aerodynamic performance parameters; the training using a loss function that evaluates an error between a neural network output and the pre-computed CFD outputs to produce a trained neural network; using the trained neural network with new inputs to generate as output a predicted aerodynamic performance of the technical object, wherein the relationship between the geometry of the at least one training technical object and the neural network input node locations comprises a vector with at least two parameters.

The present invention comprises an aerodynamic profile body with an outer flow surface for flow by a fluid, wherein the aerodynamic profile body comprises: - an upper cover layer and a lower cover layer, which form at least part of the outer flow surface and are designed to be flexurally elastic in an end section of the aerodynamic profile body, and - an actuator device with at least one actuator provided in an interior of the aerodynamic profile body, which actuator interacts with at least one of the cover layers in the flexurally elastic end section in such a way that the cross section of the aerodynamic profile body in the flexurally elastic end section can be changed by the at least one actuator, characterized in that - the at least one actuator is fastened with a first actuator end to a first fastening point in the interior and with at least a second actuator end to a second fastening point in the interior, - wherein the second attachment point is arranged transversely to the span of the aerodynamic profile body at a distance from the first attachment point and on an inner side of one of the cover layers in the flexurally elastic end section, and - the at least one actuator is designed such that the linear distance between the first attachment point and the second attachment point can be changed in order to change the cross-section of the aerodynamic profile body.

The invention discloses a ramjet numerical simulation method, device and equipment and a storage medium, and relates to the technical field of aerodynamics, and the method comprises the steps: determining a dimensionless temperature corresponding to a gas component of an initial flow field; based on the dimensionless temperature, determining a molecular viscosity collision integral function of the gas component in a polynomial fraction fitting mode; determining the viscosity coefficient of the gas component according to the molecular viscosity collision integral function; and generating a computational grid of the ramjet based on the viscosity coefficient so as to perform numerical simulation operation on the ramjet. Therefore, in the numerical simulation process of the ramjet, the polynomial fraction is adopted to fit the viscosity collision integral function, the calculation time of the gas viscosity coefficient can be effectively shortened, and the calculation precision is kept to meet the use requirement; in addition, the method can adapt to the combustion flow field temperature requirement and the component requirement of the ramjet engine, and the numerical simulation efficiency of the ramjet engine can be improved.

The invention discloses an aerodynamic thermal analysis method, device and equipment under multiple conditions and a medium, and relates to the technical field of aerodynamics, and the method comprises the steps: obtaining a target high-temperature gas flow field of an aircraft, and extracting wall surface parameter information and wall surface sub-layer parameter information; calculating the inflow and outflow mass flux of each component in a control body, determining condition parameters of each wall surface effect condition, and obtaining a component mass conservation equation; constructing a wall surface total mass conservation equation based on the mass flux, the component diffusion conservation condition and the catalytic conservation condition of each component; constructing a wall surface energy conservation equation based on the total mass ejection flux, the wall surface parameter information and the wall surface secondary layer parameter information determined by the wall surface total mass conservation equation; performing mathematical operation on the component mass conservation equation, the wall surface total mass conservation equation and the wall surface energy conservation equation to obtain a wall surface heat flow calculation equation; and substituting the current wall surface condition into the wall surface heat flow calculation equation to obtain an aerodynamic heat analysis result, and realizing accurate aerodynamic heat analysis under different working conditions.

The invention discloses a neural operator-based particle image velocimetry (PIVNO) method. Efficient mapping of a particle image pair to a flow field is realized through an end-to-end learning framework. According to the method, a neural operator normal form is adopted, cost volume construction with large calculation amount in a traditional method is avoided, and calculation efficiency and estimation precision are improved. The method comprises the steps of obtaining a synthetic data set and carrying out multi-scale down-sampling, constructing a PIVNO model to realize high-precision flow field prediction, supervising pre-training on the synthetic data set, self-supervising a fine-tuning optimization model on real data, finally predicting a real flow field, and supporting estimation of any resolution. According to the method, global feature aggregation, iterative optimization and high-resolution reconstruction technologies are combined, the flow field estimation precision is improved, and the adaptability of the model on real data is enhanced. The method is efficient in calculation, high in generalization ability and suitable for the fields of aerodynamics, turbulence research, biological fluid and the like, and provides technical support for high-precision flow field measurement.

