A method, apparatus, equipment, and medium for evaluating visual measurement results of a magnetic levitation wind tunnel.

Abstract

This application discloses a method, apparatus, equipment, and medium for evaluating visual measurement results in a maglev wind tunnel, relating to the field of maglev wind tunnels. The method includes: when a test model placed on a levitating mover moves at high speed within a wind tunnel duct, multiple measurement units deployed within the wind tunnel duct perform visual and temperature measurements on the test model based on a collaborative control strategy to obtain actual motion data including velocity and attitude data, as well as temperature data; extracting motion data within a target motion segment from the actual motion data to generate a time series, and establishing a corresponding time series model to output predicted motion data; determining the R-index for evaluating velocity performance and the error integral performance index for evaluating attitude stability based on the predicted motion data, and determining a temperature safety index based on temperature data and a preset threshold; and using a fuzzy comprehensive evaluation method to comprehensively evaluate each index to obtain the evaluation result. This application achieves a comprehensive evaluation of the motion characteristics of the test model from multiple dimensions and all aspects.

Description

Technical Field

[0001] This invention relates to the field of magnetic levitation wind tunnels, and in particular to a method, apparatus, equipment, and medium for evaluating visual measurement results of magnetic levitation wind tunnels. Background Technology

[0002] A maglev wind tunnel is a novel type of wind tunnel equipment that combines superconducting maglev propulsion technology with supersonic dynamic model testing technology. Its characteristics are: first, "body motion, wind stillness," where the moving object moves at supersonic speeds within the tunnel; and second, wind tunnel testing requires precise information on the moving object's position, velocity changes, and attitude. Existing wind tunnel visual measurement techniques are mostly used in conventional wind tunnels and often have limited measurement dimensions, making it difficult to accurately and comprehensively describe the motion characteristics of the target object. However, maglev wind tunnels, due to the high speed of the suspended moving object and the need to obtain more measurement information, present a significant challenge: how to achieve a comprehensive assessment of the motion characteristics of high-speed moving objects within a maglev wind tunnel remains a problem to be solved. Summary of the Invention

[0003] In view of this, the purpose of this invention is to provide a method, device, equipment, and medium for evaluating the visual measurement results of a magnetic levitation wind tunnel. This method can evaluate indicators corresponding to speed, attitude, and temperature using a fuzzy comprehensive evaluation method, thereby achieving a comprehensive evaluation of the motion characteristics of the test model from multiple dimensions and aspects. The specific solution is as follows:

[0004] Firstly, this application provides a method for evaluating the visual measurement results of a magnetic levitation wind tunnel, including:

[0005] When the test model mounted on the magnetic levitation mover moves at high speed in the wind tunnel duct, multiple measurement units deployed in the wind tunnel duct perform visual and temperature measurements on the test model based on a preset collaborative control strategy to obtain the actual motion data and temperature data of the test model in the entire duct; wherein, the motion data includes velocity data and attitude data;

[0006] The target motion data of the test model within the target motion segment is extracted from the actual motion data to generate a corresponding time series, and a corresponding target time series model is established based on the time series to output the predicted motion data.

[0007] Based on the predicted motion data, an R index for evaluating speed performance and an error integral performance index for evaluating attitude stability are determined, and a temperature safety index is determined based on the temperature data and a preset temperature threshold.

[0008] The fuzzy comprehensive evaluation method is used to evaluate the R index, the error integral performance index, and the temperature safety index to obtain a comprehensive evaluation result for the test model.

[0009] Optionally, the multiple measurement units are units obtained by connecting multiple measurement units; each measurement unit includes an infrared camera for temperature measurement, a supplementary light source, and two high-speed cameras for visual measurement; the two high-speed cameras in each measurement unit are placed at different positions on the inner wall of the wind tunnel duct and simultaneously perform visual measurement on the same area inside the wind tunnel duct; the measurement range of the multiple measurement units covers the entire wind tunnel duct.

[0010] Optionally, when the test model mounted on the magnetic levitation mover is moving at high speed inside the wind tunnel duct, multiple measurement units deployed inside the wind tunnel duct perform visual and temperature measurements on the test model based on a preset collaborative control strategy, including:

[0011] When the test model moves at high speed inside the wind tunnel duct, several measurement units that are currently in the open state and have completed camera debugging are determined from the multiple measurement units; the number of the several measurement units is a positive integer N greater than 1;

[0012] The cameras in each of the several measurement units that are currently in the open state and have completed camera debugging are used to perform visual and temperature measurements on the corresponding areas inside the wind tunnel duct, and feature marking and recognition are performed on the images obtained from the visual measurements.

[0013] The first measurement unit among several measurement units that are currently in the on state and have completed camera debugging is taken as the current measurement unit. If the current measurement unit changes from recognizing a feature mark to not recognizing a feature mark, a pulse signal is sent through the current measurement unit to the target measurement unit that is N-1 measurement units away from the current measurement unit. The direction of the target measurement unit relative to the current measurement unit is consistent with the direction in which the test model moves at high speed in the wind tunnel duct.

[0014] The target measurement unit is activated based on the pulse signal, and the camera contained therein is debugged through the target measurement unit in the activated state so that the two high-speed cameras in the target measurement unit focus on the same area inside the wind tunnel duct. After the camera debugging is completed, the current measurement unit is controlled to be turned off, and the process jumps back to the step of determining several measurement units that are currently in the activated state and have completed camera debugging from the multiple measurement units, until there is no target measurement unit in the multiple measurement units that is N-1 measurement units away from the current measurement unit.

