A distributed power layout optimization method for hydrogen-powered UAVs

Abstract

The present invention discloses a method for optimizing the distributed power layout of a hydrogen-powered UAV, which relates to the technical field of hydrogen-powered UAVs and aims to solve the problem of poor presentation of power layout solutions. By retrieving historical distributed power layout solutions and combining them with current analysis results, the present invention can draw on past successful experiences, avoid repeated errors, and improve design efficiency and success rate. The particle swarm optimization algorithm is used to optimize the layout of the initial position of the power components. This intelligent algorithm can efficiently search for the optimal solution, improve the overall performance of the layout solution, optimize the component position and installation angle, reduce resistance, increase lift, improve pitch moment balance, and enhance flight stability and maneuverability. It is particularly suitable for high-speed or high-angle-of-attack flight scenarios. The simulation analysis covers multiple aspects such as energy management, aerodynamic layout, structural strength, and thermal management, ensuring comprehensive evaluation and optimization of multiple key performances of the UAV.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrogen-powered UAVs, and in particular to a method for optimizing the distributed power layout of hydrogen-powered UAVs. Background Art

[0002] Hydrogen-powered drones refer to drones that use hydrogen as energy, and they usually use hydrogen fuel cells as their power source.

[0003] Chinese patent publication number CN111695203B discloses a method for aerodynamic layout design and performance evaluation of an anti-swarm UAV. This method primarily uses flight altitude, level flight speed, takeoff weight, and lift coefficient as aerodynamic layout design constraints. Based on these constraints, the geometric dimensions, center of gravity, tail, and installation angle of the wings and tail of the anti-swarm UAV are determined. This method, combined with practical application scenarios, effectively improves the aerodynamic efficiency of the UAV during actual application, enhancing its lift-to-drag ratio and stability. Furthermore, by establishing a first model with a propeller and a second model without a propeller, the takeoff flow field and level flight flow field of the UAV under the two conditions are predicted and analyzed, and the two calculation results are evaluated and compared, making the evaluation results more consistent with actual conditions. Although the aforementioned Chinese patent solves the problem of aerodynamic layout design, the following problems still exist in actual operation:

[0004] 1. There is no effective establishment of the actual entity model of the UAV and the standard teaching model of the UAV, which makes it impossible to further understand the detailed component composition.

[0005] 2. Failure to conduct targeted performance analysis based on the actual model of the UAV results in an inability to make accurate power layout.

[0006] 3. Failure to conduct more careful management analysis of the completed layout plan resulted in poor integrity of the power layout plan. Summary of the Invention

[0007] The purpose of the present invention is to provide a distributed power layout optimization method for hydrogen-powered UAVs. By retrieving historical distributed power layout schemes and combining them with current analysis results, we can draw on past successful experiences, avoid repeated errors, improve design efficiency and success rate, and use the particle swarm optimization algorithm to optimize the layout of the initial position of the power component. This intelligent algorithm can efficiently search for the optimal solution, improve the overall performance of the layout scheme, optimize the component position and installation angle, reduce resistance, increase lift, improve pitch moment balance, and enhance flight stability and controllability. It is particularly suitable for high-speed or high-angle-of-attack flight scenarios. The simulation analysis covers multiple aspects such as energy management, aerodynamic layout, structural strength, and thermal management, ensuring a comprehensive evaluation and optimization of multiple key performance aspects of the UAV, which can solve the problems in the existing technology.

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

[0009] A method for optimizing the distributed power layout of a hydrogen-powered UAV, comprising:

[0010] Establish a parametric model based on the UAV's geometric structure and power system, establish a teaching model for the UAV's hydrogen power system based on the established parametric model, conduct a distributed power layout based on the established parametric model, and define the constraints;

[0011] Conduct global management based on the distributed power layout plan, including energy management, aerodynamic layout optimization, structural strength analysis, and thermal management optimization. Conduct global collaborative optimization based on the results of global management, and conduct testing and verification after the collaborative optimization is completed.

[0012] Before carrying out the distributed power layout, the design goals of the UAV should be determined first. After the design goals are determined, the constraints of the layout design should be determined;

[0013] After the design goals and constraints are defined, the parametric model of the UAV is analyzed.

[0014] Preferably, a parameterized model is established based on the geometric structure and power system of the UAV, including:

[0015] First, the geometric structure of the UAV is parametrically modeled;

[0016] The first step is to collect the geometric dimensions, shape characteristics and relative positions of the UAV's components, including the fuselage, wing profile and tail. The collected geometric dimensions, shape characteristics and relative positions of the UAV's components are then used to generate a three-dimensional model of the UAV using computer-aided tools.

[0017] The generated UAV 3D model is parameterized. Parametric processing is to define geometric features by controlling key dimensions and shapes.

[0018] Discretize the continuous geometric features in the parametrically processed three-dimensional UAV model into a mesh model suitable for numerical calculation, and finally obtain the UAV geometric model;

[0019] Then, a parameterized model of the UAV's power system is established;

[0020] First, the relevant parameters of the UAV power system are collected, including the technical parameters, power characteristics and energy density of the battery, hydrogen storage tank, fuel cell and motor, and the interaction relationship between each power component is determined. The power components include batteries, hydrogen storage tanks, fuel cells and motors;

[0021] Based on the collected data on the geometric dimensions, shape characteristics, and relative positions of the drone's components, a mathematical model of the hydrogen power system was established. The mathematical model of the hydrogen power system included energy conversion and power output. The mathematical model of the hydrogen power system was dynamically modeled using the equation of state and the principle of energy conservation, ultimately resulting in a drone power model.

[0022] The UAV geometric model and the UAV dynamic model are coupled, and after the coupling is completed, the UAV parameterized model is obtained.