The invention discloses a method for path planning of an eVTOL unmanned aerial vehicle in a dynamic environment, and the method comprises the steps: S1, designing a reinforcement learning framework TDDPG, and employing an LSTM model as a strategy model; s2, solving exploration and path planning problems in a dynamic environment in combination with a continuous action space; s3, constructing a model based on kinematics and aerodynamics principles; s4, designing a composite reward function; s5, introducing an initialization exploration mechanism and a priority experience playback mechanism; the continuous action optimization capability of the DDPG and the time sequence modeling capability of the LSTM are utilized, so that the unmanned aerial vehicle can perform dynamic obstacle avoidance and dynamic end point planning based on historical states and action information, and the problem of three-dimensional path planning of the unmanned aerial vehicle in a dynamic obstacle environment is solved; a model based on kinematics and aerodynamics principles is designed, it is ensured that a simulation result truly reflects the flight trajectory of the unmanned aerial vehicle in a multi-obstacle environment, meanwhile, state changes of the unmanned aerial vehicle in different flight stages can be effectively simulated, and the accuracy of the motion trajectory of the unmanned aerial vehicle is ensured.

The invention discloses a mooring type floating wind power generation device, and belongs to the technical field of wind power generation. The device comprises a first bag body, the peripheral surface of the first bag body is a rotary surface, and the diameter of the first bag body is gradually increased from front to back; the peripheral surface of the second capsule body is a rotary surface, the diameter of the second capsule body is gradually reduced from front to back, the second capsule body is arranged on the rear side of the first capsule body at intervals, and a crack is formed between the second capsule body and the first capsule body; the first ring wing sleeves the radial outer side of the crack; the radial outer side of the second bag body is sleeved with the second ring wing; and the contra-rotating fan blades comprise two fan blades with opposite rotating directions, each fan blade comprises a hub and a blade body connected to the hub, the hubs are located in the cracks, and at least part of the fan blades are located outside the cracks in the radial direction and located in the area defined by the first ring wings. According to the mooring type floating wind power generation device, the aerial high-density wind energy capturing capacity is considered, and meanwhile the aerodynamics and the aerial floating capacity of the aerostat are enhanced.

The invention provides an aerodynamic task processing method and device based on multiple agents, and relates to the technical field of aircraft simulation design, and the method comprises the steps: obtaining a task target and working condition parameters inputted by a user; based on the capability of each agent group in the multi-agent system, generating a plurality of sub-tasks based on the task target; distributing the plurality of sub-tasks to corresponding agent groups in the multi-agent system for task processing to obtain a calculation result corresponding to the task target; the multi-agent system comprises a first agent group, a second agent group and a third agent group. According to the multi-agent-based aerodynamic task processing method and device provided by the invention, the role of a person in a traditional CFD normal form is replaced by the agents, automatic execution of the whole process of the CFD task is realized, and the processing efficiency of the aerodynamic task is greatly improved.

The invention discloses a wind power prediction method and system based on mesoscale-microscale dynamics, and the method comprises the following steps: constructing a wind power plant microscale aerodynamic model, setting an inflow boundary condition, generating data according to the inflow boundary condition and the wind power plant microscale aerodynamic model, and constructing a database; constructing a mesoscale-microscale aerodynamic coupling model and a prediction network of the wind power plant; taking the mesoscale-microscale aerodynamic coupling model of the wind power plant as a system environment, training a prediction network by using a database, and inputting mesoscale meteorological prediction data and corresponding inflow boundary conditions into the trained prediction network to obtain a wind power prediction result; compared with an existing method, the method is more beneficial to meeting the requirement of wind power prediction, the reliability of wind power prediction is improved, and the speed and precision of wind power prediction are improved.

