Energy self-adaptive optimization system and method for hydrogen fuel cell hybrid power unmanned aerial vehicle

Abstract

The invention provides a hydrogen fuel cell hybrid power unmanned aerial vehicle energy adaptive optimization system and method. The system and method aim at achieving adaptive optimization when multiple uncertain factors exist in the flight process of an unmanned aerial vehicle. Through mechanical analysis of the typical flight profile of the unmanned aerial vehicle, an estimation model of load demand power in each stage in the flight process of the unmanned aerial vehicle is constructed. The core of the method is that the flight process of the unmanned aerial vehicle is modeled as a Markov decision process, and a self-adaptive optimization model composed of a power energy consumption state space, a power supply power distribution action space, a reward function, an electric energy supply constraint condition and the like is reasonably constructed. And for an electric energy distribution reward function, a near-end strategy optimization algorithm is applied to train an intelligent agent to continuously update an actor network and iterative learning to approach an expected control strategy, so that self-adaptive intelligent optimal distribution of the hydrogen energy and the electric energy by the hydrogen fuel hybrid power unmanned aerial vehicle energy management system is realized, and a system implementation scheme is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and in particular to an energy adaptive optimization system and method for a hydrogen fuel cell hybrid power unmanned aerial vehicle. Background Art

[0002] As an advanced energy conversion device, hydrogen fuel cells are based on directly converting the chemical energy of hydrogen and oxygen into electrical energy. This process follows the reverse reaction principle of water electrolysis. Its most significant advantage is environmental friendliness. Secondly, hydrogen fuel cells have high energy conversion efficiency, which can usually reach more than 50%, much higher than traditional internal combustion engines. In addition, hydrogen fuel cells run quietly with extremely low noise levels. Finally, the fuel of hydrogen fuel cells, hydrogen, is widely available and renewable. Hydrogen can be produced through renewable energy (such as photovoltaics and wind energy) to form a completely clean energy cycle.

[0003] In recent years, with the transformation of the global energy structure and the improvement of environmental awareness, the application research of hydrogen fuel cells in the field of drones has become increasingly in-depth. Many scientific research institutions and enterprises at home and abroad have invested resources to develop efficient and reliable hydrogen fuel cell drone energy management systems. However, the current technological development still faces many challenges, such as the optimization of energy allocation strategies and real-time response to multiple uncertain factors (such as flight environment, load changes, battery status, etc.). Traditional energy management methods often fail to fully consider these complex factors, making it difficult for drones to achieve optimal performance in practical applications.

[0004] Therefore, in response to the above problems, this patent proposes a hydrogen fuel cell hybrid UAV energy adaptive optimization method and system. This technology can sense and process various uncertain factors in the UAV flight process in real time through the proximal strategy optimization algorithm, and dynamically adjust the energy allocation strategy to maximize the UAV's endurance, flight efficiency and safety. Summary of the invention

[0005] In order to overcome the deficiencies in the prior art, the present invention proposes a hydrogen fuel cell hybrid UAV energy adaptive optimization method and system. First, it can more accurately predict and respond to various changes in the flight process, thereby improving the efficiency and stability of energy utilization; second, through the self-optimization capability of the proximal strategy optimization algorithm, it continuously learns and adapts to new flight environments and mission requirements, thereby improving the intelligence level and adaptability of the UAV; third, it realizes the mixed use of hydrogen fuel cells and lithium batteries, and further improves the overall performance and reliability of the UAV through adaptive intelligent optimal allocation.

[0006] The present invention provides a hydrogen fuel cell hybrid power UAV energy adaptive optimization system, comprising:

[0007] A partial modeling module, used to build a load demand power model, a hydrogen fuel cell model and a lithium battery model of the hydrogen fuel cell hybrid UAV according to the basic equipment parameters of the hydrogen fuel cell hybrid UAV;

[0008] A model analysis module, used to build the power energy consumption state space and power supply allocation space of the hydrogen fuel cell hybrid UAV based on the load demand power model, the hydrogen fuel cell model and the lithium battery model, as well as to build the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV;

[0009] An algorithm optimization module, used to construct an actor neural network and a commentator neural network of the hydrogen fuel cell hybrid UAV using a preset PPO algorithm and the basic equipment parameters, and to optimize the power consumption state space and the power supply allocation space using the actor neural network to obtain a plurality of optimization conditions, and to perform feedback analysis on the optimization conditions according to the flight reward function and the power supply constraint conditions using the commentator neural network to obtain a plurality of hyperparameters;

[0010] The optimization training module is used to construct an energy management agent according to the hyperparameters, map the load demand power model, the hydrogen fuel cell model and the lithium battery model into the energy management agent respectively to generate a training agent for the hydrogen fuel cell hybrid UAV, and run the training agent to obtain the optimal strategy presented by the hydrogen fuel cell hybrid UAV when it converges to the flight reward function and display it.

[0011] In one practicable manner,

[0012] The process of building the load demand power model of the hydrogen fuel cell hybrid UAV includes:

[0013] The induced power of the hydrogen fuel cell hybrid UAV is calculated according to formula (1);

[0014] P ik =T d ·v ik (1)

[0015] Among them, P ik represents the induced power of the hydrogen fuel cell hybrid UAV, v ik represents the actual induced speed of the hydrogen fuel cell hybrid UAV;

[0016] The drag power of the hydrogen fuel cell hybrid UAV is calculated according to formula (2);

[0017]

[0018] Among them, P pr represents the drag power of the hydrogen fuel cell hybrid UAV, As represents the UAV blade section area, ω represents the blade rotation angular velocity, R represents the turntable radius, and δ represents the profile tension coefficient;

[0019] The waste power of the hydrogen fuel cell hybrid UAV is calculated according to formula (3);

[0020]

