Wind vane accurate positioning detection system and method

Abstract

The embodiment of the invention provides a wind indicator accurate positioning detection system and method. The system is applied to the field of wind direction detection equipment, and comprises a height calculation module used for obtaining real-time wind speed information and real-time environment information of a wind tunnel and a wind direction angle transmitted by a wind direction sensor, and inputting the information to a preset height confirmation model to obtain the rising height of a three-hole probe; the airflow deflection angle calculation module is used for controlling the three-hole probe to be adjusted to the rising height, receiving the differential pressure data transmitted by the three-hole probe, calculating a calibration coefficient according to the differential pressure data, and calculating an airflow deflection angle according to the calibration coefficient and a preset fitting formula; and the wind direction angle adjusting module is used for adjusting the wind direction angle transmitted by the wind direction sensor according to the airflow deflection angle and transmitting the adjusted wind direction angle to the control center. According to the scheme, the ideal rising height of the three-hole probe is determined, then measurement is carried out, measurement errors caused by improper height can be reduced, and the measurement precision of the airflow deflection angle and the wind direction angle is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of wind direction detection devices, and particularly to a precise positioning detection system and method for a wind vane. Background Art

[0002] In the field of wind tunnel experiments, the accuracy and reliability of wind direction sensors are crucial for evaluating the performance of aircraft, vehicles, and other aerodynamic devices.

[0003] Traditional methods for calibrating wind direction sensors require installing the sensor at a specific position in the wind tunnel, manually adjusting the wind direction angle, and measuring its output values at different wind speeds.

[0004] However, this method is time-consuming and vulnerable to human errors and equipment accuracy limitations, resulting in insufficient accuracy of the calibration results. In addition, changes in external environmental conditions may also interfere with the calibration process, further reducing the reliability of the calibration results. Summary of the Invention

[0005] To address the deficiencies of the prior art, the present disclosure provides a precise positioning detection system and method for a wind vane. The present disclosure solves the technical problems that the current method for calibrating wind direction sensors is time-consuming and vulnerable to human errors and equipment accuracy limitations, resulting in insufficient accuracy of the calibration results. In addition, changes in external environmental conditions may also interfere with the calibration process, further reducing the reliability of the calibration results.

[0006] According to a first aspect of the present disclosure, there is provided a precise positioning detection system for a wind vane, comprising: a height calculation module for obtaining real-time wind speed information, real-time environmental information, and the wind direction angle transmitted by a wind direction sensor of a wind tunnel, inputting the real-time wind speed information, real-time environmental information, and wind direction angle into a preset height confirmation model to obtain the rising height of a three-hole probe;

[0007] An air flow deviation angle calculation module for controlling the three-hole probe to adjust to the rising height, receiving differential pressure data transmitted by the three-hole probe, calculating a calibration coefficient based on the differential pressure data, and calculating an air flow deviation angle based on the calibration coefficient and a preset fitting formula; wherein the calibration coefficient includes a speed coefficient and an angle coefficient;

[0008] A wind direction angle adjustment module for adjusting the wind direction angle transmitted by the wind direction sensor according to the air flow deviation angle and transmitting the adjusted wind direction angle to a control center.

[0009] According to a second aspect of the present disclosure, a method for accurately positioning and detecting a wind vane is provided, including: obtaining real-time wind speed information, real-time environmental information of a wind tunnel, and the wind direction angle transmitted by a wind direction sensor, and inputting the real-time wind speed information, real-time environmental information, and the wind direction angle into a preset height confirmation model to obtain the rising height of a three-hole probe;

[0010] Controlling the three-hole probe to adjust to the rising height, receiving differential pressure data transmitted by the three-hole probe, calculating a calibration coefficient according to the differential pressure data, and calculating an air flow deflection angle according to the calibration coefficient and a preset fitting formula; wherein, the calibration coefficient includes a velocity coefficient and an angle coefficient;

[0011] Adjusting the wind direction angle transmitted by the wind direction sensor according to the air flow deflection angle, and transmitting the adjusted wind direction angle to a control center.

[0012] In a wind vane accurate positioning detection system and method provided as above, in the embodiments of the present disclosure, the ideal rising height of the three-hole probe is determined and then measurement is carried out, which can reduce measurement errors caused by improper height, and improve the measurement accuracy of the air flow deflection angle and the wind direction angle. The automated and intelligent system reduces errors caused by human operation, and improves the reliability and consistency of the verification process. The verification time is significantly shortened, and the work efficiency is improved. Through the preset height confirmation model and fitting formula, the system can dynamically adjust according to different wind speeds, environmental conditions, and wind direction angles, has strong adaptability, and can cope with complex and changeable experimental environments. Through real-time wind speed prediction and motor adjustment, the wind speed in the wind tunnel can be maintained stably, reducing the interference of external environmental condition changes on the verification process, and further enhancing the reliability of the verification results. Through the fault identification module, the system can detect potential faults of the wind direction sensor in advance, prevent experiment interruption or data distortion caused by equipment failures, and improve the overall stability and reliability of the system. In addition, the system integrates multiple intelligent modules to realize the comprehensive intelligent management of the wind vane verification process. In summary, the present disclosure significantly improves the accuracy, efficiency, and reliability of wind vane verification by introducing intelligent and automated technical means, reduces the influence of human errors and external environmental interference, and provides strong technical support for wind tunnel experiments and other aerodynamic research. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0014] Figure 1Shows a schematic block diagram of a precise positioning detection system for a wind vane according to an embodiment of the present disclosure;

[0015] Figure 2 Shows a schematic block diagram of a precise positioning detection system for a wind vane according to an embodiment of the present disclosure;

[0016] Figure 3 Shows a schematic block diagram of a precise positioning detection system for a wind vane according to an embodiment of the present disclosure;

[0017] Figure 4 Shows a flowchart of a precise positioning detection method for a wind vane according to an embodiment of the present disclosure. Detailed implementation manners

[0018] Now, various exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present disclosure.

[0019] Those skilled in the art can understand that terms such as "first", "second", etc. in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate an inevitable logical order between them. It should also be understood that in the embodiments of the present disclosure, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more. It should also be understood that for any component, data or structure mentioned in the embodiments of the present disclosure, without clear limitation or contrary indication in the context, it can generally be understood as one or more. In addition, the term "and / or" in the present disclosure is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present disclosure generally represents an "or" relationship between the associated objects before and after. It should also be understood that the present disclosure emphasizes the differences between various embodiments, and the same or similar parts can be referred to each other. For the sake of brevity, they will not be described one by one.

