Hydrogen-electric hybrid unmanned aerial vehicle energy management method, system, device, medium and product

Abstract

This application discloses a method, system, device, medium, and product for energy management of hydrogen-electric hybrid unmanned aerial vehicles (UAVs), relating to the field of energy management for long-endurance hydrogen fuel cell hybrid UAVs. The method includes: constructing a hybrid power system model containing a fuel cell, lithium battery, and supercapacitor; real-time acquisition of load demand power, fuel cell output power, and lithium battery state of charge data; constructing an objective function to minimize the overall cost for long-endurance flight missions; the objective function includes an equivalent hydrogen consumption cost term and a fuel cell lifespan degradation cost term; setting a power allocation strategy according to the UAV flight phase, and setting constraints on state variables and decision variables; using an optimization algorithm to solve the objective function to obtain the optimal power allocation sequence; and generating a power reference command to control the DC / DC converter to execute power output. This application reduces the cost of replacing the fuel cell stack later and can fully leverage the advantages of hydrogen-electric hybrid systems in long-endurance applications.

Description

Technical Field

[0001] This application relates to the field of energy management for long-endurance hydrogen fuel cell hybrid unmanned aerial vehicles (UAVs), and in particular to a method, system, device, medium, and product for energy management of hydrogen-electric hybrid UAVs. Background Technology

[0002] Hydrogen fuel cell drones, with their high energy density, zero emissions, and low noise, demonstrate unique advantages in long-endurance flight missions (such as power line inspection, border patrol, and environmental monitoring). Compared to traditional lithium battery drones, hydrogen-electric hybrid drones can extend their flight time to over 2 hours.

[0003] Currently, energy management strategies are mainly divided into rule-based strategies and optimization-based strategies. Rule-based strategies, such as state machine control and fuzzy logic control, are simple to implement but rely on expert experience; optimization-based strategies, such as dynamic programming (DP), model predictive control (MPC), and equivalent consumption minimization strategy (ECMS), can achieve global or local optima.

[0004] However, most existing energy management strategies focus on a single objective: minimizing hydrogen consumption or maintaining a balanced state of charge (SOC) in the fuel cell, neglecting the economic impact of fuel cell lifespan degradation. While some technologies do consider lifespan, this is usually achieved indirectly by setting constraints (such as limiting the rate of change of fuel cell power). This approach lacks flexibility and fails to provide a comprehensive economic trade-off between hydrogen consumption and lifespan.

[0005] Current technologies do not quantify the lifespan degradation of fuel cells into specific economic costs in the objective function. This leads to situations where, in actual operation, strategies may prioritize saving a small amount of hydrogen by operating the fuel cell stack under severely degraded conditions (such as frequent start-stop cycles and prolonged high loads), increasing the high cost of replacing the stack later. Furthermore, while current technologies consider the impact of weight changes on energy consumption, they are not optimized for the characteristics of long-endurance flight missions, failing to fully leverage the advantages of hydrogen-electric hybrid systems in long-endurance applications. Summary of the Invention

[0006] The purpose of this application is to provide a method, system, device, medium and product for energy management of hydrogen-electric hybrid unmanned aerial vehicles (UAVs) to solve the problems of high cost of replacing fuel cells later and the inability to fully utilize the advantages of hydrogen-electric hybrid systems in long-endurance applications.

[0007] To achieve the above objectives, this application provides the following solution.

[0008] In a first aspect, this application provides an energy management method for a hydrogen-electric hybrid unmanned aerial vehicle, comprising the following steps.

[0009] Construct a hybrid power system model that includes fuel cells, lithium batteries, and supercapacitors.

[0010] Based on the hybrid power system model, load demand power, fuel cell output power and lithium battery state of charge data are collected in real time.

[0011] For long-endurance flight missions, an objective function for minimizing the overall cost is constructed based on the load power requirement, the fuel cell output power, and the lithium battery state of charge data. The objective function includes an equivalent hydrogen consumption cost term and a fuel cell lifespan degradation cost term, which is calculated based on the number of start-stop cycles, the duration of high and low loads, and the load switching amount.

