Method and device for acquiring structural parameters of contra-rotating ducted propeller

Abstract

The invention discloses a method and a device for acquiring structural parameters of a contra-rotating ducted propeller, and relates to the field of propeller structural design, the method comprises the following steps: acquiring a control vector according to the current structural parameters of the contra-rotating ducted propeller, and acquiring an optimization vector according to the performance parameters of the contra-rotating ducted propeller; obtaining a transfer relationship between the control vector and the optimization vector, and obtaining a loss function according to the transfer relationship and the control vector; acquiring a gradient function according to the loss function, and acquiring an iterative structure parameter of the contra-rotating ducted propeller according to the gradient function and the control vector; and if the predicted performance parameter corresponding to the iterative structure parameter meets the preset performance requirement, taking the iterative structure parameter as an actual structure parameter of the contra-rotating ducted propeller. According to the technical scheme provided by the embodiment of the invention, the cost consumed in the structural parameter acquisition process is reduced, the acquisition efficiency of the structural parameters is improved, and the design error of the structural parameters is reduced.

Description

Technical Field

[0001] This invention relates to the field of propeller structure design, and in particular to a method and apparatus for obtaining structural parameters of a counter-rotating ducted propeller. Background Technology

[0002] The counter-rotating ducted propeller is a propulsion system that combines the features of a counter-rotating propeller and a duct design. It combines the technical characteristics of torque cancellation, improved propulsion efficiency, and enhanced lift, and is widely used in the field of propeller design.

[0003] Because ducted propellers involve complex fluid dynamics, multi-objective optimization, multidisciplinary coupling, high-precision numerical simulation, experimental verification, and complex manufacturing processes, their optimization design is quite difficult. In the existing technology, the structural design of ducted propellers, especially counter-rotating ducted propellers, is usually based on the designer's experience, and then analyzed with the help of computational fluid dynamics (CFD) models to complete the manual adjustment of structural parameters.

[0004] However, the above design method not only requires high manpower, time and computing resources, but also relies on the experience of designers, resulting in large design errors and failing to meet the high-precision design requirements of ducted propellers. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for obtaining the structural parameters of a counter-rotating ducted propeller, in order to solve the problem of large design errors in the structural parameters of counter-rotating ducted propellers.

[0006] According to another aspect of the present invention, a method for obtaining structural parameters of a counter-rotating ducted propeller is provided, comprising:

[0007] The control vector is obtained based on the current structural parameters of the counter-rotating ducted propeller, and the optimization vector is obtained based on the performance parameters of the counter-rotating ducted propeller.

[0008] Obtain the transitivity relationship between the control vector and the optimization vector, and obtain the loss function based on the transitivity relationship and the control vector;

[0009] The gradient function is obtained based on the loss function, and the iterative structural parameters of the counter-rotating ducted propeller are obtained based on the gradient function and the control vector.

[0010] If the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements, the iterative structural parameters will be used as the actual structural parameters of the counter-rotating ducted propeller.

[0011] The step of obtaining the loss function based on the transitivity and the control vector includes: configuring a penalty term for the gradient function based on the control vector; wherein the penalty term is used to adjust the iteration rate of the control vector and the optimization vector.

[0012] The step of obtaining the loss function based on the transitivity and the control vector further includes: obtaining the diagonal weight matrix of the gradient function based on the weight coefficients of the control vector and the weight coefficients of the optimization vector; wherein the diagonal weight matrix is ​​used to adjust the iteration range of the control vector and the optimization vector.

[0013] The step of using the iterative structural parameters as the actual structural parameters of the counter-rotating ducted propeller if the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements includes: obtaining the iterative performance difference of each performance parameter based on the predicted performance parameters corresponding to the iterative structural parameters and the predicted performance parameters corresponding to the current structural parameters; if the iterative performance difference of each performance parameter is less than the corresponding iterative tolerance threshold, the iterative structural parameters are used as the actual structural parameters of the counter-rotating ducted propeller.

