Composite energy collaborative energy supply unmanned aerial vehicle

Abstract

The invention belongs to the technical field of unmanned aerial vehicle energy management, and particularly relates to a composite energy cooperative energy supply unmanned aerial vehicle, which particularly realizes dynamic energy distribution and fault tolerance control through a multi-objective optimization algorithm, and comprises a composite energy bin carried on a vehicle body, the hydrogen generator is used for generating electric energy through electrochemical reaction of input hydrogen and oxygen in air; and the battery module is connected with the hydrogen energy source module and used for storing electric energy and supplying energy to the unmanned aerial vehicle. Through intelligent cooperation of the hydrogen fuel and the lithium battery, a multi-objective optimization algorithm and modular design, the problems that a traditional unmanned aerial vehicle is short in endurance, poor in dynamic performance, low in reliability and the like are solved, the unmanned aerial vehicle is suitable for complex scenes such as electric power inspection tour, agricultural plant protection and emergency disaster relief, and the unmanned aerial vehicle has high efficiency, safety and environmental protection performance and is worthy of popularization. And the method has remarkable technical advantages and market competitiveness.

Description

Technical Field

[0001] The present invention belongs to the technical field of UAV energy management, and specifically relates to a composite energy collaborative power supply UAV, especially realizing dynamic energy distribution and fault-tolerant control through a multi-objective optimization algorithm. Background Art

[0002] Existing drones primarily rely on lithium batteries as a single energy source. Their endurance is limited by the battery's energy density, making them difficult to meet the demands of long-duration flight missions. While hydrogen fuel cells offer high energy density, their dynamic response is poor, making them incapable of adapting to high-power scenarios like drone takeoff and acceleration. Furthermore, existing energy management systems often employ fixed power allocation strategies, lacking coordinated optimization of battery life, load balancing, and safety risks. This results in low system efficiency and reliability. Therefore, there is an urgent need for a hybrid energy-powered drone that combines the advantages of hydrogen fuel and lithium batteries and possesses intelligent dynamic management capabilities. Summary of the Invention

[0003] (1) Technical issues to be resolved The existing hybrid energy drones that use hydrogen and battery energy have the following defects: the single energy system has short endurance and insufficient dynamic performance; the energy allocation strategy lacks coordinated optimization of multiple objectives (such as efficiency, life, and safety); and the fault tolerance capability is weak, which cannot guarantee the system reliability in extreme scenarios.

[0004] (2) Technical solution The present invention is implemented through the following technical solution: The present invention proposes a UAV fuselage, which is equipped with a composite energy tank (the composite energy tank is made of lightweight carbon fiber to reduce the load of the UAV), which is internally integrated with: The hydrogen energy module is used to generate electricity through electrochemical reaction between the input hydrogen and oxygen in the air; The battery module is connected to the hydrogen energy module to store electrical energy and power the drone; It also integrates a central control module, which is connected to the battery module and hydrogen energy module, and integrates: an energy management unit configured to run a multi-objective optimization algorithm and dynamically allocate the output ratio of the hydrogen energy module and the battery module according to the flight phase of the UAV; a fault diagnosis unit configured to detect the operating status of the hydrogen energy module and the battery module based on sensor data and perform abnormality warning and fault-tolerant control; The multi-objective optimization algorithm is run, and its objective function J Defined as: ; in: For the comprehensive energy efficiency of hydrogen energy module and battery module, , is the total output power of the UAV, Input power to the hydrogen energy module, Input power to the battery module; is the battery life protection factor of the battery module, , SOC is the remaining battery capacity of the battery module, is the battery temperature of the battery module; is the hydrogen reactor load balancing factor of the hydrogen energy module, , is the power fluctuation standard deviation of the hydrogen energy module, is the average power of the hydrogen energy module; is a safety risk factor, , is the hydrogen pressure change rate of the hydrogen energy module, is the time interval of pressure change of hydrogen energy module, is the temperature rise of the hydrogen reactor of the hydrogen energy module, The maximum temperature allowed for the hydrogen reactor of the hydrogen energy module, and is the safety weight coefficient; ; is the stress change risk weight, For temperature rise risk weight, in real-time operation and Can be dynamically optimized according to environmental conditions; if the risk of pressure changes dominates, increase To prioritize the response to pressure change risk; if the temperature rise risk is more critical, increase To enhance sensitivity to temperature rise; and Determine the weight ratio through actual testing or simulation: Step 1: Collect the pressure change rate under different working conditions ( ) and temperature rise data ( ); Step 2: Analyze historical fault data to determine the impact of both on system safety; Step 3: Fitting by regression analysis or optimization algorithm and , so that the risk score matches the actual failure probability.

