A method and equipment for calibrating the rotor pitch of an electric aircraft

Abstract

This application provides a method and apparatus for calibrating the rotor pitch of an electric aircraft, belonging to the field of rotor pitch calibration. The method includes: controlling a servo motor to drive the rotor rotation; recording the servo motor travel value during the rotation process; measuring the collective pitch, longitudinal periodic pitch, and lateral periodic pitch of the rotor when the servo motor reaches each travel value; calculating the forward transformation matrix between the servo motor travel value and the three corresponding pitch coefficients using a cubic fitting method; generating training samples using the forward transformation matrix; inputting the training samples into a neural network for training to obtain the inverse transformation relationship between the servo motor travel value and the three pitch coefficients; and calibrating the rotor pitch of the electric aircraft using the aforementioned forward transformation matrix and inverse transformation relationship.

Description

Technical Field

[0001] This application relates to the field of rotor pitch calibration technology, specifically to a method and equipment for calibrating the rotor pitch of an electric aircraft. Background Technology

[0002] As aircraft begin to integrate into people's production and daily lives, the aircraft manufacturing industry is booming, and various small and medium-sized electric aircraft are providing convenience for people's lives. Using electrical equipment to replace mechanical equipment and controlling electric aircraft through electrical control strategies has become a current research hotspot, including the main propulsion motor of the aircraft rotor. Compared to traditional rotor drive and control methods, controlling the operation of the main propulsion motor allows for precise control of rotor speed and rotation angle, while controlling the electric servo motor allows for precise control of the servo motor's travel value. This fundamentally changes the rotor control method, but it also places higher demands on the accuracy of pitch calibration, and traditional pitch calibration methods still have considerable room for improvement. Therefore, in the context of aircraft electrification, it is necessary to propose new rotor pitch calibration methods suitable for electrically driven rotors.

[0003] Since research on aircraft electrification has only gradually emerged in recent years, the methods applicable to rotor pitch calibration for electric aircraft need to be optimized. Therefore, there is an urgent need to propose a new method for rotor pitch calibration of electric aircraft to more accurately calibrate rotor pitch. Summary of the Invention

[0004] In view of the technical problems existing in the background art, this application provides a method and device for calibrating the rotor pitch of an electric aircraft. The method obtains the positive transformation matrix relationship and inverse transformation relationship between the servo travel value and the collective pitch value, the longitudinal periodic pitch value and the lateral periodic pitch value through cubic fitting and neural network training, thereby realizing the calibration of the rotor pitch of the electric aircraft.

[0005] In a first aspect, embodiments of this application provide a method for calibrating the rotor pitch of an electric aircraft, including:

[0006] Control the servo motor to drive the rotor to rotate;

[0007] During the process of controlling the servo motor to drive the rotor to rotate, the servo motor travel value during the rotation process is recorded; and the total pitch value, longitudinal periodic pitch value and lateral periodic pitch value of the rotor are measured when the servo motor moves to each of the servo motor travel values.

[0008] By using a cubic fitting method, the positive transformation matrix between the collective pitch value, the longitudinal periodic pitch value, and the lateral periodic pitch value and the servo travel value is calculated using each of the servo travel values ​​and the corresponding collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value.

[0009] Multiple sets of collective pitch values, longitudinal periodic pitch values, and lateral periodic pitch values ​​are randomly generated and input into the positive transformation matrix to generate servo travel values ​​corresponding to the servo travel values, thereby forming training samples;

[0010] The training samples are input into the neural network for training to obtain the inverse transformation relationship between the collective pitch value, the longitudinal periodic pitch value, the lateral periodic pitch value and the servo travel value.

[0011] In the technical solution of this application embodiment, the positive transformation matrix relationship and inverse transformation relationship between the servo travel value and the collective pitch value, the longitudinal periodic pitch value and the lateral periodic pitch value are obtained by means of cubic fitting and neural network training, thereby realizing the calibration of the rotor pitch of the electric aircraft.

[0012] In some embodiments, measuring the collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch of the rotor when the servo motor moves to each of the servo motor travel values ​​includes:

[0013] Set the advance control angle of the rotor;

[0014] The rotor rotation is controlled according to the servo travel value;

[0015] Control the rotation of the rotor blades and measure the blade angular distance at 0°, 90°, 180°, and 270° azimuths;

[0016] The collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch values ​​corresponding to the servo travel value are calculated based on the advance control angle and the propeller pitch measured at 0°, 90°, 180°, and 270° azimuths.

