Aircraft multi-parameter joint design method and system based on deep learning and storage medium

Abstract

The invention provides an aircraft multi-parameter joint design method and system based on deep learning and a storage medium, and relates to the technical field of aircraft parameter design, and the method specifically comprises the steps: collecting multiple groups of known original parameters of a fuselage, wings and an engine, constructing an aircraft performance evaluation model, inputting a parameter combination matrix into a trained model, and calculating the performance of the aircraft. And acquiring a climbing coefficient, performing data processing and correlation analysis, generating an aircraft cruise coefficient and a landing risk coefficient, calculating a comprehensive performance coefficient according to the aircraft cruise coefficient and the landing risk coefficient, and optimizing the initial population through a genetic algorithm by taking the maximization of the comprehensive performance coefficient as a target to obtain an optimal design parameter. According to the method, the performance of the aircraft can be comprehensively evaluated in different flight stages, it is ensured that the design can better understand the mutual influence among the stages, then the overall design is optimized, and the aircraft can find the optimal balance among multiple performance indexes through the multi-objective optimization method.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft parameter design, and specifically to a method, system and storage medium for joint design of aircraft multiple parameters based on deep learning. Background Art

[0002] In modern aircraft design, aircraft performance evaluation and optimization is a complex and critical technical issue. Traditional design methods often rely on experience and experiments, resulting in long design cycles, high costs, and limited optimization effects. In addition, as aircraft design parameters increase, the amount of calculation and time required for manual optimization also increase significantly, making it difficult to effectively respond to complex design requirements. Therefore, how to use advanced computing technology and deep learning methods to improve the efficiency and accuracy of aircraft design has become a technical challenge that needs to be solved urgently.

[0003] In the prior art, a method for estimating aircraft design parameters based on machine learning is provided in the publication number CN115048874B, which includes the following steps: according to the type of aircraft for which rapid parameter estimation is to be performed, the dependent variable parameters that need to be estimated and the independent variable parameters that need to be used as input are determined, relevant data are collected to form a parameter data set, and after data preprocessing and feature engineering data processing of the acquired parameter data set, the determined independent variable parameters are used as input parameters, and a regression algorithm based on machine learning is used for training to form a parameter estimator; and according to the formed parameter estimator, the relevant input parameters are changed to obtain the parameter estimation results of this type of aircraft. This method solves the problem that a large amount of empirical data needs to be accumulated in traditional aircraft parameter estimation, the iterative process is complex, and it is not easy to quickly obtain aircraft parameter combinations. It can quickly realize the aircraft parameter combination space in the aircraft system simulation.

[0004] However, there are still some deficiencies. As can be seen from the above statements, the existing technology only focuses on the design parameters and performance indicators of one state of the aircraft, lacks a comprehensive evaluation of the aircraft in different flight phases (climb, cruise, landing), and the parameter estimation method mainly targets a single goal and cannot effectively handle multi-objective optimization problems. This limitation will lead to performance imbalance problems in actual operation of the aircraft.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method, system and storage medium for joint design of aircraft multi-parameters based on deep learning to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A multi-parameter joint design method for an aircraft based on deep learning, the specific steps include:

[0009] S1. Collect multiple sets of known original parameters of the fuselage, wings and engines, including fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed, and construct individuals in the initial population using the multiple sets of known parameters of the fuselage, wings and engines;

[0010] S2. Construct an aircraft performance evaluation model. The aircraft performance evaluation model is based on a deep learning network of a multi-layer perceptron. The fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple known initial populations are combined to construct a parameter combination matrix. The known parameter combination matrix is ​​used as input, and the aircraft climb coefficient is determined by the expert group scoring method. The aircraft climb coefficient is used as a label to train the aircraft performance evaluation model.

[0011] S3. Process the wing width, fuselage weight, wing surface area and engine speed of the individuals in the initial population, and perform correlation analysis to generate an aircraft cruise coefficient for evaluating the aircraft cruise performance; process the wing thickness, fuselage weight, wing surface area and engine thrust of the individuals in the initial population, and perform correlation analysis to generate a landing risk coefficient for evaluating the aircraft landing risk; process the aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft;

[0012] S4. Taking the maximization of the comprehensive performance coefficient as the objective function, and constructing the constraints of the fuselage, wing and engine parameters, the individuals in the initial population are iteratively optimized through the genetic algorithm under the constraints to obtain the optimal individuals. Based on the optimal individuals, the optimal values ​​of the fuselage, wing and engine parameters are extracted.

[0013] Furthermore, using multiple sets of known parameters of the fuselage, wings, and engines, individuals in the initial population are constructed. The specific process is as follows:

[0014] Collect the known original parameters of the fuselage, wing and engine, including fuselage diameter D, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V, to form an initial population calibrated as Q, and the initial population Q = {Q1, Q2, ..., Q j ,…,Q m}, Q j is the jth individual in the initial population, j is the index of the initial population, and j∈[1,m], m is the number of the initial population, and Q j={D j ,M j ,W j ,A j ,H j ,T j ,V j}, D j ,M j ,W j ,A j ,H j ,T j ,V j are the fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed of the jth individual respectively.

