Energy management method and device of unmanned aerial vehicle

Abstract

The invention provides an energy management method and device of an unmanned aerial vehicle, which can be used for the unmanned aerial vehicle capable of autonomous flight and can significantly improve the energy utilization efficiency of the unmanned aerial vehicle capable of autonomous flight, and the unmanned aerial vehicle can perform autonomous flight. The unmanned aerial vehicle flight power demand table comprises load powers required by the unmanned aerial vehicle for executing different flight actions at various speeds of the unmanned aerial vehicle; according to the flight task, performing flight path planning; according to the optimal flight path obtained by planning, querying an unmanned aerial vehicle flight power demand table, obtaining load power required by different flight stages in the flight path, and further obtaining global load power change of the unmanned aerial vehicle completing a flight task; a global load power change is derived based on the path planning, and the fuel cells and the power output of the cells are optimized to meet load power consumption and minimize hydrogen consumption of the fuel cells.

Description

Technical Field

[0001] The present invention relates to the field of energy management of fuel cell hybrid power systems of unmanned aerial vehicles, and in particular to an energy management method and device for unmanned aerial vehicles. Background Art

[0002] In the current industry, drones are mainly powered by batteries. However, as the demand for drones' endurance increases and the demand for special applications increases, hydrogen fuel cells can provide drones with long-lasting green energy as the main energy source. Hydrogen fuel cells are more suitable for outputting relatively stable energy and cannot absorb energy. Therefore, they will form a hybrid energy management system with batteries and serve as the energy source for drones.

[0003] Reasonable energy management, that is, the load change caused by the change of flight instructions of the drone is provided by the fuel cell or battery respectively, which can effectively reduce the hydrogen consumption of the fuel cell. Since the amount of hydrogen in the hydrogen cylinder carried by the drone is limited, reducing hydrogen consumption can effectively improve the endurance of the drone. The energy management of the hybrid system can be roughly divided into offline energy management and online energy management. Offline energy management is that the energy management system knows the entire path or load changes in advance, so that it can perform global energy management optimization and achieve the optimization goal, mainly hydrogen consumption, to obtain the output power of the fuel cell and battery with the optimal energy distribution. In the actual system operation or the flight of the drone, the entire load change cannot be obtained in advance, so it is impossible to achieve global optimization. It can only be designed in real time according to the current load demand and the previous load changes to achieve power distribution. In current industrial applications, offline energy is mainly used for simulation testing and is almost impossible to deploy and use in actual systems.

[0004] Commonly used algorithms for online energy management include rule-based, model predictive control and local optimization methods. Rule-based energy management mainly relies on the designer's knowledge and experience to design reasonable energy management rules to allocate the output power of fuel cells and batteries. Model predictive control uses the framework of model predictive control to achieve energy management, while other local optimization schemes are mainly based on past and current system status and load data to achieve local or sub-optimization of the system. Since online energy management methods cannot know the full picture of load changes, they inevitably cannot achieve optimization and cannot effectively reduce hydrogen consumption.

[0005] For autonomous drones, since they no longer require human intervention and control, energy management can ensure that drones can use energy efficiently and reliably during missions. Therefore, it is very important for autonomous drones to find effective energy management strategies to reduce unnecessary energy consumption and extend flight time. Summary of the Invention

[0006] In view of the above problems, the present invention provides an energy management method and device for an unmanned aerial vehicle (UAV), which can be used for UAVs capable of autonomous flight and can significantly improve the energy utilization efficiency of autonomous flight UAVs.

[0007] The technical solution is as follows: An energy management method for an unmanned aerial vehicle, the unmanned aerial vehicle being capable of autonomous flight, characterized by comprising the following steps:

[0008] Construct a UAV flight power demand table, the UAV flight power demand table including the load power required for the UAV to perform different flight actions at various speeds.

[0009] Perform flight path planning according to the flight mission.

[0010] According to the optimal flight path obtained from the planning, query the UAV flight power demand table to obtain the load power required for different flight stages in the flight path, and further obtain the global load power change of the UAV to complete the flight mission.