[0017] In this embodiment, the pitch angles of the blades are measured at four positions (0°, 90°, 180°, 270°) to ensure that the pitch angles of the blades are uniform in different positions, thereby providing more accurate parameter support for the rotor pitch calibration process.

[0018] In some embodiments, measuring the collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch of the rotor when the servo motor moves to each of the servo motor travel values ​​further includes:

[0019] Set the initial installation angle, lateral deflection angle, and longitudinal deflection angle of the rotor;

[0020] After obtaining the propeller pitches at 0°, 90°, 180°, and 270° azimuths, the propeller pitches at 0°, 90°, 180°, and 270° azimuths are corrected using the initial installation angle, the lateral deflection angle, and the longitudinal deflection angle to obtain the corrected propeller pitches.

[0021] The collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch values ​​corresponding to the servo travel value are calculated based on the advance control angle and the corrected propeller pitch measured at 0°, 90°, 180°, and 270° azimuths.

[0022] In this embodiment, the propeller pitches at 0°, 90°, 180°, and 270° azimuths are corrected using the initial installation angle, the lateral deflection angle, and the longitudinal deflection angle. The corrected propeller pitches can then be used to calculate more accurate collective pitch values. Longitudinal periodic pitch Lateral periodic pitch .

[0023] In some embodiments, recording the servo motor travel value during the servo motor rotation process while controlling the servo motor to drive the rotor rotation includes:

[0024] Set the total distance, the highest point of the servo travel, the lowest point of the servo travel, the minimum displacement difference, and the maximum displacement difference;

[0025] A sequence of servo travel values ​​is generated based on the total distance, the highest point of the servo travel, the lowest point of the servo travel, the minimum displacement difference, and the maximum displacement difference;

[0026] The servo travel value is calculated using the servo travel value sequence.

[0027] In this embodiment, the servo travel value is calculated by the servo travel value sequence, which can greatly improve the control accuracy of the servo, optimize power output and response time, and prevent overtravel damage.

[0028] In some embodiments, in calculating the positive transformation matrix between the servo travel value and the collective pitch value, the longitudinal periodic pitch value and the lateral periodic pitch value, the positive transformation matrix is:

[0029]

[0030] Where: L1, L2, and L3 are a set of servo travel values. This is the total distance value. For longitudinal periodic pitch value, , where is the lateral periodic pitch value, and A, B, C, and C are the coefficients obtained by fitting each group of servo travel values ​​with the corresponding collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value through three-dimensional fitting.

[0031] In this embodiment, the positive transformation matrix between the servo travel value and the collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch values ​​is obtained through cubic fitting. Actual experiments revealed that the relationship between the servo travel value and the three pitch coefficients (collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch) is approximately a straight line in the image, but it is not a perfect match and still has some deviation. Therefore, compared to traditional linear fitting, the cubic fitting method used in this embodiment is closer to the actual situation, has smaller errors, and better fitting results, enabling better calibration of the rotor pitch of electric aircraft.

[0032] In some embodiments, after calculating the positive transformation matrix between the collective pitch value, the longitudinal periodic pitch value, the lateral periodic pitch value, and the servo travel value, the target collective pitch value, the target longitudinal periodic pitch value, and the target lateral periodic pitch value are input into the positive transformation matrix to calculate the target servo travel value. The drive rotor is controlled to rotate according to the target servo travel value, and the actual collective pitch value, the actual longitudinal periodic pitch value, and the actual lateral periodic pitch value of the rotor are measured. The accuracy of the positive transformation matrix is ​​verified by comparing the target collective pitch value, the target longitudinal periodic pitch value, and the target lateral periodic pitch value with the actual collective pitch value, the actual longitudinal periodic pitch value, and the actual lateral periodic pitch value.

[0033] In this embodiment, by verifying the accuracy of the positive transformation matrix, the reliability of the servo travel value obtained by the positive transformation matrix can be determined, which can effectively improve the stability and reliability of the rotor pitch calibration.

[0034] In some embodiments, inputting the training samples into a neural network for training includes:

[0035] Construct a BP neural network with 3, 10, and 3 neurons in the input layer, hidden layer, and output layer, respectively.

[0036] The servo travel value in the training samples is used as input, and the collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value corresponding to the servo travel value are used as output. The BP neural network automatically adjusts the weight coefficients of the connections between each layer by comparing the error between the network output and the target output, thus completing the training of the BP neural network.