[0015] Furthermore, the aircraft performance evaluation model is composed of a deep learning network based on a multilayer perceptron, wherein the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, wherein the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function;

[0016] The process of training the aircraft performance evaluation model is as follows:

[0017] According to the fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple groups of known initial populations, the corresponding aircraft climb coefficient is determined based on the expert scoring method. The larger the aircraft climb coefficient, the better the aircraft climb performance;

[0018] The known parameter combination matrix is ​​used as the input, the aircraft climb coefficient is used as the output label for training, and the mean square error is used as the loss function. When the mean square error is in the range of [0, 0.1], the training of the aircraft performance evaluation model is completed.

[0019] Furthermore, the wing width, fuselage weight, wing surface area and engine speed are processed and correlated to generate the aircraft cruise coefficient for evaluating the aircraft cruise performance. The constructed function is as follows:

[0020]

[0021] Among them, XS XH is the aircraft cruise coefficient, A is the wing surface area, W is the wing width, V is the engine speed, M is the fuselage weight, α is the weight coefficient of the wing surface area and wing width, which is used to adjust the influence of the wing surface area and wing width on the cruise performance, β is the weight coefficient of the fuselage weight, which is used to adjust the influence of the fuselage weight on the cruise performance.

[0022] Furthermore, the wing thickness, fuselage weight, wing surface area, and engine thrust are processed and correlated to generate a landing risk coefficient for assessing the aircraft landing risk. The constructed function is as follows:

[0023]

[0024] Among them, XS JF is the landing risk coefficient, T is the engine thrust, H is the wing thickness, M is the fuselage weight, ω1 is the weight coefficient of the wing surface area, ω2 is the weight coefficient of the engine thrust, ω3 is the weight coefficient of the wing thickness, ω4 is the weight coefficient of the fuselage weight, 0<ω4<ω3<ω2<ω1<1, ω4+ω3+ω2+ω1=1.

[0025] Furthermore, the aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient are processed to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft, based on the following formula:

[0026] ZX=ω PS ·XS PS +ω XH ·XS XH -ω JF ·XS JF

[0027] Among them, ZX is the comprehensive performance coefficient, XS PS is the aircraft climb coefficient, ω PS is the weight coefficient of the aircraft climb coefficient, ω XH is the weight coefficient of the aircraft cruise coefficient, ω JF is the weight coefficient of the landing risk factor, ω PS >ω XH >ω JF ,ω PS +ω XH +ω JF =1.

[0028] Furthermore, the specific process of step S5 is as follows:

[0029] A balance point is sought between the aircraft climb coefficient, the aircraft cruise coefficient and the landing risk coefficient to maximize the comprehensive performance coefficient. The maximization of the comprehensive performance coefficient ZX is taken as the optimization goal, and the initial population Q is iteratively optimized, that is, the individuals in the initial population Q are selected, crossed and mutated. In the iterative optimization process, constraints are set, that is, the maximum and minimum values ​​of the fuselage diameter D, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V are set respectively. T and the engine speed V, the initial population Q is iteratively optimized, specifically, the individuals with the top comprehensive performance coefficient are selected as the parents, the top refers to the individuals in the top 50% of the comprehensive performance coefficient, and the genes of the parent individuals are exchanged and combined through crossover operation to generate new individuals. In the iterative optimization process, the constant workpiece characteristic parameters are kept unchanged, and then the genes of the fuselage diameter D, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V in the newly generated individuals are mutated, and the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached;

[0030] After iterative optimization of the initial population Q, the optimal individual is marked as Q j1 ={D j1 ,M j1 ,W j1 ,A j1 ,H j1 ,T j1 ,V j1}, the optimal value of the fuselage, wing and engine parameters is the fuselage diameter D j1 、Body weight M j1 , wing width W j1 , Wing surface area A j1 , Wing thickness H j1 , engine thrust T j1 and engine speed V j1 .

[0031] A system for multi-parameter joint design of an aircraft based on deep learning, the system being used to execute any of the above-mentioned methods for multi-parameter joint design of an aircraft based on deep learning, comprising:

[0032] A data acquisition module is used to collect multiple sets of known original parameters of the fuselage, wings and engines, including fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed, and construct individuals in the initial population using multiple sets of known parameters of the fuselage, wings and engines;

[0033] The performance evaluation module is used to build an aircraft performance evaluation model. The aircraft performance evaluation model is based on a deep learning network of a multi-layer perceptron. The fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple groups of known initial populations are combined to build a parameter combination matrix. The known parameter combination matrix is ​​used as input to determine the aircraft climb coefficient through the expert group scoring method. The aircraft climb coefficient is used as a label to train the aircraft performance evaluation model.