[0005] , , , It is a dynamic weight coefficient, which is adjusted in real time through the fuzzy logic rule base and deep neural network; The objective function J The constraints are as follows: The total output power of the hydrogen energy module and the battery module shall not be less than the power required by the UAV; The SOC range is limited to 20% to 80%; The hydrogen reactor temperature of the hydrogen energy module does not exceed 80°C; No more than 10% per second.

[0006] Preferably, the energy management unit dynamically allocates the output ratio of the hydrogen energy module and the battery module during the flight phase of the UAV, specifically: Takeoff phase: The battery module provides 80% of the required power, and the hydrogen energy module provides 20% of the required power; Cruising phase: The hydrogen energy module provides 90% of the required power and charges the battery module, with the charging power accounting for 10% of the required power; Landing phase: The hydrogen energy module provides 70% of the required power, and the battery module recovers the energy corresponding to 30% of the required power (recovery efficiency is 85%).

[0007] Preferably, the hydrogen energy module includes an inflation valve, an air release unit, a gas transmission unit, a reaction unit and a hydrogen storage tank; the hydrogen storage tank and the reaction unit are both installed in the composite energy warehouse; the hydrogen storage tank is provided with an air release unit; the hydrogen storage tank is connected to the reaction unit through the gas transmission unit; the inflation valve is connected to the hydrogen storage tank and passes through the surface of the composite energy warehouse; The deflation unit includes a deflation pipe and an intelligent deflation valve; one end of the deflation pipe is connected to the hydrogen storage tank, and the other end passes through the surface of the composite energy warehouse; the deflation pipe is equipped with an intelligent deflation valve; The gas transmission unit includes a pressure sensor, an intelligent gas transmission valve and a gas transmission pipeline; One end of the gas transmission pipeline is connected to the hydrogen storage tank, and the other end is connected to the reaction unit; The gas pipeline is equipped with pressure sensors and intelligent gas valves; The reaction unit includes a hydrogen reactor and a DC-DC converter; the hydrogen reactor is connected to the battery module through the DC-DC converter; the composite energy compartment is provided with heat dissipation holes on the side of the hydrogen reactor to facilitate heat dissipation; The intelligent air release valve, pressure sensor, intelligent gas transmission valve, hydrogen reactor and battery module are all communicatively connected to the central control module; 35MPa carbon fiber wrapped bottle, volume 2.6L, diameter 80mm, length 300mm, with pressure warning sign on the surface; in, Hydrogen storage tank: 35MPa carbon fiber wrapped bottle, volume 2.6L, diameter 80mm, length 300mm, with pressure warning sign on the surface; Deflating unit: includes a deflating pipe (inner diameter 5mm) and an intelligent deflating valve (response time ≤50ms) for emergency pressure relief; Gas transmission unit: gas transmission pipeline (pressure resistance 40MPa), pressure sensor (accuracy ±0.1MPa) and intelligent gas transmission valve (flow adjustment range 0-5L / min); Reaction unit: The hydrogen reactor adopts a proton exchange membrane fuel cell stack (rated power 2000W, efficiency ≥50%), equipped with a DC-DC converter (conversion efficiency ≥95%).