[0015] Optionally, before the test model undergoes high-speed motion within the wind tunnel duct, it further includes:

[0016] When the test model is at the starting position inside the wind tunnel duct, control the first N measurement units in the multi-measurement unit to be turned on;

[0017] The cameras contained in the first N measurement units, which are in the active state, are adjusted so that two high-speed cameras in the same measurement unit focus on the same area inside the wind tunnel duct.

[0018] Optionally, the step of establishing a corresponding target time series model based on the time series to output predicted motion data includes:

[0019] The time series is preprocessed to obtain a processed time series; the preprocessing includes bad value removal, smoothing, centering, and stationarity testing.

[0020] Based on the processed time series, the characteristics of the current correlation coefficient are determined, and based on the characteristics of the current correlation coefficient, a time series model to be established is determined from several different types of stationary time series models; wherein, the correlation coefficient includes the autocorrelation coefficient and the partial autocorrelation coefficient;

[0021] Estimate the model parameters and model order of the time series model to be built, and reconstruct the time series model to be built based on the model parameters and model order to obtain the current time series model;

[0022] If the current time series model fails the residual verification, the process jumps back to the step of determining the features of the current correlation coefficient based on the processed time series.

[0023] If the current time series model passes the residual verification, then the current time series model is determined as the target time series model, and the predicted motion data is output based on the target time series model.

[0024] Optionally, determining the R-index for evaluating velocity performance and the error integral performance index for evaluating attitude stability based on the predicted motion data includes:

[0025] The speed error is determined based on the pre-set speed data and the predicted speed data in the predicted motion data, and the R index for evaluating speed performance is determined based on the speed error and the moving average parameter.

[0026] The attitude error is determined based on the pre-set attitude data and the predicted attitude data in the predicted motion data, and an error integral performance index for evaluating attitude stability is determined based on the attitude error.

[0027] Optionally, the evaluation of the R index, the error integral performance index, and the temperature safety index using the fuzzy comprehensive evaluation method to obtain a comprehensive evaluation result for the test model includes:

[0028] Determine the weight vectors corresponding to each factor in a preset factor set; the preset factor set includes speed factor, attitude factor, and temperature factor.

[0029] Determine the evaluation matrix between each factor in the preset factor set and each evaluation result in the preset evaluation set;

[0030] The R index, the error integral performance index, and the temperature safety index are evaluated using the weight vector and the evaluation matrix to obtain a comprehensive evaluation result for the test model.

[0031] Secondly, this application provides a device for evaluating the visual measurement results of a magnetic levitation wind tunnel, comprising:

[0032] The data measurement module is used to perform visual and temperature measurements on the test model mounted on the magnetic levitation mover when it is moving at high speed in the wind tunnel duct. This is achieved by using multiple measurement units deployed in the wind tunnel duct based on a preset collaborative control strategy. The results are used to obtain the actual motion data and temperature data of the test model throughout the duct. The motion data includes velocity data and attitude data.

[0033] The data prediction module is used to extract the target motion data of the test model within the target motion segment from the actual motion data, so as to generate the corresponding time series, and to build the corresponding target time series model based on the time series, so as to output the predicted motion data.

[0034] The index determination module is used to determine the R index for evaluating speed performance and the error integral performance index for evaluating attitude stability based on the predicted motion data, and to determine the temperature safety index based on the temperature data and a preset temperature threshold.

[0035] The evaluation result acquisition module is used to evaluate the R index, the error integral performance index, and the temperature safety index using the fuzzy comprehensive evaluation method, so as to obtain a comprehensive evaluation result for the test model.

[0036] Thirdly, this application provides an electronic device, comprising:

[0037] Memory, used to store computer programs;

[0038] A processor is used to execute the computer program to implement the aforementioned method for evaluating the visual measurement results of a magnetic levitation wind tunnel.

[0039] Fourthly, this application provides a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the aforementioned method for evaluating the visual measurement results of a magnetic levitation wind tunnel.

[0040] In this application, when the test model mounted on a magnetically levitated mover moves at high speed inside a wind tunnel duct, multiple measurement units deployed inside the wind tunnel duct perform visual and temperature measurements on the test model based on a preset collaborative control strategy to obtain the actual motion data and temperature data of the test model throughout the duct. The motion data includes velocity data and attitude data. Target motion data of the test model within a target motion segment is extracted from the actual motion data to generate a corresponding time series. A corresponding target time series model is then established based on the time series to output predicted motion data. Based on the predicted motion data, an R-index for evaluating velocity performance and an error integral performance index for evaluating attitude stability are determined. A temperature safety index is determined based on the temperature data and a preset temperature threshold. The R-index, the error integral performance index, and the temperature safety index are evaluated using a fuzzy comprehensive evaluation method to obtain a comprehensive evaluation result for the test model. Therefore, this application measures the high-speed motion test model by deploying multiple measurement units within the wind tunnel duct based on a preset collaborative control strategy. This ensures that the measurement range covers the entire wind tunnel duct, eliminating blind spots and enabling complete measurement of the test model within the entire duct. Furthermore, this application predicts motion data using a time series model, avoiding potential errors caused by directly using actual measured motion data. Moreover, this application evaluates the indicators corresponding to velocity, attitude, and temperature using a fuzzy comprehensive evaluation method, achieving a comprehensive assessment of the motion characteristics of the test model from multiple dimensions and aspects. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0042] Figure 1 This is a flowchart of a method for evaluating visual measurement results of a magnetic levitation wind tunnel disclosed in this application;

[0043] Figure 2 This is a flowchart of a time series model establishment and prediction method disclosed in this application;

[0044] Figure 3 This application discloses a fuzzy comprehensive evaluation flowchart;

[0045] Figure 4 This application discloses a measurement flowchart for a multi-measurement unit deployed inside a wind tunnel duct.