[0034] The data processing and analysis module is used to process the wing width, fuselage weight, wing surface area and engine speed of the individuals in the initial population, and perform correlation analysis to generate an aircraft cruise coefficient for evaluating the aircraft cruise performance; process the wing thickness, fuselage weight, wing surface area and engine thrust of the individuals in the initial population, and perform correlation analysis to generate a landing risk coefficient for evaluating the aircraft landing risk; and process the aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft;

[0035] The parameter optimization module is used to maximize the comprehensive performance coefficient as the objective function and construct the constraints of the fuselage, wing and engine parameters. Under the constraints, the individuals in the initial population are iteratively optimized through the genetic algorithm to obtain the optimal individual. Based on the optimal individual, the optimal values ​​of the fuselage, wing and engine parameters are extracted.

[0036] A storage medium for storing a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for multi-parameter joint design of an aircraft based on deep learning.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention collects multiple groups of known original parameters of fuselage, wing and engine, uses multiple groups of known parameters of fuselage, wing and engine, constructs individuals in the initial population, combines multiple groups of known fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust, constructs a parameter combination matrix, obtains aircraft climb coefficient, processes data of individuals in the initial population, generates aircraft cruise coefficient and landing risk coefficient, processes aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient, generates comprehensive performance coefficient, takes comprehensive performance coefficient maximization as objective function, iteratively optimizes individuals in the initial population through genetic algorithm, obtains optimal individuals, extracts optimal values ​​of fuselage, wing and engine parameters based on the optimal individuals. Therefore, the present invention can comprehensively evaluate the performance of the aircraft in different flight stages, and this comprehensiveness ensures that the design can better understand the mutual influence between each stage, thereby optimizing the overall design, and the multi-objective optimization method makes the design of the aircraft more flexible, can find the best balance between multiple performance indicators, and avoids the performance imbalance problem caused by single-objective design. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0040] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0041] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0042] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0043] Embodiment 1:

[0044] See also Figure 1 , the present invention provides a technical solution:

[0045] A multi-parameter joint design method for an aircraft based on deep learning, the specific steps include:

[0046] S1. Collect multiple sets of known original parameters of the fuselage, wings and engines, including fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed, and construct individuals in the initial population using the multiple sets of known parameters of the fuselage, wings and engines;

[0047] The original parameters of the fuselage, wings and engines can be collected from the aviation database;

[0048] S2. Construct an aircraft performance evaluation model. The aircraft performance evaluation model is based on a deep learning network of a multi-layer perceptron. The fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple known initial populations are combined to construct a parameter combination matrix. The known parameter combination matrix is ​​used as input, and the aircraft climb coefficient is determined by the expert group scoring method. The aircraft climb coefficient is used as a label to train the aircraft performance evaluation model.

[0049] S4. Process the wing width, fuselage weight, wing surface area and engine speed of the individuals in the initial population, and perform correlation analysis to generate an aircraft cruise coefficient for evaluating the aircraft cruise performance; process the wing thickness, fuselage weight, wing surface area and engine thrust of the individuals in the initial population, and perform correlation analysis to generate a landing risk coefficient for evaluating the aircraft landing risk; process the aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft;

[0050] S5. Taking the maximization of the comprehensive performance coefficient as the objective function, and constructing the constraints of the fuselage, wing and engine parameters, the individuals in the initial population are iteratively optimized through the genetic algorithm under the constraints to obtain the optimal individuals. Based on the optimal individuals, the optimal values ​​of the fuselage, wing and engine parameters are extracted.

[0051] On the basis of the above embodiment, multiple sets of known parameters of the fuselage, wings and engines are used to construct individuals in the initial population. The specific process is as follows:

[0052] Collect the known original parameters of the fuselage, wing and engine, including fuselage diameter D, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V, to form an initial population calibrated as Q, and the initial population Q = {Q1, Q2, ..., Q j ,…,Q m}, Q jis the jth individual in the initial population, j is the index of the initial population, and j∈[1,m], m is the number of the initial population, and Q j ={D j ,M j ,W j ,A j ,H j ,T j ,T j}, D j ,M j ,W j ,A j ,H j ,T j ,V j are the fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed of the jth individual respectively.

[0053] On the basis of the above embodiment, the aircraft performance evaluation model is composed of a deep learning network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function.

[0054] In this embodiment, the input features of the deep learning network of the multilayer perceptron include five features: fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust.

[0055] The structure of the deep learning network of multi-layer perceptron is:

[0056] Input layer: receives input of 5 features;

[0057] The first hidden layer has 64 neurons and uses ReLU as the activation function.

[0058] The second hidden layer has 32 neurons and also uses the ReLU activation function.

[0059] The third hidden layer has 16 neurons and uses the ReLU activation function.

[0060] Output layer: has a single neuron, the aircraft climb coefficient.