[0011] Based on the global load power change obtained from the path planning, optimize the power output of the fuel cell and the battery to meet the load power consumption and minimize the hydrogen consumption of the fuel cell.

[0012] Further, the construction of the UAV flight power demand table is performed according to the following steps:

[0013] Test the load power required for the UAV to start / stop, fly, ascend / descend at various speeds, and establish a UAV flight power demand table based on the obtained test data.

[0014] Further, the flight path planning according to the flight mission is performed according to the following steps:

[0015] Use the perception module of the UAV to perceive the environment around the flight mission area and obtain the three-dimensional map information of the flight mission area.

[0016] According to the obtained three-dimensional map information of the flight mission area, plan the optimal flight path, the optimal flight path having the shortest flight distance and being able to avoid obstacles in the flight mission area.

[0017] Decompose the optimal flight path into multiple flight stages in chronological order and configure the flight actions for each flight stage.

[0018] Further, the perception module includes a navigation system, a camera, and a radar.

[0019] Furthermore, the global load power variation obtained based on path planning is used to optimize the power outputs of the fuel cell and the battery, which is executed according to the following steps:

[0020] Set the energy consumption optimization goal, which includes: the power outputs of the fuel cell and the battery at any time satisfy the power consumption of the load, the battery will not be overcharged or over-discharged and ensure that the state of charge of the battery is within the set range, and reduce the overall absolute value of the fuel cell output. Based on the optimization goal, set a cost function to measure the performance of the energy management strategy;

[0021] Adopt the method of dynamic programming to optimize the power outputs of the fuel cell and the battery.

[0022] Furthermore, set the cost function according to the optimization goal, and execute as follows:

[0023] According to the optimization goal, the power outputs of the fuel cell and the battery at any time satisfy the power consumption of the load, and satisfy the formula:

[0024] P load =ηf c P fc +η ba P ba (1)

[0025] Wherein, the power of the load is P load , the powers of the fuel cell and the battery are P fc and P ba respectively, the efficiency of the fuel cell is η fc and the efficiency of the battery is η ba ;

[0026] The cost function is constructed as:

[0027]

[0028] Wherein, J is the total cost, SoC(i) is the state of charge of the battery, SoC ref represents the reference value of the state of charge, i fc (i) is the fuel cell current, and the hydrogen consumption is proportional to the fuel cell current. Converting the reduction of hydrogen consumption into the reduction of the absolute value of the current, μ 1 and are the weights of the optimization goal that the battery will not be overcharged or over-discharged and ensure that the state of charge of the battery is within the set range, μ 2 is the weight of the optimization goal of reducing the overall absolute value of the fuel cell output, and T is the time;

[0029] The value ranges of SoC(i) and i fc (i) are limited to:

[0030]

[0031] wherein, i fc_min and i fc_max are the minimum and maximum currents that the fuel cell can output.

[0032] Furthermore, the method of using dynamic programming to optimize the power output of the fuel cell and the battery is implemented as follows:

[0033] First, discretize time, divide time T into n time steps, and transform the formula (2) of the cost function into:

[0034]

[0035] Discretize the currents of the battery and the fuel cell, starting from the final flight stage, gradually calculate the optimal cost function for each flight stage, then update the cost function through the Bellman equation to obtain the optimal cost for each flight stage, and then start forward simulation. Starting from the initial stage, sequentially calculate the output power distribution of the fuel cell and the battery for each optimized flight stage.

[0036] A computer device includes a memory and a processor. The memory stores a computer program. It is characterized in that: when the processor executes the computer program, the energy management method of the above-mentioned unmanned aerial vehicle is implemented.

[0037] A computer-readable storage medium stores a program on it. It is characterized in that: when the program is executed by the processor, the energy management method of the above-mentioned unmanned aerial vehicle is implemented.

[0038] A computer program product includes a computer program / instructions. It is characterized in that when the computer program / instructions are executed by the processor, the steps of the above-mentioned method are implemented.