[0037] In this embodiment, the servo travel value and the three pitch coefficients are not in a one-to-one correspondence in the forward transformation matrix obtained by cubic fitting, which may lead to inverse transformation errors. Therefore, if inverse cubic fitting is still used to implement the inverse transformation process, the resulting error cannot be explained by which formula it originates from, which may cause errors when the servo travel value is inversely transformed into the three pitch coefficients. Therefore, in order to solve the problem of potential errors in the inverse transformation process achieved by inverse cubic fitting, this embodiment also uses the cubic fitting equation to obtain a large number of data samples, uses these data samples to train a neural model, and implements the inverse transformation between the servo travel value and the three pitch coefficients, thereby effectively reducing the error in the inverse transformation between the servo travel value and the three pitch coefficients.

[0038] In some embodiments, after obtaining the inverse transformation relationship between the collective pitch value, the longitudinal periodic pitch value, the lateral periodic pitch value, and the servo travel value, a set of given servo travel values ​​is input into the BP neural network. The theoretical collective pitch value, theoretical longitudinal periodic pitch value, and theoretical lateral periodic pitch value corresponding to the given servo travel value are calculated by the BP neural network. The drive rotor is controlled to rotate according to the given servo travel value, and the actual collective pitch value, actual longitudinal periodic pitch value, and actual lateral periodic pitch value of the rotor are measured. By comparing the theoretical collective pitch value, the theoretical longitudinal periodic pitch value, and the theoretical lateral periodic pitch value with the actual collective pitch value, the actual longitudinal periodic pitch value, and the actual lateral periodic pitch value, the accuracy of the inverse transformation relationship between the collective pitch value, the longitudinal periodic pitch value, the lateral periodic pitch value, and the servo travel value is verified.

[0039] In this embodiment, the reliability of the pitch coefficient obtained by the inverse transform relationship of the BP neural network is judged by verifying the accuracy of the BP neural network inverse transform relationship, thereby improving the stability and reliability of the rotor pitch calibration.

[0040] This application also discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the electric aircraft rotor pitch calibration method as described in any of the preceding claims.

[0041] This application also discloses an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor is used to execute the computer program stored in the memory to implement the electric aircraft rotor pitch calibration method as described in any of the preceding claims.

[0042] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in this application will be briefly described below. Obviously, the drawings described below are merely some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort.

[0044] Figure 1 This is a flowchart of the rotor pitch calibration method in the embodiments of this application;

[0045] Figure 2 This is a diagram of a three-layer BP neural network model in an embodiment of this application;

[0046] Figure 3 This is a flowchart of the BP neural network algorithm in the embodiments of this application. Detailed Implementation

[0047] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0048] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0049] In this document, the term "comprising" indicates the presence of a described feature, integral, step, operation, element, and / or component, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," with exclusions being otherwise specifically emphasized. Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying one or more of the feature. In the description of embodiments of this application, unless otherwise stated, "a plurality of" means two or more.

[0050] In this text, the term "and / or" simply describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " in this text generally indicates that the preceding and following related objects have an "or" relationship.

[0051] As aircraft begin to integrate into people's production and daily lives, the aircraft manufacturing industry is booming, and various small and medium-sized electric aircraft are providing convenience for people's lives. Using electrical equipment to replace mechanical equipment and controlling electric aircraft through electrical control strategies has become a current research hotspot, including the main propulsion motor of the aircraft rotor. Compared to traditional rotor drive and control methods, controlling the operation of the main propulsion motor allows for precise control of rotor speed and rotation angle, while controlling the electric servo motor allows for precise control of the servo motor's travel value. This fundamentally changes the rotor control method, but it also places higher demands on the accuracy of pitch calibration, and traditional pitch calibration methods still have considerable room for improvement. Therefore, in the context of aircraft electrification, it is necessary to propose new rotor pitch calibration methods suitable for electrically driven rotors.

[0052] To address the technical problem of how to more accurately calibrate the rotor pitch of electric aircraft using a novel method, this application provides a method and apparatus for calibrating the rotor pitch of electric aircraft. This method obtains the positive and inverse transformation matrix relationships between servo travel values ​​and collective pitch, longitudinal cyclic pitch values, and lateral cyclic pitch values ​​through cubic fitting and neural network training, thereby achieving the technical effect of calibrating the rotor pitch of electric aircraft.