The invention discloses an aircraft aerodynamic parameter prediction method based on multi-view airfoil profile concept correlation learning, and belongs to the technical field of aerodynamics, deep learning and computer vision crossing, and the method comprises the steps: converting a three-dimensional model into a multi-view image sequence through a hybrid projection strategy combining orthogonality and surround view; utilizing an optimal transmission theory to map visual features to a learnable airfoil profile concept space to realize semantization and discretization of the features; in combination with flow field working condition coding, aerodynamic parameters are regressed under the constraint of aerodynamic physical laws; and finally, by displaying the matching relationship between the input sample and the airfoil profile concept, the inherent interpretability based on the instance is provided.

The invention discloses an explainable appearance feature learning and quantitative representation method for aerodynamic parameter prediction, and belongs to the technical field of aerodynamics and artificial intelligence crossing. The method comprises the following steps: constructing a collaborative network architecture comprising an aerodynamic prediction module, an airfoil concept learning module and a quantitative distillation agent module; while high-precision and high-efficiency aerodynamic parameter prediction is realized, a prediction result can be decomposed into the sum of quantitative contributions of different airfoil profile concepts, so that a direct explainable basis is provided for the prediction result, and expert users are assisted in understanding and verifying the prediction process of the model.

The invention relates to the technical field of computer aided design, in particular to a fan model generation method and system. The method comprises the following steps: acquiring basic design parameters and constraint conditions of a fan, and performing fan model simulation generation and aerodynamics analogue simulation to generate aerodynamics simulation fields corresponding to different fan models; performing fan blade power curvature and airflow vibration evaluation analysis on the aerodynamic simulation fields corresponding to the different fan models, and performing fan airflow efficiency calculation at the same time to obtain fan air flow efficiency corresponding to the different fan models; performing operation acoustic noise evaluation analysis and performance curve simulation analysis on the corresponding fan three-dimensional models to generate airflow efficiency-noise performance curves corresponding to different fan models; a fan optimization model is generated by obtaining a corresponding fan constraint optimization target and performing time sequence energy efficiency ratio optimization design. The design effect and efficiency of the fan model can be improved.

The invention relates to a multi-target aerodynamic-structure optimization method based on a deep neural network proxy model, and solves the problem that an existing method is insufficient in efficiency, feasibility and credibility, and the method comprises the steps: firstly, carrying out the sampling in a parameterized design target, building an aerodynamic-structure database through CFD / FEA high-fidelity simulation; the method comprises the steps that firstly, a multi-task neural network is used for predicting the lift-drag ratio, quality and stress at the same time, uncertainty is output, then, in NSGA-III multi-target optimization, a proxy model is used for rapidly evaluating and searching out a Pareto leading edge meeting constraints, finally, the precision of the model is gradually improved through high-fidelity checking and incremental updating, and an optimal design scheme is output. According to the method, sub-optimization and repeated iteration caused by'pneumatic first and then structure 'are avoided; the design universality and robustness are improved; a compromise scheme set of the system is directly obtained; and the optimization cost and the optimization period can be obviously reduced.

The invention discloses a bilateral support balance structure for measuring intake and exhaust influence, and belongs to the field of aerodynamics. The device comprises an aircraft fuselage shell, an air inlet channel upper cover, a double-support balance, a corrugated pipe and a fixed support, the double-support balance comprises a front shell matching section, a front air inlet channel, an air inlet channel lower cover, support balances and a rear shell matching section, the aircraft fuselage shell is connected with the double-support balance through the shell matching section, the air inlet channel lower cover is connected with the front shell matching section, and the two sides of the front shell matching section and the two sides of the rear shell matching section are connected through the support balances. The air inlet channel lower cover is provided with an air inlet channel upper cover, the air inlet channel upper cover and the air inlet channel lower cover jointly form a middle air inlet channel, the rear shell matching section is provided with a fixed support, and the rear air inlet channel of the rear shell matching section is communicated with the air inlet passage through a corrugated pipe. The problems that a complete air inlet channel is formed in the middle of an aircraft wing body, the internal space is narrow, a balance cannot be installed, and the six-component load measurement requirement cannot be met are solved.

