Optimization design method for paddle of multi-rotor bomb-dropping type fire extinguishing unmanned aerial vehicle

Abstract

The invention provides a multi-rotor bomb-dropping fire extinguishing unmanned aerial vehicle paddle optimization design method, and relates to the technical field of unmanned aerial vehicles, the method comprises the following steps: obtaining fuselage geometric design data and paddle design data, using CFD software to construct a fire extinguishing unmanned aerial vehicle model, using the model to carry out aerodynamic analysis, and obtaining flight power data; generating a blade flight evaluation coefficient according to the blade material property data and the flight power data; obtaining a blade flight evaluation coefficient under each rotating speed gear, and analyzing the blade flight evaluation coefficient to obtain a flight quality evaluation coefficient; constructing and training a flight quality evaluation model by taking the historical blade design data as input and the corresponding historical flight quality evaluation coefficient as a label; and by taking the blade design data as an initial solution and taking blade flight evaluation coefficient maximization as an optimization target, optimizing the blade design data by using a simulated annealing algorithm to obtain optimal blade design data.

Description

Technical Field

[0001] The invention relates to the technical field of unmanned aerial vehicles, and in particular to a method for optimizing the blade design of a multi-rotor bomb-throwing fire-fighting unmanned aerial vehicle. Background Art

[0002] In recent years, with the acceleration of urbanization and the popularization of high-rise buildings, the frequency of fire accidents has gradually increased, posing a serious threat to the safety of people's lives and property. Traditional fire-fighting methods mainly rely on fire trucks and manual fire-fighting, which usually have problems such as long response time, inconvenient operation, and complex working environment. This makes traditional fire-fighting methods seem powerless when dealing with sudden fires. Especially when facing fires in high-rise buildings, narrow alleys and complex terrains, firefighters have a greater difficulty in their operations and the rescue efficiency is greatly reduced. Therefore, it is particularly important to develop new fire-fighting equipment and improve fire-fighting efficiency.

[0003] As an emerging high-tech firefighting auxiliary tool, drones are gradually gaining attention due to their flexibility and rapid deployment capabilities. The application of multi-rotor drones at fire scenes can effectively improve firefighting efficiency by dropping fire extinguishing agents from the air and conducting fire reconnaissance. However, existing firefighting drones still have shortcomings in terms of flight performance, load capacity, and operational stability, especially the lack of optimization of blade design, which makes it impossible to perform at its best in actual operations. Traditional blade design often ignores the interaction between material properties and aerodynamic properties, resulting in low flight efficiency and insufficient aviation power.

[0004] In addition, for the simulation and optimization of UAV blade design, traditional methods mostly rely on experience and simple calculations, lacking scientific and systematic analysis. This makes it difficult for the designed blades to meet the needs of efficient firefighting in practical applications, especially when facing different types of fires, the performance of the blades may be affected. Therefore, comprehensive optimization of blades in multiple dimensions such as aerodynamic characteristics, material properties, and flight evaluation has become the key to improving the performance of firefighting UAVs. In this context, an integrated and systematic blade optimization design method was developed, which can not only improve the working efficiency of multi-rotor bomb-dropping firefighting UAVs, but also provide new ideas and directions for the further development of UAVs.

[0005] In the prior art, publication number CN113408044A discloses a blade optimization design method, system, equipment and storage medium for a multi-rotor bomb-throwing fire-fighting UAV, by: determining the working condition parameters and selecting a reference airfoil; parameterizing the reference airfoil to obtain a basic airfoil; optimizing the basic airfoil to obtain an optimal airfoil; and three-dimensional simulation verification of the optimal airfoil. The prior art multi-rotor UAV blade optimization design method has many advantages such as wide applicability, high optimization dimension, high optimization efficiency, and good optimization effect. However, the prior art still has defects. When optimizing the blade parameters, the prior art only considers the influence of the geometric characteristics of the blade on the flight effect during the flight process, and ignores the important influence of the blade's own material on the flight condition and the important influence of the pressure on the blade on the flight effect and the life of the blade.