[0020] Meanwhile, it should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationships. The following description of at least one exemplary embodiment is actually merely illustrative and in no way restricts the present disclosure and its application or use. Technologies, systems, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, systems, and devices should be regarded as part of the specification. It should be noted that like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts fall within the scope of protection of the present disclosure.

[0022] Figure 1 The following is a schematic structural diagram of a precise positioning detection system for a wind vane provided by an embodiment of the present disclosure. The system in the embodiments of the present disclosure aims to ensure the reliability and consistency of wind direction measurement data. The system includes:

[0023] A height calculation module 101, configured to obtain the real-time wind speed information, real-time environmental information of the wind tunnel, and the wind direction angle transmitted by the wind direction sensor, and input the real-time wind speed information, real-time environmental information, and wind direction angle into a preset height confirmation model to obtain the rising height of the three-hole probe.

[0024] An air flow deflection angle calculation module 102, configured to control the three-hole probe to adjust to the rising height, receive the differential pressure data transmitted by the three-hole probe, calculate a calibration coefficient according to the differential pressure data, and calculate the air flow deflection angle according to the calibration coefficient and a preset fitting formula; wherein the calibration coefficient includes a velocity coefficient and an angle coefficient.

[0025] A wind direction angle adjustment module 103, configured to adjust the wind direction angle transmitted by the wind direction sensor according to the air flow deflection angle, and transmit the adjusted wind direction angle to the control center.

[0026] In this embodiment, the wind tunnel can be an experimental device for simulating and testing aerodynamics, usually used to study the behavior of objects (such as airplanes, cars, probes) in airflows. It simulates the air flow under different environmental conditions by controlling airflow parameters (such as wind speed and wind direction) to measure and analyze the dynamic performance of objects.

[0027] Real-time wind speed information can refer to the air flow velocity data measured in real time in a wind tunnel. Wind speed information is used to understand the air flow intensity and the acting force on an object, and is one of the most important parameters in the testing and simulation processes. Wind speed is usually expressed in meters per second (m / s).

[0028] Real-time environmental information can refer to other environmental parameters that affect the air flow characteristics or the behavior of an object, including temperature, humidity, air pressure, etc. Obtaining this information in real time helps to more accurately simulate the external conditions in order to study the influence of wind speed on an object under different environments.

[0029] A wind direction sensor can be a device installed in a wind tunnel for measuring the air flow direction. By detecting the direction of air flow, the wind direction sensor provides real-time wind direction angle information to assist in adjusting the air flow or the positioning of the test object. The measurement result of the wind direction sensor is expressed in degrees.

[0030] The wind direction angle can refer to the direction angle of the air flow, which is the value measured by the wind direction sensor and is used to characterize the air flow direction in the wind tunnel. The wind direction angle is the deviation angle relative to a certain reference direction (usually the due north direction), and the unit is degree.

[0031] A preset height confirmation model can be a mathematical or computational model based on input parameters (such as wind speed, wind direction, environmental information) for predicting or calculating the rising height of an object (such as a three-hole probe). This model is usually pre-designed and calibrated and can take real-time data as input and output the predicted height value.

[0032] A three-hole probe can be an air flow measurement tool, usually used in wind tunnel experiments to measure aerodynamic parameters. It has three holes that can measure the air pressure in different directions respectively, so as to calculate the air flow velocity, flow direction and dynamic pressure. This probe is used in wind tunnel experiments to capture the air flow changes in three-dimensional directions.

[0033] The rising height can be the upward displacement of the three-hole probe under the action of the air flow in the wind tunnel. This displacement height is usually related to the air flow force, direction and speed received by the probe and is used to analyze the probe response and air flow behavior.

[0034] The wind speed can be measured using a wind speed sensor (such as a Pitot tube or an ultrasonic anemometer) installed in the wind tunnel. The wind speed sensor is usually located at the wind tunnel entrance or the position where measurement is required to obtain real-time air flow velocity data. The sensor samples regularly and outputs wind speed data. The environmental parameters inside the wind tunnel are measured by environmental sensors such as temperature sensors, humidity sensors, and pressure sensors. The environmental data is used to supplement the wind speed information, making the input for simulation and altitude confirmation models more accurate. The direction of the air flow inside the wind tunnel is measured using a wind direction sensor (such as a cup anemometer, a wind vane, or an electronic wind direction indicator) to obtain the wind direction angle. The angle value of the wind direction sensor reflects the deviation of the air flow relative to the reference direction. Then, a pre-trained or pre-set altitude confirmation model is loaded, and the cleaned wind speed, environmental information, and wind direction angle are input into the model. The model calculates based on the current input features and outputs a predicted rising height value, that is, the height that the probe is expected to reach under these air flow conditions.

[0035] The differential pressure data can be the differential pressure data of different orifices measured by a pressure sensor in the air flow using a three-hole probe. A three-hole probe usually has three holes, which are aligned with different directions of the air flow, and measures the pressure difference acting on different orifices.

[0036] The calibration coefficient can be a correction coefficient that needs to be introduced when determining the measurement accuracy of the probe. This coefficient corrects the possible errors in the actual measurement of the probe. Among them, the velocity coefficient can be used to correct the accuracy of the three-hole probe in measuring the air flow velocity. The angle coefficient can be used to correct the accuracy of the probe in measuring the air flow angle, ensuring the accuracy of the deflection angle calculation.

[0037] The pre-set fitting formula can be a mathematical relationship established based on experimental calibration data or theoretical models, and is used to calculate the air flow deflection angle. Through the pre-set fitting formula, the differential pressure data output by the sensor is converted into a physical quantity (such as the air flow deflection angle).

[0038] The air flow deflection angle can refer to the offset angle of the air flow relative to the reference axis of the three-hole probe. It reflects the directional change of the air flow.