[0046] Figure 5 This is a schematic diagram of a collaborative control strategy disclosed in this application;

[0047] Figure 6 This is a flowchart illustrating the workflow of a single measurement unit disclosed in this application;

[0048] Figure 7 This is a data flow diagram of a single measurement unit disclosed in this application;

[0049] Figure 8 This is a schematic diagram of the structure of a magnetic levitation wind tunnel visual measurement result evaluation device disclosed in this application;

[0050] Figure 9 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Due to the high speed of the suspended motion vehicles and the greater amount of measurement information required in maglev wind tunnels, a comprehensive evaluation of the motion characteristics of high-speed moving bodies within the tunnel remains a challenge. To address this, this application provides a visual measurement result evaluation method for maglev wind tunnels. This method uses fuzzy comprehensive evaluation to assess indicators corresponding to speed, attitude, and temperature, achieving a multi-dimensional and comprehensive evaluation of the motion characteristics of the experimental model.

[0053] See Figure 1 As shown, this embodiment of the invention discloses a method for evaluating the visual measurement results of a magnetic levitation wind tunnel, including:

[0054] Step S11: When the test model mounted on the magnetic levitation mover moves at high speed in the wind tunnel pipe, the test model is subjected to visual and temperature measurements by multiple measurement units deployed in the wind tunnel pipe based on a preset collaborative control strategy, so as to obtain the actual motion data and temperature data of the test model in the entire pipe; wherein, the motion data includes speed data and attitude data.

[0055] In this embodiment, a single measurement unit is established within the maglev wind tunnel duct based on optical path characteristics and field-of-view requirements. This single measurement unit includes two high-speed cameras for binocular visual measurement, one infrared camera for temperature measurement, and two supplementary lighting sources, all positioned inside the wind tunnel duct and close to the duct wall. It should be noted that the two high-speed cameras in the single measurement unit are positioned at different locations on the inner wall of the wind tunnel duct and simultaneously perform visual measurements on the same area within the duct. The multi-measurement unit, on the other hand, is a unit formed by connecting multiple single measurement units. These units are connected via transmission lines to achieve data transmission between them. Furthermore, the measurement range of the multi-measurement unit covers the entire wind tunnel duct, thus avoiding blind spots within the duct's field of view.

[0056] In this embodiment, after the multiple measurement units are deployed in the wind tunnel duct, when the test model mounted on the magnetic levitation mover is moving at high speed in the wind tunnel duct, the multiple measurement units deployed in the wind tunnel duct perform visual and temperature measurements on the high-speed moving test model based on a pre-set cooperative control strategy, thereby obtaining the actual motion data and temperature data of the test model in the entire duct; wherein, the motion data includes speed data and attitude data.

[0057] Step S12: Extract the target motion data of the test model within the target motion segment from the actual motion data to generate a corresponding time series, and establish a corresponding target time series model based on the time series to output the predicted motion data.

[0058] In this embodiment, target motion data of the experimental model within a target motion segment is extracted from the actual motion data of the experimental model within the entire pipeline; the target motion segment can be any segment within the entire pipeline. Then, a corresponding time series is generated based on the target motion data, and a corresponding target time series model is established based on the time series to output predicted motion data. Specifically, a corresponding velocity time series is generated based on the velocity data contained in the target motion data, and a corresponding target time series model is established based on the velocity time series to output predicted velocity data. A corresponding attitude time series is generated based on the attitude data contained in the target motion data, and a corresponding target time series model is established based on the attitude time series to output predicted attitude data.

[0059] Specifically, such as Figure 2As shown, target motion data of the experimental model within the target motion segment is extracted from the actual motion data of the experimental model within the entire pipeline, and a corresponding time series is generated based on the target motion data. The time series is then preprocessed to obtain a processed time series; the preprocessing includes outlier handling, smoothing, centering, and stationarity testing. Based on the processed time series, the characteristics of the current correlation coefficient are determined; the correlation coefficient includes the autocorrelation coefficient (AC) and the partial autocorrelation coefficient (PAC); the characteristics of the correlation coefficient are tailing and truncation; truncation includes p-order truncation and q-order truncation. Then, based on the characteristics of the current correlation coefficient, the time series model to be established is identified from several different types of stationary time series models; these different types of stationary time series models include the autoregressive moving average (ARMA), autoregressive (AR), and moving average (MA) models. It should be noted that if the autocorrelation coefficient exhibits tailing and the partial autocorrelation coefficient exhibits p-order truncation, then an AR model should be selected; if the autocorrelation coefficient exhibits q-order truncation and the partial autocorrelation coefficient exhibits tailing, then an MA model should be selected; if both the autocorrelation coefficient and the partial autocorrelation coefficient exhibit tailing, then an ARMA model should be selected.