[0006] 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

[0007] The purpose of the present invention is to provide a method for optimizing the blade design of a multi-rotor bomb-dropping fire-fighting UAV to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A method for optimizing the blade design of a multi-rotor bomb-dropping fire-fighting UAV comprises the following specific steps:

[0010] Step 1: Obtain the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, divide the multi-rotor bomb-throwing fire-fighting drone into N speed gears according to the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, and obtain the intermediate speed value of each speed gear;

[0011] Step 2: Obtain the fuselage geometry design data and blade design data, use CFD software to build a fire-fighting UAV model, use the fire-fighting UAV model to perform aerodynamic analysis, and obtain flight power data at different intermediate speeds; obtain blade material property data, and generate corresponding blade flight evaluation coefficients based on the blade material property data and flight power data;

[0012] Step 3: Analyze the blade flight evaluation coefficient at each intermediate speed value to obtain the flight quality evaluation coefficient;

[0013] Step 4: Build a flight quality assessment model, obtain historical blade design data and historical flight quality assessment coefficients, and use the historical blade design data as input and the corresponding historical flight quality assessment coefficients as labels to train the flight quality assessment model;

[0014] Step 5: Take the blade design data obtained in step 2 as the initial solution, and take maximizing the blade flight evaluation coefficient as the optimization goal. Use the simulated annealing algorithm to optimize the blade design data to obtain the optimal blade design data.

[0015] Furthermore, the specific logic for dividing the speed gears is: obtaining the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, dividing the multi-rotor bomb-throwing fire-fighting drone into N speed gears according to the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, and the specific formula for dividing the speed gears is:

[0016]

[0017] Among them, SP i is the speed of the i-th speed gear, SP0 is the maximum speed gear, N is the number of speed gears, and i is the speed gear index.

[0018] Furthermore, the blade design data includes the total length, total width, maximum thickness, minimum thickness, surface area and maximum bending angle of the blade of the multi-rotor bomb-dropping fire-fighting drone; the flight power data includes the drone lift, drone drag, blade root pressure and blade tip pressure;

[0019] Furthermore, the specific logic for generating the blade flight evaluation coefficient is as follows: obtaining blade material property data, generating a material performance coefficient according to the blade material property data, and generating a blade flight evaluation coefficient according to the material performance coefficient and flight power data; the material property data includes hardness, fatigue strength, compressive strength, tensile strength and Poisson's ratio of the blade material;

[0020] The specific formula used to generate the material performance coefficient is:

[0021]

[0022] Wherein, CL is the material performance coefficient, Ha is the hardness of the blade material, R is the fatigue strength of the blade material, F is the tensile strength of the blade material, B is the compressive strength of the blade material, and SB is the Poisson's ratio of the blade material;

[0023] The specific formula used to generate the blade flight evaluation coefficient is:

[0024]

[0025] Where Y is the blade flight evaluation coefficient, F u is the lift of the drone, F do is the drag of the drone, P g is the blade root pressure, P j is the blade tip pressure.

[0026] Furthermore, the specific logic for generating the flight quality assessment coefficient is as follows: calculating the blade flight assessment coefficient corresponding to the intermediate speed value; analyzing the blade flight assessment coefficient at each intermediate speed value to obtain the flight quality assessment coefficient; and generating the flight quality assessment coefficient according to the specific formula is as follows:

[0027]

[0028] Among them, FY is the flight quality assessment coefficient, Y i is the blade flight evaluation coefficient corresponding to the intermediate value of the speed of the i-th gear, SP i is the middle speed value of the i-th speed gear, N is the number of speed gears, and i is the speed gear index.

[0029] Further, the optimization target of the blade design data is determined to be the maximum flight quality assessment coefficient, and the blade design data obtained in step 2 is used as the initial solution of the blade design data in the simulated annealing algorithm;

[0030] The optimal blade design data is found through simulated annealing algorithm, the initial annealing temperature and the cooling coefficient are set, and a neighborhood search is performed on the initial solution at the initial annealing temperature. A neighboring solution is randomly selected within the parameter range, and the flight quality assessment coefficient of the neighboring solution is predicted using the flight quality assessment model. The probability of accepting the new solution is determined according to the Metropolis criterion.