[0023] Preferably, the teaching model of the hydrogen power system of the UAV is established according to the established parameterized model, including:

[0024] The key technical parameters in the parametric model of the UAV are retrieved. The key technical parameters include the hydrogen storage tank, fuel cell, electric motor and battery. The parameters of the hydrogen storage tank are the capacity, pressure, volume and material of the hydrogen storage; the parameters of the fuel cell are the power output, efficiency, energy density and reaction kinetics of the fuel cell; the parameters of the electric motor are the power, speed, efficiency and torque curve of the electric motor; the parameters of the battery are the charging and discharging characteristics, capacity, durability and charging time of the battery;

[0025] After the key technical parameters are confirmed and retrieved, the interaction relationship between components is determined;

[0026] After the interaction relationship is confirmed, a teaching model is established;

[0027] The teaching model is to establish a data model for each power system component, including the static and dynamic behavior models of the components;

[0028] Integrate the component models into a complete power system model and define the energy flow and signal interaction between components;

[0029] Finally, the teaching model development tool is used to build a UAV hydrogen power system teaching model of the power system model and design the user interface.

[0030] Preferably, the distributed power layout is carried out according to the established parameterized model, and the constraints are defined, including:

[0031] Design goals include maximum flight time, payload capacity, energy efficiency, and flight stability;

[0032] Constraints include center of mass location, center of gravity location, structural strength, heat dissipation requirements, and space occupied by the power system;

[0033] Finally, complete the definition of design goals and constraints.

[0034] Preferably, the distributed power layout is performed according to the established parameterized model, and the constraint conditions are defined, further comprising:

[0035] The key parameters and performance characteristics of the power components in the parameterized model are analyzed. The power components include hydrogen storage tanks, fuel cells, electric motors, and batteries. After the analysis is completed, the interaction relationship between the power components is confirmed.

[0036] Retrieving historical distributed power layout plans from a database, combining the historical distributed power layout plans with analysis results of key parameters and performance characteristics and the interaction relationships between power components, and obtaining preliminary positions of the power components after the combination is completed;

[0037] The particle swarm optimization algorithm is used to optimize the initial position of the power components. During the optimization process, the key parameters of the power components in the layout plan are adjusted, including changing the installation position and angle of the power components and adjusting the connection method between the components.

[0038] After the adjustment is completed, the distributed power layout scheme of the parameterized model is obtained.

[0039] Preferably, the particle swarm optimization algorithm is used to optimize the layout of the preliminary position of the power assembly, including:

[0040] Based on the overall characteristics of the hydrogen-powered UAV and the characteristics of its power components, determine the constraints on the layout of the power components;

[0041] Based on the current flight mission of the hydrogen-powered UAV, determining the index requirements for flight air resistance, flight balance center of gravity, and flight endurance, and based on the index requirements, determining the weighted weights of flight air resistance, flight balance center of gravity, and flight endurance;

[0042] Determine the target optimization index based on flight air resistance, flight balance center of gravity, flight endurance, and weighted weights;

[0043] Based on the target optimization index and the constraint conditions, the installation position of the power component is solved using a particle swarm optimization algorithm to obtain the optimal installation position;

[0044] Determine feasible installation angles and feasible connection modes of the power components in the optimal safety position;

[0045] Based on the optimal installation location, a mathematical model of hydrogen-powered UAVs was established with hydrogen energy consumption and battery energy consumption as prediction indicators.

[0046] Based on the mathematical model, the predicted hydrogen energy consumption and predicted battery energy consumption under feasible installation angles and feasible connection modes of the power components in the current flight mission are determined, and the feasible installation angle and feasible connection mode of the power components with the lowest combined energy consumption of the predicted hydrogen energy consumption and the predicted battery energy consumption are selected as the target installation angle and target connection mode.

[0047] Preferably, global management is performed according to a distributed power layout solution, including:

[0048] First, confirm the key data in the distributed power layout plan, including layout plan data, parameterized model data, and external environment data;

[0049] Energy management is carried out according to the distributed power layout plan. Energy management is based on the design objectives of the UAV, combined with the flight mission profile, to analyze the power required at different stages, and then formulate an energy allocation strategy based on the performance characteristics of the power components. At the same time, an energy monitoring system is established to obtain the energy status and power output of each power component in real time, and the energy allocation strategy is dynamically adjusted based on the monitoring results.

[0050] Aerodynamic layout optimization is carried out according to the distributed power layout scheme. Aerodynamic layout optimization uses computational fluid dynamics tools to numerically simulate the aerodynamic performance of the UAV under the distributed power layout, analyze the impact of different power component positions on the airflow, evaluate the lift, drag and pitch moment, evaluate the aerodynamic performance, and adjust the position and installation angle parameters of the power components based on the evaluation results.

[0051] Preferably, global management is performed according to the distributed power layout solution, further comprising:

[0052] Conduct a structural strength analysis based on the distributed power layout scheme. This involves calculating the dynamic loads on the UAV structure based on the operating status of the power components. Combined with the aerodynamic performance evaluation results, the aerodynamic loads borne by the UAV under different flight conditions are determined. Finite element analysis software is then used to build a structural finite element model of the UAV. Dynamic and aerodynamic loads are then applied to the model, and the stress and strain distribution of the UAV structure under various loads is analyzed. Finally, based on the strength analysis results, appropriate materials are selected and the structural layout is adjusted.

[0053] Thermal management optimization is performed based on the distributed power layout plan. This involves determining the heat generation of the power components during operation, analyzing the distribution of heat sources and heat flow transfer paths, and establishing a thermal management model using the physical principles of heat conduction, convection, and radiation. This model simulates the temperature field distribution of the UAV under different flight conditions. Based on the temperature field simulation results, the heat dissipation method is confirmed, including air cooling, liquid cooling, or heat pipe cooling. Temperature sensors are installed to monitor the temperature of the power components and key parts in real time. Based on the temperature monitoring results, the operating parameters of the heat dissipation system are dynamically adjusted.