[0039] For an unmanned aerial vehicle (UAV) capable of autonomous flight, path planning is often required before flight. By using the method of the present invention, path planning and energy management are transformed from two relatively uncorrelated aspects into closely related key aspects. Through path planning, the flight trajectory of the UAV is determined, and an optimal flight path with the shortest flight distance and capable of avoiding obstacles in the flight mission area is obtained. The optimal flight path is decomposed into multiple flight stages in chronological order, and the flight actions that the UAV can perform in each flight stage are determined. Thus, the path planning is directly associated with the load power change of the UAV. For different UAVs, the load power under different flight actions can be obtained through pre-testing, and the test data is organized into a table with the input being the flight actions of the path planning and the output being the corresponding load power. Furthermore, the global load change of the entire flight mission can be obtained. According to the load power change provided by the path planning, the power output of the fuel cell and the battery can be optimized to meet the load power consumption and minimize the hydrogen consumption of the fuel cell, ensuring that the UAV can efficiently and reliably utilize energy during the mission execution, reducing unnecessary energy consumption, and thus extending the flight time of the UAV. By using the method of the present invention, through the combination of path planning and energy management, the global load change information can be obtained in advance, the global energy management optimization can be realized, the hydrogen consumption can be more effectively reduced, the energy utilization efficiency of the autonomous flight UAV can be significantly improved, its endurance time can be extended, and its application ability in various tasks can be enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a framework diagram of the UAV power system;

[0041] Figure 2 is a schematic diagram of the steps of an energy management method for a UAV;

[0042] Figure 3 is the internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0043] The framework of the UAV power system to which the present invention is applied is as shown in Figure 1 The energy sources are a fuel cell and a battery, which are connected to the load through a DC / DC converter. Among them, the battery can also be directly connected to the load without using a DC / DC converter. In the application of the UAV, the load is mainly the propeller motor of the UAV. With the start, stop, flight, lift, and descent of the UAV, etc., the load will change.

[0044] In the application scenarios of autonomous flying drones, path planning before flight is originally an important link to ensure the smooth progress of flight, while energy management is related to the energy utilization efficiency and endurance of drones. Under the traditional technical system, the correlation between the two links is relatively low, and they operate independently. Autonomous flying drones can still only manage energy through some online energy management methods. To change this situation, as Figure 2 shown, in an embodiment of the present invention, an energy management method for drones is provided, which can be used for drones capable of autonomous flight, and includes the following steps:

[0045] Step 1: Construct a flight power demand table for the drone. The flight power demand table for the drone includes the load power required for the drone to perform different flight actions at various speeds.

[0046] Step 2: Perform flight path planning according to the flight mission.

[0047] Step 3: According to the optimal flight path obtained from the planning, query the flight power demand table of the drone to obtain the load power required for different flight stages in the flight path, and then obtain the global load power change of the drone to complete the flight mission.

[0048] Step 4: Based on the global load power change obtained from the path planning, optimize the power output of the fuel cell and the battery to meet the load power consumption and minimize the hydrogen consumption of the fuel cell.

[0049] This specification provides the method operation steps as described in the embodiments or flowcharts, but based on routine or non-creative labor, it may include more or fewer operation steps. The step order listed in the embodiments is only one way among the execution orders of numerous steps, and does not represent the only execution order. In actual execution, it can be executed in the method order shown in the embodiments or the drawings, or executed in parallel, or the step order can be swapped. For example, swap the order of Step 1 and Step 2, or execute Step 1 and Step 2 in parallel.

[0050] Specifically, in an embodiment of the present invention, in Step 1 of constructing the flight power demand table for the drone, it is executed according to the following steps:

[0051] Test the load power required for the drone to start, stop, fly, ascend, and descend at various speeds, and establish a flight power demand table for the drone based on the obtained test data.

[0052] For most drones, it is possible to offline test the load power required for starting, stopping, flying, and ascending / descending at various speeds, thereby forming a corresponding drone flight power requirement table. The input of the table is the flight instruction for path planning, and the output is the corresponding required power. In addition to obtaining the drone flight power requirement table through testing, in other embodiments of the present invention, it can also be achieved by modeling the motor and the drone.