[0060] Furthermore, such as Figure 2As shown, after identifying the time series model to be built, the model parameters and model order are estimated. The model parameters can be estimated using methods such as the method of moments, maximum likelihood estimation, and least squares estimation. The model order can be estimated using the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC). After determining the model parameters and model order, the time series model is reconstructed based on these parameters and order to obtain the current time series model. Residual verification is then performed on the current time series model to determine whether it passes the residual verification, i.e., whether it has sufficiently extracted the time series. If the current time series model fails the residual verification, it indicates that the current time series model has not sufficiently extracted the time series, triggering a model adjustment operation to return to the steps described above for determining the characteristics of the current correlation coefficient based on the processed time series. If the current time series model passes the residual verification, it indicates that the current time series model has fully extracted the time series, thus determining the current time series model as the target time series model, and performing prediction and control based on the target time series model to output predicted motion data; wherein, the predicted motion data includes predicted velocity data and predicted attitude data.

[0061] Step S13: Based on the predicted motion data, determine the R index for evaluating speed performance and the error integral performance index for evaluating attitude stability, and determine the temperature safety index based on the temperature data and a preset temperature threshold.

[0062] In this embodiment, an R-index for evaluating speed performance is determined based on predicted velocity data included in the predicted motion data, and an error integral performance index for evaluating attitude stability is determined based on predicted attitude data included in the predicted motion data. The error integral performance indices include IAE (Integral Absolute Error), ISE (Integral Square Error), ITAE (Integral Time Absolute Error), and ITSE (Integral Time Square Error). Furthermore, a temperature safety index is determined based on temperature data and a preset temperature threshold, provided by the provider of the experimental model. The temperature safety index increases rapidly as the temperature data approaches the preset temperature threshold.

[0063] According to one embodiment, for predicted speed data included in predicted motion data, a speed error is determined based on pre-set speed data and the predicted speed data included in the predicted motion data, and an R-index for evaluating speed performance is determined based on the speed error and a moving average parameter. The relevant formula is as follows:

[0064] ;

[0065] ;

[0066] ;

[0067] ;

[0068] Among them, y sp This represents the preset speed data; y i Indicates predicted speed data; e i α represents the speed error; α represents the moving average parameter; σ represents the speed error. 2 and δ 2 These are two representations of variance; R i The R index is used to evaluate speed performance.

[0069] According to another embodiment, for the predicted attitude data included in the predicted motion data, an attitude error is determined based on pre-set attitude data and the predicted attitude data included in the predicted motion data, and an error integral performance index for evaluating attitude stability is determined based on the attitude error. The relevant formula is as follows:

[0070] ;

[0071] ;

[0072] ;

[0073] ;

[0074] Among them, IAE, ISE, ITAE, and ITSE are four error integral performance indicators used to evaluate attitude stability; t represents time; e(t) represents the attitude error, which is the error determined based on pre-set attitude data and the predicted attitude data included in the predicted motion data. It should be noted that by using velocity and attitude data predicted by time series models, it is possible to avoid directly using velocity and attitude data from actual motion data that may contain measurement errors, thereby improving the accuracy of the comprehensive evaluation of the motion characteristics of the experimental model.

[0075] Step S14: Use the fuzzy comprehensive evaluation method to evaluate the R index, the error integral performance index, and the temperature safety index to obtain a comprehensive evaluation result for the test model.

[0076] In this embodiment, as Figure 3 As shown, before using the fuzzy comprehensive evaluation method, it is necessary to first determine the preset factor set U and the preset evaluation set V of the evaluation object; where the evaluation object is the test model that moves at high speed in the wind tunnel duct; the preset factor set U includes speed factor, attitude factor and temperature factor; the preset evaluation set V includes excellent, good and average and poor.

[0077] Furthermore, such as Figure 3 As shown, after obtaining the R index, error integral performance index, and temperature safety index, the weight vectors corresponding to each factor in the preset factor set are determined to obtain the weight vector matrix A; and the evaluation matrix R between each factor in the preset factor set and each evaluation result in the preset evaluation set is determined; the weight vectors and evaluation matrix are used to perform fuzzy synthesis of the R index, error integral performance index, and temperature safety index to obtain the comprehensive evaluation result B for the motion characteristics of the test model, and the comprehensive evaluation result can be further analyzed and processed to provide a visual display for the user.

[0078] Therefore, this application measures the high-speed motion test model by deploying multiple measurement units within the wind tunnel duct based on a preset collaborative control strategy. This ensures that the measurement range covers the entire wind tunnel duct, eliminating blind spots and enabling complete measurement of the test model within the entire duct. Furthermore, this application predicts motion data using a time series model, avoiding potential errors caused by directly using actual measured motion data. Moreover, this application evaluates the indicators corresponding to velocity, attitude, and temperature using a fuzzy comprehensive evaluation method, achieving a comprehensive assessment of the motion characteristics of the test model from multiple dimensions and aspects.

[0079] Based on the previous embodiment, this embodiment will now elaborate on how to perform visual and temperature measurements on a high-speed moving test model using multiple measurement units deployed within a wind tunnel duct, based on a preset collaborative control strategy. See [link to previous embodiment]. Figure 4 As shown, an embodiment of the present invention discloses a measurement process with multiple measurement units, including:

[0080] Step S21: When the test model is moving at high speed in the wind tunnel duct, determine a number of measurement units that are currently in the open state and have completed camera debugging from the multiple measurement units; the number of the number of measurement units is a positive integer N greater than 1.

[0081] In this embodiment, as Figure 5As shown, before the test model undergoes high-speed motion inside the wind tunnel duct, it is initially positioned within the duct's starting point. Specifically, the test model mounted on the magnetically levitated mover is initially stationary within the field of view of the initial measurement unit in the multi-measurement unit system. At this point, the first N measurement units are activated, where N is a positive integer greater than 1, for example, N can be chosen as 2. Then, the cameras within each of the activated first N measurement units are adjusted to ensure that the two high-speed cameras in the same measurement unit focus on the same area within the wind tunnel duct.