[0012] Set a power allocation strategy based on the UAV's flight phases, and define constraints for state and decision variables.

[0013] Based on the power allocation strategy and the constraints, an optimization algorithm is used to solve the objective function to obtain the optimal power allocation sequence, and a power reference command is generated to control the DC / DC converter to perform power output.

[0014] Secondly, this application provides a hydrogen-electric hybrid drone energy management system, including the following modules.

[0015] The model building module is used to build hybrid power system models that include fuel cells, lithium batteries, and supercapacitors.

[0016] The data acquisition module is used to collect load demand power, fuel cell output power and lithium battery state of charge data in real time based on the hybrid power system model.

[0017] The objective function construction module is used to construct an objective function that minimizes the overall cost for long-endurance flight missions, based on the load power demand, the fuel cell output power, and the lithium battery state of charge data. The objective function includes an equivalent hydrogen consumption cost term and a fuel cell lifespan degradation cost term, which is calculated based on the number of start-stop cycles, the duration of high and low loads, and the load switching amount.

[0018] The strategy and constraint module is used to set power allocation strategies according to the flight phase of the UAV and to set constraints on state variables and decision variables.

[0019] The solution control module is used to solve the objective function based on the power allocation strategy and the constraints to obtain the optimal power allocation sequence, and generate power reference commands to control the DC / DC converter to perform power output.

[0020] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described hydrogen-electric hybrid drone energy management method.

[0021] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described energy management method for hydrogen-electric hybrid unmanned aerial vehicles.

[0022] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described energy management method for hydrogen-electric hybrid unmanned aerial vehicles.

[0023] According to the specific embodiments provided in this application, this application has the following technical effects: Based on the constructed hybrid power system model including fuel cells, lithium batteries, and supercapacitors, this application collects load demand power, fuel cell output power, and lithium battery state of charge data in real time to construct an objective function that minimizes the overall cost. The objective function explicitly introduces a fuel cell lifespan degradation cost term, quantifying stress factors such as start-stop cycle count, high and low load duration, and load conversion amount into economic costs. These costs, together with the equivalent hydrogen consumption cost, constitute a comprehensive optimization objective. Through multi-objective collaborative optimization, this application enables the energy management strategy to dynamically and economically balance "instantaneous hydrogen consumption" and "fuel cell stack lifespan loss," avoiding sacrificing the lifespan of core components for short-term energy saving. This minimizes the total operating cost throughout the entire lifespan and reduces the cost of replacing the fuel cell stack later. A power allocation strategy is set according to the UAV's flight phase, and constraints are defined for state variables and decision variables. An optimization algorithm is used to solve the objective function to obtain the optimal power allocation sequence, and a power reference command is generated to control the DC / DC converter to execute power output, thereby fully leveraging the advantages of the hydrogen-electric hybrid system in long-endurance applications. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1This is a flowchart illustrating an energy management method for a hydrogen-electric hybrid unmanned aerial vehicle (UAV) according to an embodiment of this application.

[0026] Figure 2 This is a topology diagram of a hydrogen-electric hybrid unmanned aerial vehicle power system provided in an embodiment of this application.

[0027] Figure 3 The image shows a Simulink simulation model of a hybrid power system. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] To make the objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] like Figure 1 As shown in the figure, this application provides an energy management method for a hydrogen-electric hybrid unmanned aerial vehicle, including the following steps.

[0031] S1: Construct a hybrid power system model that includes fuel cells, lithium batteries, and supercapacitors.

[0032] S2: Based on the hybrid power system model, collect load demand power, fuel cell output power and lithium battery state of charge data in real time.

[0033] S3: For long-endurance flight missions, an objective function for minimizing the overall cost is constructed based on the load power requirement, the fuel cell output power, and the lithium battery state of charge data. The objective function includes an equivalent hydrogen consumption cost term and a fuel cell lifespan degradation cost term, which is calculated based on the number of start-stop cycles, the duration of high and low loads, and the load switching amount.

[0034] S4: Set the power allocation strategy according to the flight phase of the UAV, and set the constraints of the state variables and decision variables.