[0021] Among them, P pa represents the waste resistance power of the hydrogen fuel cell hybrid UAV;

[0022] The interfered power of the hydrogen fuel cell hybrid UAV is calculated according to formula (4);

[0023] P dis (t)~N(0,1)×c,P dis_min <P dis (t) <P dis_max (4)

[0024] Wherein, c represents the disturbance amplitude coefficient of the hydrogen fuel cell hybrid UAV;

[0025] According to formula (5), the corresponding load mass of the hydrogen fuel cell hybrid UAV at different flight times is calculated;

[0026]

[0027] Where m(t) represents the total weight of the hydrogen fuel cell hybrid UAV at time t, represents the consumption of hydrogen, M represents the molar mass of hydrogen, P represents the working pressure of the hydrogen fuel cell stack, R represents the Avogadro constant, and T represents the working thermodynamic temperature of the stack;

[0028] According to the calculation result of formula (5), the corresponding load mass of the hydrogen fuel cell hybrid UAV at different flight times is determined, and the load demand power model of the fuel cell hybrid UAV is established.

[0029] In one practicable manner,

[0030] Also includes:

[0031] Calculate the pulling force required by the hydrogen fuel cell hybrid UAV during flight according to formula (6);

[0032]

[0033] Among them, T drepresents the pulling force required by the hydrogen fuel cell hybrid UAV during flight, a c represents the acceleration of the hydrogen fuel cell hybrid UAV, v represents the airspeed of the hydrogen fuel cell hybrid UAV, and v f represents the air velocity, β represents the angle between the air velocity direction and the flight direction of the hydrogen fuel cell hybrid UAV, θ represents the angle between the flight direction of the hydrogen fuel cell hybrid UAV and the vertical direction, ρ represents the air density, A f represents the vertical projection area of ​​the hydrogen fuel cell hybrid UAV, m represents the total mass of the hydrogen fuel cell hybrid UAV, and g represents the gravitational acceleration;

[0034] Obtain the force value corresponding to each propeller disc on the hydrogen fuel cell hybrid UAV respectively;

[0035] When the force values ​​corresponding to each of the paddle discs are the same, it is determined that the hydrogen fuel cell hybrid UAV is in a normal flight state;

[0036] When the hydrogen fuel cell hybrid UAV is in a normal flight state, the theoretical speed of the hydrogen fuel cell hybrid UAV is calculated according to formula (7);

[0037]

[0038] Among them, S T represents the calculation of the real-time speed of the hydrogen fuel cell hybrid UAV, A p represents the horizontal projection area of ​​the hydrogen fuel cell hybrid UAV, γ represents the tilt angle of the hydrogen fuel cell hybrid UAV, v in represents the theoretical induced velocity;

[0039] The actual speed of the hydrogen fuel cell hybrid UAV is obtained, and the actual speed is substituted into the formula (7) to obtain the actual induced speed of the hydrogen fuel cell hybrid UAV.

[0040] In one practicable manner,

[0041] The process of building the hydrogen fuel cell model and the lithium battery model of the hydrogen fuel cell hybrid UAV includes:

[0042] The hydrogen fuel consumption per unit time of the hydrogen fuel cell hybrid UAV is calculated according to formula (8);

[0043]

[0044] in, represents the hydrogen fuel consumption per unit time of the hydrogen fuel cell hybrid UAV, P fc Indicates the output power of hydrogen fuel cells;

[0045] Establishing a hydrogen fuel cell model of the hydrogen fuel cell hybrid UAV according to the hydrogen fuel consumption;

[0046] The discharge cycle output power of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (9), the output current of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (10), and the state of charge of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (11);

[0047]

[0048] Among them, V OC represents the open circuit voltage, R0 represents the internal resistance, I b Indicates the output current, P batt Indicates the output power during the charge and discharge cycle, SOC t Indicates the state of charge, Q0 indicates the initial battery capacity, and Q indicates the rated battery capacity;

[0049] The lithium battery model of the hydrogen fuel cell hybrid UAV is established according to the calculation results of formulas (9), (10) and (11).

[0050] In one practicable manner,

[0051] The process of constructing the power consumption state space and power supply allocation space of the hydrogen fuel cell hybrid UAV includes:

[0052] The load demand power model is used to determine the load demand power P of the hydrogen fuel cell hybrid UAV at the current moment. t ;

[0053] The hydrogen fuel cell model is used to determine the remaining amount of hydrogen in the hydrogen fuel cell hybrid UAV at the current moment.

[0054] The remaining power SOC of the hydrogen fuel cell hybrid UAV at the current moment is determined by using the lithium battery model. t ;

[0055] According to the load demand power P of the hydrogen fuel cell hybrid UAV at the current moment t 、Remaining amount of hydrogen Remaining power SOC tEstablishing a power energy consumption state space of the hydrogen fuel cell hybrid UAV;

[0056] Determine the hydrogen fuel cell output power of the hydrogen fuel cell hybrid UAV according to the hydrogen fuel cell model, and set the hydrogen fuel cell output power within a preset continuous interval [P fc_min ,P fc_max ] is discretized to obtain the power set;

[0057] Among them, P fc_min Indicates the preset minimum hydrogen fuel cell output power, P fc_max Indicates the preset maximum hydrogen fuel cell output power;

[0058] The distribution characteristics of hydrogen fuel in the power set are analyzed to establish a power distribution space for the hydrogen fuel cell hybrid UAV.