[0039] The three-hole probe can be placed in the air flow, the pressure values of each orifice are collected, the differential pressure data is calculated, and the three-hole probe is calibrated through a wind tunnel calibration experiment or measurement under known standard conditions. Record the probe responses at different air flow velocities and angles, and use these data to calculate the velocity coefficient and the angle coefficient. Then, substitute the collected differential pressure data and the calibration coefficient into the pre-set fitting formula to calculate the air flow deflection angle. And the reason for raising the three-hole probe to a specified height and then collecting the differential pressure data is that the measurement accuracy of the three-hole probe is closely related to its position height in the air flow. At a specific height, the interaction between the probe and the air flow reaches the best state, generating stable and accurate differential pressure data. If the probe is randomly placed at a non-optimal height, the measured value may deviate from the true value, resulting in an increase in error.

[0040] The control center can generally be the core control system for collecting, processing, and analyzing wind tunnel measurement data. It can be a central server, a data processing module, or an integrated control platform that can receive sensor data in real time, monitor the system status, and command the equipment to make corresponding adjustments. The control center may also display data to the operator through an interface or feedback the data to other subsystems for further analysis or decision-making.

[0041] After the measurement of the three-hole probe is completed, the system has calculated the airflow deflection angle based on the differential pressure data and the calibration coefficient. This deflection angle represents the deviation of the actual airflow direction relative to the reference direction. The system corrects the original wind direction angle of the wind direction sensor according to the airflow deflection angle. Assuming that the initially detected angle by the wind direction sensor is the "original wind direction angle", the corrected wind direction angle can be expressed as:

[0042] Adjusted wind direction angle = Original wind direction angle + Airflow deflection angle

[0043] Then, the adjusted wind direction angle can be transmitted to the control center through the data transmission module. This step may be achieved through wireless networks, wired connections, local area networks, etc. The transmission protocol should ensure the integrity and real-time nature of the data. After receiving the data, the control center stores and records it as the current accurate wind direction angle for real-time monitoring or further data analysis.

[0044] In the embodiment of this application, the height calculation module is used to obtain the real-time wind speed information, real-time environmental information of the wind tunnel, and the wind direction angle transmitted by the wind direction sensor, input the real-time wind speed information, real-time environmental information, and wind direction angle into a preset height confirmation model to obtain the rising height of the three-hole probe; the airflow deflection angle calculation module is used to control the three-hole probe to adjust to the rising height, receive the differential pressure data transmitted by the three-hole probe, calculate the calibration coefficient according to the differential pressure data, and calculate the airflow deflection angle according to the calibration coefficient and a preset fitting formula; wherein, the calibration coefficient includes a speed coefficient and an angle coefficient; the wind direction angle adjustment module is used to adjust the wind direction angle transmitted by the wind direction sensor according to the airflow deflection angle and transmit the adjusted wind direction angle to the control center. Through the above-mentioned wind vane precise positioning detection system, the ideal rising height of the three-hole probe is determined and then measured, which can reduce the measurement error caused by improper height and improve the measurement accuracy of the airflow deflection angle and the wind direction angle. Through the preset height confirmation model and fitting formula, the system can dynamically adjust according to different wind speeds, environmental conditions, and wind direction angles, has strong adaptability, and can cope with complex and changeable experimental environments.

[0045] Based on the above technical solution, optionally, the preset fitting formula is:

[0046]

[0047] Among them, α1 is the airflow deflection angle; m is the summation range in the formula, which controls the highest order involved in the fitting formula; p is the coefficient related to the Mach number (Ma); q is the coefficient related to the angle α of the three-hole probe; C pq is a preset fitting coefficient, is the velocity coefficient, is the angle coefficient.

[0048] In this solution, the calibrated three-hole probe only needs to measure the pressures of three pressure measurement holes, and the airflow deflection angle can be calculated according to the characteristic curve or the fitting function. Specifically, the calibration of the three-hole probe is carried out in a normal temperature wind tunnel. The general process is as follows: Install the probe on the angular displacement mechanism at the outlet of the wind tunnel, and measure the three-hole pressure data p1, p2, and p3 at different Mach numbers Ma and different angles α of the three-hole probe. The calculation formulas for the calibration coefficients (velocity coefficient, angle coefficient) are as follows:

[0049]

[0050] Among them, p m =(p1 + p2) / 2.

[0051] And C pq is used to adjust the contribution of different terms, and a reasonable initial value can be set according to past data or actual experience. After calculating the velocity coefficient and the angle coefficient, these coefficients can be substituted into the formula to obtain the airflow deflection angle.

[0052] On the basis of the above technical solution, optionally, the training process of the preset height confirmation model includes:

[0053] Obtain historical height adjustment records, and determine historical wind speed information, historical environmental information, historical wind direction angle, and the historical rising height of the three-hole probe according to the historical height adjustment records;

[0054] Create a first data set according to the historical wind speed information, historical environmental information, and historical wind direction angle, and label the rising height label of the first data set according to the historical rising height;

[0055] Construct a height confirmation model, and train the height confirmation model according to the rising height label until the height confirmation model reaches the preset height confirmation model training standard.

[0056] In this solution, the historical altitude adjustment record can refer to all altitude adjustments made by a three-hole probe or other equipment during wind tunnel experiments in past operations. It usually includes information such as the time point of each altitude adjustment, the adjustment amplitude, the actual altitudes before and after the adjustment, and possible control instructions. This record helps to understand the experiments and operations conducted at different altitudes in the past.

[0057] The historical wind speed information can be the record of wind speed data during a certain period in the past in the wind tunnel experiment, which may be extracted from a wind speed sensor or system. Wind speed is an important factor affecting the airflow characteristics and the probe's ascent.

[0058] The historical environmental information can be the record of past environmental conditions, including temperature, humidity, atmospheric pressure, etc. These environmental factors affect the airflow properties and the movement of the three-hole probe.

[0059] The historical wind direction angle can be the wind direction data recorded in the wind tunnel experiment, indicating the direction of the wind. This is a key factor for determining the probe's position and its interaction with the airflow.

[0060] The historical ascent altitude of the three-hole probe can be the record of the ascent altitude of the three-hole probe during the experiment. It represents the altitude that the probe ascends relative to the wind tunnel reference position or the ground and is used to calibrate the probe data.

[0061] The first data set can be a data collection generated by collecting and organizing historical wind speed information, historical environmental information, historical wind direction angle, and the historical ascent altitude of the three-hole probe. These data are used to train the altitude confirmation model. Each record in the data set should include wind speed, environmental factors, wind direction, and the corresponding ascent altitude value.