[0035] S5: Based on the power allocation strategy and the constraints, an optimization algorithm is used to solve the objective function to obtain the optimal power allocation sequence, and a power reference command is generated to control the DC / DC converter to perform power output.

[0036] In practical applications, hybrid power system models are built on the MATLAB / Simulink simulation platform, such as... Figure 2 The diagram shows the topology of the hydrogen-electric hybrid drone's power system. This model uses a fuel cell 1 as the main power source, connected to the DC bus via a unidirectional DC / DC converter 2. A lithium battery 3 serves as an auxiliary power source, connected to the DC bus via a bidirectional DC / DC converter 4, providing instantaneous high power and energy recovery. A supercapacitor 5 is directly connected in parallel to the DC bus, acting as a peak shaving and valley filling mechanism to reduce the frequent response of the lithium battery 3. An energy management system 6 collects real-time signals such as DC bus voltage, lithium battery SOC, and load power demand, outputting a reference value for the fuel cell power. A hydrogen tank 7, as a primary energy storage unit, supplies hydrogen to the proton exchange membrane fuel cell (PEMFC) stack after pressure reduction to generate DC power. After the power is fed into the DC bus, a DC / AC converter 8 performs DC-to-AC conversion and power modulation, thereby driving a motor 9 to output mechanical torque to power the rotor / propeller of the hydrogen-electric hybrid drone. As the final energy execution end of the system, the motor 9 feeds back its real-time power demand to the energy management system 6 through the load measurement module; the operating conditions of the hydrogen-electric hybrid UAV are fed back in real-time through the load module, forming a closed-loop coupling with the energy management system 6 from operating condition perception to power allocation to execution response, thereby coordinating and optimizing hydrogen consumption, fuel cell degradation costs and overall system efficiency while meeting flight mission requirements.

[0037] Simulink simulation model of hybrid power system model, such as Figure 3 As shown, the model employs a three-source hybrid topology consisting of fuel cell 1, lithium battery 3, and supercapacitor 5. Fuel cell 1 serves as the main power source, with its output connected to the DC bus via a unidirectional DC / DC converter 2. Lithium battery 3 acts as an auxiliary power source, achieving bidirectional energy flow through a bidirectional DC / DC converter 4. The energy management system 6 acquires the fuel cell output power P of fuel cell 1. fc The lithium battery voltage V of lithium battery 3 dc and lithium battery state of charge (SOC) bat and the load power P of the drone load module 10 loadThe energy management system 6 controls the unidirectional DC / DC converter 2 and the bidirectional DC / DC converter 4 through the control of the unidirectional DC / DC port and the control of the bidirectional DC / DC port, supplying power to the UAV load module 10. The supercapacitor 5 is directly connected in parallel to the DC bus for instantaneous high-power compensation, with V+ being the positive terminal and V- being the negative terminal. The UAV load module 10 is used to simulate the power requirements under different flight conditions. The energy management system 6 collects the bus voltage, battery state of charge, and load power signals in real time and outputs control commands to each power converter. Simultaneously, a protection resistor module is configured to prevent battery overcharging, a measurement module is used to monitor key operating parameters, and a discrete simulation setting module is used to set the sampling time. Regarding energy flow, the fuel cell 1, after being boosted, supplies power to the DC bus along with the lithium battery 3 and the supercapacitor 5. The electrical energy drives the motor to output mechanical power through the inverter stage. Under light load conditions, the fuel cell 1 can charge the lithium battery 3 through a buck converter. This model realizes a closed-loop simulation process of state acquisition, optimization solution and control command issuance through signal interaction and dynamic calculation, which is used for the development and verification of energy management strategies.

[0038] In practical applications, real-time acquisition of the operating status data of the hybrid power system model is performed, including the load demand power P. load Fuel cell output power P fc Lithium-ion battery state of charge (SOC) bat Lithium battery voltage V dc Key parameters, etc.

[0039] This application models stress factors such as fuel cell stack start-up and shutdown, high and low loads, and load transfer as voltage decay rates, which are then converted into economic costs. These costs, along with hydrogen consumption costs, constitute the optimization objective, achieving synergistic optimization of economic efficiency and durability. Simultaneously, a complete hybrid power system model is built based on the MATLAB / Simulink platform, providing a reliable simulation platform for the development and verification of power allocation strategies.