[0059] In one practicable manner,

[0060] The process of constructing the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV includes:

[0061] Calculate the flight reward function of the hydrogen fuel cell hybrid UAV according to formula (12);

[0062]

[0063] Wherein, F represents the flight reward function of the hydrogen fuel cell hybrid UAV, a1 and a2 represent reward weights, a3 and a4 represent penalty weights, Indicates the maximum hydrogen consumption, SOC ref Indicates the current remaining power, and SOC indicates the initial power;

[0064] Calculate the power supply constraint of the hydrogen fuel cell hybrid UAV according to formula (13);

[0065]

[0066] Among them, P load represents the load power requirement of the hydrogen fuel cell hybrid UAV, P fc represents the hydrogen fuel cell output power of the hydrogen fuel cell hybrid UAV, P batt represents the lithium battery output power of the hydrogen fuel cell hybrid UAV, P fc_max , P fc_min represent the maximum output power of the hydrogen fuel cell of the hydrogen fuel cell hybrid UAV and the minimum output power of the hydrogen fuel cell of the hydrogen fuel cell hybrid UAV, P batt_max , Pbatt_min They respectively represent the maximum power of the lithium battery of the hydrogen fuel cell hybrid UAV and the minimum power of the lithium battery of the hydrogen fuel cell hybrid UAV.

[0067] In one practicable manner,

[0068] The process of running the training agent to obtain the optimal strategy presented when the hydrogen fuel cell hybrid UAV converges to the flight reward function and displaying the strategy comprises:

[0069] Running the training agent and inputting the running data into (14) calculating the corresponding flight characteristics of the hydrogen fuel cell hybrid UAV when performing the flight action;

[0070]

[0071] Among them, z represents the actor network weight, φ represents the commentator network weight, λ represents the smoothing coefficient, γ represents the discount factor, V(;φ) represents the state value function, and ts represents the start time of the round;

[0072] Analyzing the flight energy consumption of the hydrogen fuel cell hybrid UAV under each of the flight characteristics using the flight reward function;

[0073] The flight energy consumption is optimized, and the optimal strategy of the hydrogen fuel cell hybrid UAV is generated and displayed.

[0074] The present invention provides a hydrogen fuel cell hybrid power UAV energy adaptive optimization method, comprising:

[0075] Step 1: Basic equipment parameters of hydrogen fuel cell hybrid UAV: ​​Build the load demand power model, hydrogen fuel cell model and lithium battery model of the hydrogen fuel cell hybrid UAV;

[0076] Step 2: Based on the load demand power model, the hydrogen fuel cell model and the lithium battery model, the power energy consumption state space and the power supply allocation space of the hydrogen fuel cell hybrid UAV are constructed, as well as the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV are constructed;

[0077] Step 3: constructing the actor neural network and the commentator neural network of the hydrogen fuel cell hybrid UAV by using the preset PPO algorithm and the basic equipment parameters, respectively optimizing the power energy consumption state space and the power supply allocation space by using the actor neural network to obtain a number of optimization conditions, and respectively performing feedback analysis on the optimization conditions according to the flight reward function and the power supply constraint by using the commentator neural network to obtain a number of hyperparameters;

[0078] Step 4: Construct an energy management agent according to the hyperparameters, map the load demand power model, the hydrogen fuel cell model and the lithium battery model into the energy management agent respectively to generate a training agent for the hydrogen fuel cell hybrid UAV, run the training agent to obtain the optimal strategy presented by the hydrogen fuel cell hybrid UAV when it converges to the flight reward function and display it.

[0079] The achievable beneficial effects of the above technical solution are as follows: (1) The proximal strategy optimization algorithm can continuously learn and adapt to changes in the flight environment, such as natural factors such as wind speed, temperature, and air pressure, as well as internal factors such as load changes and battery status. This adaptive capability enables the drone to maintain an efficient and stable flight state under complex and changeable flight conditions, reducing energy waste and unnecessary flight risks.

[0080] (2) Through the proximal strategy optimization algorithm, a variety of uncertain factors in the flight process can be responded to in real time, and energy can be adaptively and intelligently optimally allocated to ensure that hydrogen fuel cells and lithium batteries work together in the best state, thereby maximizing the flight time and mission range of the UAV.

[0081] (3) This patent applies deep reinforcement learning technology to the energy management system of drones, achieving a leap from data-driven to intelligent decision-making. Drones can autonomously adjust energy allocation strategies based on their own status and external environment without human intervention or preset rules, thereby improving the intelligence level and autonomous decision-making ability of drones.

[0082] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0083] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0085] Figure 1 It is the load demand power curve without considering uncertain factors under fixed flight mission;

[0086] Figure 2 The power curve of the UAV load requirement considering uncertain factors under a fixed flight mission;

[0087] Figure 3 This is the training flow chart of the PPO algorithm;

[0088] Figure 4 Hardware implementation diagram for energy management of UAV;

[0089] Figure 5 Energy distribution curve for the test case;

[0090] Figure 6 The SOC curve of the lithium battery for the test case;

[0091] Figure 7 The hydrogen consumption curve of the hydrogen fuel cell for the test case;

[0092] Figure 8 It is a schematic diagram of the composition of the present invention. DETAILED DESCRIPTION

[0093] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0094] Example 1

[0095] This embodiment provides a hydrogen fuel cell hybrid UAV energy adaptive optimization system, such as Figure 8 As shown, including:

[0096] A partial modeling module, used to build a load demand power model, a hydrogen fuel cell model and a lithium battery model of the hydrogen fuel cell hybrid UAV according to the basic equipment parameters of the hydrogen fuel cell hybrid UAV;

[0097] A model analysis module, used to build the power energy consumption state space and power supply allocation space of the hydrogen fuel cell hybrid UAV based on the load demand power model, the hydrogen fuel cell model and the lithium battery model, as well as to build the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV;

[0098] An algorithm optimization module, used to construct an actor neural network and a commentator neural network of the hydrogen fuel cell hybrid UAV using a preset PPO algorithm and the basic equipment parameters, and to optimize the power consumption state space and the power supply allocation space using the actor neural network to obtain a plurality of optimization conditions, and to perform feedback analysis on the optimization conditions according to the flight reward function and the power supply constraint conditions using the commentator neural network to obtain a plurality of hyperparameters;

[0099] The optimization training module is used to construct an energy management agent according to the hyperparameters, map the load demand power model, the hydrogen fuel cell model and the lithium battery model into the energy management agent respectively to generate a training agent for the hydrogen fuel cell hybrid UAV, and run the training agent to obtain the optimal strategy presented by the hydrogen fuel cell hybrid UAV when it converges to the flight reward function and display it.