[0061] The process of training the aircraft performance evaluation model is as follows:

[0062] According to the fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple groups of known initial populations, the corresponding aircraft climb coefficient is determined based on the expert scoring method, such as scoring in the range of 0-10. The larger the aircraft climb coefficient, the better the aircraft climb performance;

[0063] The known parameter combination matrix is ​​used as the input, the aircraft climb coefficient is used as the output label for training, and the mean square error is used as the loss function. When the mean square error is in the range of [0, 0.01], the training of the aircraft performance evaluation model is completed.

[0064] Based on the above embodiment, the correlation between wing width, fuselage weight, wing surface area, engine speed and aircraft cruise performance is as follows:

[0065] There is a positive correlation between wing width and aircraft cruise performance. This is because the increase in wing width means that the aerodynamic shape of the wing can generate more lift. During the cruise phase, sufficient lift is the key to ensuring that the aircraft maintains its flight altitude and stability. When the wing width increases, the wing can generate sufficient lift at a relatively low speed, thereby improving the aircraft's cruise performance.

[0066] The weight of the fuselage is negatively correlated with the cruise performance of the aircraft. Because the aircraft needs to generate enough lift to counteract gravity when cruising, an increase in the weight of the fuselage means that more lift is needed to maintain the same flight altitude, which usually requires the aircraft to fly at a higher angle of attack, which will increase air resistance and reduce the flight cruise performance.

[0067] There is a positive correlation between wing surface area and aircraft cruise performance. Because the main function of a wing is to generate lift, an increase in wing surface area means that at the same flight speed and air density, the ability to generate lift is enhanced, which allows the aircraft to remain in flight at a lower speed, thereby improving cruise efficiency.

[0068] The engine speed is positively correlated with the aircraft cruise performance. Because the increase in engine speed means that the engine can generate greater thrust. During the cruise phase, sufficient thrust is essential to maintain and increase the aircraft speed. Higher thrust can help the aircraft overcome air resistance, thereby improving cruise performance.

[0069] Therefore, according to the correlation between wing width, fuselage weight, wing surface area, engine speed and aircraft cruise performance, the wing width, fuselage weight, wing surface area and engine speed are processed and correlated to generate the aircraft cruise coefficient for evaluating the aircraft cruise performance. The constructed function form is as follows:

[0070]

[0071] Among them, XSXH is the aircraft cruise coefficient, A is the wing surface area, W is the wing width, V is the engine speed, M is the fuselage weight, α is the weight coefficient of the wing surface area and wing width, which is used to adjust the influence of the wing surface area and wing width on the cruise performance, β is the weight coefficient of the fuselage weight, which is used to adjust the influence of the fuselage weight on the cruise performance;

[0072] Aircraft cruise coefficient XS XH The range of is [0.1,10];

[0073] When XS XH When it is close to 0.1, it means that the lift of the aircraft is insufficient in the cruising state, and unstable flight will occur, or even unable to maintain effective cruising;

[0074] When XS XH When it is close to 10, it means that the aircraft has achieved excellent aerodynamic efficiency during cruising, which means that the aircraft can maintain a higher flight speed and stability with low fuel consumption.

[0075] Therefore, the aircraft cruise coefficient XS XH The larger it is, the better the aircraft's cruising performance.

[0076] The reason why the above function form is used to express the relationship between wing width, fuselage weight, wing surface area, engine speed and aircraft cruise coefficient is as follows:

[0077] First, wing surface area A and wing width W: These two parameters have a direct impact on the lift and aerodynamic performance of the aircraft. The larger the wing surface area A or the larger the wing width W, the greater the lift of the aircraft. Therefore, using the product form (A·W) to express the combined effect of these two parameters can better reflect the impact of wing design on cruise performance.

[0078] Second, engine speed V: The engine speed V has a significant impact on the cruise performance of the aircraft, but its impact is usually not linear, and as the speed increases, the improvement rate of cruise performance will slow down. The introduction of the logarithmic function can show the diminishing marginal effect between the engine speed and the cruise performance of the aircraft. (V+1) is set to avoid lg(V+1) being valid within the definition domain.

[0079] Third, fuselage weight M: The fuselage weight M has a negative impact on the aircraft's cruise performance. Increasing weight usually increases lift demand, thereby affecting fuel consumption and flight stability. Therefore, expressed in the form of a fraction, the M in the denominator can effectively reflect the downward trend of flight cruise performance as the fuselage weight M increases.

[0080] Fourth, under different design or operating conditions, the influence of wing surface area A, wing width W and fuselage weight M on cruise performance will vary. By setting the weight coefficients α and β, the contribution of these parameters in the calculation can be flexibly adjusted. Moreover, the performance of the aircraft is determined by multiple interrelated factors. By introducing the weight coefficients α and β, the influence of each parameter can be comprehensively considered to avoid a single factor from excessively affecting the final calculation result, thus ensuring the comprehensiveness and accuracy of the analysis.