[0040] In an exemplary embodiment, to achieve global optimization of system operation while accurately meeting the real-time power requirements of the UAV, an objective function for minimizing comprehensive costs is constructed. This objective function aims to simultaneously optimize the system's economy and durability, and consists of two parts: first, the equivalent hydrogen consumption cost reflecting the immediate consumption of hydrogen fuel; and second, the degradation cost characterizing the performance decline of the PEMFC due to operating conditions. By minimizing the sum of these two costs, the system can significantly improve fuel utilization efficiency and extend the service life of core components while ensuring mission completion, achieving intelligent, efficient, and sustainable energy allocation.

[0041] In practical applications, the system first collects key operating parameters such as load demand power, fuel cell output power, and lithium battery state of charge (SOC) in real time as input. Then, it proceeds to the objective function construction stage, which consists of two parts: first, the equivalent hydrogen consumption cost, calculated based on the hydrogen consumption rate, conversion efficiency, and lower calorific value of hydrogen for fuel cell 1 and lithium battery 3; second, the fuel cell lifespan degradation cost, converted into economic cost by quantifying stress factors such as the number of start-stop cycles, high load duration, low load duration, and load transfer amount. In the constraint setting stage, the system limits the power output range of fuel cell 1 and lithium battery 3, the safe range of lithium battery SOC, and the dynamic update law of SOC. The upper-level controller is responsible for global optimization decisions, combining predicted operating conditions and multi-objective cost functions, and using algorithms such as dynamic programming or model predictive control to solve for the optimal power allocation sequence under constraints. The lower-level controller is responsible for low-level execution and tracking, receiving power commands from the upper level and adjusting the DC / DC converter duty cycle in real time to accurately allocate the output power of each power source to maintain stable bus voltage. Finally, the output control module generates power reference commands for fuel cell 1, lithium battery 3 and supercapacitor 5 based on the solution results, and controls the unidirectional and bidirectional DC-DC converters to perform the corresponding power outputs, thereby achieving synergistic optimization of hydrogen consumption economy and fuel cell durability in long-endurance flight missions.

[0042] The objective function is: in, F The objective function is constructed with the goal of minimizing the sum of equivalent hydrogen consumption cost and PEMFC degradation cost; C Np Heq,k To predict step size N p At that time, the first k The equivalent hydrogen consumption cost per second; , N Total seconds; C Np fc,k To predict step size N p At that time, the first k The degradation cost of PEMFC per second; N p To predict the step size; γ H The hydrogen coefficient; γ fc This refers to the price of PEMFC.

[0043] No. k Equivalent hydrogen consumption per second for: in, η fc , η b The efficiencies are those of fuel cells and lithium batteries, respectively. LHV H2 Hydrogen has a low calorific value (120 kJ / g); P b，k For the first k The power of a lithium battery; Hydrogen consumption rate of fuel cells; This refers to the equivalent hydrogen consumption rate of lithium batteries. For the first k The power of a fuel cell per second; t is time.

[0044] Cost of fuel cell in the kth second : in, △U EOL,fc The voltage decay threshold at the end of fuel cell life (EOL) is set to 60000uV. P fc,max This indicates the maximum output power of the fuel cell. α on-off The rate of decrease in fuel voltage during each on / off cycle. α high The attenuation rate under high load (PEMFC power exceeds 80% of its maximum power). α low The attenuation rate at low load (PEMFC power is less than 20% of its maximum power); α high_eff The degradation rate of PEMFC in the high-efficiency range of 20% to 80% of maximum power. α shift The voltage degradation rate during load switching can be a user-defined constant. N cycle , T high , T low , N shift These represent the number of start-stop cycles, high load duration (h), low load duration (h), and load transfer amount (kW), respectively. T high_eff This refers to the duration of PEMFC in its high-efficiency range of 20% to 80% of maximum power.