[0054] Finally, a distributed power layout plan with global management is obtained.

[0055] Preferably, global collaborative optimization is performed based on the global management results, and testing and verification are performed after the collaborative optimization is completed, including:

[0056] Integrate the teaching model of the UAV hydrogen power system into the collaborative optimization platform and determine the optimization objectives and constraints;

[0057] Confirm the model data in the distributed power layout scheme obtained after global management, and perform simulation analysis on each data;

[0058] Simulation analysis includes energy management simulation, aerodynamic layout simulation, structural strength simulation and thermal management simulation;

[0059] Compare and evaluate the simulation analysis results with the optimization objectives and constraints in the teaching model of the UAV hydrogen power system, and determine whether the simulation analysis results meet the optimization objectives and constraints based on the evaluation results;

[0060] According to the evaluation results, the design variables are adjusted using a genetic algorithm, wherein the genetic algorithm automatically iterates;

[0061] After the design variables are adjusted, simulated flight tests of the UAV are conducted and simulated flight test data is collected in real time;

[0062] Compare the simulation analysis test data collected in real time with the simulation data, and optimize the solution again based on the comparison results.

[0063] Preferably, based on the target optimization index and the constraint conditions, the installation position of the power assembly is solved based on the particle swarm optimization algorithm to obtain the optimal installation position, including:

[0064] Based on the current flight mission, combined with the target optimization index and constraints, the iteration coefficient of the particle swarm optimization algorithm is determined;

[0065] Obtain the maximum number of iterations corresponding to the iteration coefficient from the preset data table;

[0066] Determining a dynamic attenuation weight determination value for the inertia weight based on a maximum number of iterations, an initial inertia weight, and an ending inertia weight;

[0067] Based on the maximum number of iterations and the determined value of the dynamic attenuation weight, a particle swarm optimization algorithm is designed, and the installation position of the power component is solved based on the particle swarm optimization algorithm to obtain the optimal installation position.

[0068] Compared with the prior art, the present invention has the following beneficial effects:

[0069] 1. This invention provides a method for optimizing the distributed power layout of a hydrogen-powered UAV. By identifying the interaction relationships between components and establishing a teaching model based on them, students can clearly see how the components within the power system work together, as well as the process of energy flow and signal interaction.

[0070] 2. The present invention provides a distributed power layout optimization method for hydrogen-powered UAVs. By retrieving historical distributed power layout plans and combining them with current analysis results, this method can draw on past successful experiences, avoid repeated errors, and improve design efficiency and success rate. It also uses a particle swarm optimization algorithm to optimize the layout of the initial positions of power components. This intelligent algorithm can efficiently search for the optimal solution and improve the overall performance of the layout plan.

[0071] 3. The present invention provides a method for optimizing the distributed power layout of a hydrogen-powered UAV, which optimizes component positions and installation angles, reduces drag, increases lift, improves pitch moment balance, and enhances flight stability and maneuverability. The method is particularly suitable for high-speed or high-angle-of-attack flight scenarios. The simulation analysis covers multiple aspects, including energy management, aerodynamic layout, structural strength, and thermal management, ensuring comprehensive evaluation and optimization of multiple key performance aspects of the UAV. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a schematic diagram of the steps for optimizing the distributed power layout of the hydrogen-powered UAV of the present invention;

[0073] Figure 2 This is a schematic diagram of the distributed power layout optimization process of the hydrogen-powered UAV of the present invention. DETAILED DESCRIPTION

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0075] In order to solve the problem that there is no effective establishment of actual entity model of UAV and standard teaching model of UAV in the existing technology, which leads to the inability to further understand the detailed component composition, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0076] A method for optimizing the distributed power layout of a hydrogen-powered UAV, comprising:

[0077] Establish a parametric model based on the UAV's geometric structure and power system, establish a teaching model for the UAV's hydrogen power system based on the established parametric model, conduct a distributed power layout based on the established parametric model, and define the constraints;

[0078] Global management is carried out according to the distributed power layout plan, which includes energy management, aerodynamic layout optimization, structural strength analysis and thermal management optimization. Global collaborative optimization is carried out according to the global management results, and testing and verification are carried out after the collaborative optimization is completed.

[0079] Specifically, by establishing a parametric model, it is possible to comprehensively consider factors such as the UAV's geometry and powertrain, enabling global layout optimization. This holistic approach helps improve the UAV's overall performance, including aerodynamic efficiency, structural strength, and thermal management. The global management component places particular emphasis on energy management, enabling the UAV to more efficiently utilize the energy provided by the hydrogen powertrain. Using intelligent algorithms and dynamic programming techniques, the UAV can adjust energy distribution in real time based on the flight mission and environmental conditions, maximizing energy utilization. Aerodynamic layout optimization is key to improving UAV flight performance. Optimizing the UAV's aerodynamic layout can reduce flight resistance and improve flight efficiency. Furthermore, incorporating the layout of the distributed propulsion system can further suppress flutter and gust response, enhancing the UAV's flight stability. Structural strength analysis is incorporated to ensure the UAV can withstand various mechanical loads during flight, ensuring flight safety. This is crucial for improving the UAV's reliability and service life.

[0080] Build a parametric model based on the UAV's geometry and power system, including:

[0081] First, the geometric structure of the UAV is parametrically modeled;

[0082] The first step is to collect the geometric dimensions, shape characteristics and relative positions of the UAV's components, including the fuselage, wing profile and tail. The collected geometric dimensions, shape characteristics and relative positions of the UAV's components are then used to generate a three-dimensional model of the UAV using computer-aided tools.

[0083] The generated UAV 3D model is parameterized. Parametric processing is to define geometric features by controlling key dimensions and shapes.