[0081] The weight coefficient α of the wing surface area and wing width and the weight coefficient β of the fuselage weight are set as follows:

[0082] The wing surface area A and wing width W directly affect the lift generation capability of the aircraft. Increasing the wing surface area and width can significantly increase lift, thereby facilitating the aircraft to maintain stable flight during cruising. Therefore, these two parameters play a more critical role in cruise performance;

[0083] When evaluating the cruise performance of an aircraft, the effect of the wing is more direct and obvious, while the weight of the fuselage usually has an indirect effect through other means, that is, the correlation between the wing surface area, wing width and the aircraft cruise coefficient is greater, while the correlation between the fuselage weight and the aircraft cruise coefficient is smaller;

[0084] Therefore, a higher weight coefficient is given to the wing-related parameters, that is, on the basis of β+α=1, 0<β<α<1 is set.

[0085] Based on the above example, the correlation between wing thickness, fuselage weight, wing surface area, engine thrust and aircraft landing risk is as follows:

[0086] There is a negative correlation between wing thickness and aircraft landing risk, because increasing wing thickness can increase aircraft lift, help the aircraft maintain flight during low-speed landing, and reduce the risk of stalling.

[0087] The fuselage weight is positively correlated with the landing risk of the aircraft, because the increase in fuselage weight means that greater lift and higher landing speed are required during landing, which will increase the impact force of the aircraft when it touches the ground, thereby increasing the landing risk.

[0088] The wing surface area is negatively correlated with the risk of aircraft landing. Because the wing surface area increases, it can provide higher lift. During the landing process, the aircraft needs to land safely at a lower speed. The wing with a large surface area can generate sufficient lift at a lower angle of attack and reduce the risk of stalling.

[0089] There is a negative correlation between engine thrust and aircraft landing risk. This is because increased engine thrust can provide the necessary lift during landing, helping the aircraft maintain control when encountering emergencies. Sufficient thrust can allow the aircraft to descend smoothly at a lower speed before landing, thereby reducing landing risks.

[0090] Therefore, according to the correlation between wing thickness, fuselage weight, wing surface area, engine thrust and aircraft landing risk, the wing thickness, fuselage weight, wing surface area, engine thrust are processed and correlated to generate a landing risk coefficient for assessing aircraft landing risk. The constructed function is as follows:

[0091]

[0092] Among them, XS JF is the landing risk coefficient, T is the engine thrust, H is the wing thickness, M is the fuselage weight, ω1 is the weight coefficient of the wing surface area, ω2 is the weight coefficient of the engine thrust, ω3 is the weight coefficient of the wing thickness, and ω4 is the weight coefficient of the fuselage weight.

[0093] Landing risk factor XS JF The range of is (0,10];

[0094] When XS JF When it is close to 0, it means that the aircraft has a high design safety factor and the landing risk is low;

[0095] When XS JF When it is close to 10, it means that the aircraft's design safety factor is low and the landing risk is high;

[0096] Therefore, the landing risk factor XS JF The larger it is, the greater the risk of the aircraft landing.

[0097] Since the wing surface area A is directly related to the lift and power control ability of the aircraft during landing, when the wing surface area A is larger, the aircraft can generate more lift during landing and reduce the risk of stalling. Therefore, among the above four parameters, the wing surface area A is considered to have the greatest impact on reducing the landing risk, and the correlation between it and the aircraft landing risk is the greatest. Therefore, the weight coefficient ω1 of the wing surface area should be the largest;

[0098] The increase in engine thrust T can provide more power to help the aircraft better control speed and attitude during landing, thereby reducing landing risks. Although it is also important, compared with the wing surface area A, its role is more to control speed and attitude based on the existing lift. Therefore, the correlation between engine thrust T and aircraft landing risk is lower than that of wing surface area A, so its weight coefficient ω2 is lower than the weight coefficient ω1 of the wing surface area;

[0099] Although the wing thickness H has a direct effect on lift, its impact on landing risk is more complicated. Wings of different thicknesses may perform differently at different speeds and angles, increasing uncertainty. Compared with engine thrust T, the impact of wing thickness H on landing risk is not as obvious as that of engine thrust T. Therefore, the correlation between wing thickness H and aircraft landing risk is lower than that of engine thrust T. Therefore, the weight coefficient ω3 of wing thickness is lower than the weight coefficient ω2 of engine thrust.

[0100] The main function of the wing is to generate lift. The wing thickness H directly affects its lift characteristics. Thicker airfoils can generate more lift at lower speeds. During flight and landing, changes in wing thickness H have a more significant impact on the aircraft's controllability and stability. Compared with wing thickness, adjustments to fuselage weight M usually make small changes to the design. Most of the time, flight performance is improved by optimizing parameters such as wing thickness, making the weight coefficient ω4 of fuselage weight lower than the weight coefficient ω3 of wing thickness.

[0101] To summarize, on the basis of ω4+ω3+ω2+ω1=1, the weight coefficients of wing thickness, fuselage weight, wing surface area, and engine thrust are set to 0<ω4<ω3<ω2<ω1<1.