[0045] In an exemplary embodiment, the power allocation strategy specifically includes: during the cruise phase (accounting for more than 70% of the mission time), controlling the fuel cell to operate within the high-efficiency range of 20%-80% of its rated power; during the takeoff and climb phases, utilizing the lithium battery 3 and supercapacitor 5 to provide peak power and limiting the rate of change of fuel cell power to avoid long-term high-load operation of the fuel cell; during the descent and landing phases, controlling the fuel cell to charge the lithium battery to prepare for the next mission, and maintaining the state of charge of the lithium battery within the safe range of 30%-80% throughout the entire process to avoid overcharging and over-discharging.

[0046] In an exemplary embodiment, during the operation of the hydrogen-electric hybrid drone, due to the limitations imposed by the physical properties of each powertrain component, the constraints on the state variables and decision variables are as follows: in, P fc_min This represents the minimum output power of the fuel cell; P fc，k For the first k The output power of a fuel cell per second; P b_min This is the minimum power of a lithium battery; P bmax This is the maximum power of the lithium battery; P dem,k For the first k The required power of the second motor; SOC min This represents the minimum state of charge (SOC) of a lithium battery. k For the first k State of charge (SOC) of a lithium battery. max This represents the maximum state of charge (SOC) of a lithium battery. k+1 For the first k +1 second lithium battery state of charge; V b This refers to the terminal voltage of the lithium battery. Q b This refers to the rated capacity of the lithium battery. This represents the sampling time step.

[0047] In an exemplary embodiment, the optimization algorithm is selected from dynamic programming algorithm, model predictive control algorithm, equivalent consumption minimum strategy algorithm, reinforcement learning algorithm, particle swarm optimization algorithm or genetic algorithm. As long as its optimization objective function contains "fuel cell life decay cost term", it is within the scope of protection of this application.

[0048] In one exemplary embodiment, the hybrid power system model includes a fuel cell output voltage model, a lithium battery dynamic characteristics model, a supercapacitor model, and a drone load model.

[0049] Construct a hybrid power system model incorporating fuel cells, lithium batteries, and supercapacitors, specifically including: A fuel cell output voltage model is established based on the polarization curve characteristics, taking into account activation loss, ohmic loss, and concentration loss.

[0050] A dynamic characteristic model of lithium battery is established based on Thevenin equivalent circuit model, taking into account charging and discharging efficiency and internal resistance changes.

[0051] A supercapacitor model is established based on the classic equivalent circuit model for instantaneous high-power compensation.

[0052] Based on the changing load requirements, a drone load model is established, and the drone flight status is input into the drone load model to simulate the power requirements under different flight conditions.

[0053] This embodiment employs a three-source hybrid architecture of "fuel cell + lithium battery + supercapacitor". Alternative solutions could be fuel cell + lithium battery (dual source), fuel cell + supercapacitor (dual source), or fuel cell + lithium battery + flywheel energy storage. As long as the fuel cell is included as the main power source and the energy management strategy considers its lifespan degradation cost, it falls within the scope of protection of this application.

[0054] In practical applications, based on the objective function and under the premise of satisfying the constraints, an optimization algorithm is used to solve for the optimal power allocation sequence: [P] fc (k), P bat (k), P sc [(k)]=arg min J, where, P fc (k) is the kth k The optimal output power of a second fuel cell, P bat (k) is the kth k The optimal charge / discharge power of a lithium battery, P sc (k) is the kth k The optimal charging and discharging power of the supercapacitor is J, which is the objective function value, i.e., the objective function value of the overall system operating cost in the predicted time domain. Based on the optimal power allocation sequence, power reference commands are generated for the fuel cell and energy storage components to control the DC / DC converter to execute power output.

[0055] The hybrid power system model in this embodiment is built using the MATLAB / Simulink platform. Alternatives include modeling and simulation based on AMESim, GT-SUITE, or a custom simulation platform based on Python. Any model capable of building a complete hydrogen-electric hybrid UAV energy management system falls within the scope of this application.

[0056] This application provides an energy management system for a hydrogen-electric hybrid unmanned aerial vehicle, including the following modules.

[0057] The model building module is used to build hybrid power system models that include fuel cells, lithium batteries, and supercapacitors.