[0053] As aircraft begin to integrate into people's production and daily lives, the aircraft manufacturing industry is booming, and various small and medium-sized electric aircraft are providing convenience for people's lives. Using electrical equipment to replace mechanical equipment and controlling electric aircraft through electrical control strategies has become a current research hotspot, including the main propulsion motor of the aircraft rotor. Compared to traditional rotor drive and control methods, controlling the operation of the main propulsion motor allows for precise control of rotor speed and rotation angle, while controlling the electric servo motor allows for precise control of the servo motor's travel value. The flight attitude and direction of an electric aircraft are mainly controlled by three independent servo systems: a longitudinal cyclic pitch servo, a lateral cyclic pitch servo, and a collective pitch servo. The longitudinal cyclic pitch servo affects the forward-backward distribution of lift by changing the angle of the front and rear blades of the main rotor, thus controlling the helicopter's pitch. The lateral cyclic pitch servo affects the left-right distribution of lift by changing the angle of the left and right blades of the main rotor, thus controlling the helicopter's roll. The collective pitch servo affects the magnitude of lift by controlling the overall pitch angle of the main rotor, i.e., controlling the helicopter's ascent or descent. The three sets of servos control parameters such as collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch of the main rotor of the electric aircraft to maintain the stability of the helicopter and achieve different flight maneuvers.

[0054] This embodiment discloses a method for calibrating the rotor pitch of an electric aircraft. Please refer to [link / reference]. Figure 1 The process includes: controlling the servo motor to drive the rotor rotation; recording the servo motor travel value during the servo motor rotation process; measuring the collective pitch, longitudinal periodic pitch, and lateral periodic pitch of the rotor when the servo motor moves to each servo motor travel value; and calculating the positive transformation matrix between the collective pitch, longitudinal periodic pitch, and lateral periodic pitch and the servo motor travel value by using a cubic fitting method.

[0055] Multiple sets of collective pitch values, longitudinal periodic pitch values, and lateral periodic pitch values ​​are randomly generated and input into the forward transformation matrix to generate servo travel values ​​corresponding to the servo travel values, thus forming training samples. The training samples are then input into the neural network for training to obtain the inverse transformation relationship between the collective pitch values, longitudinal periodic pitch values, lateral periodic pitch values, and servo travel values.

[0056] In this embodiment, the forward transformation matrix and inverse transformation relationship between the servo travel value and the collective pitch value, the longitudinal periodic pitch value, and the lateral periodic pitch value are obtained through cubic fitting and neural network training. The forward transformation matrix describes the relationship between the servo travel value and the collective pitch value, the longitudinal periodic pitch value, and the lateral periodic pitch value, while the inverse transformation relationship is used to derive the collective pitch value, the longitudinal periodic pitch value, and the lateral periodic pitch value from the servo travel value. The above forward transformation matrix and inverse transformation relationship can be used to calibrate the rotor pitch of the electric aircraft.

[0057] Secondly, in this embodiment, the positive transformation matrix between the servo travel value and the collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch values ​​is obtained through cubic fitting. Actual experiments revealed that the relationship between the servo travel value and the three pitch coefficients (collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch) is approximately a straight line in the image, but it is not a perfect match and still has some deviation. Therefore, compared to traditional linear fitting, the cubic fitting method used in this embodiment is closer to the actual situation, has smaller errors, and better fitting results, enabling better calibration of the rotor pitch of electric aircraft.

[0058] However, since the servo travel value and the three pitch coefficients are not in a one-to-one correspondence in the forward transformation matrix obtained by cubic fitting, inverse transformation errors may exist. Therefore, if inverse cubic fitting is still used to implement the inverse transformation process, the resulting error cannot be explained by which formula it originates from, which may lead to errors when the servo travel value is inversely transformed into the three pitch coefficients. Therefore, in order to solve the problem of potential errors in the inverse transformation process achieved by inverse cubic fitting, this embodiment also uses the cubic fitting equation to obtain a large number of data samples, uses these data samples to train a neural model, and implements the inverse transformation between the servo travel value and the three pitch coefficients, thereby effectively reducing the error in the inverse transformation between the servo travel value and the three pitch coefficients.

[0059] In this embodiment, measuring the rotor's collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch when the servo motor moves to each servo motor travel value includes:

[0060] Set the advance control angle of the rotor; and control the rotor rotation according to the servo travel value;

[0061] After the servo controls the rotor to rotate to a predetermined angle, it controls the rotor blades to rotate and measures the blade pitch at 0°, 90°, 180°, and 270°.