[0100] In this example, the hyperparameters include sampling time, discount factor, number of steps to calculate the advantage function, neural network learning rates of actors and critics, gradient threshold, etc.

[0101] In this example, the preset PPO algorithm represents a reinforcement learning algorithm.

[0102] The working principle and beneficial effects of the above technical solution: In order to solve the problems in traditional technology, when the hydrogen fuel cell hybrid UAV is flying, the corresponding load demand power model, hydrogen fuel cell model and lithium battery model are built, and then the corresponding power energy consumption state space and power supply power distribution space are further built, so that the power consumption of the hydrogen fuel cell hybrid UAV during the flight can be more clearly seen. In order to make the system adapt to more different types of hydrogen fuel cell hybrid UAVs, a unique flight reward function and power supply constraint conditions for the hydrogen fuel cell hybrid UAV are built, and then the actor neural network and the commentator neural network are used to optimize the strategy and feedback processing of the power energy consumption state space and the power supply power distribution space, generate the corresponding hyperparameters, and finally use the hyperparameters to construct a training agent, and analyze the optimal strategy of the hydrogen fuel cell hybrid UAV by running the training agent, so as to realize the adaptive intelligent optimal allocation of hydrogen energy and electric energy by the hydrogen fuel cell hybrid UAV energy management system.

[0103] Example 2

[0104] Based on Example 1, the process of establishing the load demand power model, the hydrogen fuel cell model and the lithium battery model is as follows:

[0105] The process of building the load demand power model of the hydrogen fuel cell hybrid UAV includes:

[0106] The induced power of the hydrogen fuel cell hybrid UAV is calculated according to formula (1);

[0107] P ik =T d ·v ik (1)

[0108] Among them, P ik represents the induced power of the hydrogen fuel cell hybrid UAV, v ikrepresents the actual induced speed of the hydrogen fuel cell hybrid UAV;

[0109] The drag power (indicating the power required to overcome the viscous resistance of the rotor when rotating in the air) of the hydrogen fuel cell hybrid UAV is calculated according to formula (2);

[0110]

[0111] Among them, P pr represents the drag power of the hydrogen fuel cell hybrid UAV, As represents the UAV blade section area, ω represents the blade rotation angular velocity, R represents the turntable radius, and δ represents the profile tension coefficient;

[0112] The waste power of the hydrogen fuel cell hybrid UAV is calculated according to formula (3);

[0113]

[0114] Among them, P pa represents the waste resistance power of the hydrogen fuel cell hybrid UAV;

[0115] The interfered power of the hydrogen fuel cell hybrid UAV is calculated according to formula (4);

[0116] It is used to quantitatively characterize other disturbance factors that the drone may encounter during the flight mission. These disturbance factors may include but are not limited to changes in ambient temperature, fluctuations in air density, micro-mechanical vibrations of the drone itself, and the effects caused by changes in the external magnetic field;

[0117] P dis (t)~N(0,1)×c,P dis_min <P dis (t) <P dis_max (4)

[0118] Wherein, c represents the disturbance amplitude coefficient of the hydrogen fuel cell hybrid UAV;

[0119] According to formula (5), the corresponding load mass of the hydrogen fuel cell hybrid UAV at different flight times is calculated;

[0120] The total mass of the payload is not constant. As the drone consumes hydrogen continuously during flight, the total mass of the drone will continue to decrease.

[0121]

[0122] Where m(t) represents the total weight of the hydrogen fuel cell hybrid UAV at time t, represents the consumption of hydrogen, M represents the molar mass of hydrogen, P represents the working pressure of the hydrogen fuel cell stack, R represents the Avogadro constant, and T represents the working thermodynamic temperature of the stack;

[0123] According to the calculation result of formula (5), the corresponding load mass of the hydrogen fuel cell hybrid UAV at different flight times is determined, and a load demand power model of the fuel cell hybrid UAV is constructed;

[0124] The hydrogen fuel consumption per unit time of the hydrogen fuel cell hybrid UAV is calculated according to formula (8);

[0125]

[0126] in, represents the hydrogen fuel consumption per unit time of the hydrogen fuel cell hybrid UAV, P fc Indicates the output power of hydrogen fuel cells;

[0127] Establishing a hydrogen fuel cell model of the hydrogen fuel cell hybrid UAV according to the hydrogen fuel consumption;

[0128] The discharge cycle output power of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (9), the output current of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (10), and the state of charge of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (11);

[0129]

[0130] Among them, V OC represents the open circuit voltage, R0 represents the internal resistance, I b Indicates the output current, P batt Indicates the output power during the charge and discharge cycle, SOC t Indicates the state of charge, Q0 indicates the initial battery capacity, and Q indicates the rated battery capacity;

[0131] The lithium battery model of the hydrogen fuel cell hybrid UAV is established according to the calculation results of formulas (9), (10) and (11).

[0132] The working principle and beneficial effects of the above technical solution are as follows: By building multiple models to express the conditions of various parts of the hydrogen fuel cell hybrid UAV, the amount of calculation can be reduced and various data can be obtained intuitively.