The invention relates to a blade (7) for a turbomachine comprising: - a sleeve (13), including a fastening part (14) configured to be connected to a variable pitch mechanism of a turbomachine, a through recess (17) being formed in the fastening part (14) of the sleeve (13), the recess (17) being delimited by an internal wall of the sleeve (13); - a fibrous structure (20) obtained by three-dimensional weaving of strands, the fibrous structure (20) comprising: - a blade root (22) including an attachment portion (23) configured to be inserted into the recess (17) of the fastening part (14) of the sleeve (13), - an aerodynamically profiled blade (12) connected to the blade root (22); - an insert (24), configured to be inserted into the recess (17) of the fastening part (14) of the sleeve (13) and to press the blade root (22) against the inner wall (18) of the sleeve (13). Figure for the abbreviation: Fig. 4c

The invention discloses a boundary layer cushion block leveling method suitable for a wind tunnel half-mode test, relates to the field of experimental aerodynamics, and aims to reduce interference of wind tunnel wallboards in the half-mode test and improve assembly efficiency. The method comprises the following steps: S1, measuring corresponding data according to an established three-dimensional model of a boundary layer cushion block and a balance adapter; s2, based on the data in the step S1, the sizes of the first tool, the second tool, the third tool and the fourth tool are determined; s3, a corresponding first tool, a second tool, a third tool and a fourth tool are manufactured; s4, a balance adapter is installed in the wind tunnel test section, and a balance is measured; and S5, a leveling tool is used for assisting in leveling of the boundary layer cushion block. By adopting the method, the leveling tool is simple and convenient to apply, measurement parameters are few, and the mounting and leveling operation of the boundary layer base plate is effectively simplified; meanwhile, the leveling precision is high enough, the requirement for the installation precision of the boundary layer cushion block of the half-mold test can be met, and labyrinth groove collision is avoided.

The invention discloses a self-adaptive sampling method for aerodynamic characteristic modeling, and belongs to the field of aerodynamics. The problem that in aerodynamic characteristic modeling, an existing traditional sampling method lacks the targeted sampling capacity for a complex function area, and consequently samples are wasted is solved. According to the method, modeling is carried out for aerodynamic characteristics, a parameter interval where a complex function is located is determined through comprehensive weighting of uncertainty of Gaussian process regression and a parameter sensitivity analysis result, non-uniform sampling is carried out according to the complexity condition of the parameter interval, and targeted sampling of a complex function area is achieved; sensitivity analysis adopts a joint data mining method, and comprises two methods of a Sobol algorithm and a decision tree; according to the method, the sample utilization efficiency of small sample aerodynamic characteristic modeling is effectively improved.

An aerodynamics control system for a vehicle may include a repositionable aerodynamic device disposed at a portion of the vehicle, a controller operably coupled to components or sensors of the vehicle to receive information including vehicle performance data and position information for the aerodynamic device, and a vehicle location sensor determining location information for the vehicle. The controller stores the vehicle performance data and the position information in association with the location information for each of a plurality of locations. Responsive to detecting an approach of the vehicle to one of the locations, the controller provides a control instruction to position the aerodynamic device based on recorded vehicle performance data and recorded position information associated with the one of the locations.

The invention discloses a flight controller and method fusing PID control and a neural network, and a storage medium, and the method comprises the steps: obtaining the real-time online flight state data of an aircraft, inputting the real-time online flight state data into a basis function, and obtaining the basis function data irrelevant to a wind field, the basis function being a pre-trained aerodynamic neural network irrelevant to the wind field; obtaining a linear coefficient related to the wind field through real-time online self-adaptive adjustment; multiplying the basis function data irrelevant to the wind field obtained in real time and on line by the linear coefficient relevant to the wind field to obtain residual force; converting the residual force into the power of the aircraft and feeding back the power to a PID controller to realize the control of the aircraft; according to the method, various interference factors are decoupled into non-real-time and real-time factors, control over various uncertain nonlinear complex processes can be effectively achieved, the robustness and fault tolerance of a flight control system are improved, and better control performance is achieved.