[0014] The step of using the predicted performance parameters corresponding to the iterative structural parameters as the actual structural parameters of the counter-rotating ducted propeller if the predicted performance parameters meet the preset performance requirements further includes: obtaining a prediction transfer relationship based on the predicted performance parameters corresponding to the iterative structural parameters and the control vector; obtaining a first weighted matrix of the difference prediction optimization vector based on the prediction transfer relationship, and obtaining a second weighted matrix of the difference control vector based on the control vector; obtaining a prediction transfer function matrix based on the first weighted matrix and the second weighted matrix, and updating the iterative structural parameters using the prediction transfer function matrix; and using the iterative structural parameters as the actual structural parameters of the counter-rotating ducted propeller if the predicted performance parameters corresponding to the updated iterative structural parameters meet the preset performance requirements.

[0015] The step of obtaining the prediction transfer function matrix based on the first weighted matrix and the second weighted matrix includes: obtaining a first intermediate matrix based on the second weighted matrix, and obtaining the calculation result of the first intermediate matrix through a recursive method, so as to obtain the prediction transfer function matrix based on the calculation results of the first weighted matrix, the second weighted matrix and the first intermediate matrix.

[0016] According to another aspect of the present invention, a device for obtaining structural parameters of a counter-rotating ducted propeller is provided, comprising:

[0017] The vector construction and execution module is used to obtain control vectors based on the current structural parameters of the counter-rotating ducted propeller, and to obtain optimization vectors based on the performance parameters of the counter-rotating ducted propeller.

[0018] The loss function acquisition module is used to acquire the transitivity between the control vector and the optimization vector, and to acquire the loss function based on the transitivity and the control vector.

[0019] The iterative parameter acquisition module is used to obtain the gradient function based on the loss function, and to obtain the iterative structural parameters of the counter-rotating ducted propeller based on the gradient function and the control vector.

[0020] The actual parameter acquisition module is used to use the iterative structural parameters as the actual structural parameters of the counter-rotating ducted propeller if the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements.

[0021] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the method for obtaining structural parameters of a counter-rotating ducted propeller as described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the method for obtaining structural parameters of a counter-rotating ducted propeller as described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method for obtaining structural parameters of a counter-rotating ducted propeller as described in any embodiment of the present invention.

[0024] The technical solution of this invention obtains a control vector based on the current structural parameters of the counter-rotating ducted propeller and an optimization vector based on the performance parameters of the counter-rotating ducted propeller; it obtains the transitivity between the control vector and the optimization vector, and obtains a loss function based on the transitivity and the control vector; it obtains a gradient function based on the loss function, and obtains iterative structural parameters of the counter-rotating ducted propeller based on the gradient function and the control vector; if the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements, the iterative structural parameters are used as the actual structural parameters of the counter-rotating ducted propeller. This not only reduces the manpower, time, and computational resource costs associated with obtaining the structural parameters of the counter-rotating ducted propeller, but also improves the efficiency of obtaining the structural parameters, avoids reliance on the designer's experience, reduces design errors in the structural parameters, and meets the high-precision design requirements of the counter-rotating ducted propeller.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a method for obtaining structural parameters of a counter-rotating ducted propeller according to Embodiment 1 of the present invention;

[0028] Figure 2 This is a schematic diagram of the structure of a counter-rotating ducted propeller according to Embodiment 1 of the present invention;

[0029] Figure 3 This is a flowchart of another method for obtaining structural parameters of a counter-rotating ducted propeller according to Embodiment 2 of the present invention;

[0030] Figure 4 This is a schematic diagram of a structural parameter acquisition device for a counter-rotating ducted propeller according to Embodiment 3 of the present invention;

[0031] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the method for obtaining structural parameters of a counter-rotating ducted propeller according to an embodiment of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] Figure 1 This is a flowchart of a method for obtaining structural parameters of a counter-rotating ducted propeller according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the structural parameters of a counter-rotating ducted propeller are obtained iteratively. This method can be executed by a device for obtaining the structural parameters of a counter-rotating ducted propeller, which can be implemented in hardware and / or software and can be configured in electronic devices such as servers. Figure 1 As shown, the method includes:

[0036] S101. Obtain a control vector based on the current structural parameters of the counter-rotating ducted propeller, and obtain an optimization vector based on the performance parameters of the counter-rotating ducted propeller.

[0037] like Figure 2 As shown, the structural parameters of the counter-rotating ducted propeller include the clearance h between the blade and the inner side of the duct, the blade radius R, the distance t between the upper blade and the duct lip, the distance d between the upper blade and the lower blade, and the distance b between the lower blade and the duct outlet. The current structural parameter refers to the structural parameter obtained after the end of the previous iteration step, and is used as the input value for the next iteration step. That is, the next iteration structural parameter is obtained based on the current structural parameter.