[0133] Example 3

[0134] Based on Example 2, the process of determining the actual induced speed of the hydrogen fuel cell hybrid UAV is as follows:

[0135] Calculate the pulling force required by the hydrogen fuel cell hybrid UAV during flight according to formula (6);

[0136]

[0137] Among them, T d represents the pulling force required by the hydrogen fuel cell hybrid UAV during flight, a c represents the acceleration of the hydrogen fuel cell hybrid UAV, v represents the airspeed of the hydrogen fuel cell hybrid UAV, and v f represents the air velocity, β represents the angle between the air velocity direction and the flight direction of the hydrogen fuel cell hybrid UAV, θ represents the angle between the flight direction of the hydrogen fuel cell hybrid UAV and the vertical direction, ρ represents the air density, A f represents the vertical projection area of ​​the hydrogen fuel cell hybrid UAV, m represents the total mass of the hydrogen fuel cell hybrid UAV (including the fixed weight of the UAV fuselage, lithium battery, hydrogen fuel cell, hydrogen storage bottle, etc. and the weight of hydrogen), and g represents the acceleration due to gravity;

[0138] (The drone adopts a quad-rotor configuration);

[0139] Obtain the force value corresponding to each propeller disc on the hydrogen fuel cell hybrid UAV respectively;

[0140] When the force values ​​corresponding to each of the paddle discs are the same, it is determined that the hydrogen fuel cell hybrid UAV is in a normal flight state;

[0141] When the hydrogen fuel cell hybrid UAV is in a normal flight state, the theoretical speed of the hydrogen fuel cell hybrid UAV is calculated according to formula (7);

[0142]

[0143] Among them, S T represents the calculation of the real-time speed of the hydrogen fuel cell hybrid UAV, A p represents the horizontal projection area of ​​the hydrogen fuel cell hybrid UAV, γ represents the tilt angle of the hydrogen fuel cell hybrid UAV, v in represents the theoretical induced velocity;

[0144] The actual speed of the hydrogen fuel cell hybrid UAV is obtained, and the actual speed is substituted into the formula (7) to obtain the actual induced speed of the hydrogen fuel cell hybrid UAV.

[0145] The working principle and beneficial effects of the above technical solution are as follows: using the pulling force to derive the induced speed can reduce the amount of normal calculations, improve the calculation efficiency of the induced power, and improve the optimization efficiency.

[0146] Example 4

[0147] On the basis of Example 1, the process of constructing the power energy consumption state space and the power supply power allocation space of the hydrogen fuel cell hybrid UAV includes:

[0148] The load demand power model is used to determine the load demand power P of the hydrogen fuel cell hybrid UAV at the current moment. t ;

[0149] The hydrogen fuel cell model is used to determine the remaining amount of hydrogen in the hydrogen fuel cell hybrid UAV at the current moment.

[0150] The remaining power SOC of the hydrogen fuel cell hybrid UAV at the current moment is determined by using the lithium battery model. t ;

[0151] According to the load demand power P of the hydrogen fuel cell hybrid UAV at the current moment t 、Remaining amount of hydrogen Remaining power SOC t Establishing a power energy consumption state space of the hydrogen fuel cell hybrid UAV;

[0152] Determine the hydrogen fuel cell output power of the hydrogen fuel cell hybrid UAV according to the hydrogen fuel cell model, and set the hydrogen fuel cell output power within a preset continuous interval [P fc_min ,P fc_max ] is discretized to obtain the power set;

[0153] Among them, P fc_min Indicates the preset minimum hydrogen fuel cell output power, P fc_max Indicates the preset maximum hydrogen fuel cell output power;

[0154] The distribution characteristics of hydrogen fuel in the power set are analyzed to establish a power distribution space for the hydrogen fuel cell hybrid UAV.

[0155] The working principle and beneficial effects of the above technical solution: by constructing the power consumption state space and the power supply allocation space, the flight operation of the UAV can be further analyzed in detail, thereby improving the accuracy of optimization.

[0156] Example 5

[0157] On the basis of Example 1, the process of constructing the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV includes:

[0158] Calculate the flight reward function of the hydrogen fuel cell hybrid UAV according to formula (12);

[0159]

[0160] Wherein, F represents the flight reward function of the hydrogen fuel cell hybrid UAV, a1 and a2 represent reward weights, and a3 and a4 represent penalty weights. Indicates the maximum hydrogen consumption, SOC ref Indicates the current remaining power, and SOC indicates the initial power;

[0161] Calculate the power supply constraint of the hydrogen fuel cell hybrid UAV according to formula (13);

[0162]

[0163] Among them, P load represents the load power requirement of the hydrogen fuel cell hybrid UAV, P fc represents the hydrogen fuel cell output power of the hydrogen fuel cell hybrid UAV, P batt represents the lithium battery output power of the hydrogen fuel cell hybrid UAV, P fc_max , P fc_min represent the maximum output power of the hydrogen fuel cell of the hydrogen fuel cell hybrid UAV and the minimum output power of the hydrogen fuel cell of the hydrogen fuel cell hybrid UAV, P batt_max , P batt_min They respectively represent the maximum power of the lithium battery of the hydrogen fuel cell hybrid UAV and the minimum power of the lithium battery of the hydrogen fuel cell hybrid UAV.

[0164] The working principle and beneficial effects of the above technical solution: Since different UAVs have different characteristics, the unique flight conditions of the UAV can be determined by analyzing the flight reward function and power supply constraints of the hydrogen fuel cell hybrid UAV, which facilitates subsequent optimization work.

[0165] Example 6

[0166] On the basis of Example 1, the process of running the training agent to obtain the optimal strategy presented when the hydrogen fuel cell hybrid UAV converges to the flight reward function and displaying it includes:

[0167] Running the training agent and inputting the running data into (14) calculating the corresponding flight characteristics of the hydrogen fuel cell hybrid UAV when performing the flight action;

[0168]

[0169] Among them, z represents the actor network weight, φ represents the commentator network weight, λ represents the smoothing coefficient, γ represents the discount factor, V(;φ) represents the state value function, and ts represents the start time of the round;

[0170] Analyzing the flight energy consumption of the hydrogen fuel cell hybrid UAV under each of the flight characteristics using the flight reward function;

[0171] The flight energy consumption is optimized, and the optimal strategy of the hydrogen fuel cell hybrid UAV is generated and displayed.