[0084] Discretize the continuous geometric features in the parametrically processed three-dimensional UAV model into a mesh model suitable for numerical calculation, and finally obtain the UAV geometric model;

[0085] Then, a parameterized model of the UAV's power system is established;

[0086] First, the relevant parameters of the UAV power system are collected, including the technical parameters, power characteristics and energy density of the battery, hydrogen storage tank, fuel cell and motor, and the interaction relationship between each power component is determined. The power components include batteries, hydrogen storage tanks, fuel cells and motors;

[0087] Based on the collected data on the geometric dimensions, shape characteristics, and relative positions of the drone's components, a mathematical model of the hydrogen power system was established. The mathematical model of the hydrogen power system included energy conversion and power output. The mathematical model of the hydrogen power system was dynamically modeled using the equation of state and the principle of energy conservation, ultimately resulting in a drone power model.

[0088] The UAV geometric model and the UAV dynamic model are coupled, and after the coupling is completed, the UAV parameterized model is obtained.

[0089] Specifically, parametric processing allows for the rapid generation of a 3D drone model by conveniently defining geometric features by controlling key dimensions and shapes. This approach significantly improves modeling efficiency compared to traditional manual modeling. The parametric modeling of the powertrain also relies on the collection and organization of key parameters, making the modeling process more systematic and efficient. Parametric models allow for the adjustment and optimization of the drone's geometry and powertrain to suit different application scenarios and requirements. For example, flight performance can be optimized by adjusting parameters such as the drone's wing profile and fuselage dimensions. Parametric models of the powertrain also allow for the adjustment of technical parameters of components such as batteries and motors to achieve better energy conversion and power output. Parametric modeling reduces reliance on physical drones, allowing for design validation and improvement through virtual simulation and testing, thereby reducing R&D and production costs. Parametric models also facilitate the comparison and optimization of multiple solutions, helping to select the most cost-effective design. Discretizing the continuous geometric features in the parametric 3D drone model into a mesh suitable for numerical calculations makes subsequent numerical calculations and simulation analysis more accurate and efficient. The establishment of mathematical models of power systems also relies on mathematical tools such as equations of state and the principle of conservation of energy, making the simulation analysis of UAV power systems more accurate and reliable.

[0090] Based on the established parameterized model, a teaching model of the UAV hydrogen power system is established, including:

[0091] The key technical parameters in the parametric model of the UAV are retrieved. The key technical parameters include the hydrogen storage tank, fuel cell, electric motor and battery. The parameters of the hydrogen storage tank are the capacity, pressure, volume and material of the hydrogen storage; the parameters of the fuel cell are the power output, efficiency, energy density and reaction kinetics of the fuel cell; the parameters of the electric motor are the power, speed, efficiency and torque curve of the electric motor; the parameters of the battery are the charging and discharging characteristics, capacity, durability and charging time of the battery;

[0092] After the key technical parameters are confirmed and retrieved, the interaction relationship between components is determined;

[0093] After the interaction relationship is confirmed, a teaching model is established;

[0094] The teaching model is to establish a data model for each power system component, including the static and dynamic behavior models of the components;

[0095] Integrate the component models into a complete power system model and define the energy flow and signal interaction between components;

[0096] Finally, the teaching model development tool is used to build a UAV hydrogen power system teaching model of the power system model and design the user interface.

[0097] Specifically, through parameterized models, detailed data retrieval and modeling are performed for each key component of the UAV hydrogen power system (hydrogen storage tank, fuel cell, electric motor, and battery). This enables students to fully and systematically understand the composition and working principles of the UAV hydrogen power system. Key technical parameters of each component, such as the capacity and pressure of the hydrogen storage tank, are listed, which helps students gain a deeper understanding of the performance characteristics of each component and their matching relationships. By identifying the interactions between components and building a teaching model based on them, students can clearly see how the components within the power system work together and the process of energy flow and signal interaction. The teaching model establishes static and dynamic behavior models for each power system component, which helps students understand the performance of the component under different operating conditions and the dynamic response characteristics of the entire system. Integrating the various component models into a complete power system model allows students to intuitively see the operating status and performance of the entire system, thereby deepening their understanding of the overall structure of the UAV hydrogen power system. Using the teaching model development tool to build the power system model not only improves the accuracy and reliability of the model but also makes the teaching more intuitive and vivid. This will help students better understand and master relevant knowledge. By establishing a teaching model of drone hydrogen power system, it will help promote the development and popularization of hydrogen energy technology in the field of education, cultivate more talents with hydrogen energy technology knowledge and skills, and lay a solid foundation for the widespread application of hydrogen energy technology.

[0098] In order to solve the problem that the existing technology does not conduct targeted performance analysis based on the actual model of the UAV, which leads to the inability to make accurate power layout, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0099] Based on the established parameterized model, the distributed power layout is carried out and the constraints are defined, including:

[0100] Before implementing a distributed power layout, the design objectives of the UAV must be determined. These objectives include maximum flight time, payload capacity, energy efficiency, and flight stability.

[0101] After the design objectives are determined, the constraints of the layout design are determined. The constraints include the center of mass position, center of gravity position, structural strength, heat dissipation requirements, and space occupied by the power system;

[0102] Finally, complete the definition of design goals and constraints.

[0103] After the design goals and constraints are defined, the parametric model of the UAV is analyzed;

[0104] The key parameters and performance characteristics of the power components in the parameterized model are analyzed. The power components include hydrogen storage tanks, fuel cells, electric motors, and batteries. After the analysis is completed, the interaction relationship between the power components is confirmed.