[0038] If there is no previous iteration step, that is, for the initial iteration step, the current structural parameters are the initial structural parameters pre-designed based on the designer's experience; the control vector U constructed based on the current structural parameters of the ducted propeller is represented as follows:

[0039] U = [h, R, t, d, b] T (Formula 1);

[0040] Performance parameters reflect the operating performance of a ducted propeller, including the thrust L of the upper blade. uThe thrust L of the lower blade d The efficiency η of the upper blade u And the efficiency η of the lower blade d The iterative operation on the structural parameters aims to optimize the performance parameters of the counter-rotating ducted propeller. The optimization vector Z constructed based on the performance parameters of the counter-rotating ducted propeller is represented as follows:

[0041] Z = [L] u L d η u η d ] T (Formula 2);

[0042] S102. Obtain the transitivity relationship between the control vector and the optimization vector, and obtain the loss function based on the transitivity relationship and the control vector.

[0043] Based on existing duct aerodynamic simulation and experimental data, data fitting revealed that the control vector and optimization vector can be approximately represented by a second-order polynomial. The transfer relationship between structural parameters and aerodynamic performance parameters expressed in second-order polynomial form can be represented as follows:

[0044] Z k =T1U k +T2(U k ) 2 +C k (Formula 3);

[0045] Among them, Z k U is the optimization vector at time step k. k Let T1 be the control vector at time step k, and T2 be the transfer function matrices for the corresponding terms, i.e., the first transfer function matrix and the second transfer function matrix; C k The reference perturbation signal is used; where the k-th time step represents the time series obtained after discretizing the continuous time, and also represents the parameter information under the k-th iteration step; for example, U k This is used to represent the control vector at the k-th iteration step; specifically, within each iteration step, T1 and T2 can be kept constant, i.e., they are fixed values, to reduce computational complexity; while C k As an intermediate variable, it can be removed in subsequent calculations through subtraction, without needing to determine its specific value.

[0046] For discrete-time multi-objective optimization control, the optimization path can be determined by defining different forms of loss functions. For example, the correlation between the transfer relationship and the control vector can be constructed using the following quadratic loss function, which can be expressed in the following form:

[0047] J(Z k U k ) = Z k T QZ k +U k T RU k (Formula 4);

[0048] In the formula, Q and R are both diagonal weight matrices used to adjust the proportion of each input and output quantity in the loss function. The larger the weight coefficient, the better the optimization effect. For example, Q and R can both be configured as a matrix with equal number of elements on the diagonal, and Q and R can both be pre-configured.

[0049] Optionally, in this embodiment of the invention, obtaining the loss function based on the transitivity and the control vector includes: configuring a penalty term for the gradient function based on the control vector; wherein the penalty term is used to adjust the iteration rate of the control vector and the optimization vector.

[0050] Specifically, for the gradient function, a penalty term can be configured. Taking Formula 4 above as an example, the gradient function after configuring the penalty term can be in the following form:

[0051] J(Z k U k ) = Z k T QZ k +ΔU k T SΔU k +U k T RU k (Formula 5);

[0052] Wherein, ΔU k T SΔU k As a penalty term, ΔU k The difference between the control vector at time step k and the control vector at time step (k-1) is called the difference control vector, or ΔU. k =U k -U k-1 S is also a diagonal weight matrix. For example, S can also be configured as a matrix with equal numbers of elements on the diagonal, and this configuration is pre-defined. By configuring a penalty term in the gradient function, the iteration speed of structural parameters and performance parameters can be avoided from being too fast, which is beneficial to the stability and robustness of the overall iteration process.

[0053] Optionally, in this embodiment of the invention, obtaining the loss function based on the transitivity and the control vector further includes: obtaining the diagonal weight matrix of the gradient function based on the weight coefficients of the control vector and the weight coefficients of the optimization vector; wherein the diagonal weight matrix is ​​used to adjust the iteration range of the control vector and the optimization vector.