[0062] The ascent altitude label can refer to the actual ascent altitude corresponding to each sample in the data set. These labels are obtained from historical records and label the true ascent altitude corresponding to each piece of data (wind speed, environmental information, wind direction angle, etc.). In model training, these labels serve as target values to teach the model how to predict the ascent altitude of the three-hole probe based on the input environmental conditions.

[0063] The preset height confirmation model training criteria can be indicators used to determine whether model training is complete. These criteria can include training accuracy criteria: referring to the accuracy that the model can achieve on the training dataset, usually setting a threshold, such as the minimum requirements for indicators like accuracy, error, etc. Loss function criteria: the loss function value during model training reaches a certain set target. For example, when the loss value drops to a certain level, it indicates that the model has learned sufficient features. Overfitting or underfitting check: to avoid the model overlearning the noise in the training data or being insufficient to generalize to new data, so evaluation criteria for the validation set are set to check whether the model has overfitting or underfitting. Training time or number of iterations: Usually, the training time or the number of training epochs will also be used as a criterion. When the model reaches a sufficient number of training epochs, the training process will stop.

[0064] Historical height adjustment records can be obtained from wind tunnel experiment records, data acquisition systems, or control systems, and past wind speed data can be obtained through the recording system or sensors. The wind speed can be extracted from wind speed sensors or measuring devices in the wind tunnel. Environmental condition data such as temperature, humidity, and air pressure can be obtained through environmental sensors. This information can be extracted from environmental monitoring systems or laboratory weather stations. Historical wind direction angle data can be obtained through wind direction sensors. Wind direction data is usually recorded by direction sensors during the experiment. According to the experiment records or measurement data, find the historical rising height. The height that the three-hole probe rises during the wind tunnel experiment will be tracked through the control system or manually recorded. Then, after collecting the historical wind speed, environmental information, and wind direction angle data, associate them with the corresponding rising height (i.e., label) to form a dataset. Each record should include wind speed, environmental conditions, wind direction, and the corresponding rising height. Use the historical rising height data to label each record in the first dataset, that is, assign an actual rising height value to each wind speed, environmental information, and wind direction angle data. These labels will be used as the target output during model training. Use an appropriate machine learning model (such as a regression model, neural network model, etc.), input the first dataset (wind speed, environmental information, wind direction angle), and use the rising height label as the target output. During the training process, continuously adjust the parameters of the model so that the model can most accurately predict the corresponding rising height. The model will be trained until it reaches the preset training criteria (such as accuracy, loss, etc.).

[0065] In this solution, by training the model using historical data, the impact of wind speed, environmental conditions, and wind direction angle on the rising height can be predicted more accurately. This helps to better control the height adjustment in wind tunnel experiments and improve the accuracy and reliability of the experiments.

[0066] Figure 2Schematic block diagram of a wind vane precise positioning detection system provided by an embodiment of the present disclosure. It is characterized in that the system further includes a model establishment module 104, and the model establishment module 104 is used for:

[0067] Obtain the structural information of the wind tunnel, and establish a wind tunnel static model according to the structural information;

[0068] Perform mesh division on the wind tunnel static model, and set the fluid characteristics and boundary conditions of the wind tunnel static model to obtain a wind tunnel CFD model.

[0069] In this embodiment, the structural information may include the geometric dimensions, internal structure, shape, material information, air flow channel design, positions of probes and sensors, etc. of the wind tunnel. Usually, this information is obtained through measurement or design drawings. This information is used to construct the initial geometric model of the wind tunnel and determine the flow path of the air flow in the wind tunnel.

[0070] The wind tunnel static model can be the geometric model of the wind tunnel, which only describes the parts that do not change with time, such as the shape and dimensions of the wind tunnel. It can be understood as the three-dimensional structure diagram of the wind tunnel, which is used to determine the air flow path and the positions of equipment.

[0071] The fluid characteristics may refer to the physical parameters of the air flow in the wind tunnel, including density, viscosity, specific heat capacity, etc. These characteristics will affect the simulation results of the air flow.

[0072] The boundary conditions can be the key parameters in the CFD simulation, which define the initial conditions and constraint conditions of the model in different regions.

[0073] The wind tunnel CFD model can be a simulation model that combines the wind tunnel static model with the fluid characteristics and boundary conditions, aiming to simulate the air flow behavior in the wind tunnel.

[0074] The structural information can be obtained through design drawings. These drawings usually include the length, width, height of the wind tunnel, the positions of various equipment (such as wind speed sensors, three-hole probes, flow meters, etc.) and other relevant parameters. Then use three-dimensional modeling software (such as SolidWorks, CATIA, etc.) or finite element analysis (FEA) software (such as ANSYS, COMSOL, etc.) to create the geometric model of the wind tunnel according to the obtained structural information. Then select an appropriate mesh fineness. Important regions (such as around the probe, air flow inlet) should use finer meshes, while other regions can use coarser meshes. And set the fluid characteristics (such as density, viscosity, specific heat capacity, etc.) of the wind tunnel static model according to the operating conditions and experimental requirements of the wind tunnel. Set the boundary conditions according to the inlet, outlet and wall conditions of the wind tunnel. Finally, combine the geometric model, mesh, fluid characteristics and boundary conditions to obtain the wind tunnel CFD model.

[0075] In this embodiment, by precisely defining the structural information and fluid characteristics of the wind tunnel, a more realistic simulation of the airflow behavior can be obtained, thereby improving the accuracy of the test and prediction results.

[0076] Based on the above technical solution, optionally, the system further includes a wind speed prediction module, and the wind speed prediction module is used for:

[0077] Inputting the real-time wind speed information, real-time environmental information, preset time step, and preset prediction time period into the wind tunnel CFD model for transient CFD simulation to obtain the predicted wind speed at the time points corresponding to each preset time step within the preset prediction time period.

[0078] In this solution, the preset time step can be the time interval based on which each calculation is performed during the simulation. It is the time interval for the model to update its state each time. For example, 1 second, 0.5 second, or other appropriate time units. By setting an appropriate time step, it can be ensured that the model can accurately track the airflow changes in the time domain.

[0079] The preset prediction time period can refer to the time range for which simulation and prediction results are desired. For example, if the prediction time period is set to 5 minutes, the simulation will predict the wind speed changes corresponding to each time step within these 5 minutes. This time period is usually set according to the experimental requirements or actual situations.