[0082] Furthermore, when the test model moves at high speed from the starting position to the terminal position in the wind tunnel duct, several measurement units that are currently in the open state and have completed camera debugging are first identified from the multiple measurement units. At this time, the several measurement units that are currently in the open state and have completed camera debugging are the first N measurement units.

[0083] Step S22: Visual and temperature measurements are performed on the corresponding areas within the wind tunnel duct using the cameras contained in each of the several measurement units that are currently in the open state and have completed camera debugging, and feature marking and recognition are performed on the images obtained from the visual measurements.

[0084] In this embodiment, the infrared cameras in each of the several measurement units, which are currently in the active state and have completed camera debugging, measure the temperature of the corresponding area inside the wind tunnel duct. The original temperature obtained from the temperature measurement is then compensated to obtain the temperature data of the test model. Two high-speed cameras in each of the several measurement units, which are currently in the active state and have completed camera debugging, perform binocular visual measurement of the corresponding area inside the wind tunnel duct. Feature marker recognition is performed on the visually measured image. If a feature marker is identified, the pixel coordinates of the center point of the feature marker are determined, and the corresponding three-dimensional world coordinates are calculated based on the parallax principle and triangulation principle. Based on these three-dimensional world coordinates, the velocity and attitude data of the test model are then calculated.

[0085] Step S23: Take the first measurement unit among the several measurement units that are currently in the on state and have completed camera debugging as the current measurement unit. If the current measurement unit changes from recognizing a feature mark to not recognizing a feature mark, then send a pulse signal through the current measurement unit to the target measurement unit that is N-1 measurement units away from the current measurement unit. The direction of the target measurement unit relative to the current measurement unit is consistent with the direction in which the test model moves at high speed in the wind tunnel duct.

[0086] In this embodiment, as Figure 5As shown, the first measurement unit among several measurement units that are currently in the on state and have completed camera debugging is determined as the current measurement unit. If the current measurement unit changes from recognizing a feature mark to not recognizing a feature mark, that is, the current measurement unit changes from acquiring a feature recognition signal to losing a feature recognition signal, then a pulse signal is sent through the current measurement unit to the target measurement unit that is N-1 measurement units away from the current measurement unit. The direction of the target measurement unit relative to the current measurement unit is consistent with the direction of the test model's high-speed movement in the wind tunnel duct.

[0087] Taking the first two measurement units as an example, which are currently in the open state and have completed camera debugging, the first measurement unit in the first two measurement units is determined as the current measurement unit. If the current measurement unit previously identified a feature mark, that is, obtained a feature recognition signal, but currently does not identify a feature mark, that is, lost the feature recognition signal, then the current measurement unit sends a pulse signal to the target measurement unit that is one measurement unit away from the current measurement unit in the multiple measurement units. At this time, the target measurement unit is the third measurement unit in the multiple measurement units.

[0088] Step S24: Based on the pulse signal, turn on the target measurement unit, and use the target measurement unit in the turned-on state to debug the camera contained locally, so that the two high-speed cameras in the target measurement unit focus on the same area in the wind tunnel duct. After the camera debugging is completed, control the current measurement unit to turn off, and jump back to the step of determining several measurement units that are currently in the turned-on state and have completed camera debugging from multiple measurement units, until there is no target measurement unit in the multiple measurement units that is N-1 measurement units away from the current measurement unit.

[0089] In this embodiment, as Figure 5As shown, after the current measurement unit sends a pulse signal to the target measurement unit that is N-1 measurement units away from the current measurement unit in the multi-measurement unit, the target measurement unit is turned on based on the pulse signal. The camera contained in the target measurement unit is then debugged through the target measurement unit in the turned-on state so that the two high-speed cameras in the target measurement unit focus on the same area inside the wind tunnel duct. After the camera debugging is completed, the current measurement unit is turned off. Then, the process jumps back to step S21, which involves determining the number of measurement units that are currently turned on and have completed camera debugging from the multi-measurement units. The corresponding areas inside the wind tunnel duct are then visually and temperature-measured again through the cameras contained in each of the number of measurement units that are currently turned on and have completed camera debugging, until there is no target measurement unit that is N-1 measurement units away from the current measurement unit in the multi-measurement units. That is, the test model mounted on the magnetic levitation mover has reached the field of view of the Nth measurement unit from the end of the multi-measurement units. At this point, as the test model mounted on the magnetic levitation rotor moves from the field of view of the Nth to the end position inside the wind tunnel duct, the last N measurement units in the multi-measurement unit remain in the open state, while the other measurement units remain in the closed state. Furthermore, when the test model mounted on the magnetic levitation rotor reaches the end position inside the wind tunnel duct, the full-duct measurement of the test model is completed.

[0090] It should be noted that, as Figure 6 As shown, the specific operation for activating a measurement unit includes: after the processor in the measurement unit is powered on, the post-processing system in the measurement unit performs an initialization operation, automatically sets the intrinsic and extrinsic parameters of the high-speed camera, and sends the intrinsic and extrinsic parameters of the high-speed camera to the vision measurement system in the measurement unit through the data transmission communication system. Then, the vision measurement system performs image calibration and target area focusing on the two high-speed cameras respectively after startup based on the intrinsic and extrinsic parameters of the high-speed camera, thereby enabling the two high-speed cameras in the measurement unit to focus on the same area inside the wind tunnel duct, realizing binocular vision measurement of the same area inside the wind tunnel duct.