[0105] Retrieving historical distributed power layout plans from a database, combining the historical distributed power layout plans with analysis results of key parameters and performance characteristics and the interaction relationships between power components, and obtaining preliminary positions of the power components after the combination is completed;

[0106] The particle swarm optimization algorithm is used to optimize the initial position of the power components. During the optimization process, the key parameters of the power components in the layout plan are adjusted, including changing the installation position and angle of the power components and adjusting the connection method between the components.

[0107] After the adjustment is completed, the distributed power layout scheme of the parameterized model is obtained.

[0108] In one embodiment, the particle swarm optimization algorithm is used to optimize the layout of the preliminary position of the power assembly, including:

[0109] Based on the overall characteristics of the hydrogen-powered UAV and the characteristics of its power components, determine the constraints on the layout of the power components;

[0110] Based on the current flight mission of the hydrogen-powered UAV, determining the index requirements for flight air resistance, flight balance center of gravity, and flight endurance, and based on the index requirements, determining the weighted weights of flight air resistance, flight balance center of gravity, and flight endurance;

[0111] Determine the target optimization index based on flight air resistance, flight balance center of gravity, flight endurance, and weighted weights;

[0112] Based on the target optimization index and the constraint conditions, the installation position of the power component is solved using a particle swarm optimization algorithm to obtain the optimal installation position;

[0113] Determine feasible installation angles and feasible connection modes of the power components in the optimal safety position;

[0114] Based on the optimal installation location, a mathematical model of hydrogen-powered UAVs was established with hydrogen energy consumption and battery energy consumption as prediction indicators.

[0115] Based on the mathematical model, the predicted hydrogen energy consumption and predicted battery energy consumption under feasible installation angles and feasible connection modes of the power components in the current flight mission are determined, and the feasible installation angle and feasible connection mode of the power components with the lowest combined energy consumption of the predicted hydrogen energy consumption and the predicted battery energy consumption are selected as the target installation angle and target connection mode.

[0116] In this embodiment, the weighted weight is determined based on the current flight mission. If there is a requirement for flight speed, a larger weighted weight is set for flight air resistance. If there is a requirement for flight time, a larger weighted weight is set for flight endurance.

[0117] In this embodiment, the target optimization is a target group including the ultimate targets of flight air resistance, flight balance center of gravity, and flight endurance.

[0118] In this embodiment, there are multiple possible installation angles and possible connection modes of the components.

[0119] The beneficial effects of the above design scheme are: by determining the constraints of the layout between the power components based on the overall characteristics of the hydrogen-powered drone and the characteristics of the power components, and determining the target optimization index based on the flight air resistance, flight balance center of gravity, flight endurance, and weighted weights, based on the target optimization index and the constraints, the installation position of the power component is solved based on the particle swarm optimization algorithm to obtain the optimal installation position, and the determination of the optimal installation position based on the particle swarm optimization algorithm is realized to ensure that the optimal installation position meets the needs of the current flight mission. At the same time, with hydrogen energy consumption and battery energy consumption as prediction indicators, the target installation angle and target connection method are determined at the optimal installation position to ensure minimum energy consumption. From the two aspects of demand and cost, the optimality of the obtained UAV distributed power layout is guaranteed.

[0120] In one embodiment, based on the target optimization index and the constraint conditions, the installation position of the power assembly is solved based on the particle swarm optimization algorithm to obtain the optimal installation position, including:

[0121] Based on the current flight mission, combined with the target optimization index and constraints, the iteration coefficient of the particle swarm optimization algorithm is determined;

[0122]

[0123] Among them, K represents the iteration coefficient of the particle swarm optimization algorithm, Indicates the complexity of the current flight mission, with a value of (0, 1). Indicates the number of target optimization indicators, Indicates the preset maximum number of indicators. represents a natural constant, with a value of 2.72. Indicates the maximum lateral movement standard value of the optimal position of the constraint condition, which is (0, 1). The maximum standard horizontal movement value of the optimal position of the constraint condition is (0, 1); Indicates the comprehensive correlation of the target optimization indicators, with a value between 0 and 1.

[0124] Obtain the maximum number of iterations corresponding to the iteration coefficient from the preset data table;

[0125] Determining a dynamic attenuation weight determination value for the inertia weight based on a maximum number of iterations, an initial inertia weight, and an ending inertia weight;

[0126]

[0127] in, Indicates the dynamic attenuation weight determination value, is the reference moving range value, represents the initial inertia weight, represents the end inertia weight, represents the maximum number of iterations, Indicates the current iteration number;

[0128] Based on the maximum number of iterations and the determined value of the dynamic attenuation weight, a particle swarm optimization algorithm is designed, and the installation position of the power component is solved based on the particle swarm optimization algorithm to obtain the optimal installation position.

[0129] In this embodiment, the initial inertia weight is typically 0.9 and the ending inertia weight is typically 0.4.

[0130] In this embodiment, the reference moving range value is preset. The larger the value, the greater the dynamic attenuation weight determination value.

[0131] In this embodiment, the larger the iteration coefficient is, the larger the corresponding maximum number of iterations is.

[0132] In this embodiment, the smaller the comprehensive correlation of the target optimization index, the more complex the particle swarm is, and the larger the corresponding iteration coefficient is.

[0133] The beneficial effect of the above design scheme is: by designing the specific parameters of the particle swarm optimization algorithm based on the current flight mission, combining the target optimization indicators and constraints, the accuracy and practicality of the optimal installation position obtained by the particle swarm optimization algorithm are guaranteed, providing a basis for power layout optimization.