[0080] The predicted wind speed can be the wind speed value at a future time point calculated by the wind tunnel CFD model. These predicted wind speeds are based on the input real-time wind speed information, real-time environmental information, and other model parameters, helping engineers understand how the wind speed will change within the preset future time period, and thus guiding the adjustment of experiments or control strategies.

[0081] The time step can be set as needed, such as 0.5 seconds or 1 second, for the time resolution of the simulation. Set the total simulation time period, such as predicting the wind speed change in the next 5 minutes. Set the real-time wind speed information as the wind speed boundary condition at the wind tunnel inlet. Use the real-time environmental information to define the physical properties of the fluid (such as density and viscosity), and update the fluid properties of the model to reflect the current environmental conditions. Confirm that the boundary conditions of the model have been set in areas such as the inlet, outlet, and wall. In the CFD software, set the time step and the total prediction time period to ensure that the model can make predictions within this time range. Set the time step as the time increment for the simulation calculation, so that the model performs a calculation update at each time step interval. Set the total prediction time period so that the model can simulate within the entire preset time and output the prediction results at each time point. Start the transient simulation to make the CFD model calculate the change of the air flow in the wind tunnel at the preset time step. The simulation will calculate the evolution of the air flow field as each time step progresses, generating wind speed data at different time points. After the simulation is completed, export the predicted wind speed data corresponding to each time step from the CFD model. Organize this data to obtain the wind speed change at each time point within the preset prediction time period.

[0082] In this solution, based on the current wind speed and environmental information, the model can predict the wind speed change in the future for a period of time, thus providing real-time data support for the experiments and tests in the wind tunnel.

[0083] On the basis of the above technical solution, optionally, the system further includes a wind tunnel motor adjustment module, and the wind tunnel motor adjustment module is used for:

[0084] If a wind speed maintenance instruction transmitted by the control center is received, determine the wind speed deviation at the time points corresponding to each preset time step within the preset prediction time period according to the predicted wind speed and the real-time wind speed information;

[0085] According to the wind speed deviation and the preset motor adjustment formula, determine the motor adjustment frequency at the time points corresponding to each preset time step within the preset prediction time period, and adjust the motor frequency at the time points corresponding to each preset time step within the preset prediction time period according to the motor adjustment frequency.

[0086] In this solution, the wind speed maintenance instruction can be an instruction transmitted from the control center, which is used to keep the wind speed in the wind tunnel within a specified range without deviation. This instruction triggers the system to adjust to ensure that the wind speed meets the set requirements.

[0087] The real-time wind speed information can be the actual wind speed data collected from the wind tunnel environment at the current time point. This information is used for comparing and calculating the wind speed deviation, so as to evaluate the difference from the target wind speed.

[0088] The wind speed deviation can be the difference between a preset target wind speed and the real-time wind speed or the predicted wind speed. The wind speed deviation is usually used for feedback control to determine the motor adjustment amount according to the degree of deviation.

[0089] The preset motor adjustment formula can be a predefined control formula that calculates the required motor adjustment frequency based on the wind speed deviation, so as to adjust the motor frequency to eliminate the wind speed deviation. Specifically, it can be:

[0090]

[0091] where e(t) is the wind speed deviation; K p is the preset proportional gain, which controls the immediate response of the deviation; K i is the preset integral gain, which processes the cumulative deviation and reduces the long-term error; K d is the preset derivative gain, which prevents overshoot according to the rate of change of the deviation;

[0092] The motor adjustment frequency can be the motor frequency adjustment value calculated according to the wind speed deviation. This frequency increment or decrement will be used to adjust the motor to narrow the wind speed deviation.

[0093] The motor speed refers to the number of revolutions per minute of the motor, usually expressed in revolutions per minute (RPM). It describes the number of revolutions of the motor shaft per unit time.

[0094] The control center will transmit a wind speed maintenance instruction to inform the wind tunnel system that it needs to maintain the current wind speed, that is, the real-time wind speed information. Then, the predicted wind speed at the time points corresponding to each preset time step within the preset prediction time period is subtracted from the real-time wind speed information to obtain the wind speed deviation at the time points corresponding to each preset time step within the preset prediction time period. If the predicted wind speed information is greater than the real-time wind speed, the deviation is positive, indicating that the wind speed needs to be increased. If the real-time wind speed information is greater than the predicted wind speed, the deviation is negative, indicating that the wind speed needs to be decreased. Then, the wind speed deviation is substituted into the preset motor adjustment formula to obtain the motor adjustment frequency at the time points corresponding to each preset time step within the preset prediction time period. Finally, according to the calculated motor adjustment frequency, the speed of the motor is adjusted. The control system adjusts the speed of the fan through the motor drive module to control the wind speed. If the wind speed deviation is large, the motor frequency adjustment amplitude is large, and the fan speed accelerates or decelerates. If the wind speed deviation is small, the adjustment amplitude is small, and the fan speed is finely adjusted.

[0095] In this solution, through real-time wind speed prediction and motor adjustment, it is ensured that the wind speed in the wind tunnel is maintained within the preset value or target range, which can maintain the stability of the wind speed in the wind tunnel, reduce the interference of external environmental conditions on the calibration process, that is, reduce the wind speed fluctuation, which is particularly important for many experiments, and enhance the consistency and reliability of the calibration results.

[0096] Based on the above technical solutions, optionally, the model building module is used for:

[0097] Set the grids corresponding to the wall region of the wind tunnel static model as preset fine grids, and set the grids corresponding to the central region of the wind tunnel static model as preset coarse grids;

[0098] Obtain the air density and air viscosity of the wind tunnel, and set the fluid properties of the wind tunnel static model according to the air density and air viscosity of the wind tunnel;

[0099] Obtain the preset initial inlet boundary conditions, preset outlet boundary conditions, and preset wall boundary conditions to set the boundary conditions of the fluid properties of the wind tunnel static model.

[0100] In this solution, the wall region can be the region of the wind tunnel model that contacts the wall, surface, or boundary. In fluid dynamics simulations, the wall region is the contact area between the fluid and the solid surface, where factors such as friction, shear stress, and temperature change between the fluid and the solid usually occur.

[0101] The preset fine grids can be the grid division for the wall region in the wind tunnel model, usually high-density grids. Fine grids can provide more accurate simulation results, especially in the region of flow-surface interaction, such as the calculation of the boundary layer. By using fine grids, the flow characteristics between the fluid and the solid surface can be captured more accurately.