[0054] Specifically, in addition to being configured as a matrix with equal elements on the diagonal, the aforementioned diagonal weight matrix can also be configured with different weight coefficients for different structural and performance parameters. That is, Q and R can be represented in the following forms:

[0055] Q = diag[λ1, λ2, r1, r2] (Formula 6);

[0056] R=diag[μ1,μ2,μ3,μ4,μ5] (Formula 7);

[0057] Wherein, λ1, λ2, r1, and r2 are the weighting coefficients corresponding to the thrust of the upper blade, the thrust of the lower blade, the efficiency of the upper blade, and the efficiency of the lower blade, respectively; μ1, μ2, μ3, μ4, and μ5 are the weighting coefficients corresponding to the clearance between the blade and the inner side of the duct, the blade radius, the distance between the upper blade and the duct lip, the distance between the upper blade and the lower blade, and the distance between the lower blade and the duct outlet, respectively. Thus, based on the weighting coefficients of the control vector and the optimization vector, the diagonal weight matrix of the gradient function is obtained, which constrains the iteration range of structural and performance parameters through the diagonal weight matrix, avoiding over-optimization of one or more parameters, ensuring that the optimization result does not exceed the optimization range limit, and improving the efficiency of obtaining the iterative structural parameters.

[0058] S103. Obtain the gradient function based on the loss function, and obtain the iterative structural parameters of the counter-rotating ducted propeller based on the gradient function and the control vector.

[0059] For the loss function in Equation 4 or Equation 5 above, the gradient descent iterative method is used to gradually approximate the optimal performance state of the counter-rotating ducted propeller. By reasonably controlling the incremental step size of the input geometric parameters, the stability of the optimization process is improved. The optimization process using the gradient descent iterative method is as follows: taking Equation 5 as an example, the derivative of Equation 5 can be used to obtain the loss function in U. k The gradient function at point is as follows:

[0060]

[0061] Where ⊙ represents the Hadamard product; and A can be represented in the following form;

[0062] A = [Q]([T1][U]k ]+[T2][U k ] 2 +[C k (Formula Nine);

[0063] The parameters are updated along the negative gradient direction of the loss function. Based on Equation 7 above, the discretized control vector U is then obtained. k The update rule can be expressed as:

[0064] U k+1 =U k -G(2[T1) T [A]+4[T2] T [A]⊙[U k ]+2[R][U k (Formula 10);

[0065] Where G is the step size control parameter, which is a pre-configured fixed value; U k and U k+1 These represent the control vectors at time step k and time step (k+1), respectively, which are the control vectors of two adjacent time steps. Based on the structure parameters obtained after the end of the previous iteration step (i.e., the current structure parameters), the structure parameters of the next iteration step (i.e., the iterative structure parameters) are obtained.

[0066] S104. If the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements, the iterative structural parameters shall be used as the actual structural parameters of the counter-rotating ducted propeller.

[0067] After obtaining the iterative structural parameters, various performance parameters of the counter-rotating ducted propeller can be calculated using a third-party high-precision fluid dynamics calculation component. The calculation results are actually performance parameters predicted based on the obtained iterative parameters, i.e., predicted performance parameters. The third-party calculation component can include ANSYS Fluent and OpenFOAM, etc.; optionally, in this embodiment of the invention, the type of third-party calculation component is not specifically limited. If the predicted performance parameters meet the numerical range of each performance parameter in the preset performance requirements, it indicates that the structural parameters have been iteratively trained. Based on this, the currently obtained iterative structural parameters are used as the actual structural parameters for the completed counter-rotating ducted propeller design.

[0068] Optionally, in this embodiment of the invention, the step of using the iterative structural parameters as the actual structural parameters of the counter-rotating ducted propeller if the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements includes: obtaining the iterative performance difference of each performance parameter based on the predicted performance parameters corresponding to the iterative structural parameters and the predicted performance parameters corresponding to the current structural parameters; if the iterative performance difference of each performance parameter is less than the corresponding iterative tolerance threshold, the iterative structural parameters are used as the actual structural parameters of the counter-rotating ducted propeller.

[0069] Specifically, the iteration tolerance threshold refers to the threshold value of the difference between two adjacent predicted performance parameters. If the difference between the predicted performance parameters corresponding to the iterative structural parameters obtained in two consecutive iterations is less than the corresponding iteration tolerance threshold, it means that the structural parameter optimization has little impact on the performance parameter changes. Even if the structural parameters are updated again, it will not have much impact on the performance parameters. At this point, it can be indicated that the iterative training of the structural parameters is complete, that is, the results of the iterative structural parameters have converged. This ensures that the structural parameters of the counter-rotating ducted propeller have good performance, improves the iteration efficiency of the structural parameters, and reduces the time and computational resource costs consumed in the iteration process of the structural parameters.