[0134] Specifically, the design objectives of the UAV were first clarified, including maximum flight time, payload capacity, energy efficiency, and flight stability. This provided a clear direction and benchmark for subsequent design and optimization. By defining constraints such as the center of mass location, center of gravity location, structural strength, heat dissipation requirements, and the space occupied by the power system, the feasibility and safety of the layout design in practical applications were ensured. An in-depth analysis of the key parameters and performance characteristics of the power components in the parametric model helped to understand the performance characteristics and interactions of each component, providing a scientific basis for layout design. By retrieving historical distributed power layout plans and combining them with current analysis results, we can learn from past successful experiences, avoid repeated errors, and improve design efficiency and success rate. The particle swarm optimization algorithm was used to optimize the initial layout of the power components. This intelligent algorithm can efficiently search for the optimal solution and improve the overall performance of the layout plan. During the optimization process, key parameters of the power components in the layout plan can be adjusted, including changing the installation position and angle of the power components and adjusting the connection method between components, which increases the flexibility and adaptability of the layout. The application of parametric models and optimization algorithms makes the layout design more standardized and modular, which helps to simplify the production, assembly, and maintenance of UAVs.

[0135] In order to solve the problem in the prior art that the layout plan is not managed and analyzed more carefully, which leads to the poor integrity of the power layout plan, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0136] Global management based on the distributed power layout plan, including:

[0137] First, confirm the key data in the distributed power layout plan, including layout plan data, parameterized model data, and external environment data;

[0138] Energy management is carried out according to the distributed power layout plan. Energy management is based on the design objectives of the UAV, combined with the flight mission profile, to analyze the power required at different stages, and then formulate an energy allocation strategy based on the performance characteristics of the power components. At the same time, an energy monitoring system is established to obtain the energy status and power output of each power component in real time, and the energy allocation strategy is dynamically adjusted based on the monitoring results.

[0139] Aerodynamic layout optimization is carried out according to the distributed power layout scheme. Aerodynamic layout optimization uses computational fluid dynamics tools to numerically simulate the aerodynamic performance of the UAV under the distributed power layout, analyze the impact of different power component positions on the airflow, evaluate the lift, drag and pitch moment, evaluate the aerodynamic performance, and adjust the position and installation angle parameters of the power components based on the evaluation results.

[0140] Conduct a structural strength analysis based on the distributed power layout scheme. This involves calculating the dynamic loads on the UAV structure based on the operating status of the power components. Combined with the aerodynamic performance evaluation results, the aerodynamic loads borne by the UAV under different flight conditions are determined. Finite element analysis software is then used to build a structural finite element model of the UAV. Dynamic and aerodynamic loads are then applied to the model, and the stress and strain distribution of the UAV structure under various loads is analyzed. Finally, based on the strength analysis results, appropriate materials are selected and the structural layout is adjusted.

[0141] Thermal management optimization is performed based on the distributed power layout plan. This involves determining the heat generation of the power components during operation, analyzing the distribution of heat sources and heat flow transfer paths, and establishing a thermal management model using the physical principles of heat conduction, convection, and radiation. This model simulates the temperature field distribution of the UAV under different flight conditions. Based on the temperature field simulation results, the heat dissipation method is confirmed, including air cooling, liquid cooling, or heat pipe cooling. Temperature sensors are installed to monitor the temperature of the power components and key parts in real time. Based on the temperature monitoring results, the operating parameters of the heat dissipation system are dynamically adjusted.

[0142] Finally, a distributed power layout plan with global management is obtained.

[0143] Specifically, by integrating modules such as energy management, aerodynamic optimization, structural strength and thermal management, the whole system coordinated optimization of power layout and aerodynamic, structural and thermal characteristics is achieved, avoiding the limitations of single-discipline optimization, unified confirmation and iterative update of key data (layout scheme, parametric model, environmental data), ensuring the consistency of design basis of each link, reducing design conflicts, matching power requirements in real time according to flight mission profiles (such as climb, cruise, landing), combining power component performance (such as motor efficiency, battery discharge characteristics), optimizing energy distribution strategy, extending UAV flight time, real-time monitoring of the energy status (remaining power, power output) of each power component (such as motor, battery), dynamic adjustment of load, avoiding energy waste or overload, and through CFD Simulate and analyze the interference of distributed power components (such as multi-rotors and ducted fans) on airflow (such as wing vortex and engine jet effects), optimize component position and installation angle, reduce drag, increase lift, improve pitch moment balance, and enhance flight stability and controllability. It is especially suitable for high-speed or high-angle-of-attack flight scenarios. Combining dynamic loads (such as motor vibration and thrust reaction force) with aerodynamic loads (such as lift and drag), finite element analysis is used to accurately evaluate structural stress and strain, avoiding traditional "empirical design" Redundancy or weakness problems are solved, material selection (such as carbon fiber composite materials) and structural layout (such as rib position) are optimized, weight is reduced while increasing strength, extending the life of the UAV, heat conduction, convection, and radiation models are established, and temperature field distribution under different working conditions (such as hovering and high-speed flight) is simulated. Targeted heat dissipation solutions (air cooling, liquid cooling, heat pipes) are designed to avoid overheating and failure of power components, real-time temperature monitoring and dynamic adjustment of the heat dissipation system (such as fan speed and coolant flow) are implemented to adapt to complex environments (high temperature, low temperature, high altitude). Parameters such as power component position, angle, and heat dissipation method are highly adjustable, which is convenient for adapting to different mission requirements (such as load, range, speed) or model iteration (such as from multi-rotor to composite wing).

[0144] Perform global collaborative optimization based on the global management results. After the collaborative optimization is completed, test and verify it, including:

[0145] Integrate the teaching model of the UAV hydrogen power system into the collaborative optimization platform and determine the optimization objectives and constraints;

[0146] Confirm the model data in the distributed power layout scheme obtained after global management, and perform simulation analysis on each data;

[0147] Simulation analysis includes energy management simulation, aerodynamic layout simulation, structural strength simulation and thermal management simulation;

[0148] Compare and evaluate the simulation analysis results with the optimization objectives and constraints in the teaching model of the UAV hydrogen power system, and determine whether the simulation analysis results meet the optimization objectives and constraints based on the evaluation results;

[0149] According to the evaluation results, the design variables are adjusted using a genetic algorithm, wherein the genetic algorithm automatically iterates;

[0150] After the design variables are adjusted, simulated flight tests of the UAV are conducted and simulated flight test data is collected in real time;

[0151] Compare the simulation analysis test data collected in real time with the simulation data, and optimize the solution again based on the comparison results.