[0102] The central region can be the region of the wind tunnel model that is far from the wall and boundary. In CFD simulations, the central region usually refers to the main part of the flow field, where the flow is relatively uniform and usually does not involve boundary layer effects, so coarser grids can be used for calculation.

[0103] The preset coarse grids can be the grid division for the central region in the wind tunnel model, with larger grids. Coarse grids are suitable for the main fluid region because the flow in these regions is relatively smooth and does not require very fine grids for calculation. Coarse grid calculations are faster but may reduce accuracy.

[0104] The air density of the wind tunnel can be the mass density of the air inside the wind tunnel under specific conditions. It is usually affected by environmental factors such as temperature, pressure, and humidity. Air density is very important in calculating characteristics such as air flow, pressure, and temperature.

[0105] The air viscosity of the wind tunnel can be the fluidity of the air or the frictional force between the internal molecules of the fluid. The viscosity of the air affects the viscous resistance of the air flow. Especially in the calculation of low-speed flow and the boundary layer, the air viscosity has an important impact on the flow behavior of the fluid.

[0106] A mesh generation tool can be used to mesh the wind tunnel model. For the wall region, a fine mesh (higher mesh density) is used to ensure that the interaction effects between the fluid and the surface, such as friction and shear force, can be accurately captured. For the central region, a coarse mesh (lower mesh density) is used, which can speed up the calculation and the flow is relatively smooth in these regions, so a very fine mesh is not required. Common mesh generation methods include structured meshes and unstructured meshes. When meshing, large mesh transformations (i.e., "mesh jumps") should be avoided because this will affect the accuracy of numerical calculations. Through appropriate mesh refinement strategies, finer meshes can be used in key boundary layer regions, and coarser meshes can be used in regions with smooth flow. Then the temperature (T), pressure (P), and humidity (H) of the air can be obtained through meteorological data outside the wind tunnel. The ideal gas equation or relevant empirical formulas are used to calculate the density and viscosity of the air. In the wind tunnel CFD model, the calculated air density and viscosity are input into the fluid properties. According to different conditions of the air flow (such as changes in air temperature and pressure), these property values can be updated at any time to improve the simulation accuracy. The initial inlet boundary conditions are usually defined as the state of the fluid entering the wind tunnel, including the flow velocity (such as wind speed) and pressure. It is usually assumed that the wind speed direction is consistent, and parameters affecting the fluid such as wind speed, temperature, and humidity may need to be considered. Set the inlet flow velocity (such as 25 m / s) and set the inlet conditions according to the change of wind speed. The outlet boundary conditions are the conditions when the fluid leaves the wind tunnel. Common outlet boundary conditions include pressure outlet conditions (for example, set to atmospheric pressure). A suitable outlet pressure value can be set according to the actual situation, or it can be set through the opening flow condition. The wall boundary conditions are usually set to the no-slip condition, that is, the velocity of the fluid on the wind tunnel wall is zero. In addition, the wall temperature, surface roughness, etc. also need to be set. For different wind tunnel wall materials, different boundary conditions may need to be set according to empirical data. Finally, the above boundary conditions and fluid properties are set into the static model of the wind tunnel. The CFD software will provide tools to automate this process, specifying the inlet, outlet, and wall conditions through the user interface and adjusting the corresponding parameters.

[0107] In this solution, by combining mesh refinement and accurate setting of fluid properties, the calculation accuracy can be improved while reducing unnecessary computational burden, thus achieving a more efficient and reliable wind tunnel simulation. This can not only optimize the design of wind tunnel experiments but also provide more accurate experimental results.

[0108] Figure 3 It is a schematic block diagram of a precise positioning detection system for a wind vane provided by an embodiment of the present disclosure. It is characterized in that the system further includes a fault identification module 105, and the fault identification module 105 is used for:

[0109] Obtain the response time, output accuracy, and wear degree of the wind direction sensor, and transmit the response time, output accuracy, and wear degree to a preset fault identification model to obtain the fault score of the wind direction sensor;

[0110] If the fault score exceeds the preset fault score threshold, determine the fault type according to the preset fault identification model, and transmit the fault type to the control center.

[0111] In this solution, the response time can refer to the time required for the wind direction sensor to generate an output signal from receiving an input signal (such as a change in wind direction). It reflects the reaction speed of the sensor to changes and is usually measured in seconds (s).

[0112] The output accuracy can refer to the difference between the output signal of the wind direction sensor and the actual wind direction. The higher the accuracy, the smaller the error between the output signal of the sensor and the actual wind direction, and it is usually measured in degrees or other appropriate units.

[0113] The wear degree can represent the degree of aging, wear, or performance degradation of the sensor components (such as sensor elements, mechanical components) of the wind direction sensor during long-term use due to the influence of mechanical, environmental, or other factors. The wear degree is usually measured by detecting factors such as the working state and performance degradation of the sensor.

[0114] The preset fault identification model can be a model based on machine learning, statistical analysis, or empirical formulas, used to analyze the working state of the sensor and determine whether there is a fault. This model evaluates the health state of the wind direction sensor based on various performance indicators (such as response time, output accuracy, wear degree, etc.) and outputs a fault score or fault type.

[0115] The fault score can be a numerical value output by the fault identification model, indicating the health status of the wind direction sensor. Usually, the higher the score, the greater the probability of the sensor having a fault. This score may be a comprehensive score, reflecting the influence of multiple factors such as response time, output accuracy, and wear degree. Usually, a threshold is set to determine whether the sensor needs to be repaired or replaced.

[0116] The preset fault score threshold can be a pre-set numerical value used to determine whether the sensor has a fault. If the fault score exceeds this threshold, the sensor is considered to have a fault and further maintenance or replacement is required. This threshold is set according to the actual application and the fault tolerance requirements of the system.

[0117] The fault type can refer to the specific categories after a fault occurs in the wind direction sensor. Different fault types may include: slow response, low accuracy, mechanical damage, aging of sensor components, etc. Identifying the fault type helps to determine the root cause of the fault, thereby formulating corresponding repair or replacement strategies.

[0118] The working condition of the wind direction sensor can be monitored to obtain data such as its response time, output accuracy, and degree of wear. These data can be obtained through sensor self-check, regular calibration, or a real-time monitoring system. Inputting these data into the fault identification model, the model will calculate a fault score based on these data. If the score exceeds the set threshold, it is considered that the wind direction sensor may have a fault. Once it is detected that the fault score exceeds the threshold, the fault identification model will further analyze and determine the fault type, such as slow response, decreased accuracy, damage, etc. Finally, the fault type information is transmitted to the control center for further repair or replacement measures.