[0070] The technical solution of this invention obtains a control vector based on the current structural parameters of the counter-rotating ducted propeller and an optimization vector based on the performance parameters of the counter-rotating ducted propeller; it obtains the transitivity between the control vector and the optimization vector, and obtains a loss function based on the transitivity and the control vector; it obtains a gradient function based on the loss function, and obtains iterative structural parameters of the counter-rotating ducted propeller based on the gradient function and the control vector; if the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements, the iterative structural parameters are used as the actual structural parameters of the counter-rotating ducted propeller. This not only reduces the manpower, time, and computational resource costs associated with obtaining the structural parameters of the counter-rotating ducted propeller, but also improves the efficiency of obtaining the structural parameters, avoids reliance on the designer's experience, reduces design errors in the structural parameters, and meets the high-precision design requirements of the counter-rotating ducted propeller.

[0071] Example 2

[0072] Figure 3 This is a flowchart of a method for obtaining structural parameters of a counter-rotating ducted propeller according to Embodiment 2 of the present invention. The relationship between this embodiment and the above embodiments is that, in each iteration step, the first transfer function matrix T1 and the second transfer function matrix T2 are not fixed values, but are obtained through an identification method, such as... Figure 3 As shown, the method specifically includes:

[0073] S201. Obtain a control vector based on the current structural parameters of the counter-rotating ducted propeller, and obtain an optimization vector based on the performance parameters of the counter-rotating ducted propeller.

[0074] S202. Obtain the transitivity relationship between the control vector and the optimization vector, and obtain the loss function based on the transitivity relationship and the control vector.

[0075] S203. Obtain the gradient function based on the loss function, and obtain the iterative structural parameters of the counter-rotating ducted propeller based on the gradient function and the control vector.

[0076] S204. Obtain the prediction propagation relationship based on the prediction performance parameters corresponding to the iterative structure parameters and the control vector.

[0077] Formula 3 above can be rewritten in the following form:

[0078]

[0079] in, This represents the optimization vector (also known as the prediction optimization vector) composed of the predicted values ​​of the predicted performance parameters. This represents the prediction optimization vector at time step k; correspondingly, the first prediction transfer function matrix at this time... Second prediction transfer function matrix The resulting predictive transfer function matrix is ​​represented as follows:

[0080] S205. Obtain the first weighted matrix of the difference prediction optimization vector according to the prediction propagation relationship, and obtain the second weighted matrix of the difference control vector according to the control vector.

[0081] The difference optimization vector between two adjacent prediction optimization vectors can be represented in the following form:

[0082]

[0083] The difference between the two corresponding control vectors can be represented by the following form:

[0084] ΔU k =U k -U k-1 (Formula Thirteen);

[0085] By assigning weight coefficients of different magnitudes to the difference optimization vectors in different iteration steps, the first weighted matrix can be obtained as follows:

[0086]

[0087] Meanwhile, by assigning different weight coefficients to the difference control vectors in different iteration steps, the second weighted matrix can be obtained as follows:

[0088] B k =[β k-1 ΔU1 β k-2 ΔU2…βΔU k-1 ΔU k (Formula 15);

[0089] Where β represents the forgetting factor, the weight coefficient of the latest data is 1, and the difference vector of the previous k-1 iterations is weighted using exponential weight coefficients, and β < 1, which means that the older the data, the smaller the weight coefficient.

[0090] S206. Obtain the prediction transfer function matrix based on the first weighting matrix and the second weighting matrix, and update the iterative structure parameters using the prediction transfer function matrix.