[0091] Furthermore, such as Figure 6As shown, the acquisition of velocity and attitude data of the test model includes: real-time visual recording of the same area inside the wind tunnel duct using two high-speed cameras in the measurement unit, storage of the acquired image data, and transmission of the acquired image data to the post-processing system via a data transmission communication system. The post-processing system receives the image data from the two high-speed cameras, performs preprocessing and feature marker recognition. If a feature marker is identified, the pixel coordinates of the center point of the feature marker are determined, and the corresponding three-dimensional world coordinates are calculated based on the parallax principle and triangulation principle. Based on these three-dimensional world coordinates, the velocity and attitude data of the test model are then calculated. Furthermore, the acquisition of temperature data of the test model includes: temperature measurement of the corresponding area inside the wind tunnel duct using an infrared camera in the measurement unit. Since the angle between the test model and the infrared camera affects the temperature measured by the infrared camera, temperature compensation is required for the original temperature measured by the infrared camera to obtain the temperature data of the test model. Further, the temperature, velocity, and attitude data of the test model are stored and analyzed to create corresponding charts for intuitive display.

[0092] Considering that two high-speed cameras in the same measurement unit need to simultaneously perform visual measurements of the same area inside the wind tunnel duct, therefore, referencing Figure 7 As shown, the image acquisition command is triggered by the synchronization controller in the measurement unit and sent to the processor in the measurement unit. The processor then sends the image acquisition command to the two high-speed cameras via a switch, thereby achieving synchronous image data acquisition from the two high-speed cameras. Furthermore, after acquiring image data, the two high-speed cameras send the image data to the processor via the switch. The processor then stores and analyzes the image data and visualizes the analysis results in the form of data reports, data documents, and data charts.

[0093] Therefore, this embodiment measures the high-speed moving test model by deploying multiple measurement units within the wind tunnel duct based on a preset collaborative control strategy. This ensures that the measurement range covers the entire wind tunnel duct, eliminating blind spots within the duct and enabling complete measurement of the test model throughout the entire duct. Furthermore, this embodiment constructs measurement units based on high-speed and infrared cameras, enabling non-contact measurement of the high-speed moving test model within the wind tunnel duct. This avoids the negative impact on the aerodynamic performance and motion characteristics of the test model caused by adding external sensors. Non-contact measurement results are objective, visible, and reliable, and offer advantages such as easy installation, detachability, and small size, ensuring the reliability of the measurement data.

[0094] See Figure 8As shown, this embodiment of the invention discloses a device for evaluating the visual measurement results of a magnetic levitation wind tunnel, comprising:

[0095] The data measurement module 11 is used to perform visual and temperature measurements on the test model mounted on the magnetic levitation mover when it is moving at high speed in the wind tunnel duct. This is done by multiple measurement units deployed in the wind tunnel duct based on a preset collaborative control strategy, so as to obtain the actual motion data and temperature data of the test model in the entire duct. The motion data includes velocity data and attitude data.

[0096] The data prediction module 12 is used to extract the target motion data of the test model in the target motion segment from the actual motion data, so as to generate the corresponding time series, and to establish the corresponding target time series model based on the time series, so as to output the predicted motion data.

[0097] The index determination module 13 is used to determine the R index for evaluating speed performance and the error integral performance index for evaluating attitude stability based on the predicted motion data, and to determine the temperature safety index based on the temperature data and a preset temperature threshold.

[0098] The evaluation result acquisition module 14 is used to evaluate the R index, the error integral performance index and the temperature safety index using the fuzzy comprehensive evaluation method, so as to obtain a comprehensive evaluation result for the test model.

[0099] Therefore, this application measures the high-speed motion test model by deploying multiple measurement units within the wind tunnel duct based on a preset collaborative control strategy. This ensures that the measurement range covers the entire wind tunnel duct, eliminating blind spots and enabling complete measurement of the test model within the entire duct. Furthermore, this application predicts motion data using a time series model, avoiding potential errors caused by directly using actual measured motion data. Moreover, this application evaluates the indicators corresponding to velocity, attitude, and temperature using a fuzzy comprehensive evaluation method, achieving a comprehensive assessment of the motion characteristics of the test model from multiple dimensions and aspects.

[0100] In some specific embodiments, the multiple measurement units are units obtained by connecting multiple measurement units; each measurement unit includes an infrared camera for temperature measurement, a supplementary light source, and two high-speed cameras for visual measurement; the two high-speed cameras in each measurement unit are placed at different positions on the inner wall of the wind tunnel duct and simultaneously perform visual measurement on the same area inside the wind tunnel duct; the measurement range of the multiple measurement units covers the entire wind tunnel duct.

[0101] In some specific embodiments, the data measurement module 11 includes:

[0102] A measurement unit determination unit is used to determine, from the multiple measurement units, a number of measurement units that are currently in the active state and have completed camera debugging when the test model is moving at high speed inside the wind tunnel duct; the number of the multiple measurement units is a positive integer N greater than 1;

[0103] The feature marker recognition unit is used to perform visual and temperature measurements on the corresponding areas inside the wind tunnel duct using the cameras contained in each of the several measurement units that are currently in the open state and have completed camera debugging, and to perform feature marker recognition on the images obtained from the visual measurements.