[0062] The collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch values ​​corresponding to the servo travel value are calculated based on the advance control angle and the propeller pitch measured at 0°, 90°, 180°, and 270° azimuths.

[0063] Specifically, the advance control angle of the electric aircraft rotor was first obtained through experiments. And control the rotor rotation based on the servo motor travel value;

[0064] After the servo motor controls the rotor to rotate to a predetermined angle, it controls the rotor blades to rotate. Once the electric aircraft rotor is running stably, the pitch angle is measured and recorded using sensors at four blade positions (0°, 90°, 180°, 270°), and marked as the pitch angle. , , , ;

[0065] Given the advance control angle Then the blades are in the azimuth angle The pitch at a certain point satisfies the following relationship:

[0066] (1)

[0067] Among them, in the above formula The blades are in azimuth angles, in order. The pitch angle, collective pitch of the rotor under this operating condition, longitudinal cyclic pitch, and lateral cyclic pitch.

[0068] Substituting the pitch angle data at the four azimuth positions above into equation (1) above, we can obtain:

[0069] (2)

[0070] Represented in matrix form, we get:

[0071] (3)

[0072] In the above equation (3), All are known, therefore, in the above formula It can be represented as:

[0073]

[0074] in, for The MP generalized inverse matrix.

[0075] So, the result calculated using this method The values ​​are, in order, the collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch of the rotor under the corresponding travel of the servo motor.

[0076] In one possible embodiment, in order to obtain more accurate propeller pitch angles, after obtaining the propeller pitches at 0°, 90°, 180°, and 270° azimuths, it is also necessary to correct the propeller pitches at 0°, 90°, 180°, and 270° azimuths.

[0077] Specifically, the initial installation angle of the rotor needs to be set before calibration. Lateral deflection angle Longitudinal deflection angle ;

[0078] After obtaining the propeller pitches at 0°, 90°, 180°, and 270° azimuths, the propeller pitches at these azimuths are corrected using the initial installation angle, lateral deflection angle, and longitudinal deflection angle according to the following formula:

[0079]

[0080] This will give you the corrected propeller pitch angles at the four azimuth positions. .

[0081] Known advance control angle Then the blades are in the azimuth angle The pitch at a certain point satisfies the following relationship:

[0082] (1)

[0083] Among them, in the above formula The blades are in azimuth angles, in order. The pitch angle, collective pitch of the rotor under this operating condition, longitudinal cyclic pitch, and lateral cyclic pitch.

[0084] Substituting the corrected pitch angle data at the four azimuth positions into the above formula, we get:

[0085]

[0086] Represented in matrix form, we get:

[0087]

[0088] In the above formula, All are known, therefore, in the above formula It can be represented as:

[0089]

[0090] in, for The MP generalized inverse matrix.

[0091] Following this method, through the corrected pitch angle It can calculate a more accurate total distance value Longitudinal periodic pitch Lateral periodic pitch .

[0092] In this embodiment, during the process of controlling the servo motor to drive the rotor rotation, the servo motor travel value recorded during the rotation process includes:

[0093] Set the total calibration distance. servo motor travel minimum point servo motor travel maximum point Minimum displacement difference Maximum displacement difference At the lowest point of the servo travel The starting point, the highest point of the servo motor travel. As the endpoint, calibrate the total distance. Given the sequence length, uniformly distribute the intervals to generate the total interval sequence. With minimum displacement difference Starting point, maximum displacement difference Midpoint, minimum displacement difference As the endpoint, calibrate the total distance. Given the sequence length, uniformly distribute the intervals to generate the displacement difference sequence. The following formula is used to generate the servo motor travel value sequence. :

[0094]

[0095] in Given a 4x3 empirical matrix, after processing, we can obtain... Group servo travel values, each group of servo travel values ​​is a set containing... A matrix of three data points, These represent the travel values ​​of the three servos, respectively.

[0096] In this embodiment, the servo travel value is calculated by the servo travel value sequence, which can greatly improve the control accuracy of the servo, optimize power output and response time, and prevent overtravel damage.

[0097] In this embodiment, the positive transformation matrix between the calculated servo travel value and collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value is:

[0098]

[0099] Where: L1, L2, and L3 are a set of servo travel values. This is the total distance value. For longitudinal periodic pitch value, , where is the lateral periodic pitch value, and A, B, C, and C are the coefficients obtained by fitting each group of servo travel values ​​with the corresponding collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value through three-dimensional fitting.