[0091] Based on the first weighting matrix and the second weighting matrix, Formula 11 above can be expressed in the following form:

[0092]

[0093] Using the least squares unbiased estimation, the prediction transfer function matrix at time step k can be expressed in the following form:

[0094]

[0095] Among them, D k It is in the following form:

[0096] D k =[[B k [B] k ] T ] -1 (Formula 18);

[0097] Therefore, through D k Solving this problem allows us to calculate and obtain the prediction transfer function matrix. and Officially by and Composition, obtained using calculation Replace T1 in Formula 10 above; simultaneously, use the calculation to obtain... Replace T2 in Formula 10 above to complete the iterative update of structural parameters; based on this, the identification method can update the transmission relationship between structural parameters and performance parameters in real time through the identification process in each time step without the need for a prior mathematical model, thereby improving the adaptive features of the above method and increasing the accuracy of the structural parameter acquisition results.

[0098] S207. If the predicted performance parameters corresponding to the updated iterative structural parameters meet the preset performance requirements, the iterative structural parameters shall be used as the actual structural parameters of the counter-rotating ducted propeller.

[0099] Optionally, in this embodiment of the invention, obtaining the prediction transfer function matrix based on the first weighted matrix and the second weighted matrix includes: obtaining a first intermediate matrix based on the second weighted matrix, and obtaining the calculation result of the first intermediate matrix through a recursive method, so as to obtain the prediction transfer function matrix based on the calculation results of the first weighted matrix, the second weighted matrix and the first intermediate matrix.

[0100] Specifically, the first intermediate matrix is ​​D in the above technical solution. k As shown in Formula 18, it is constructed from the second weighted matrix. However, Formula 18 requires matrix inversion. When the dimension of the second weighted matrix is ​​large, the inversion operation will significantly reduce the computational efficiency. Therefore, a recursive method can be used here, applying the matrix inversion to D at each time step. k The inverse calculation is transformed into a correction of adjacent iteration steps to reduce the computational load.

[0101] Specifically, according to Formulas 17 and 18, the (k+1)th time step can be expressed as:

[0102] [D k+1 ] -1 =β 2 [D k ] -1 +[ΔU k+1 ][ΔU k+1 ] T (Formula 19);

[0103] Simplifying Formula 19 above, we can obtain:

[0104]

[0105] From Formula 19, we can see that:

[0106]

[0107] By recursively applying Formula 17 to the (k+1)th time step, we can obtain:

[0108]

[0109] Substituting formula 20 into formula 22, we get:

[0110]

[0111] According to the matrix inversion lemma, and taking Equation 19 as invertible, we obtain:

[0112]

[0113] Substituting formula 25 into formula 24, we get:

[0114]

[0115] Through the above derivation, the following recurrence relation can be obtained:

[0116]

[0117] Among them, P k and D k These are all intermediate variables; no specific values ​​need to be calculated. Only the prediction transfer function matrix at time step k needs to be derived. This completes the prediction of the transfer function matrix. The calculation is obtained.

[0118] Finally, the result after updating the iterative structure parameters by predicting the transfer function matrix is ​​as follows:

[0119]

[0120] The technical solution of this invention obtains the prediction transfer relationship based on the predicted performance parameters and control vectors corresponding to the iterative structural parameters; obtains a first weighted matrix of the difference prediction optimization vector based on the prediction transfer relationship, and a second weighted matrix of the difference control vector based on the control vector; obtains the prediction transfer function matrix based on the first and second weighted matrices, and updates the iterative structural parameters using the prediction transfer function matrix; if the predicted performance parameters corresponding to the updated iterative structural parameters meet the preset performance requirements, the iterative structural parameters are used as the actual structural parameters of the counter-rotating ducted propeller. Thus, through the identification method, without requiring a prior mathematical model, the transfer relationship between structural parameters and performance parameters is updated in real time through the identification step within each time step, improving the adaptive features of the above method and increasing the accuracy of the structural parameter acquisition results.

[0121] Example 3

[0122] Figure 4 This is a structural block diagram of a device for obtaining structural parameters of a counter-rotating ducted propeller provided in Embodiment 3 of the present invention. The device specifically includes:

[0123] The vector construction execution module 401 is used to obtain a control vector based on the current structural parameters of the counter-rotating ducted propeller, and to obtain an optimization vector based on the performance parameters of the counter-rotating ducted propeller.

[0124] The loss function acquisition module 402 is used to acquire the transitivity between the control vector and the optimization vector, and to acquire the loss function based on the transitivity and the control vector.

[0125] The iterative parameter acquisition module 403 is used to acquire the gradient function based on the loss function, and to acquire the iterative structural parameters of the counter-rotating ducted propeller based on the gradient function and the control vector.