[0119] In this solution, by monitoring the performance parameters of the sensor (such as response time, accuracy, and degree of wear), potential faults in the sensor can be detected in advance. Early identification of faults can prevent the sensor from failing at critical moments, avoid experiment interruption or data distortion, and ensure the overall stability and reliability of the system.

[0120] Based on the above technical solution, optionally, the training process of the preset fault identification model includes:

[0121] Obtain historical score records, and determine the historical response time, historical output accuracy, historical degree of wear, and historical fault score of the wind direction sensor according to the historical score records;

[0122] Create a second data set according to the historical response time, historical output accuracy, and historical degree of wear, and label the fault score label of the second data set according to the historical fault score;

[0123] Obtain historical fault records, and determine the fault response time, fault output accuracy, fault degree of wear, and fault type when the wind direction sensor has a fault according to the historical fault records;

[0124] Create a third data set according to the fault response time, fault output accuracy, and fault degree of wear, and label the fault type label of the third data set according to the fault type;

[0125] Construct a fault identification model, and train the fault identification model according to the second data set, fault score label, third data set, and fault type label until the fault identification model reaches the preset fault identification model training standard.

[0126] In this solution, the historical scoring records can be records of scoring the historical performance of the wind direction sensor. It can include various evaluation criteria, such as response time, output accuracy, degree of wear, etc. Based on these indicators, a comprehensive score of the working state of the sensor is given. The historical scoring records are used to evaluate the performance of the wind direction sensor in different historical time periods.

[0127] The historical response time can be the time delay from when the wind direction sensor receives an input signal to when it generates an output. Record its response time at different historical time points.

[0128] The historical output accuracy can be the difference between the output value of the wind direction sensor and the actual value. Record its accuracy changes in history.

[0129] The historical degree of wear can be the degree of performance degradation of the wind direction sensor due to mechanical wear or aging and other factors during use.

[0130] The historical fault score can be a score for the faults that occurred in the wind direction sensor in history, evaluating the severity or impact of the faults.

[0131] The second data set can be a collection containing data such as historical response time, historical output accuracy, historical degree of wear, etc., used to train the fault recognition model. Each data sample represents the performance information of the wind direction sensor at a certain time point or in a specific situation.

[0132] The fault score label can be a label used to mark each sample in the second data set, indicating the fault score of the wind direction sensor corresponding to the sample. The fault scores can be classified according to certain criteria (such as 0 - 5 points), and these labels are used to supervise the training of the model.

[0133] The fault response time can be the delay from when the wind direction sensor receives an input signal to when it generates an output in the fault state. Record the response time in the fault state.

[0134] The fault output accuracy can be the output accuracy of the wind direction sensor when a fault occurs, which may be lower than that in the normal state and result in errors.

[0135] The fault degree of wear can be the change in the degree of wear due to damage or aging of the internal components of the wind direction sensor in the fault situation.

[0136] The third data set can be a collection containing characteristic data such as the response time, output accuracy, degree of wear, etc. of the wind direction sensor when a fault occurs. Each data sample corresponds to a specific fault situation and is used to train the model to identify the fault type.

[0137] The fault type label can be a label used to mark each sample in the third dataset, indicating the specific fault type that occurred in the sensor (e.g., electrical fault, mechanical fault, environmental adaptability fault, etc.).

[0138] The preset fault identification model training standard can be a standard used to evaluate the training effect of the fault identification model. Generally, the model needs to meet certain indicators such as accuracy, recall rate, or F1 score before it can be considered to have reached the preset training standard.

[0139] The historical scoring records can be obtained through the operation data, performance monitoring records, or maintenance records of the wind direction sensor. Generally, these data include information such as the response time, output accuracy, and wear degree of the wind direction sensor. Extract the reaction delay or response time of the wind direction sensor from the scoring records. Extract the deviation between the measurement result of the wind direction sensor and the actual value from the scoring records. Estimate the wear degree through long-term operation records, or evaluate the wear condition of the sensor based on the maintenance history. The historical fault score is a score for the severity of each fault. It can be generated through manual recording, automatic fault detection, or sensor self-diagnosis. Integrate the data on response time, output accuracy, and wear degree in the historical scoring records into a dataset. Each data point represents the working state of a sensor and contains multiple features (such as response time, accuracy, wear, etc.). Based on the historical fault score (possibly through fault logs or manual evaluation), add a fault score label to each sample in the dataset, representing the severity of the fault of the sensor in this state. The historical fault records can be obtained from device fault logs, sensor status monitoring systems, maintenance records, etc. It includes detailed information such as the time when the sensor fault occurred, the fault type, the response time, and the output accuracy. Then extract data such as fault response time, output accuracy, and wear degree from the historical fault records to construct the third dataset. Each data point represents the characteristics of a fault situation. Add a label to each data record, and this label indicates the type of the fault (e.g., electrical fault, mechanical fault, environmental fault, etc.). Then, according to the characteristics of the data, a classification model (such as random forest, support vector machine, deep learning model, etc.) can be selected for training. Use the second dataset, fault score label, third dataset, and fault type label as inputs for training. Evaluate the quality of the model according to the performance of the model (such as indicators like accuracy, precision, recall rate, etc.) during the training process. Train until the performance of the model reaches the preset standard. For example, the model can be optimized according to different indicators to reach the set accuracy or recall rate. When the model reaches or exceeds these standards, the training process can be stopped, and this model can be used for actual fault identification tasks.

[0140] In this solution, through the analysis of historical data and model training, potential failure risks can be discovered in advance, so as to take preventive measures in advance and avoid production stagnation or serious losses caused by sudden equipment failures.

[0141] The various embodiments of the systems and techniques described above in this article can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] The program code for implementing the system of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, so that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0143] Figure 4 The flowchart of a method for accurately positioning and detecting a wind vane provided for an embodiment of the present disclosure, characterized in that the method includes:

[0144] S401, obtaining the real-time wind speed information, real-time environmental information of the wind tunnel, and the wind direction angle transmitted by the wind direction sensor, and inputting the real-time wind speed information, real-time environmental information, and wind direction angle into a preset height confirmation model to obtain the rising height of the three-hole probe.