[0053] Specifically, in an embodiment of the present invention, step 2 of performing flight path planning according to the flight mission is executed as follows:

[0054] Use the sensing module of the drone to sense the environment around the flight mission area and obtain the three-dimensional map information of the flight mission area. The sensing module uses the inputs of the navigation system, camera, and radar to sense the surrounding environment;

[0055] According to the obtained three-dimensional map information of the flight mission area, plan the optimal flight path. The optimal flight path has the shortest flight distance and can avoid obstacles in the flight mission area;

[0056] Decompose the optimal flight path into multiple flight stages in chronological order and configure the flight actions for each flight stage.

[0057] When the drone performs autonomous flight, the control module of the drone itself controls the flight of the drone based on the planned path, so that the drone flies according to the planned path. In the embodiment, the flight path is decomposed into multiple flight stages through path planning, and the information on the start, stop, flight, and ascent / descent of the drone is provided. Specifically, in step 3 of an embodiment of the present invention, according to the obtained optimal flight path, the corresponding power change required by the load can be converted. When the drone is running, the path planning module in autonomous driving plans the flight path according to the input of the sensing module and inputs it into the look-up table to obtain the load power required for different flight stages in the flight path, and then obtains the global load power change for the drone to complete the flight mission. Providing the load change to the energy management module of the drone can achieve the global optimization of energy management. Finally, the optimal power output distribution between the fuel cell and the battery is obtained.

[0058] In step 4 of an embodiment of the present invention, an energy consumption optimization target is set, and the energy consumption optimization target includes:

[0059] Optimization target 1: The power outputs of the fuel cell and the battery at any time satisfy the power consumption of the load;

[0060] Optimization target 2: The battery will not be overcharged or over-discharged and ensure that the state of charge of the battery is within the set range;

[0061] Optimization objective 3: Reduce the overall absolute value of the fuel cell output.

[0062] In the embodiment, a cost function is set based on optimization objectives 1, 2, and 3 to measure the performance of the energy management strategy;

[0063] The dynamic programming method is used to optimize the power outputs of the fuel cell and the battery.

[0064] Specifically in the embodiment, the cost function is set according to the optimization objective and executed as follows:

[0065] According to optimization objective 1, the power outputs of the fuel cell and the battery at any moment satisfy the power consumption of the load, satisfying the formula:

[0066] P load =η fc P fc +η ba P ba (1)

[0067] Wherein, the power of the load is P load , the powers of the fuel cell and the battery are P fc and P ba , the efficiency of the fuel cell is η fc and the efficiency of the battery is η ba ;

[0068] The cost function is constructed as:

[0069]

[0070] Wherein, J is the total cost, SoC(i) is the charge state of the battery, Soc ref represents the reference value of the charge state, i fc (i) is the fuel cell current, and the hydrogen consumption is proportional to the fuel cell current. Converting the reduction of hydrogen consumption into reducing the absolute value of the current, μ 1 and are the weights of optimization objective 2, μ 2 is the weight of optimization objective 3, and T is the time;

[0071] SoC(i) and i fc (i) are limited as follows:

[0072]

[0073] Wherein, i fc_min and i fc_max are the minimum and maximum currents that the fuel cell can output.

[0074] In the embodiment, the dynamic programming method is used to optimize the power outputs of the fuel cell and the battery, and the specific execution is as follows:

[0075] First, discretize time. Divide time T into n time steps and transform formula (2) of the cost function into:

[0076]

[0077] Discretize the currents of the battery and the fuel cell. Starting from the final flight phase, gradually calculate the optimal cost function for each flight phase, then update the cost function through the Bellman equation to obtain the optimal cost for each flight phase, and then start the forward simulation. Starting from the initial phase, sequentially calculate the output power distribution of the fuel cell and the battery for each optimized flight phase.

[0078] In the present invention, in addition to using the dynamic programming method to optimize the power output of the fuel cell and the battery, it can also be realized by other similar optimization algorithms, such as model predictive control, etc.

[0079] In the embodiment, the path generated by the path planning in the autonomous drone is associated with the load change and provided to the energy management, thereby realizing the global energy management optimization, greatly reducing the hydrogen consumption, and improving the endurance of the drone.