[0104] The pulse signal transmitting unit is used to select the first measurement unit among several measurement units that are currently in the on state and have completed camera debugging as the current measurement unit. If the current measurement unit changes from recognizing a feature mark to not recognizing a feature mark, a pulse signal is sent through the current measurement unit to the target measurement unit that is N-1 measurement units away from the current measurement unit. The direction of the target measurement unit relative to the current measurement unit is consistent with the direction in which the test model moves at high speed in the wind tunnel duct.

[0105] The first step jump unit is used to turn on the target measurement unit based on the pulse signal, and to debug the camera contained in the local area through the target measurement unit in the turned-on state, so that the two high-speed cameras in the target measurement unit focus on the same area in the wind tunnel duct. After the camera debugging is completed, the current measurement unit is controlled to turn off, and the jump is restarted to the step of determining several measurement units that are currently in the turned-on state and have completed camera debugging from the multiple measurement units, until there is no target measurement unit in the multiple measurement units that is N-1 measurement units away from the current measurement unit.

[0106] In some specific embodiments, the magnetic levitation wind tunnel visual measurement result evaluation device further includes:

[0107] The measurement unit activation unit is used to control the activation of the first N measurement units among the multiple measurement units when the test model is at the starting position inside the wind tunnel duct.

[0108] A camera debugging unit is used to debug the cameras contained in the first N measurement units, which are in the open state, so that two high-speed cameras in the same measurement unit can focus on the same area inside the wind tunnel duct.

[0109] In some specific embodiments, the data prediction module 12 includes:

[0110] A time series processing unit is used to preprocess the time series to obtain a processed time series; the preprocessing includes bad value handling, smoothing, centering, and stationarity testing;

[0111] The model determination unit is used to determine the characteristics of the current correlation coefficient based on the processed time series, and to determine the time series model to be established from several different types of stationary time series models based on the characteristics of the current correlation coefficient; wherein, the correlation coefficient includes the autocorrelation coefficient and the partial autocorrelation coefficient;

[0112] The model reconstruction unit is used to estimate the model parameters and model order of the time series model to be built, and to reconstruct the time series model to be built based on the model parameters and model order to obtain the current time series model.

[0113] The second step jump unit is used to jump back to the step of determining the features of the current correlation coefficient based on the processed time series if the current time series model fails the residual verification.

[0114] The prediction data output unit is used to determine the current time series model as the target time series model if the current time series model passes the residual verification, and output the predicted motion data based on the target time series model.

[0115] In some specific embodiments, the indicator determination module 13 includes:

[0116] The first index determination unit is used to determine the speed error based on the pre-set speed data and the predicted speed data in the predicted motion data, and to determine the R index for evaluating speed performance based on the speed error and the moving average parameter.

[0117] The second index determination unit is used to determine the attitude error based on the pre-set attitude data and the predicted attitude data in the predicted motion data, and to determine the error integral performance index for evaluating attitude stability based on the attitude error.

[0118] In some specific embodiments, the evaluation result acquisition module 14 includes:

[0119] The weight vector determination unit is used to determine the weight vectors corresponding to each factor in a preset factor set; the preset factor set includes speed factor, attitude factor, and temperature factor.

[0120] The evaluation matrix determination unit is used to determine the evaluation matrix between each factor in the preset factor set and each evaluation result in the preset evaluation set.

[0121] The index evaluation unit is used to evaluate the R index, the error integral performance index, and the temperature safety index using the weight vector and the evaluation matrix, so as to obtain a comprehensive evaluation result for the test model.

[0122] Furthermore, embodiments of this application also disclose an electronic device, Figure 9 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0123] Figure 9 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the magnetic levitation wind tunnel visual measurement result evaluation method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0124] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0125] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored thereon can include an operating system 221, computer programs 222, etc., and the storage method can be temporary storage or permanent storage.

[0126] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the magnetic levitation wind tunnel visual measurement result evaluation method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0127] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned method for evaluating the visual measurement results of a magnetic levitation wind tunnel. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0128] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0129] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0130] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0131] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0132] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for evaluating the visual measurement results of a magnetic levitation wind tunnel, characterized in that, include: When the test model mounted on the magnetic levitation mover moves at high speed in the wind tunnel duct, multiple measurement units deployed in the wind tunnel duct perform visual and temperature measurements on the test model based on a preset collaborative control strategy to obtain the actual motion data and temperature data of the test model in the entire duct; wherein, the motion data includes velocity data and attitude data; The target motion data of the test model within the target motion segment is extracted from the actual motion data to generate a corresponding time series, and a corresponding target time series model is established based on the time series to output the predicted motion data. Based on the predicted motion data, an R index for evaluating speed performance and an error integral performance index for evaluating attitude stability are determined, and a temperature safety index is determined based on the temperature data and a preset temperature threshold. The fuzzy comprehensive evaluation method is used to evaluate the R index, the error integral performance index, and the temperature safety index to obtain a comprehensive evaluation result for the test model. The multiple measurement units are units formed by connecting multiple measurement units; each measurement unit includes an infrared camera for temperature measurement, a supplementary light source, and two high-speed cameras for visual measurement; the two high-speed cameras in each measurement unit are placed at different positions on the inner wall of the wind tunnel duct and simultaneously perform visual measurement on the same area inside the wind tunnel duct; the measurement range of the multiple measurement units covers the entire wind tunnel duct. Specifically, when the test model mounted on the magnetic levitation mover moves at high speed inside the wind tunnel duct, multiple measurement units deployed inside the wind tunnel duct perform visual and temperature measurements on the test model based on a preset collaborative control strategy, including: When the test model moves at high speed inside the wind tunnel duct, several measurement units that are currently in the open state and have completed camera debugging are determined from the multiple measurement units; the number of the several measurement units is a positive integer N greater than 1; The cameras in each of the several measurement units that are currently in the open state and have completed camera debugging are used to perform visual and temperature measurements on the corresponding areas inside the wind tunnel duct, and feature marking and recognition are performed on the images obtained from the visual measurements. The first measurement unit among several measurement units that are currently in the on state and have completed camera debugging is taken as the current measurement unit. If the current measurement unit changes from recognizing a feature mark to not recognizing a feature mark, a pulse signal is sent through the current measurement unit to the target measurement unit that is N-1 measurement units away from the current measurement unit. The direction of the target measurement unit relative to the current measurement unit is consistent with the direction in which the test model moves at high speed in the wind tunnel duct. The target measurement unit is activated based on the pulse signal, and the camera contained therein is debugged through the target measurement unit in the activated state so that the two high-speed cameras in the target measurement unit focus on the same area inside the wind tunnel duct. After the camera debugging is completed, the current measurement unit is controlled to be turned off, and the process jumps back to the step of determining several measurement units that are currently in the activated state and have completed camera debugging from the multiple measurement units, until there is no target measurement unit in the multiple measurement units that is N-1 measurement units away from the current measurement unit.