[0031] Furthermore, the formula for determining the probability of accepting a new solution according to the Metropolis criterion is:

[0032]

[0033] Where P is the probability of the new flight quality assessment coefficient being accepted, FY k+1 is the k+1th generated flight quality assessment coefficient, FY k is the kth generated flight quality assessment coefficient, k is the generation order index of the flight quality assessment coefficient, T is the annealing temperature, and the annealing temperature is continuously adjusted by the cooling coefficient until the termination condition is reached;

[0034] The termination condition of the simulated annealing algorithm is set as:

[0035] The total number of solutions for generating the flight quality assessment coefficient is X. For a currently found optimal flight quality assessment coefficient FY L , if the flight quality assessment coefficient is FY in the subsequent XL iterations L , then the output flight quality assessment coefficients at the end of the iteration are all FY L The corresponding blade design data.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] Based on the consideration of the influence of blade geometry design data on the flight performance of the UAV, the present invention further integrates the influence of blade material properties and the pressure on the blade during flight on the flight performance. This multi-dimensional analysis can more accurately evaluate the overall flight effect of the UAV, while also fully considering the service life of the blade. By integrating all relevant factors, we generated a flight quality assessment coefficient that reflects the comprehensive performance of the blade as the main direction of optimization. The optimized blade design data will show more outstanding performance and provide strong support for the application of UAVs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0039] 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.

[0040] 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.

[0041] Example:

[0042] See also Figure 1 , the present invention provides a technical solution:

[0043] A method for optimizing the blade design of a multi-rotor bomb-dropping fire-fighting UAV comprises the following specific steps:

[0044] Step 1: Obtain the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, divide the multi-rotor bomb-throwing fire-fighting drone into N speed gears according to the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, and obtain the intermediate speed value of each speed gear;

[0045] The specific logic for dividing the speed gears is: obtain the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, divide the multi-rotor bomb-throwing fire-fighting drone into N speed gears according to the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, and obtain the specific formula for the intermediate value of the speed as follows:

[0046]

[0047] Among them, SP i is the speed intermediate value of the i-th speed gear, SP0 is the maximum speed gear, N is the speed gear number, and i is the speed gear index.

[0048] Step 2: Obtain the fuselage geometry design data and blade design data, use CFD software to build a fire-fighting UAV model, use the fire-fighting UAV model to perform aerodynamic analysis, and obtain flight power data at different intermediate speeds; obtain blade material property data, and generate corresponding blade flight evaluation coefficients based on the blade material property data and flight power data;

[0049] The blade design data includes the total length, total width, maximum thickness, minimum thickness, surface area and maximum bending angle of the blades of the multi-rotor bomb-dropping fire-fighting UAV; the flight power data includes the lift of the UAV, the drag of the UAV, the pressure at the root of the blade and the pressure at the tip of the blade;

[0050] The specific logic for generating the blade flight evaluation coefficient is as follows: obtaining blade material property data, generating a material performance coefficient according to the blade material property data, and generating a blade flight evaluation coefficient according to the material performance coefficient and flight power data; the material property data includes hardness, fatigue strength, compressive strength, tensile strength and Poisson's ratio of the blade material;

[0051] The specific formula used to generate the material performance coefficient is:

[0052]

[0053] Among them, CL is the material performance coefficient, Ha is the hardness of the blade material, R is the fatigue strength of the blade material, F is the tensile strength of the blade material, B is the compressive strength of the blade material, and SB is the Poisson's ratio of the blade material; the material performance coefficient CL reflects the performance of the blade material. The larger its value, the better the performance of the blade material. The generation of this coefficient can provide an important basis for the evaluation of flight quality.

[0054] The specific formula used to generate the blade flight evaluation coefficient is:

[0055]

[0056] Where Y is the blade flight evaluation coefficient, F u is the lift of the drone, Fdo is the drag of the drone, P g is the blade root pressure, P j The blade flight evaluation coefficient Y reflects the comprehensive performance of the blade during flight, which includes the flight effect of the UAV, blade stability and blade life. The larger the value, the better the comprehensive performance of the blade during flight. It is the lift-to-drag ratio, which reflects the ability of the multi-rotor bomb-dropping fire-fighting drone to adjust its speed and attitude during flight. The larger the value, the stronger the ability of the multi-rotor bomb-dropping fire-fighting drone to adjust its speed and attitude. It is the main pressure borne by the blades, and can reflect the pressure borne by the blades during flight. The larger the value, the greater the pressure borne by the blades during flight, the more unfavorable it is for the normal flight of the aircraft, and the shorter the life of the blades.