[0172] The working principle and beneficial effects of the above technical solution are: improving the overall performance and reliability of the UAV.

[0173] Example 7

[0174] This embodiment provides a hydrogen fuel cell hybrid UAV energy adaptive optimization method, which is characterized by comprising:

[0175] Step 1: Basic equipment parameters of hydrogen fuel cell hybrid UAV: ​​Build the load demand power model, hydrogen fuel cell model and lithium battery model of the hydrogen fuel cell hybrid UAV;

[0176] Step 2: Based on the load demand power model, the hydrogen fuel cell model and the lithium battery model, the power energy consumption state space and the power supply allocation space of the hydrogen fuel cell hybrid UAV are constructed, as well as the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV are constructed;

[0177] Step 3: constructing the actor neural network and the commentator neural network of the hydrogen fuel cell hybrid UAV by using the preset PPO algorithm and the basic equipment parameters, respectively optimizing the power energy consumption state space and the power supply allocation space by using the actor neural network to obtain a number of optimization conditions, and respectively performing feedback analysis on the optimization conditions according to the flight reward function and the power supply constraint by using the commentator neural network to obtain a number of hyperparameters;

[0178] Step 4: Construct an energy management agent according to the hyperparameters, map the load demand power model, the hydrogen fuel cell model and the lithium battery model into the energy management agent respectively to generate a training agent for the hydrogen fuel cell hybrid UAV, run the training agent to obtain the optimal strategy presented by the hydrogen fuel cell hybrid UAV when it converges to the flight reward function and display it.

[0179] In this example, the hyperparameters include sampling time, discount factor, number of steps to calculate the advantage function, neural network learning rates of actors and critics, gradient threshold, etc.

[0180] In this example, the preset PPO algorithm represents a reinforcement learning algorithm.

[0181] The working principle and beneficial effects of the above technical solution: In order to solve the problems in traditional technology, when the hydrogen fuel cell hybrid UAV is flying, the corresponding load demand power model, hydrogen fuel cell model and lithium battery model are built, and then the corresponding power energy consumption state space and power supply power distribution space are further built, so that the power consumption of the hydrogen fuel cell hybrid UAV during the flight can be more clearly seen. In order to make the system adapt to more different types of hydrogen fuel cell hybrid UAVs, a unique flight reward function and power supply constraint conditions for the hydrogen fuel cell hybrid UAV are built, and then the actor neural network and the commentator neural network are used to optimize the strategy and feedback processing of the power energy consumption state space and the power supply power distribution space, generate the corresponding hyperparameters, and finally use the hyperparameters to construct a training agent, and analyze the optimal strategy of the hydrogen fuel cell hybrid UAV by running the training agent, so as to realize the adaptive intelligent optimal allocation of hydrogen energy and electric energy by the hydrogen fuel cell hybrid UAV energy management system.

[0182] This method uses the PPO algorithm to train the energy management agent. The training process is as follows: ① Initialize the weights of the actor network and the commentator network, and the experience return pool. ② Start training. The energy management system will continuously interact with the hydrogen fuel cell hybrid drone and collect the trajectory data {s(t), a(t), r(t+1), s(t+1), log p(a t |s t )} is stored in the experience replay pool. ③ When the experience replay pool is full of data, the energy management agent stops interacting with the hydrogen fuel cell hybrid drone and takes data from the experience replay pool instead. It uses the commentator network to estimate the state value, uses formula xx to calculate the advantage function of the state action pair to update the weight of the policy network, and uses formula xx to calculate the loss function to update the weight of the commentator network. This is repeated a certain number of times. ④ After the update is complete, the experience replay pool is cleared and steps 2, 3, and 4 are repeated.

[0183] The following is an explanation based on specific cases:

[0184] In order to fully simulate the power consumption characteristics of the UAV when performing a typical flight mission, the UAV flight mission shown in Table 1 is set. According to the UAV load demand power model, the power demand curve is obtained, as shown in Figure 1 , Figure 2 shown.

[0185] Table 1 Description of UAV flight missions

[0186]

[0187] The agent is trained based on the simulink platform, and the relevant algorithm parameter settings are shown in Table 2. After a certain round of training, the agent is saved after convergence. A new load curve is randomly generated as the input of the agent to test the generalization ability of the agent. The test results are shown in Figure 5 , Figure 6 , Figure 7 shown.

[0188] Table 2 PPO training parameter settings

[0189]

[0190] As can be seen from the result graph, the fuel cell provides a large amount of power during the takeoff phase to meet the high load demand; during the cruise phase, the fuel cell power continues to remain at a high level to maintain flight, and hydrogen is consumed steadily throughout the entire flight profile. The lithium battery power rises rapidly at the beginning of the flight, providing auxiliary power to support the fuel cell; then the lithium battery power fluctuates at a lower level, balancing the load demand and the output of the fuel cell; in the middle and late stages of the flight, the lithium battery power gradually decreases and tends to be negative, and the fuel cell charges the battery. The SOC remains near the reference value of 0.8 throughout the flight, indicating that the energy management strategy effectively protects the lithium battery, avoids over-discharge and over-charging, and helps to extend battery life.