[0152] Specifically, collaborative optimization, through global management of results, ensures optimal overall performance for all components of the UAV's hydrogen powertrain (e.g., energy management, aerodynamic layout, structural strength, and thermal management). This systematic optimization approach improves overall UAV performance more effectively than optimizing each component individually. The UAV hydrogen powertrain teaching model is integrated into the collaborative optimization platform, enabling unified model management and optimization. Furthermore, a genetic algorithm is used to automatically and iteratively adjust design variables, further automating the optimization process, reducing manual intervention and improving efficiency. Simulation analysis encompasses multiple aspects, including energy management, aerodynamic layout, structural strength, and thermal management, ensuring comprehensive evaluation and optimization of multiple key UAV performance indicators. This comprehensive simulation analysis helps identify potential issues and implement targeted improvements. Real-time data collection and analysis during simulated flight tests is compared with simulation data. This real-time data collection and analysis helps verify the accuracy of simulation results and allows for further optimization based on actual conditions. This adjustment and optimization based on evaluation results demonstrates a high degree of flexibility and iterativeness. This means that during the optimization process, the solution can be continuously adjusted and refined based on actual conditions to achieve optimal performance.

[0153] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0154] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A method for optimizing the distributed power layout of a hydrogen-powered UAV, characterized in that: include: Establish a parametric model based on the UAV's geometric structure and power system, establish a teaching model for the UAV's hydrogen power system based on the established parametric model, conduct a distributed power layout based on the established parametric model, and define the constraints; Conduct global management based on the distributed power layout plan, including energy management, aerodynamic layout optimization, structural strength analysis, and thermal management optimization. Conduct global collaborative optimization based on the results of global management, and conduct testing and verification after the collaborative optimization is completed. Before carrying out the distributed power layout, the design goals of the UAV should be determined first. After the design goals are determined, the constraints of the layout design should be determined; After the design goals and constraints are defined, the parametric model of the UAV is analyzed; Based on the established parameterized model, the distributed power layout is carried out and the constraints are defined, including: Design goals include maximum flight time, payload capacity, energy efficiency, and flight stability; Constraints include center of mass location, center of gravity location, structural strength, heat dissipation requirements, and space occupied by the power system; Finally, complete the definition of design goals and constraints; The key parameters and performance characteristics of the power components in the parameterized model are analyzed. The power components include hydrogen storage tanks, fuel cells, electric motors, and batteries. After the analysis is completed, the interaction relationship between the power components is confirmed. Retrieving historical distributed power layout plans from a database, combining the historical distributed power layout plans with analysis results of key parameters and performance characteristics and the interaction relationships between power components, and obtaining preliminary positions of the power components after the combination is completed; The particle swarm optimization algorithm is used to optimize the initial position of the power components. During the optimization process, the key parameters of the power components in the layout plan are adjusted, including changing the installation position and angle of the power components and adjusting the connection method between the components. After the adjustment is completed, the distributed power layout scheme of the parameterized model is obtained.

2. The method for optimizing the distributed power layout of a hydrogen-powered UAV according to claim 1, characterized in that: Build a parametric model based on the UAV's geometry and power system, including: First, the geometric structure of the UAV is parametrically modeled; The first step is to collect the geometric dimensions, shape characteristics and relative positions of the UAV's components, including the fuselage, wing profile and tail. The collected geometric dimensions, shape characteristics and relative positions of the UAV's components are then used to generate a three-dimensional model of the UAV using computer-aided tools. The generated UAV 3D model is parameterized. Parametric processing is to define geometric features by controlling key dimensions and shapes. Discretize the continuous geometric features in the parametrically processed three-dimensional UAV model into a mesh model suitable for numerical calculation, and finally obtain the UAV geometric model; Then, a parameterized model of the UAV's power system is established; First, the relevant parameters of the UAV power system are collected, including the technical parameters, power characteristics and energy density of the battery, hydrogen storage tank, fuel cell and motor, and the interaction relationship between each power component is determined. The power components include batteries, hydrogen storage tanks, fuel cells and motors; Based on the collected data on the geometric dimensions, shape characteristics, and relative positions of the drone's components, a mathematical model of the hydrogen power system was established. The mathematical model of the hydrogen power system included energy conversion and power output. The mathematical model of the hydrogen power system was dynamically modeled using the equation of state and the principle of energy conservation, ultimately resulting in a drone power model. The UAV geometric model and the UAV dynamic model are coupled, and after the coupling is completed, the UAV parameterized model is obtained.

3. The method for optimizing the distributed power layout of a hydrogen-powered UAV according to claim 1, characterized in that: Based on the established parameterized model, a teaching model of the UAV hydrogen power system is established, including: The key technical parameters in the parametric model of the UAV are retrieved. The key technical parameters include the hydrogen storage tank, fuel cell, electric motor and battery. The parameters of the hydrogen storage tank are the capacity, pressure, volume and material of the hydrogen storage; the parameters of the fuel cell are the power output, efficiency, energy density and reaction kinetics of the fuel cell; the parameters of the electric motor are the power, speed, efficiency and torque curve of the electric motor; the parameters of the battery are the charging and discharging characteristics, capacity, durability and charging time of the battery; After the key technical parameters are confirmed and retrieved, the interaction relationship between components is determined; After the interaction relationship is confirmed, a teaching model is established; The teaching model is to establish a data model for each power system component, including the static and dynamic behavior models of the components; Integrate the component models into a complete power system model and define the energy flow and signal interaction between components; Finally, the teaching model development tool is used to build a UAV hydrogen power system teaching model of the power system model and design the user interface.