[0102] The reason why the above function form is used to express the relationship between wing thickness, fuselage weight, wing surface area, engine thrust and aircraft landing risk is as follows:

[0103] First, the function combines multiple key parameters (wing surface area A, engine thrust T, wing thickness H and fuselage weight M) to form a comprehensive landing risk factor XS JF This comprehensiveness can more comprehensively reflect the contribution of various factors to the risk during the aircraft landing process.

[0104] Second, according to the correlation between wing thickness H, fuselage weight M, wing surface area A, engine thrust T and aircraft landing risk, a fractional function is used to express the relationship between wing surface area A, engine thrust T, wing thickness H, fuselage weight M and landing risk coefficient. The wing thickness H, wing surface area A and engine thrust T are set in the denominator, and the larger the wing thickness H, wing surface area A and engine thrust T, the greater the landing risk coefficient XS. JF The smaller the fuselage weight M is, the greater the landing risk factor XS is. JF The bigger.

[0105] Third, the weight coefficients (ω4, ω3, ω2, ω1) are used to quantify the relative importance of different parameters in landing risk assessment. Different parameters contribute differently to landing risk. The weight coefficients can accurately reflect this relative importance. In aircraft design and performance evaluation, some parameters are more critical than other parameters. By setting weight coefficients, designers can focus on those parameters that have a greater impact on safety, thereby optimizing the design.

[0106] On the basis of the above embodiment, the aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient are processed to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft, according to the following formula:

[0107] ZX=ω PS ·XS PS +ω XH ·XS XH -ω JF ·XS JF

[0108] Among them, ZX is the comprehensive performance coefficient, XS PS is the aircraft climb coefficient, ω PS is the weight coefficient of the aircraft climb coefficient, ω XH is the weight coefficient of the aircraft cruise coefficient, ω JF is the weight coefficient of the landing risk factor.

[0109] When evaluating the overall performance of an aircraft, more attention is paid to the aircraft's climbing performance, followed by cruising performance, and finally landing safety. Therefore, the weight coefficients are set according to the following principles:

[0110] Climbing performance priority: Since climbing performance is the most important, a higher weight coefficient ω can be assigned to it PS ;

[0111] Cruise performance is second: Cruise performance is second to climb performance in importance and can be assigned a medium weight coefficient ω XH ;

[0112] Lowest landing performance: Although landing safety is also important, it should be given a lower weight coefficient in the comprehensive evaluation JF , because the higher the value of the landing risk coefficient, the greater the risk.

[0113] The reason why the above function form is used to express the relationship between the aircraft climb coefficient, aircraft cruise coefficient, landing risk coefficient and comprehensive performance coefficient is as follows:

[0114] The use of linear combination allows the various performance indicators (climb, cruise and landing risk) to be directly added or subtracted, which is easy to quantify and calculate, thus simply and clearly reflecting the contribution of each factor to the overall performance.

[0115] Landing risk factor XS JF It is an indicator of risk. The higher the value, the greater the risk. In the comprehensive performance evaluation, the risk factor is subtracted (negative weight), which is in line with the actual situation, because high risk will reduce overall safety and performance. Therefore, directly deducting the landing risk factor can effectively reflect the negative impact of risk on comprehensive performance.

[0116] This formula can comprehensively consider the aircraft's climbing performance, cruising performance and landing safety, so that the comprehensive performance coefficient can comprehensively evaluate the overall performance of the aircraft, rather than just a single aspect.

[0117] Based on the above embodiment, the specific process of step S5 is as follows:

[0118] A balance point is sought between the aircraft climb coefficient, the aircraft cruise coefficient and the landing risk coefficient to maximize the comprehensive performance coefficient. The maximization of the comprehensive performance coefficient ZX is taken as the optimization goal, and the initial population Q is iteratively optimized, that is, the individuals in the initial population Q are selected, crossed and mutated. In the iterative optimization process, constraints are set, that is, the maximum and minimum values ​​of the fuselage diameter D, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V are set respectively. T and the engine speed V, the initial population Q is iteratively optimized, specifically, the individuals with the top comprehensive performance coefficient are selected as the parents, the top refers to the individuals in the top 50% of the comprehensive performance coefficient, and the genes of the parent individuals are exchanged and combined through crossover operation to generate new individuals. In the iterative optimization process, the constant workpiece characteristic parameters are kept unchanged, and then the genes of the fuselage diameter D, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V in the newly generated individuals are mutated, and the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached;

[0119] After iterative optimization of the initial population Q, the optimal individual is marked as Q j1 ={D j1 ,M j1 ,W j1 ,A j1 ,H j1 ,T j1 ,V j1}, the optimal value of the fuselage, wing and engine parameters is the fuselage diameter Dj1 、Body weight M j1 , wing width W j1 , Wing surface area A j1 , Wing thickness H j1 , engine thrust T j1 and engine speed V j1 .