[0191] The corresponding energy management system topology in this example is as follows Figure 4As shown. The system mainly includes an energy management system, a drone, a proton exchange membrane fuel cell (PEMFC) and a lithium battery. In the entire system, the proton exchange membrane fuel cell provides the main flight power and is connected to the DC bus load through a unidirectional DC / DC converter. In order to meet the load power requirements under rapid changes in working conditions, a lithium battery is used as an auxiliary energy storage device and is connected to the DC bus through a bidirectional DC / DC converter. As the core control unit, the energy management system is responsible for the energy management and control strategy execution of the entire system. It receives reference signals (SOC, SH2, P t ), and generate the energy output (P FC , P Batt ), the power control module according to P FC , P Batt Calculate the switching frequency (Feq) input to the LM5118 and TPS40210 FC 、Feq Batt ) and duty cycle (D FC , D Batt ), thereby controlling the power output of PEMFC and lithium batteries and completing the intelligent allocation of the UAV energy system.

[0192] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. Hydrogen fuel cell hybrid UAV energy adaptive optimization system, characterized by: include: A partial modeling module, used to build a load demand power model, a hydrogen fuel cell model and a lithium battery model of the hydrogen fuel cell hybrid UAV according to the basic equipment parameters of the hydrogen fuel cell hybrid UAV; A model analysis module, used to build the power energy consumption state space and power supply allocation space of the hydrogen fuel cell hybrid UAV based on the load demand power model, the hydrogen fuel cell model and the lithium battery model, as well as to build the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV; An algorithm optimization module, used to construct an actor neural network and a commentator neural network of the hydrogen fuel cell hybrid UAV using a preset PPO algorithm and the basic equipment parameters, and to optimize the power consumption state space and the power supply allocation space using the actor neural network to obtain a plurality of optimization conditions, and to perform feedback analysis on the optimization conditions according to the flight reward function and the power supply constraint conditions using the commentator neural network to obtain a plurality of hyperparameters; The optimization training module is used to construct an energy management agent according to the hyperparameters, map the load demand power model, the hydrogen fuel cell model and the lithium battery model into the energy management agent respectively to generate a training agent for the hydrogen fuel cell hybrid UAV, and run the training agent to obtain the optimal strategy presented by the hydrogen fuel cell hybrid UAV when it converges to the flight reward function and display it.

2. The hydrogen fuel cell hybrid UAV energy adaptive optimization system according to claim 1, characterized in that: The process of building the load demand power model of the hydrogen fuel cell hybrid UAV includes: The induced power of the hydrogen fuel cell hybrid UAV is calculated according to formula (1); P ik =T d ·v ik (1) Among them, P ik represents the induced power of the hydrogen fuel cell hybrid UAV, v ik represents the actual induced speed of the hydrogen fuel cell hybrid UAV; The drag power of the hydrogen fuel cell hybrid UAV is calculated according to formula (2); Among them, P pr represents the drag power of the hydrogen fuel cell hybrid UAV, As represents the UAV blade section area, ω represents the blade rotation angular velocity, R represents the turntable radius, and δ represents the profile tension coefficient; The waste power of the hydrogen fuel cell hybrid UAV is calculated according to formula (3); Among them, P pa represents the waste resistance power of the hydrogen fuel cell hybrid UAV; The interfered power of the hydrogen fuel cell hybrid UAV is calculated according to formula (4); P dis (t)~N(0,1)×c,P dis_min <P dis (t)<P dis_max (4) Wherein, c represents the disturbance amplitude coefficient of the hydrogen fuel cell hybrid UAV; According to formula (5), the corresponding load mass of the hydrogen fuel cell hybrid UAV at different flight times is calculated; Where m(t) represents the total weight of the hydrogen fuel cell hybrid UAV at time t, represents the consumption of hydrogen, M represents the molar mass of hydrogen, P represents the working pressure of the hydrogen fuel cell stack, R represents the Avogadro constant, and T represents the working thermodynamic temperature of the stack; According to the calculation result of formula (5), the corresponding load mass of the hydrogen fuel cell hybrid UAV at different flight times is determined, and the load demand power model of the fuel cell hybrid UAV is established.

3. The hydrogen fuel cell hybrid UAV energy adaptive optimization system according to claim 2, characterized in that: Also includes: Calculate the pulling force required by the hydrogen fuel cell hybrid UAV during flight according to formula (6); Among them, T d represents the pulling force required by the hydrogen fuel cell hybrid UAV during flight, a c represents the acceleration of the hydrogen fuel cell hybrid UAV, v represents the airspeed of the hydrogen fuel cell hybrid UAV, and v f represents the air velocity, β represents the angle between the air velocity direction and the flight direction of the hydrogen fuel cell hybrid UAV, θ represents the angle between the flight direction of the hydrogen fuel cell hybrid UAV and the vertical direction, ρ represents the air density, A f represents the vertical projection area of ​​the hydrogen fuel cell hybrid UAV, m represents the total mass of the hydrogen fuel cell hybrid UAV, and g represents the acceleration of gravity; Obtain the force value corresponding to each propeller disc on the hydrogen fuel cell hybrid UAV respectively; When the force values ​​corresponding to each of the paddle discs are the same, it is determined that the hydrogen fuel cell hybrid UAV is in a normal flight state; When the hydrogen fuel cell hybrid UAV is in a normal flight state, the theoretical speed of the hydrogen fuel cell hybrid UAV is calculated according to formula (7); Among them, S T represents the calculation of the real-time speed of the hydrogen fuel cell hybrid UAV, A p represents the horizontal projection area of ​​the hydrogen fuel cell hybrid UAV, γ represents the tilt angle of the hydrogen fuel cell hybrid UAV, v in represents the theoretical induced velocity; The actual speed of the hydrogen fuel cell hybrid UAV is obtained, and the actual speed is substituted into the formula (7) to obtain the actual induced speed of the hydrogen fuel cell hybrid UAV.