4. The method for optimizing the distributed power layout of a hydrogen-powered UAV according to claim 1, characterized in that: The particle swarm optimization algorithm is used to optimize the layout of the preliminary position of the power components, including: Based on the overall characteristics of the hydrogen-powered UAV and the characteristics of its power components, determine the constraints on the layout of the power components; Based on the current flight mission of the hydrogen-powered UAV, determining the index requirements for flight air resistance, flight balance center of gravity, and flight endurance, and based on the index requirements, determining the weighted weights of flight air resistance, flight balance center of gravity, and flight endurance; Determine the target optimization index based on flight air resistance, flight balance center of gravity, flight endurance, and weighted weights; Based on the target optimization index and the constraint conditions, the installation position of the power component is solved using a particle swarm optimization algorithm to obtain the optimal installation position; Determine feasible installation angles and feasible connection modes of the power components in the optimal safety position; Based on the optimal installation location, a mathematical model of hydrogen-powered UAVs was established with hydrogen energy consumption and battery energy consumption as prediction indicators. Based on the mathematical model, the predicted hydrogen energy consumption and predicted battery energy consumption under feasible installation angles and feasible connection modes of the power components in the current flight mission are determined, and the feasible installation angle and feasible connection mode of the power components with the lowest combined energy consumption of the predicted hydrogen energy consumption and the predicted battery energy consumption are selected as the target installation angle and target connection mode.

5. The method for optimizing the distributed power layout of a hydrogen-powered UAV according to claim 1, characterized in that: Global management based on the distributed power layout plan, including: First, confirm the key data in the distributed power layout plan, including layout plan data, parameterized model data, and external environment data; Energy management is carried out according to the distributed power layout plan. Energy management is based on the design objectives of the UAV, combined with the flight mission profile, to analyze the power required at different stages, and then formulate an energy allocation strategy based on the performance characteristics of the power components. At the same time, an energy monitoring system is established to obtain the energy status and power output of each power component in real time, and the energy allocation strategy is dynamically adjusted based on the monitoring results. Aerodynamic layout optimization is carried out according to the distributed power layout scheme. Aerodynamic layout optimization uses computational fluid dynamics tools to numerically simulate the aerodynamic performance of the UAV under the distributed power layout, analyze the impact of different power component positions on the airflow, evaluate the lift, drag and pitch moment, evaluate the aerodynamic performance, and adjust the position and installation angle parameters of the power components based on the evaluation results.

6. The method for optimizing the distributed power layout of a hydrogen-powered UAV according to claim 5, characterized in that: Global management based on the distributed power layout plan also includes: Conduct a structural strength analysis based on the distributed power layout scheme. This involves calculating the dynamic loads on the UAV structure based on the operating status of the power components. Combined with the aerodynamic performance evaluation results, the aerodynamic loads borne by the UAV under different flight conditions are determined. Finite element analysis software is then used to build a structural finite element model of the UAV. Dynamic and aerodynamic loads are then applied to the model, and the stress and strain distribution of the UAV structure under various loads is analyzed. Finally, based on the strength analysis results, appropriate materials are selected and the structural layout is adjusted. Thermal management optimization is performed based on the distributed power layout plan. This involves determining the heat generation of the power components during operation, analyzing the distribution of heat sources and heat flow transfer paths, and establishing a thermal management model using the physical principles of heat conduction, convection, and radiation. This model simulates the temperature field distribution of the UAV under different flight conditions. Based on the temperature field simulation results, the heat dissipation method is confirmed, including air cooling, liquid cooling, or heat pipe cooling. Temperature sensors are installed to monitor the temperature of the power components and key parts in real time. Based on the temperature monitoring results, the operating parameters of the heat dissipation system are dynamically adjusted. Finally, a distributed power layout plan with global management is obtained.

7. The method for optimizing the distributed power layout of a hydrogen-powered UAV according to claim 6, characterized in that: Perform global collaborative optimization based on the global management results. After the collaborative optimization is completed, test and verify it, including: Integrate the teaching model of the UAV hydrogen power system into the collaborative optimization platform and determine the optimization objectives and constraints; Confirm the model data in the distributed power layout scheme obtained after global management, and perform simulation analysis on each data; Simulation analysis includes energy management simulation, aerodynamic layout simulation, structural strength simulation and thermal management simulation; Compare and evaluate the simulation analysis results with the optimization objectives and constraints in the teaching model of the UAV hydrogen power system, and determine whether the simulation analysis results meet the optimization objectives and constraints based on the evaluation results; According to the evaluation results, the design variables are adjusted using a genetic algorithm, wherein the genetic algorithm automatically iterates; After the design variables are adjusted, simulated flight tests of the UAV are conducted and simulated flight test data is collected in real time; Compare the simulation analysis test data collected in real time with the simulation data, and optimize the solution again based on the comparison results.

8. The method for optimizing the distributed power layout of a hydrogen-powered UAV according to claim 1, characterized in that: Based on the target optimization index and constraints, the installation position of the power component is solved using the particle swarm optimization algorithm to obtain the optimal installation position, including: Based on the current flight mission, combined with the target optimization index and constraints, the iteration coefficient of the particle swarm optimization algorithm is determined; Obtain the maximum number of iterations corresponding to the iteration coefficient from the preset data table; Determining a dynamic attenuation weight determination value for the inertia weight based on a maximum number of iterations, an initial inertia weight, and an ending inertia weight; Based on the maximum number of iterations and the determined value of the dynamic attenuation weight, a particle swarm optimization algorithm is designed, and the installation position of the power component is solved based on the particle swarm optimization algorithm to obtain the optimal installation position.

Images