[0145] S402, controlling the three-hole probe to adjust to the rising height, receiving the differential pressure data transmitted by the three-hole probe, calculating the calibration coefficient according to the differential pressure data, and calculating the airflow deflection angle according to the calibration coefficient and a preset fitting formula; wherein, the calibration coefficient includes a velocity coefficient and an angle coefficient.

[0146] S403, adjusting the wind direction angle transmitted by the wind direction sensor according to the airflow deflection angle, and transmitting the adjusted wind direction angle to the control center.

[0147] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0148] For providing interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0149] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or in a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0150] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, or a server of a distributed system, or a server incorporating a blockchain.

[0151] It should be understood that the various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0152] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A precise positioning detection system for a wind vane, characterized in that, The system includes: A height calculation module, which is used to obtain the real-time wind speed information, real-time environmental information of the wind tunnel, and the wind direction angle transmitted by the wind direction sensor, input the real-time wind speed information, real-time environmental information, and wind direction angle into a preset height confirmation model, and obtain the rising height of the three-hole probe; An air flow deflection angle calculation module, which is used to control the three-hole probe to adjust to the rising height, receive the differential pressure data transmitted by the three-hole probe, calculate the calibration coefficient according to the differential pressure data, and calculate the air flow deflection angle according to the calibration coefficient and a preset fitting formula; wherein, the calibration coefficient includes a speed coefficient and an angle coefficient; A wind direction angle adjustment module, which is used to adjust the wind direction angle transmitted by the wind direction sensor according to the air flow deflection angle, and transmit the adjusted wind direction angle to the control center.

2. The system according to claim 1, wherein Wherein, The preset fitting formula is: Among them, α1 is the airflow deflection angle; m is the summation range in the formula, which controls the highest order involved in the fitting formula; p is the coefficient related to the Mach number (Ma); q is the coefficient related to the angle α where the three-hole probe is located; C pq is the preset fitting coefficient, is the velocity coefficient, is the angle coefficient.

3. The system according to claim 1, characterized in that Wherein, The system further includes a model establishment module, and the model establishment module is used for: Obtain the structural information of the wind tunnel, and establish a static wind tunnel model according to the structural information; Perform mesh division on the static wind tunnel model, and set the fluid characteristics and boundary conditions of the static wind tunnel model to obtain a wind tunnel CFD model.

4. The system according to claim 3, wherein, Wherein, The system further includes a wind speed prediction module, and the wind speed prediction module is used for: Input the real-time wind speed information, real-time environmental information, a preset time step, and a preset prediction time period into the wind tunnel CFD model for transient CFD simulation, and obtain the predicted wind speed at the time points corresponding to each preset time step within the preset prediction time period.

5. The system according to claim 4, wherein Wherein, The system further includes a wind tunnel motor adjustment module, and the wind tunnel motor adjustment module is used for: If receiving a wind speed maintenance instruction transmitted by the control center, determine the wind speed deviation at the time points corresponding to each preset time step within the preset prediction time period according to the predicted wind speed and the real-time wind speed information; Determine the motor adjustment frequency at the time points corresponding to each preset time step within the preset prediction time period according to the wind speed deviation and a preset motor adjustment formula, and adjust the motor speed at the time points corresponding to each preset time step within the preset prediction time period according to the motor adjustment frequency.

6. The system according to claim 3, wherein Wherein, The model establishment module is used for: Set the grid corresponding to the wall area of the static wind tunnel model as a preset fine grid, and set the grid corresponding to the central area of the static wind tunnel model as a preset coarse grid; Obtain the air density and air viscosity of the wind tunnel, and set the fluid characteristics of the static wind tunnel model according to the air density and air viscosity of the wind tunnel; Obtain a preset initial inlet boundary condition, a preset outlet boundary condition, and a preset wall boundary condition to set the boundary conditions of the fluid characteristics of the static wind tunnel model.

7. The system according to claim 1, wherein Wherein, The system further includes a fault identification module, and the fault identification module is used for: Obtain the response time, output accuracy, and wear degree of the wind direction sensor, transmit the response time, output accuracy, and wear degree to a preset fault identification model, and obtain the fault score of the wind direction sensor; If the fault score exceeds a preset fault score threshold, determine the fault type according to the preset fault identification model, and transmit the fault type to the control center.

8. The system according to claim 1, wherein Wherein, The training process of a preset height confirmation model includes: Obtain historical height adjustment records, and determine historical wind speed information, historical environmental information, historical wind direction angle, and the historical rising height of the three-hole probe according to the historical height adjustment records; Create a first data set according to the historical wind speed information, historical environmental information, and historical wind direction angle, and label the rising height label of the first data set according to the historical rising height; Construct a height confirmation model, and train the height confirmation model according to the rising height label until the height confirmation model meets the preset height confirmation model training standard.

9. The system according to claim 7, characterized in that, Wherein, The training process of a preset fault identification model includes: Obtain historical scoring records, and determine the historical response time, historical output accuracy, historical wear degree, and historical fault score of the wind direction sensor according to the historical scoring records; Create a second data set according to the historical response time, historical output accuracy, and historical wear degree, and label the fault score label of the second data set according to the historical fault score; Obtain historical fault records, and determine the fault response time, fault output accuracy, fault wear degree, and fault type when the wind direction sensor fails according to the historical fault records; Create a third data set according to the fault response time, fault output accuracy, and fault wear degree, and label the fault type label of the third data set according to the fault type; Construct a fault identification model, and train the fault identification model according to the second data set, fault score label, third data set, and fault type label until the fault identification model meets the preset fault identification model training standard.

10. A method for accurately positioning and detecting a wind vane, characterized in that, The method includes: Obtain the real-time wind speed information, real-time environmental information, and wind direction angle transmitted by the wind direction sensor of the wind tunnel, and input the real-time wind speed information, real-time environmental information, and wind direction angle into the preset height confirmation model to obtain the rising height of the three-hole probe; Control the three-hole probe to adjust to the rising height, receive the differential pressure data transmitted by the three-hole probe, calculate the calibration coefficient according to the differential pressure data, and calculate the airflow deflection angle according to the calibration coefficient and the preset fitting formula; wherein, the calibration coefficient includes a speed coefficient and an angle coefficient; Adjust the wind direction angle transmitted by the wind direction sensor according to the airflow deflection angle, and transmit the adjusted wind direction angle to the control center.

Images