[0120] See also Figure 2 , the present invention also provides a technical solution:

[0121] A system for aircraft multi-parameter joint design based on deep learning, the system being used to execute any of the above-mentioned aircraft multi-parameter joint methods based on deep learning, comprising:

[0122] A data acquisition module is used to collect multiple sets of known original parameters of the fuselage, wings and engines, including fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed, and construct individuals in the initial population using multiple sets of known parameters of the fuselage, wings and engines;

[0123] The performance evaluation module is used to build an aircraft performance evaluation model. The aircraft performance evaluation model is based on a deep learning network of a multi-layer perceptron. The fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple groups of known initial populations are combined to build a parameter combination matrix. The known parameter combination matrix is ​​used as input to determine the aircraft climb coefficient through the expert group scoring method. The aircraft climb coefficient is used as a label to train the aircraft performance evaluation model.

[0124] The data processing and analysis module is used to process the wing width, fuselage weight, wing surface area and engine speed of the individuals in the initial population, and perform correlation analysis to generate an aircraft cruise coefficient for evaluating the aircraft cruise performance; process the wing thickness, fuselage weight, wing surface area and engine thrust of the individuals in the initial population, and perform correlation analysis to generate a landing risk coefficient for evaluating the aircraft landing risk; and process the aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft;

[0125] The parameter optimization module is used to maximize the comprehensive performance coefficient as the objective function and construct the constraints of the fuselage, wing and engine parameters. Under the constraints, the individuals in the initial population are iteratively optimized through the genetic algorithm to obtain the optimal individual. Based on the optimal individual, the optimal values ​​of the fuselage, wing and engine parameters are extracted.

[0126] A storage medium for storing a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for multi-parameter joint design of an aircraft based on deep learning.

[0127] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0128] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0129] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0130] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A multi-parameter joint design method for aircraft based on deep learning, characterized in that: The specific steps include: S1. Collect multiple sets of known original parameters of the fuselage, wings and engines, including fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed, and construct individuals in the initial population using the multiple sets of known parameters of the fuselage, wings and engines; S2. Construct an aircraft performance evaluation model. The aircraft performance evaluation model is based on a deep learning network of a multi-layer perceptron. The fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple known initial populations are combined to construct a parameter combination matrix. The known parameter combination matrix is ​​used as input, and the aircraft climb coefficient is determined by the expert group scoring method. The aircraft climb coefficient is used as a label to train the aircraft performance evaluation model. S3. Process the wing width, fuselage weight, wing surface area and engine speed of the individuals in the initial population, and perform correlation analysis to generate an aircraft cruise coefficient for evaluating the aircraft cruise performance; process the wing thickness, fuselage weight, wing surface area and engine thrust of the individuals in the initial population, and perform correlation analysis to generate a landing risk coefficient for evaluating the aircraft landing risk; process the aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft; S4. Taking the maximization of the comprehensive performance coefficient as the objective function, and constructing the constraints of the fuselage, wing and engine parameters, the individuals in the initial population are iteratively optimized through the genetic algorithm under the constraints to obtain the optimal individuals. Based on the optimal individuals, the optimal values ​​of the fuselage, wing and engine parameters are extracted.

2. The aircraft multi-parameter joint design method based on deep learning according to claim 1, characterized in that: Using multiple sets of known fuselage, wing and engine parameters, individuals in the initial population are constructed. The specific process is as follows: Collect the known original parameters of the fuselage, wing and engine, including fuselage diameter S, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V, to form an initial population calibrated as Q, and the initial population Q = {Q1, Q2, ..., Q j ,…,Q m }, Q j is the jth individual in the initial population, j is the index of the initial population, and j∈[1,m], m is the number of the initial population, and Q j ={D j ,M j ,W j ,A j ,H j ,T j ,V j }, D j ,M j ,W j ,A j ,H j ,T j ,V j are the fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed of the jth individual respectively.

3. The aircraft multi-parameter joint design method based on deep learning according to claim 2, characterized in that: The aircraft performance evaluation model is composed of a deep learning network based on a multi-layer perceptron, wherein the deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, wherein the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function; The process of training the aircraft performance evaluation model is as follows: According to the fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple groups of known initial populations, the corresponding aircraft climb coefficient is determined based on the expert scoring method. The larger the aircraft climb coefficient, the better the aircraft climb performance; The known parameter combination matrix is ​​used as the input, the aircraft climb coefficient is used as the output label for training, and the mean square error is used as the loss function. When the mean square error is in the range of [0, 0.1], the training of the aircraft performance evaluation model is completed.

4. The method for multi-parameter joint design of an aircraft based on deep learning according to claim 3, characterized in that: The wing width, fuselage weight, wing surface area and engine speed are processed and correlated to generate the aircraft cruise coefficient used to evaluate the aircraft cruise performance. The constructed function form is as follows: Among them, XS XH is the aircraft cruise coefficient, A is the wing surface area, W is the wing width, V is the engine speed, M is the fuselage weight, α is the weight coefficient of the wing surface area and wing width, which is used to adjust the influence of the wing surface area and wing width on the cruise performance, β is the weight coefficient of the fuselage weight, which is used to adjust the influence of the fuselage weight on the cruise performance.