4. The hydrogen fuel cell hybrid UAV energy adaptive optimization system according to claim 1, characterized in that: The process of building the hydrogen fuel cell model and the lithium battery model of the hydrogen fuel cell hybrid UAV includes: The hydrogen fuel consumption per unit time of the hydrogen fuel cell hybrid UAV is calculated according to formula (8); in, represents the hydrogen fuel consumption per unit time of the hydrogen fuel cell hybrid UAV, P fc Indicates the output power of hydrogen fuel cells; Establishing a hydrogen fuel cell model of the hydrogen fuel cell hybrid UAV according to the hydrogen fuel consumption; The discharge cycle output power of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (9), the output current of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (10), and the state of charge of the lithium battery of the hydrogen fuel cell hybrid UAV is calculated according to formula (11); Among them, V OC represents the open circuit voltage, R0 represents the internal resistance, I b Indicates the output current, P batt Indicates the output power during the charge and discharge cycle, SOC t Indicates the state of charge, Q0 indicates the initial battery capacity, and Q indicates the rated battery capacity; The lithium battery model of the hydrogen fuel cell hybrid UAV is established according to the calculation results of formulas (9), (10) and (11).

5. The hydrogen fuel cell hybrid UAV energy adaptive optimization system according to claim 1, characterized in that: The process of constructing the power consumption state space and power supply allocation space of the hydrogen fuel cell hybrid UAV includes: The load demand power model is used to determine the load demand power P of the hydrogen fuel cell hybrid UAV at the current moment. t ; The hydrogen fuel cell model is used to determine the remaining amount of hydrogen in the hydrogen fuel cell hybrid UAV at the current moment. The remaining power SOC of the hydrogen fuel cell hybrid UAV at the current moment is determined by using the lithium battery model. t ; According to the load demand power P of the hydrogen fuel cell hybrid UAV at the current moment t 、Remaining amount of hydrogen Remaining power SOC t Establishing a power energy consumption state space of the hydrogen fuel cell hybrid UAV; Determine the hydrogen fuel cell output power of the hydrogen fuel cell hybrid UAV according to the hydrogen fuel cell model, and set the hydrogen fuel cell output power within a preset continuous interval [P fc_min ,P fc_max ] is discretized to obtain the power set; Among them, P fc_min Indicates the preset minimum hydrogen fuel cell output power, P fc_max Indicates the preset maximum hydrogen fuel cell output power; The distribution characteristics of hydrogen fuel in the power set are analyzed to establish a power distribution space for the hydrogen fuel cell hybrid UAV.

6. The hydrogen fuel cell hybrid UAV energy adaptive optimization system according to claim 1, characterized in that: The process of constructing the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV includes: Calculate the flight reward function of the hydrogen fuel cell hybrid UAV according to formula (12); Wherein, F represents the flight reward function of the hydrogen fuel cell hybrid UAV, a1 and a2 represent reward weights, a3 and a4 represent penalty weights, Indicates the maximum hydrogen consumption, SOC ref Indicates the current remaining power, and SOC indicates the initial power; Calculate the power supply constraint of the hydrogen fuel cell hybrid UAV according to formula (13); Among them, P load represents the load power requirement of the hydrogen fuel cell hybrid UAV, P fc represents the hydrogen fuel cell output power of the hydrogen fuel cell hybrid UAV, P batt represents the lithium battery output power of the hydrogen fuel cell hybrid UAV, P fc_max , P fc_min represent the maximum output power of the hydrogen fuel cell of the hydrogen fuel cell hybrid UAV and the minimum output power of the hydrogen fuel cell of the hydrogen fuel cell hybrid UAV, P batt_max , P batt_min They respectively represent the maximum power of the lithium battery of the hydrogen fuel cell hybrid UAV and the minimum power of the lithium battery of the hydrogen fuel cell hybrid UAV.

7. The hydrogen fuel cell hybrid UAV energy adaptive optimization system according to claim 1, characterized in that: The process of running the training agent to obtain the optimal strategy presented when the hydrogen fuel cell hybrid UAV converges to the flight reward function and displaying the strategy comprises: Running the training agent and inputting the running data into (14) calculating the corresponding flight characteristics of the hydrogen fuel cell hybrid UAV when performing the flight action; Among them, z represents the actor network weight, φ represents the commentator network weight, λ represents the smoothing coefficient, γ represents the discount factor, V(;φ) represents the state value function, and ts represents the start time of the round; Analyzing the flight energy consumption of the hydrogen fuel cell hybrid UAV under each of the flight characteristics using the flight reward function; The flight energy consumption is optimized, and the optimal strategy of the hydrogen fuel cell hybrid UAV is generated and displayed.

8. The hydrogen fuel cell hybrid UAV energy adaptive optimization method according to claim 1, characterized in that: include: Step 1: Basic equipment parameters of hydrogen fuel cell hybrid UAV: ​​Build the load demand power model, hydrogen fuel cell model and lithium battery model of the hydrogen fuel cell hybrid UAV; Step 2: Based on the load demand power model, the hydrogen fuel cell model and the lithium battery model, the power energy consumption state space and the power supply allocation space of the hydrogen fuel cell hybrid UAV are constructed, as well as the flight reward function and power supply constraint conditions of the hydrogen fuel cell hybrid UAV are constructed; Step 3: constructing the actor neural network and the commentator neural network of the hydrogen fuel cell hybrid UAV by using the preset PPO algorithm and the basic equipment parameters, respectively optimizing the power energy consumption state space and the power supply allocation space by using the actor neural network to obtain a number of optimization conditions, and respectively performing feedback analysis on the optimization conditions according to the flight reward function and the power supply constraint by using the commentator neural network to obtain a number of hyperparameters; Step 4: Construct an energy management agent according to the hyperparameters, map the load demand power model, the hydrogen fuel cell model and the lithium battery model into the energy management agent respectively to generate a training agent for the hydrogen fuel cell hybrid UAV, run the training agent to obtain the optimal strategy presented by the hydrogen fuel cell hybrid UAV when it converges to the flight reward function and display it.

Images