[0126] The actual parameter acquisition module 404 is used to take the iterative structural parameters as the actual structural parameters of the counter-rotating ducted propeller if the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements.

[0127] The technical solution of this invention obtains a control vector based on the current structural parameters of the counter-rotating ducted propeller and an optimization vector based on the performance parameters of the counter-rotating ducted propeller; it obtains the transitivity between the control vector and the optimization vector, and obtains a loss function based on the transitivity and the control vector; it obtains a gradient function based on the loss function, and obtains iterative structural parameters of the counter-rotating ducted propeller based on the gradient function and the control vector; if the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements, the iterative structural parameters are used as the actual structural parameters of the counter-rotating ducted propeller. This not only reduces the manpower, time, and computational resource costs associated with obtaining the structural parameters of the counter-rotating ducted propeller, but also improves the efficiency of obtaining the structural parameters, avoids reliance on the designer's experience, reduces design errors in the structural parameters, and meets the high-precision design requirements of the counter-rotating ducted propeller.

[0128] Optionally, the loss function acquisition module 402 is specifically used to configure the penalty term of the gradient function according to the control vector; wherein the penalty term is used to adjust the iteration rate of the control vector and the optimization vector.

[0129] Optionally, the loss function acquisition module 402 is further configured to acquire the diagonal weight matrix of the gradient function based on the weight coefficients of the control vector and the weight coefficients of the optimization vector; wherein the diagonal weight matrix is ​​used to adjust the iteration range of the control vector and the optimization vector.

[0130] Optionally, the actual parameter acquisition module 404 is specifically used to obtain the iterative performance difference of each performance parameter based on the predicted performance parameter corresponding to the iterative structural parameter and the predicted performance parameter corresponding to the current structural parameter; if the iterative performance difference of each performance parameter is less than the corresponding iterative tolerance threshold, the iterative structural parameter is used as the actual structural parameter of the counter-rotating ducted propeller.

[0131] Optionally, the actual parameter acquisition module 404 is further configured to: acquire a prediction transfer relationship based on the predicted performance parameters corresponding to the iterative structure parameters and the control vector; acquire a first weighted matrix of the difference prediction optimization vector based on the prediction transfer relationship, and acquire a second weighted matrix of the difference control vector based on the control vector; acquire a prediction transfer function matrix based on the first weighted matrix and the second weighted matrix, and update the iterative structure parameters using the prediction transfer function matrix; if the predicted performance parameters corresponding to the updated iterative structure parameters meet the preset performance requirements, use the iterative structure parameters as the actual structure parameters of the counter-rotating ducted propeller.

[0132] Optionally, the actual parameter acquisition module 404 is further configured to obtain the first intermediate matrix based on the second weighted matrix, and obtain the calculation result of the first intermediate matrix through a recursive method, so as to obtain the prediction transfer function matrix based on the calculation results of the first weighted matrix, the second weighted matrix and the first intermediate matrix.

[0133] The above-described device can execute the method for obtaining structural parameters of a counter-rotating ducted propeller provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the method for obtaining structural parameters of a counter-rotating ducted propeller provided in any embodiment of the present invention.

[0134] Example 4

[0135] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, electronic devices, blade electronic devices, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0136] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0138] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for obtaining structural parameters of a ducted propeller.

[0139] In some embodiments, the method for obtaining the structural parameters of a counter-rotating ducted propeller can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed on a heterogeneous hardware accelerator via ROM and / or a communication unit. When the computer program is loaded into RAM and executed by a processor, one or more steps of the method for obtaining the structural parameters of a counter-rotating ducted propeller described above can be performed. Alternatively, in other embodiments, the processor can be configured to perform the method for obtaining the structural parameters of a counter-rotating ducted propeller by any other suitable means (e.g., by means of firmware).

[0140] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0142] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0143] To provide interaction with a user terminal, the systems and techniques described herein can be implemented on a heterogeneous hardware accelerator, which includes: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user terminal; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user terminal provides input to the heterogeneous hardware accelerator. Other types of devices can also be used to provide interaction with the user terminal; for example, the feedback provided to the user terminal can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback); and input from the user terminal can be received in any form (including sound input, voice input, or haptic input).