The invention discloses an aircraft flow field reconstruction method, and belongs to the technical field of aerodynamics. According to the method, the problems of unstable precision and poor reliability of a three-dimensional flow field reconstruction prediction result of an aircraft with a complex shape are solved. According to the method, geometric shapes of different aircrafts are generated through parameterization, and flow field calculation is carried out by adopting a CFD calculation method; carrying out geometric expression point sampling on the obtained different aircraft geometric shapes, and extracting geometric shape feature information by adopting a symbolic distance expression method; the aircraft appearance feature information and the incoming flow condition are combined into an input feature matrix, a three-direction velocity field and a pressure field obtained through calculation of a corresponding flow field serve as an output feature matrix, a flow field reconstruction data set is formed, and a training set, a verification set and a test set are divided; and importing the obtained data set into a network of a dual nested attention mechanism, and carrying out model training, so that flow field accurate prediction can be realized for aircrafts with different input appearance characteristics and different working conditions.

The invention belongs to the technical field of aerodynamic wind tunnel tests, and discloses a test device and method for a dynamic derivative wind tunnel test, and the device comprises an aircraft model which is formed by assembling a nose, a middle fuselage, a rear fuselage, a balance, wings and an empennage; the oscillation mechanism is provided with an adapter, and the adapter is connected with the balance; and one end of the wind tunnel strut is connected with the wind tunnel attitude control system and the other end is connected with the oscillation mechanism. The problem that an existing dynamic derivative wind tunnel test model and a test device are low in efficiency is solved, heaving, sidesway, yawing, pitching and rolling oscillation of the model are achieved by replacing the adapters, and the test efficiency of a dynamic derivative wind tunnel test can be effectively improved.

The invention discloses a multi-scale vortex recognition method based on topology analysis, and aims to solve the problems that an existing vortex recognition method depends on a single scale and is insufficient in adaptability, limited in generalization ability, poor in visualization effect and the like. According to the method, firstly, a merge tree is constructed to obtain a multi-scale topological structure of a flow field, candidate vortex regions are screened based on extreme point-saddle point branches, and multi-scale vortex extraction is carried out in combination with a scalar criterion, so that dependence of a traditional method on a fixed threshold is avoided. In order to adapt to unstructured grid data, the method enhances the applicability and robustness of the method in a complex flow environment through adjacency relation reconstruction. In addition, a region diffusion algorithm is adopted to identify the vortex region, and surface extraction and smoothing processing are combined to optimize the visualization effect, so that the boundary of the vortex structure is more continuous and natural. Experimental results show that the method can accurately extract vortex structures of different scales, shows good generalization ability on flow field data of different Reynolds numbers, and has higher adaptability on complex flow fields and unstructured grids compared with a traditional method. The method can be widely applied to turbulence research, aerodynamic optimization, meteorological analysis and engineering flow problems, and an efficient, robust and accurate vortex recognition technology is provided for fluid mechanics research.

The invention discloses a calibration board and wind tunnel feature point-based binocular system wind tunnel coordinate system calibration method, and belongs to the field of aerodynamic tests. Comprising the following steps: reconstructing surface mark points of a calibration plate by photogrammetry outside a hole and establishing a local coordinate system to obtain coordinates under the local coordinate system; a binocular system is arranged in the hole, and binocular internal and external parameters are calibrated through a special cross calibration ruler; arranging a plurality of circular feature mark points on the surface of the hole wall with overlapped visual fields of the binocular system; the calibration plate is correctly placed according to the geometrical relationship, so that each vector of the local coordinate system is parallel or perpendicular to an incoming vector, and the binocular system reconstructs global points of the calibration plate and registers the global points to achieve alignment of a measurement coordinate system of the binocular system and a wind tunnel coordinate system; reconstructing a three-dimensional coordinate of the fixed point in a wind tunnel coordinate system through a binocular system; and in a subsequent test, adopting resection to realize the recalibration of the wind tunnel coordinate system. According to the invention, high-precision and high-efficiency alignment requirements of a measurement coordinate system and a wind tunnel coordinate system of a binocular system can be met.