[0057] Step 3: Analyze the blade flight evaluation coefficient at each intermediate speed value to obtain the flight quality evaluation coefficient;

[0058] The specific logic for generating the flight quality assessment coefficient is as follows: calculate the blade flight assessment coefficient corresponding to the intermediate speed value; analyze the blade flight assessment coefficient at each intermediate speed value to obtain the flight quality assessment coefficient; the specific formula for generating the flight quality assessment coefficient is as follows:

[0059]

[0060] Among them, FY is the flight quality assessment coefficient, Y i is the blade flight evaluation coefficient corresponding to the intermediate value of the speed of the i-th gear, SP i is the middle speed value of the i-th speed gear, N is the number of speed gears, and i is the speed gear index.

[0061] The flight quality assessment coefficient FY reflects the comprehensive flight capability of the UAV at various speeds. The larger the value, the stronger the comprehensive flight capability of the UAV at various speeds. It can provide important direction for optimizing the UAV blade parameters.

[0062] Step 4: Build a flight quality assessment model, obtain historical blade design data and historical flight quality assessment coefficients, and use the historical blade design data as input and the corresponding historical flight quality assessment coefficients as labels to train the flight quality assessment model;

[0063] A feedforward neural network is used to train and optimize the flight quality assessment model using flight quality assessment coefficient labels and historical blade design data. It should be noted that the existing technology can be used to train and optimize the flight quality assessment model using flight quality assessment coefficient labels and historical blade design data, specifically including: an input layer, a hidden layer, an output layer, and an activation function, and a root mean square error loss function is used. The input data is calculated once through the network to obtain an output result, and the loss function is calculated based on the predicted value and the true value. The gradient of the loss function for each weight and bias is calculated by the chain rule, and the weights and biases of the network are updated using the gradient descent algorithm to minimize the loss function.

[0064] Step 5: Take the blade design data obtained in step 2 as the initial solution, and take maximizing the blade flight evaluation coefficient as the optimization goal. Use the simulated annealing algorithm to optimize the blade design data to obtain the optimal blade design data.

[0065] Determine that the optimization target of the blade design data is to maximize the flight quality assessment coefficient, and use the blade design data obtained in step 2 as the initial solution of the blade design data in the simulated annealing algorithm;

[0066] The optimal blade design data is found through simulated annealing algorithm, the initial annealing temperature and the cooling coefficient are set, and a neighborhood search is performed on the initial solution at the initial annealing temperature. A neighboring solution is randomly selected within the parameter range, and the flight quality assessment coefficient of the neighboring solution is predicted using the flight quality assessment model. The probability of accepting the new solution is determined according to the Metropolis criterion.

[0067] The formula for determining the probability of accepting a new solution according to the Metropolis criterion is:

[0068]

[0069] Where P is the probability of the new flight quality assessment coefficient being accepted, FY k+1 is the k+1th generated flight quality assessment coefficient, FY k is the kth generated flight quality assessment coefficient, k is the generation order index of the flight quality assessment coefficient, T is the annealing temperature, and the annealing temperature is continuously adjusted by the cooling coefficient until the termination condition is reached;

[0070] The termination condition of the simulated annealing algorithm is set as:

[0071] The total number of solutions for generating the flight quality assessment coefficient is X. For a currently found optimal flight quality assessment coefficient FY L , if the flight quality assessment coefficient is FY in the subsequent XL iterations L , then the output flight quality assessment coefficients at the end of the iteration are all FY LThe corresponding blade design data.

[0072] 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.

[0073] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by 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 electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0074] 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.

[0075] 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 method for optimizing the blade design of a multi-rotor bomb-dropping fire-fighting drone, characterized in that: The specific steps include: Step 1: Obtain the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, divide the multi-rotor bomb-throwing fire-fighting drone into N speed gears according to the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, and obtain the intermediate speed value of each speed gear; Step 2: Obtain the fuselage geometry design data and blade design data, use CFD software to build a fire-fighting UAV model, use the fire-fighting UAV model to perform aerodynamic analysis, and obtain flight power data at different intermediate speeds; obtain blade material property data, and generate corresponding blade flight evaluation coefficients based on the blade material property data and flight power data; Step 3: Analyze the blade flight evaluation coefficient at each intermediate speed value to obtain the flight quality evaluation coefficient; Step 4: Build a flight quality assessment model, obtain historical blade design data and historical flight quality assessment coefficients, and use the historical blade design data as input and the corresponding historical flight quality assessment coefficients as labels to train the flight quality assessment model; Step 5: Take the blade design data obtained in step 2 as the initial solution, and take maximizing the blade flight evaluation coefficient as the optimization goal. Use the simulated annealing algorithm to optimize the blade design data to obtain the optimal blade design data.