[0100] Specifically, a cubic fitting method is used to obtain the servo motor travel value. and three pitch coefficients The relationship can be fitted into the following matrix form:

[0101]

[0102] in,

[0103] Expanding the above equation, we get the following three equations:

[0104]

[0105] Each set of servo travel values ​​and three propeller pitch coefficients yields three equations. To solve for the 30 unknowns in the four coefficient matrices (A, B, C, and D) of these equations, at least 10 sets of measurement data are required. Assuming that through measurement, we obtain... If there are multiple sets of data, then a total of [number] can be listed. The equations are divided into three systems as follows:

[0106]

[0107]

[0108]

[0109] This overdetermined system of equations can be transformed into standard matrix equations through rearrangement and transformation. Format:

[0110]

[0111]

[0112]

[0113] Then use the formula It can then be calculated The least squares solution can be obtained, and the remaining equations can be solved in the same way. This will yield the values ​​of the 30 unknowns in the four coefficient matrices, and thus the relationship between the servo travel value and the pitch coefficient can be obtained.

[0114] In this embodiment, after calculating the positive transformation matrix between the collective pitch, longitudinal periodic pitch, and lateral periodic pitch values ​​and the servo travel value, the target collective pitch, target longitudinal periodic pitch, and target lateral periodic pitch values ​​are input into the positive transformation matrix to calculate the target servo travel value. The rotor is controlled to rotate according to the target servo travel value, and the actual collective pitch, actual longitudinal periodic pitch, and actual lateral periodic pitch values ​​of the rotor are measured. The accuracy of the positive transformation matrix is ​​verified by comparing the target collective pitch, target longitudinal periodic pitch, and target lateral periodic pitch values ​​with the actual collective pitch, actual longitudinal periodic pitch, and actual lateral periodic pitch values. The reliability of the servo travel value obtained by the positive transformation matrix is ​​judged by verifying the accuracy of the positive transformation matrix, thereby improving the stability and reliability of the rotor pitch calibration.

[0115] Secondly, in this embodiment, three target pitch coefficients can be given, and the servo travel value can be calculated using linear fitting and cubic fitting methods respectively. Using this travel value as input, a pitch calibration experiment is conducted to obtain the measured values ​​of the three pitch coefficients. By comparing the target values ​​and measured values ​​of the three pitch coefficients, and using the mean square error (MSE) as the evaluation index, the errors and fitting effects of the two methods are calculated and compared. The results are shown in Table 1 below. The pitch calibration method using cubic fitting in this application can significantly improve the fitting effect compared to linear fitting, which is of great help to engineering practice.

[0116] Table 1 Comparison of errors between linear fitting and cubic fitting

[0117]

[0118] See Figure 2-3 In this embodiment, during the process of inputting training samples into the neural network for training:

[0119] Use the newff function from the MATLAB Neural Network Toolbox to build a BP neural network with 3, 10, and 3 neurons in the input layer, hidden layer, and output layer, respectively.

[0120] The transfer functions of the hidden layer and output layer neurons are the tansig function and the purelin function, respectively, and the network training algorithm uses the Levenberg-Marquardt algorithm trainlm.

[0121] The servo travel value in the training samples is used as input, and the collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value corresponding to the servo travel value are used as output. The BP neural network automatically adjusts the weight coefficients of the connections between each layer by comparing the error between the network output and the target output, thus completing the training of the BP neural network and obtaining the inverse transformation relationship between the collective pitch value, longitudinal periodic pitch value, lateral periodic pitch value and servo travel value.

[0122] In this embodiment, since the servo travel value and the three pitch coefficients are not in a one-to-one correspondence in the forward transformation matrix obtained by cubic fitting, there may be inverse transformation errors. Therefore, if the inverse cubic fitting is still used to implement the inverse transformation process, the resulting error cannot be explained by which formula it originates from, which may lead to errors when the servo travel value is inversely transformed into the three pitch coefficients. Therefore, in order to solve the problem of potential errors in the inverse transformation process using the inverse cubic fitting, this embodiment also uses the cubic fitting equation to obtain a large number of data samples, and uses these data samples to train a neural model to realize the inverse transformation between the servo travel value and the three pitch coefficients, thereby effectively reducing the error in the inverse transformation between the servo travel value and the three pitch coefficients. Therefore, this enables the BP neural network to quickly and accurately implement the inverse transformation process, meeting the needs of engineering practice.