A method of determining a repair method for a defect in a bladed rotor can comprise comparing the defect in a three-dimensional model of an inspected integrally bladed rotor (IBR) to a plurality of known defects from a repair database; determining the defect is matching a known defect in the plurality of known defects in the repair database; and generating a repair process associated with the known defect in response to determining the defect is matching the known defect. A method can also comprise determining a potential repair process; performing a structural simulation of a finite element model for the inspected IBR with the potential repair; performing an aerodynamic simulation of an aerodynamic model for the inspected IBR with the potential repair; and generating the potential repair process for the defect in response to determining the inspected IBR with the potential repair meets structural and the aerodynamic criteria.

The invention discloses a multi-vortex system space energy evolution process analysis method, belongs to the field of fluid mechanics and aerodynamics, and aims to solve the problem of energy analysis errors caused by integral radius dependence and single-vortex hypothesis limitation in a traditional method. According to the method, a vortex core is positioned through a Liutex method, a vortex to be analyzed is translated to an original point, a pseudo time sequence is generated in combination with evolution direction slices, and a first modal energy distribution and evolution law is extracted through eigen-orthogonal modal decomposition. According to the method, the integral radius does not need to be manually set, the adaptability is high, the vortex global energy space change process can be comprehensively reflected, the method is particularly suitable for energy evolution analysis in complex vortex system scenes such as bird flight and complex aircraft wake flow, a brand new view angle is provided for vortex energy evolution, and the method has certain engineering practical value. The method can be used for quantitative analysis of complex vortex field scenes such as aircraft design, biological bionics and wind energy engineering, and has important engineering application value.

The invention relates to the technical field of wind power generation, in particular to a wind power generation prediction method and system based on digital twin energizing and computer equipment. Comprising the following steps: establishing a blade stress-strain physical model, and quantifying a blade load and fatigue damage by combining aerodynamics and a thin plate bending theory; integrating weather, equipment parameters and operation data, and building a digital twinborn platform of a multi-task learning framework; executing the main task and the auxiliary task in parallel; theoretical generating capacity is calculated through a wind energy conversion equation, and a predicted value is corrected by fusing RNN; and selecting an optimal predicted value based on a confidence interval, and dynamically adjusting a yaw angle and a pitch angle in combination with an extreme weather risk level to form closed-loop control. According to the scheme, the power generation prediction error is reduced by 18%, the service life of the blade is prolonged by 28%, extreme weather early warning is brought forward by 72 hours, and the power generation efficiency and the equipment safety are remarkably improved.

The invention discloses a cross-domain variable configuration high-speed aircraft adaptive attitude control method and system based on neural network identification, and a storage medium, relates to the technical field of aircraft control, and aims to solve the problems that in an existing method, unified parametric modeling needs to be carried out on aircraft pneumatics in advance, and parameters need to be identified; the attitude control problem caused by aerodynamic uncertainty cannot be solved under the condition that the aerodynamic parameter model of the cross-domain variable-configuration high-speed aircraft is completely unknown. A three-channel neural network model is constructed and comprises a pitching channel neural network model, a yawing channel neural network model and a rolling channel neural network model; a loss function is constructed based on the influence sensitivity weighting of the rudder deviation error on the attitude change, and a three-channel rudder deviation solver neural network model is obtained through training; and an online transfer learning sample library is constructed for online transfer learning, aerodynamic torque is solved based on a backstepping method controller, and finally a yaw instruction is obtained through solving.