[0080] Adopting the method of the present invention breaks the original gap between the path planning and the energy management, transforming the two into closely related key links. In the method of the embodiment, based on the multi-source perception data of the existing navigation system, camera, and radar of the drone, the drone can plan the optimal flight path with the shortest flight distance and effectively avoid obstacles in the complex flight mission area. In the method of the embodiment, through path planning, the autonomous flying drone can obtain the optimal flight path with the shortest flight distance and avoid obstacles in the flight mission area, thereby improving the flight efficiency and reducing unnecessary energy consumption;

[0081] The method of the embodiment then decomposes the optimal flight path into multiple flight phases according to the time sequence and determines the flight actions that the drone can perform in each flight phase. The flight actions in different flight phases have corresponding load power data, and all these data can be obtained through pre-testing. The drone can predict the load power demand in advance according to the real-time change of the flight path. In the embodiment, the test data is organized into a drone flight power demand table, with the input being the flight actions of the path planning and the output being the corresponding load power. The drone flight power demand table realizes the direct mapping from the path planning to the load power change, embeds the path planning information into the energy management framework, breaks the information barrier between traditional modules, and gives full play to the advantages of the autonomous flying drone, and can better meet the power demand of the drone in different flight phases;

[0082] Finally, based on path planning, the global load power change is obtained, and the power outputs of the fuel cell and the battery are optimized, enabling precise regulation of energy management. For example, during different flight phases such as startup, flight, ascent, and descent, according to different load power requirements, the output powers of the fuel cell and the battery can be reasonably allocated to avoid waste and excessive consumption of energy, improve the energy utilization efficiency and the endurance of the UAV, not only meet the load power consumption, but also avoid overcharging / overdischarging of the battery, extend the battery life, and at the same time reduce the frequent startup and shutdown of the fuel cell, reduce the fuel cell current fluctuation, and lower the hydrogen consumption.

[0083] By closely integrating path planning and energy management, and optimizing energy distribution based on the load power change, the present invention can improve the energy utilization efficiency. The stable energy supply can ensure flight stability and reliability, and ensure that the UAV accurately executes tasks. When the autonomous UAV is applied in the logistics distribution scenario, it can carry more goods and fly longer distances while ensuring safe flight, expanding the coverage of logistics services; when the autonomous UAV is applied in the agricultural plant protection scenario, through path planning, according to the actual shape of the farmland, crop distribution, and obstacle conditions, a precise flight trajectory can be planned for the UAV, and optimizing energy management reduces energy consumption and the energy cost of agricultural operations; when the autonomous UAV is applied in the power facility inspection scenario, it can accurately fly along the planned path according to the layout of the established facilities, reduce manual inspections, and through energy management optimization, the overall maintenance cost of the facilities can be reduced.

[0084] In an embodiment of the present invention, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the energy management method of the UAV as described above is implemented.

[0085] This computer device can be a terminal, and its internal structure diagram can be as Figure 3 shown. This computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of this computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the energy management method of the UAV is implemented. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0086] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc. Among them, the memory is used to store programs, and the processor executes the programs after receiving execution instructions.

[0087] The processor can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc. The processor can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0088] Those skilled in the art can understand that Figure 3 the structure shown in [the figure] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0089] In an embodiment of the present invention, there is also provided a computer-readable storage medium with a program stored thereon, characterized in that: when the program is executed by a processor, it implements the energy management method of the drone as described above.

[0090] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a computer device, or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0091] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, computer devices, or computer program products according to the embodiments of the present invention. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing terminal devices generate a device for realizing the functions specified in the flowcharts and / or block diagrams.

[0092] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that realizes the functions specified in the flowchart.

[0093] In an embodiment of the present invention, a computer program product is also provided, including a computer program / instructions, characterized in that when the computer program / instructions are executed by a processor, the steps of the above method are realized.

[0094] In actual application processes, the above computer program product includes but is not limited to: unmanned aerial vehicles, smart phones, desktop computers, laptop computers, tablet computers, host computers, and server platforms, etc., and no specific limitations are made here.