[0123] In this embodiment, after obtaining the inverse transformation relationship between the collective pitch, longitudinal periodic pitch, and lateral periodic pitch values ​​and the servo travel value, a set of given servo travel values ​​is input into the BP neural network. The theoretical collective pitch, theoretical longitudinal periodic pitch, and theoretical lateral periodic pitch values ​​corresponding to the given servo travel values ​​are calculated by the BP neural network. The rotor rotation is controlled according to the given servo travel values, and the actual collective pitch, actual longitudinal periodic pitch, and actual lateral periodic pitch values ​​of the rotor are measured. By comparing the theoretical collective pitch, theoretical longitudinal periodic pitch, and theoretical lateral periodic pitch values ​​with the actual collective pitch, actual longitudinal periodic pitch, and actual lateral periodic pitch values, the accuracy of the inverse transformation relationship between the collective pitch, longitudinal periodic pitch, and lateral periodic pitch values ​​and the servo travel value is verified. By verifying the accuracy of the inverse transformation relationship of the BP neural network, the reliability of the pitch coefficient obtained by the inverse transformation relationship of the BP neural network is judged, thereby improving the stability and reliability of the rotor pitch calibration.

[0124] Secondly, in this embodiment, given a set of servo travel values, the theoretical values ​​of three pitch coefficients are calculated using inverse linear fitting, inverse cubic fitting, and BP neural network methods, respectively. Simultaneously, in the pitch calibration test, measurements are taken when the servo is at the given servo travel value to obtain the measured values ​​of the three pitch coefficients. By comparing the target values ​​and measured values ​​of the three pitch coefficients, and using the mean square error (MSE) as the evaluation index, the errors and fitting effects of the three methods are calculated and compared. The results are shown in Table 2 below. It is found that the error of the result calculated by the BP neural network is negligible. Furthermore, the calculation speed of the three methods is similar during the solution process. Therefore, it is considered that the BP neural network can quickly and accurately realize the inverse transformation process, meeting the needs of engineering practice.

[0125] Table 2 Comparison of errors of inverse linear fitting, inverse cubic fitting, and BP neural network

[0126]

[0127] Those skilled in the art will 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, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application of the technical solution and the constraints involved. 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.

[0128] When the embodiments of this application are implemented using software, they can be implemented entirely or partially in the form of a computer program product. That is, the implementation of all or part of the processes in the methods of the above embodiments can also be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0129] This application also discloses an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to execute the computer program stored in the memory to implement the electric aircraft rotor pitch calibration method described above.

[0130] It should be noted that this application is not limited to the above-described embodiments. The above embodiments are merely examples, and any embodiments with the same structure and effect as the technical concept within the scope of this application are included in the technical scope of this application. Furthermore, various modifications that can be conceived by those skilled in the art to the embodiments, and other ways of constructing by combining some of the constituent elements of the embodiments, without departing from the spirit of this application, are also included in the scope of this application.

Claims

1. A method for calibrating the rotor pitch of an electric aircraft, characterized in that, include: Control the servo motor to drive the rotor to rotate; During the process of controlling the servo motor to drive the rotor rotation, the servo motor travel value during the rotation process is recorded; And measure the total pitch, longitudinal cyclic pitch, and lateral cyclic pitch of the rotor when the servo moves to each of the servo travel values; By using a cubic fitting method, the positive transformation matrix between the collective pitch value, the longitudinal periodic pitch value, and the lateral periodic pitch value and the servo travel value is calculated using each of the servo travel values ​​and the corresponding collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value. Multiple sets of collective pitch values, longitudinal periodic pitch values, and lateral periodic pitch values ​​are randomly generated and input into the positive transformation matrix to generate servo travel values ​​corresponding to the servo travel values, thereby forming training samples; The training samples are input into the neural network for training to obtain the inverse transformation relationship between the collective pitch value, the longitudinal periodic pitch value, the lateral periodic pitch value and the servo travel value; The process of recording the servo motor travel value during the control of the servo motor to drive the rotor rotation includes: Set the total distance, the highest point of the servo travel, the lowest point of the servo travel, the minimum displacement difference, and the maximum displacement difference; A sequence of servo travel values ​​is generated based on the total distance, the highest point of the servo travel, the lowest point of the servo travel, the minimum displacement difference, and the maximum displacement difference; The servo travel value is calculated using the servo travel value sequence.