5. The method for aircraft multi-parameter joint design based on deep learning according to claim 4, characterized in that: The wing thickness, fuselage weight, wing surface area, and engine thrust are processed and correlated to generate a landing risk coefficient for assessing the aircraft landing risk. The constructed function is as follows: Among them, XS JF is the landing risk coefficient, T is the engine thrust, H is the wing thickness, M is the fuselage weight, ω1 is the weight coefficient of the wing surface area, ω2 is the weight coefficient of the engine thrust, ω3 is the weight coefficient of the wing thickness, ω4 is the weight coefficient of the fuselage weight, 0<ω4<ω3<ω2<ω1<1, ω4+ω3+ω2+ω1=1.

6. The method for aircraft multi-parameter joint design based on deep learning according to claim 5, characterized in that: The aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient are processed to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft. The formula is as follows: ZX=ω PS ·XS PS +oh XH ·XS XH -oh JF ·XS JF Among them, ZX is the comprehensive performance coefficient, XS PS is the aircraft climb coefficient, ω PS is the weight coefficient of the aircraft climb coefficient, ω XH is the weight coefficient of the aircraft cruise coefficient, ω JF is the weight coefficient of the landing risk factor, ω PS >ω XH >ω JF ,ω PS +ω XH +ω JF =1.

7. The method for aircraft multi-parameter joint design based on deep learning according to claim 6, characterized in that: The specific process of step S5 is as follows: A balance point is sought between the aircraft climb coefficient, the aircraft cruise coefficient and the landing risk coefficient to maximize the comprehensive performance coefficient. The maximization of the comprehensive performance coefficient ZX is taken as the optimization goal, and the initial population Q is iteratively optimized, that is, the individuals in the initial population Q are selected, crossed and mutated. In the iterative optimization process, constraints are set, that is, the maximum and minimum values ​​of the fuselage diameter D, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V are set respectively. T and the engine speed V, the initial population Q is iteratively optimized, specifically, the individuals with the top comprehensive performance coefficient are selected as the parents, the top refers to the individuals in the top 50% of the comprehensive performance coefficient, and the genes of the parent individuals are exchanged and combined through crossover operation to generate new individuals. In the iterative optimization process, the constant workpiece characteristic parameters are kept unchanged, and then the genes of the fuselage diameter D, fuselage weight M, wing width W, wing surface area A, wing thickness H, engine thrust T and engine speed V in the newly generated individuals are mutated, and the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached; After iterative optimization of the initial population Q, the optimal individual is marked as Q j1 ={D j1 ,M j1 ,W j1 ,A j1 ,H j1 ,T j1 ,V j1 }, the optimal value of the fuselage, wing and engine parameters is the fuselage diameter D j1 、Body weight M j1 , wing width W j1 , Wing surface area A j1 , Wing thickness H j1 , engine thrust T j1 and engine speed V j1 .

8. A system for aircraft multi-parameter joint design based on deep learning, the system being used to execute the method for aircraft multi-parameter joint design based on deep learning according to any one of claims 1 to 7, characterized in that: include: A data acquisition module is used to collect multiple sets of known original parameters of the fuselage, wings and engines, including fuselage diameter, fuselage weight, wing width, wing surface area, wing thickness, engine thrust and engine speed, and construct individuals in the initial population using multiple sets of known parameters of the fuselage, wings and engines; The performance evaluation module is used to build an aircraft performance evaluation model. The aircraft performance evaluation model is based on a deep learning network of a multi-layer perceptron. The fuselage diameter, fuselage weight, wing surface area, wing thickness and engine thrust of individuals in multiple groups of known initial populations are combined to build a parameter combination matrix. The known parameter combination matrix is ​​used as input to determine the aircraft climb coefficient through the expert group scoring method. The aircraft climb coefficient is used as a label to train the aircraft performance evaluation model. The data processing and analysis module is used to process the wing width, fuselage weight, wing surface area and engine speed of the individuals in the initial population, and perform correlation analysis to generate an aircraft cruise coefficient for evaluating the aircraft cruise performance; process the wing thickness, fuselage weight, wing surface area and engine thrust of the individuals in the initial population, and perform correlation analysis to generate a landing risk coefficient for evaluating the aircraft landing risk; and process the aircraft climb coefficient, aircraft cruise coefficient and landing risk coefficient to generate a comprehensive performance coefficient for evaluating the comprehensive performance of the aircraft; The parameter optimization module is used to maximize the comprehensive performance coefficient as the objective function and construct the constraints of the fuselage, wing and engine parameters. Under the constraints, the individuals in the initial population are iteratively optimized through the genetic algorithm to obtain the optimal individual. Based on the optimal individual, the optimal values ​​of the fuselage, wing and engine parameters are extracted.

9. A storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements a method for multi-parameter joint design of an aircraft based on deep learning as described in any one of claims 1-7.

Images