[0095] The above has introduced in detail the energy management method, computer device, computer-readable storage medium, and application of the computer program product of the unmanned aerial vehicle provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An energy management method for an unmanned aerial vehicle capable of autonomous flight, characterized in that: The following steps are involved: Constructing a UAV flight power demand table, wherein the UAV flight power demand table includes the load power required for the UAV to perform different flight actions at various speeds; Plan the flight path according to the flight mission; According to the optimal flight path obtained by planning, query the UAV flight power demand table to obtain the load power required for different flight stages in the flight path, and obtain the global load power change of the UAV to complete the flight mission; The global load power change is obtained based on path planning, and the power output of the fuel cell and battery is optimized to meet the load power consumption and minimize the hydrogen consumption of the fuel cell.

2. The energy management method of a drone according to claim 1, characterized in that: The construction of the UAV flight power requirement table is performed according to the following steps: Test the load power required for the UAV to start, stop, fly, and ascend and descend at various speeds, and establish a UAV flight power requirement table based on the test data obtained.

3. The energy management method of a drone according to claim 1, characterized in that: The flight path planning is performed according to the flight mission, and is performed according to the following steps: Use the perception module of the drone to perceive the environment around the flight mission area and obtain three-dimensional map information of the flight mission area; Planning an optimal flight path based on the three-dimensional map information of the flight mission area, wherein the optimal flight path has the shortest flight distance and can avoid obstacles in the flight mission area; The optimal flight path is decomposed into multiple flight stages in chronological order, and the flight actions for each flight stage are configured.

4. The energy management method of a drone according to claim 3, characterized in that: The perception module includes a navigation system, a camera and a radar.

5. The energy management method of a drone according to claim 1, characterized in that: The above-mentioned path planning-based method for obtaining global load power changes and optimizing the power output of the fuel cell and the battery is performed in the following steps: Setting an energy consumption optimization target, wherein the energy consumption optimization target includes: the power output of the fuel cell and the battery at any time meets the power consumption of the load, the battery will not be overcharged or over-discharged and the charging state of the battery is guaranteed to be within a set range, and the overall absolute value of the fuel cell output is reduced, and the cost function is set according to the optimization target; Dynamic programming is used to optimize the power output of fuel cells and batteries.

6. The energy management method of a drone according to claim 5, characterized in that: Set the cost function according to the optimization goal and execute as follows: According to the optimization target, the power output of the fuel cell and the battery at any time meets the power consumption of the load, satisfying the formula: P load =the fc P fc +n ba P ba (1) Among them, the power of the load is P load , the power of the fuel cell and the battery are P fc and P ba , the efficiency of the fuel cell is η fc and the efficiency of the battery is η ba ; The cost function is constructed as: Where J is the total cost, SoC(i) is the state of charge of the battery, and SoC ref Indicates the reference value of the charging state, i fc (i) is the fuel cell current. The hydrogen consumption is proportional to the fuel cell current. Reducing the hydrogen consumption is converted into reducing the absolute value of the current. μ1 and μ2 are the weights of the optimization goal of ensuring that the battery will not be overcharged or over-discharged and the battery charging state is within the set range. μ2 is the weight of the optimization goal of reducing the overall absolute value of the fuel cell output. T is time. SoC(i) and i fc (i) The value is limited to: Among them, i fc_min and i fc_max are the minimum and maximum currents that the fuel cell can output.

7. The energy management method of a drone according to claim 5, characterized in that: The above-mentioned method of using dynamic programming to optimize the power output of the fuel cell and the battery is specifically performed as follows: First, time is discretized, time T is divided into n time steps, and the cost function formula (2) is transformed into: The currents of the battery and fuel cell are discretized, and starting from the final flight stage, the optimal cost function of each flight stage is calculated step by step. Then, the cost function is updated through the Bellman equation to obtain the optimal cost of each flight stage. Then, the forward simulation is started, starting from the initial stage, and the output power distribution of the fuel cell and battery in each flight stage after optimization is calculated in turn.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the energy management method for the drone as claimed in claim 1 is implemented.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by the processor, the energy management method of the drone as claimed in claim 1 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to claim 1 are implemented.

Images