2. The method for calibrating the rotor pitch of an electric aircraft according to claim 1, characterized in that, The measurement of the rotor's collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch when the servo motor moves to each of the servo motor travel values ​​includes: Set the advance control angle of the rotor; The rotor rotation is controlled according to the servo travel value; Control the rotation of the rotor blades and measure the blade angular distance at 0°, 90°, 180°, and 270° azimuths; The collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch values ​​corresponding to the servo travel value are calculated based on the advance control angle and the propeller pitch measured at 0°, 90°, 180°, and 270° azimuths.

3. The method for calibrating the rotor pitch of an electric aircraft according to claim 2, characterized in that, The measurement of the rotor's collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch values ​​when the servo motor moves to each of the servo motor travel values ​​also includes: Set the initial installation angle, lateral deflection angle, and longitudinal deflection angle of the rotor; After obtaining the propeller pitches at 0°, 90°, 180°, and 270° azimuths, the propeller pitches at 0°, 90°, 180°, and 270° azimuths are corrected using the initial installation angle, the lateral deflection angle, and the longitudinal deflection angle to obtain the corrected propeller pitches. The collective pitch, longitudinal cyclic pitch, and lateral cyclic pitch values ​​corresponding to the servo travel value are calculated based on the advance control angle and the corrected propeller pitch measured at 0°, 90°, 180°, and 270° azimuths.

4. The method for calibrating the rotor pitch of an electric aircraft according to claim 1, characterized in that, In the positive transformation matrix calculated between the servo travel value and the collective pitch value, the longitudinal periodic pitch value, and the lateral periodic pitch value, the positive transformation matrix is: Wherein: L1, L2, and L3 are a set of servo motor travel values. The total distance value, For the longitudinal periodic pitch value, The lateral periodic pitch value is denoted as A, B, C, and D, which are coefficients obtained by cubic fitting of each of the servo travel values ​​with the corresponding collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value.

5. The method for calibrating the rotor pitch of an electric aircraft according to claim 1, characterized in that, After calculating the positive transformation matrix between the collective pitch value, the longitudinal periodic pitch value, the lateral periodic pitch value, and the servo travel value, the target collective pitch value, the target longitudinal periodic pitch value, and the target lateral periodic pitch value are input into the positive transformation matrix to calculate the target servo travel value. The rotor rotation is controlled according to the target servo travel value, and the actual collective pitch value, the actual longitudinal periodic pitch value, and the actual lateral periodic pitch value of the rotor are measured. The accuracy of the positive transformation matrix is ​​verified by comparing the target collective pitch value, the target longitudinal periodic pitch value, and the target lateral periodic pitch value with the actual collective pitch value, the actual longitudinal periodic pitch value, and the actual lateral periodic pitch value.

6. The method for calibrating the rotor pitch of an electric aircraft according to claim 1, characterized in that, The training samples are input into the neural network for training, including: Construct a BP neural network with 3, 10, and 3 neurons in the input layer, hidden layer, and output layer, respectively. The servo travel value in the training samples is used as input, and the collective pitch value, longitudinal periodic pitch value, and lateral periodic pitch value corresponding to the servo travel value are used as output. The BP neural network automatically adjusts the weight coefficients of the connections between each layer by comparing the error between the network output and the target output, thus completing the training of the BP neural network.

7. The method for calibrating the rotor pitch of an electric aircraft according to claim 6, characterized in that, After obtaining the inverse transformation relationship between the collective pitch value, the longitudinal periodic pitch value, the lateral periodic pitch value, and the servo travel value, a set of given servo travel values ​​is input into the BP neural network. The theoretical collective pitch value, theoretical longitudinal periodic pitch value, and theoretical lateral periodic pitch value corresponding to the given servo travel value are calculated by the BP neural network. The rotor rotation is controlled according to the given servo travel value, and the actual collective pitch value, actual longitudinal periodic pitch value, and actual lateral periodic pitch value of the rotor are measured. By comparing the theoretical collective pitch value, the theoretical longitudinal periodic pitch value, and the theoretical lateral periodic pitch value with the actual collective pitch value, the actual longitudinal periodic pitch value, and the actual lateral periodic pitch value, the accuracy of the inverse transformation relationship between the collective pitch value, the longitudinal periodic pitch value, the lateral periodic pitch value, and the servo travel value is verified.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the electric aircraft rotor pitch calibration method as described in any one of claims 1-7.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program stored in the memory, implements the electric aircraft rotor pitch calibration method as described in any one of claims 1-7.

Images