[0058] The data acquisition module is used to collect load demand power, fuel cell output power and lithium battery state of charge data in real time based on the hybrid power system model.

[0059] The objective function construction module is used to construct an objective function that minimizes the overall cost for long-endurance flight missions, based on the load power demand, the fuel cell output power, and the lithium battery state of charge data. The objective function includes an equivalent hydrogen consumption cost term and a fuel cell lifespan degradation cost term, which is calculated based on the number of start-stop cycles, the duration of high and low loads, and the load switching amount.

[0060] The strategy and constraint module is used to set power allocation strategies according to the flight phase of the UAV and to set constraints on state variables and decision variables.

[0061] The solution control module is used to solve the objective function based on the power allocation strategy and the constraints to obtain the optimal power allocation sequence, and generate power reference commands to control the DC / DC converter to perform power output.

[0062] This application constructs an objective function that includes an equivalent hydrogen consumption cost term and a fuel cell lifetime degradation cost term. By quantifying lifetime loss, the optimizer can perceive lifetime costs and proactively avoid high-degradation operating conditions. By explicitly introducing the fuel cell lifetime degradation cost term into the objective function, this application enables the energy management strategy to proactively balance instantaneous hydrogen consumption with stack lifetime loss during decision-making. Although instantaneous hydrogen consumption may increase slightly under certain operating conditions, it can significantly reduce the rate of fuel cell performance degradation. Considering both hydrogen consumption costs and fuel cell stack replacement costs, it effectively reduces the total operating cost of the UAV throughout its entire lifecycle.

[0063] This application employs refined modeling and cost quantification of four main degradation factors: start-up / shutdown, high / low load, and load switching. This enables the optimizer to accurately identify and avoid harmful operating conditions. This application can prevent fuel cells from operating under high-degradation-risk conditions for extended periods, such as frequent start-up / shutdown, prolonged low-load or high-load operation. By optimizing the power distribution sequence, stress impacts on the fuel cell stack are reduced, thereby effectively extending the fuel cell's lifespan and reducing maintenance frequency.

[0064] Because the objective function considers the attenuation cost caused by load power transfer, the resulting power allocation sequence is smoother, reducing drastic fluctuations in fuel cell output power. This not only helps protect the fuel cell stack but also reduces the fluctuation amplitude of the DC bus voltage in the power system, improving the stability of the power supply system.

[0065] This application has made adaptive optimizations for the characteristics of long-endurance flight missions, and set up a power distribution strategy to prioritize the operation of fuel cells in the high-efficiency range during the cruise phase, and to make reasonable use of auxiliary power under dynamic operating conditions. This not only meets the energy density requirements of long-endurance missions, but also takes into account the durability of the system.

[0066] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments. The computer device can be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device stores data to be processed. The I / O interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with an external terminal via a network connection. When the computer program is executed by the processor, it implements the above-described methods.

[0067] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0068] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0069] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0070] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by hardware related to computer program instructions. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0071] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0072] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0073] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for energy management of a hydrogen-electric hybrid unmanned aerial vehicle, characterized in that, include: Construct a hybrid power system model that includes fuel cells, lithium batteries, and supercapacitors; Based on the hybrid power system model, load demand power, fuel cell output power and lithium battery state of charge data are collected in real time. For long-endurance flight missions, an objective function for minimizing the overall cost is constructed based on the load power demand, the fuel cell output power, and the lithium battery state of charge data. The objective function includes an equivalent hydrogen consumption cost term and a fuel cell lifespan degradation cost term, which is calculated based on the number of start-stop cycles, the duration of high and low loads, and the load switching amount. The objective function is: in, F The objective function is constructed with the goal of minimizing the sum of equivalent hydrogen consumption cost and PEMFC degradation cost; This is the equivalent hydrogen consumption cost item; C Np Heq,k To predict step size N p At that time, the first k The equivalent hydrogen consumption cost per second; , N Total seconds; This is the cost item for fuel cell lifespan degradation. C Np fc,k To predict step size N p At that time, the first k The degradation cost of PEMFC per second; N p To predict the step size; γ H The hydrogen coefficient; γ fc For PEMFC price; Set a power allocation strategy based on the UAV's flight phases, and define constraints for state variables and decision variables; Based on the power allocation strategy and the constraints, an optimization algorithm is used to solve the objective function to obtain the optimal power allocation sequence, and a power reference command is generated to control the DC / DC converter to perform power output; the DC / DC converter includes a unidirectional DC / DC converter and a bidirectional DC / DC converter.