[0144] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., client computers with graphical user interfaces or web browsers through which client computers can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0145] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0146] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0147] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for obtaining structural parameters of a counter-rotating ducted propeller, characterized in that, include: The control vector is obtained based on the current structural parameters of the counter-rotating ducted propeller, and the optimization vector is obtained based on the performance parameters of the counter-rotating ducted propeller. Obtain the transitivity relationship between the control vector and the optimization vector, and obtain the loss function based on the transitivity relationship and the control vector; The gradient function is obtained based on the loss function, and the iterative structural parameters of the counter-rotating ducted propeller are obtained based on the gradient function and the control vector. If the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements, the iterative structural parameters will be used as the actual structural parameters of the counter-rotating ducted propeller.

2. The method for obtaining structural parameters of a counter-rotating ducted propeller according to claim 1, characterized in that, The step of obtaining the loss function based on the transitivity and the control vector includes: The penalty term of the gradient function is configured according to the control vector; wherein the penalty term is used to adjust the iteration rate of the control vector and the optimization vector.

3. The method for obtaining structural parameters of a counter-rotating ducted propeller according to claim 1, characterized in that, The step of obtaining the loss function based on the transitivity and the control vector further includes: Based on the weight coefficients of the control vector and the optimization vector, the diagonal weight matrix of the gradient function is obtained; wherein, the diagonal weight matrix is ​​used to adjust the iteration range of the control vector and the optimization vector.

4. The method for obtaining structural parameters of a counter-rotating ducted propeller according to claim 1, characterized in that, If the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements, the iterative structural parameters will be used as the actual structural parameters of the counter-rotating ducted propeller, including: Based on the predicted performance parameters corresponding to the iterative structure parameters and the predicted performance parameters corresponding to the current structure parameters, the iterative performance difference of each performance parameter is obtained. If the iterative performance difference of each of the aforementioned performance parameters is less than the corresponding iterative tolerance threshold, the iterative structural parameters shall be used as the actual structural parameters of the counter-rotating ducted propeller.

5. The method for obtaining structural parameters of a counter-rotating ducted propeller according to claim 1, characterized in that, If the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements, the iterative structural parameters are used as the actual structural parameters of the counter-rotating ducted propeller. The method further includes: Based on the prediction performance parameters corresponding to the iterative structure parameters and the control vector, the prediction propagation relationship is obtained; The first weighted matrix of the difference prediction optimization vector is obtained based on the prediction transitivity, and the second weighted matrix of the difference control vector is obtained based on the control vector. The prediction transfer function matrix is ​​obtained based on the first weighting matrix and the second weighting matrix, and the iterative structure parameters are updated using the prediction transfer function matrix. If the predicted performance parameters corresponding to the updated iterative structural parameters meet the preset performance requirements, the iterative structural parameters will be used as the actual structural parameters of the counter-rotating ducted propeller.

6. The method for obtaining structural parameters of a counter-rotating ducted propeller according to claim 5, characterized in that, The step of obtaining the prediction transfer function matrix based on the first weighting matrix and the second weighting matrix includes: The first intermediate matrix is ​​obtained based on the second weighted matrix, and the calculation result of the first intermediate matrix is ​​obtained by recursion. Based on the calculation results of the first weighted matrix, the second weighted matrix, and the first intermediate matrix, the prediction transfer function matrix is ​​obtained.

7. A device for obtaining structural parameters of a counter-rotating ducted propeller, characterized in that, include: The vector construction and execution module is used to obtain control vectors based on the current structural parameters of the counter-rotating ducted propeller, and to obtain optimization vectors based on the performance parameters of the counter-rotating ducted propeller. The loss function acquisition module is used to acquire the transitivity between the control vector and the optimization vector, and to acquire the loss function based on the transitivity and the control vector. The iterative parameter acquisition module is used to obtain the gradient function based on the loss function, and to obtain the iterative structural parameters of the counter-rotating ducted propeller based on the gradient function and the control vector. The actual parameter acquisition module is used to use the iterative structural parameters as the actual structural parameters of the counter-rotating ducted propeller if the predicted performance parameters corresponding to the iterative structural parameters meet the preset performance requirements.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for obtaining the structural parameters of the counter-rotating ducted propeller as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for obtaining the structural parameters of the counter-rotating ducted propeller as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method for obtaining structural parameters of a counter-rotating ducted propeller as described in any one of claims 1-6.

Images