2. The method for evaluating the visual measurement results of a magnetic levitation wind tunnel according to claim 1, characterized in that, Before the test model undergoes high-speed motion within the wind tunnel duct, it also includes: When the test model is at the starting position inside the wind tunnel duct, control the first N measurement units in the multi-measurement unit to be turned on; The cameras contained in the first N measurement units, which are in the active state, are adjusted so that two high-speed cameras in the same measurement unit focus on the same area inside the wind tunnel duct.

3. The method for evaluating the visual measurement results of a magnetic levitation wind tunnel according to claim 1, characterized in that, The step of establishing a corresponding target time series model based on the time series to output predicted motion data includes: The time series is preprocessed to obtain a processed time series; the preprocessing includes bad value removal, smoothing, centering, and stationarity testing. Based on the processed time series, the characteristics of the current correlation coefficient are determined, and based on the characteristics of the current correlation coefficient, a time series model to be established is determined from several different types of stationary time series models; wherein, the correlation coefficient includes the autocorrelation coefficient and the partial autocorrelation coefficient; Estimate the model parameters and model order of the time series model to be built, and reconstruct the time series model to be built based on the model parameters and model order to obtain the current time series model; If the current time series model fails the residual verification, the process jumps back to the step of determining the features of the current correlation coefficient based on the processed time series. If the current time series model passes the residual verification, then the current time series model is determined as the target time series model, and the predicted motion data is output based on the target time series model.

4. The method for evaluating the visual measurement results of a magnetic levitation wind tunnel according to claim 1, characterized in that, The determination of the R-index for evaluating velocity performance and the error integral performance index for evaluating attitude stability based on the predicted motion data includes: The speed error is determined based on the pre-set speed data and the predicted speed data in the predicted motion data, and the R index for evaluating speed performance is determined based on the speed error and the moving average parameter. The attitude error is determined based on the pre-set attitude data and the predicted attitude data in the predicted motion data, and an error integral performance index for evaluating attitude stability is determined based on the attitude error.

5. The method for evaluating the visual measurement results of a magnetic levitation wind tunnel according to any one of claims 1 to 4, characterized in that, The evaluation of the R-index, the error integral performance index, and the temperature safety index using the fuzzy comprehensive evaluation method to obtain a comprehensive evaluation result for the test model includes: Determine the weight vectors corresponding to each factor in a preset factor set; the preset factor set includes speed factor, attitude factor, and temperature factor. Determine the evaluation matrix between each factor in the preset factor set and each evaluation result in the preset evaluation set; The R index, the error integral performance index, and the temperature safety index are evaluated using the weight vector and the evaluation matrix to obtain a comprehensive evaluation result for the test model.

6. A device for evaluating the visual measurement results of a magnetic levitation wind tunnel, characterized in that, The apparatus is used to implement the method for evaluating the visual measurement results of a magnetic levitation wind tunnel as described in any one of claims 1 to 5, the apparatus comprising: The data measurement module is used to perform visual and temperature measurements on the test model mounted on the magnetic levitation mover when it is moving at high speed in the wind tunnel duct. This is achieved by using multiple measurement units deployed in the wind tunnel duct based on a preset collaborative control strategy. The results are used to obtain the actual motion data and temperature data of the test model throughout the duct. The motion data includes velocity data and attitude data. The data prediction module is used to extract the target motion data of the test model within the target motion segment from the actual motion data, so as to generate the corresponding time series, and to build the corresponding target time series model based on the time series, so as to output the predicted motion data. The index determination module is used to determine the R index for evaluating speed performance and the error integral performance index for evaluating attitude stability based on the predicted motion data, and to determine the temperature safety index based on the temperature data and a preset temperature threshold. The evaluation result acquisition module is used to evaluate the R index, the error integral performance index, and the temperature safety index using the fuzzy comprehensive evaluation method, so as to obtain a comprehensive evaluation result for the test model.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the method for evaluating the visual measurement results of a magnetic levitation wind tunnel as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store a computer program, which, when executed by a processor, implements the method for evaluating the visual measurement results of a magnetic levitation wind tunnel as described in any one of claims 1 to 5.

Images