2. The energy management method for a hydrogen-electric hybrid unmanned aerial vehicle according to claim 1, characterized in that, The power allocation strategy specifically includes: During the cruise phase, the fuel cell is controlled to operate within the high-efficiency range of 20%-80% of its rated power; During takeoff and climb, peak power is provided by lithium batteries and supercapacitors, and the rate of change of fuel cell power is limited. During the descent and landing phases, the fuel cell is controlled to charge the lithium battery, and the lithium battery's state of charge is maintained within a safe range of 30%-80% throughout the entire process.

3. The energy management method for a hydrogen-electric hybrid unmanned aerial vehicle according to claim 1, characterized in that, The constraints on the state variables and decision variables are as follows: in, P fc_min This represents the minimum output power of the fuel cell; P fc_max This represents the maximum output power of the fuel cell; P fc，k For the first k The output power of a fuel cell per second; P b_min This is the minimum power of a lithium battery; P bmax This is the maximum power of the lithium battery; P b，k For the first k The power of a lithium battery; P dem,k For the first k The required power of the second motor; SOC min This represents the minimum state of charge (SOC) of a lithium battery. k For the first k State of charge (SOC) of a lithium battery. max This represents the maximum state of charge (SOC) of the lithium battery. k+1 For the first k+1 The state of charge of a lithium battery; V b This refers to the terminal voltage of the lithium battery. Q b This refers to the rated capacity of the lithium battery. This is the sampling time step.

4. The energy management method for a hydrogen-electric hybrid unmanned aerial vehicle according to claim 1, characterized in that, The optimization algorithm is selected from dynamic programming, model predictive control, equivalent cost minimization strategy, reinforcement learning, particle swarm optimization, or genetic algorithm.

5. The energy management method for a hydrogen-electric hybrid unmanned aerial vehicle according to claim 1, characterized in that, The hybrid power system model includes a fuel cell output voltage model, a lithium battery dynamic characteristic model, a supercapacitor model, and a drone load model. Construct a hybrid power system model incorporating fuel cells, lithium batteries, and supercapacitors, specifically including: A fuel cell output voltage model was established based on polarization curve characteristics; A dynamic characteristic model of lithium battery is established based on Thevenin equivalent circuit model. A supercapacitor model is established based on the classic equivalent circuit model; Establish a drone load model based on changing load requirements.

6. A hydrogen-electric hybrid unmanned aerial vehicle (UAV) energy management system, characterized in that, The method for energy management of a hydrogen-electric hybrid unmanned aerial vehicle according to any one of claims 1-5 includes: The model building module is used to build hybrid power system models that include fuel cells, lithium batteries, and supercapacitors. The data acquisition module is used to collect load demand power, fuel cell output power and lithium battery state of charge data in real time based on the hybrid power system model. The objective function construction module is used to construct an objective function that minimizes the overall cost for long-endurance flight missions, based on the load power demand, the fuel cell output power, and the lithium battery state of charge data. The objective function includes an equivalent hydrogen consumption cost term and a fuel cell life decay cost term, which is calculated based on the number of start-stop cycles, the duration of high and low loads, and the load switching amount. The strategy and constraint module is used to set power allocation strategies according to the flight phase of the UAV and to set constraints on state variables and decision variables. The solution control module is used to solve the objective function based on the power allocation strategy and the constraints to obtain the optimal power allocation sequence, and generate power reference commands to control the DC / DC converter to perform power output.

7. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the energy management method for a hydrogen-electric hybrid unmanned aerial vehicle according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the energy management method for the hydrogen-electric hybrid unmanned aerial vehicle as described in any one of claims 1-5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the energy management method for the hydrogen-electric hybrid unmanned aerial vehicle as described in any one of claims 1-5.

Images