2. The method for optimizing blade design of a multi-rotor bomb-dropping fire-fighting drone according to claim 1 is characterized in that: The specific logic for dividing the speed gears is: obtain the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, divide the multi-rotor bomb-throwing fire-fighting drone into N speed gears according to the maximum speed of the blades of the multi-rotor bomb-throwing fire-fighting drone, and obtain the specific formula for the intermediate value of the speed as follows: Among them, SP i is the speed intermediate value of the i-th speed gear, SP0 is the maximum speed gear, N is the speed gear number, and i is the speed gear index.

3. The method for optimizing blade design of a multi-rotor bomb-dropping fire-fighting drone according to claim 1 is characterized in that: The blade design data includes the total length, total width, maximum thickness, minimum thickness, surface area and maximum bending angle of the blades of the multi-rotor bomb-dropping fire-fighting UAV; the flight power data includes the UAV lift, UAV drag, blade root pressure and blade tip pressure.

4. The method for optimizing blade design of a multi-rotor bomb-dropping fire-fighting drone according to claim 1 is characterized in that: The specific logic for generating the blade flight evaluation coefficient is as follows: obtaining blade material property data, generating a material performance coefficient according to the blade material property data, and generating a blade flight evaluation coefficient according to the material performance coefficient and flight power data; the material property data includes hardness, fatigue strength, compressive strength, tensile strength and Poisson's ratio of the blade material; The specific formula used to generate the material performance coefficient is: Wherein, CL is the material performance coefficient, Ha is the hardness of the blade material, R is the fatigue strength of the blade material, F is the tensile strength of the blade material, B is the compressive strength of the blade material, and SB is the Poisson's ratio of the blade material; The specific formula used to generate the blade flight evaluation coefficient is: Where Y is the blade flight evaluation coefficient, F u is the lift of the drone, F do is the drag of the drone, P g is the blade root pressure, P j is the blade tip pressure.

5. The method for optimizing blade design of a multi-rotor bomb-dropping fire-fighting drone according to claim 1 is characterized in that: The specific logic for generating the flight quality assessment coefficient is as follows: calculate the blade flight assessment coefficient corresponding to the intermediate speed value; analyze the blade flight assessment coefficient at each intermediate speed value to obtain the flight quality assessment coefficient; the specific formula for generating the flight quality assessment coefficient is as follows: Among them, FY is the flight quality assessment coefficient, Y i is the blade flight evaluation coefficient corresponding to the intermediate value of the speed of the i-th gear, SP i is the middle speed value of the i-th speed gear, N is the number of speed gears, and i is the speed gear index.

6. The method for optimizing blade design of a multi-rotor bomb-dropping fire-fighting drone according to claim 1, characterized in that: Determine that the optimization target of the blade design data is to maximize the flight quality assessment coefficient, and use the blade design data obtained in step 2 as the initial solution of the blade design data in the simulated annealing algorithm; The optimal blade design data is found through simulated annealing algorithm, the initial annealing temperature and the cooling coefficient are set, and a neighborhood search is performed on the initial solution at the initial annealing temperature. A neighboring solution is randomly selected within the parameter range, and the flight quality assessment coefficient of the neighboring solution is predicted using the flight quality assessment model. The probability of accepting the new solution is determined according to the Metropolis criterion.

7. The method for optimizing blade design of a multi-rotor bomb-dropping fire-fighting drone according to claim 6 is characterized in that: The formula for determining the probability of accepting a new solution according to the Metropolis criterion is: Where P is the probability of the new flight quality assessment coefficient being accepted, FY k+1 is the k+1th generated flight quality assessment coefficient, FY k is the kth generated flight quality assessment coefficient, k is the generation order index of the flight quality assessment coefficient, T is the annealing temperature, and the annealing temperature is continuously adjusted by the cooling coefficient until the termination condition is reached; The termination condition of the simulated annealing algorithm is set as: The total number of solutions for generating the flight quality assessment coefficient is X. For a currently found optimal flight quality assessment coefficient FY L , if the flight quality assessment coefficient is FY in the subsequent XL iterations L , then the output flight quality assessment coefficients at the end of the iteration are all FY L The corresponding blade design data.

Images