[0008] Preferably, the battery module is a lithium polymer battery pack, which is equipped with a battery management system connected to an energy management unit; the lithium polymer battery pack has a capacity of 20,000 mAh (6S, voltage 22.2 V), a flat square design (200 mm × 150 mm × 30 mm), a maximum continuous discharge rate of 15C, and monitors voltage, temperature and SOC through a battery management system (BMS).

[0009] Preferably, the energy management unit runs a multi-objective optimization algorithm in real time through a microcontroller, specifically an STM32F7 series, interacting with a CAN bus communication module with a response delay of no more than 10 milliseconds, and the ground station software records the energy supply data and transmits it back to the cloud for continuous training of the neural network model and optimization of the rule base; The microcontroller uses STM32F767IGT6 with a main frequency of 216MHz. It communicates with sensors through the CAN bus (baud rate 1Mbps) with a response delay of ≤10m. In addition, it uses a 4G / 5G dual-mode communication module to support cloud streaming and remote command reception. The ground station software displays the remaining hydrogen, reactor temperature, battery SOC and flight trajectory in real time, supporting mission planning and secondary development.

[0010] Preferably, the fault diagnosis unit includes: Anomaly detection algorithms, based on support vector machines or random forest models, analyze hydrogen pressure, reactor temperature, and battery voltage data in the hydrogen energy module and battery module. This algorithm, primarily based on support vector machine (SVM) models, analyzes hydrogen pressure (sampling frequency 100Hz), reactor temperature (±0.5°C accuracy), and battery voltage data in real time. Fault-tolerant control strategy: when the hydrogen energy module fails, it switches to the battery module for independent power supply and reduces the drone load to less than 12 kg; when the battery module fails, it switches to full power output of the hydrogen energy module and limits maneuvering movements.

[0011] Preferably, the fault diagnosis unit integrates a hydrogen leak detection sensor, specifically a MEMS hydrogen-sensitive sensor, and a distributed battery temperature monitoring node, with a sampling frequency of not less than 100 Hz, and the abnormality judgment threshold is dynamically calibrated through a machine learning model.

[0012] Preferably, the deep neural network model is deployed based on the TensorFlow Lite framework, the input layer contains 20-dimensional feature parameters, including the hydrogen flow rate in the hydrogen energy module and the battery module, the remaining battery power and the ambient temperature, the output layer is the energy supply ratio weight, and the model update cycle does not exceed 24 hours.

[0013] Preferably, the UAV or composite energy compartment is equipped with a standardized quick-release interface to support the rapid replacement of the optoelectronic pod, cargo compartment or spraying device, and the power consumption data of the mission module is fed back to the energy management unit in real time for dynamic adjustment of the energy supply strategy.

[0014] (3) Beneficial effects This invention solves the pain points of traditional drones such as short flight time, poor dynamic performance, and low reliability through the intelligent collaboration of hydrogen fuel and lithium batteries, multi-objective optimization algorithm and modular design. It is suitable for complex scenarios such as power inspection, agricultural plant protection, and emergency disaster relief. It is efficient, safe, and environmentally friendly, and has significant technical advantages and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings: Figure 1 It is a structural schematic diagram of the present invention.

[0016] Figure 2 This is a schematic diagram of the composite energy warehouse structure of the present invention.

[0017] Figure 3 This is a schematic diagram of the composite energy warehouse connection structure of the present invention. The markings in the accompanying drawings are: 1-fuselage, 2-composite energy compartment, 21-heat dissipation hole, 3-hydrogen energy module, 31-inflation valve, 32-deflation unit, 321-deflation pipeline, 322-intelligent deflation valve, 33-gas transmission unit, 331-pressure sensor, 332-intelligent gas transmission valve, 333-gas transmission pipeline, 34-reaction unit, 341-hydrogen reactor, 342-DC-DC converter, 35-hydrogen storage tank, 4-battery module, 5-energy management module. DETAILED DESCRIPTION

[0018] Reference Figure 1-Figure 3As shown, the present invention proposes a UAV fuselage equipped with a composite energy tank (the composite energy tank is made of lightweight carbon fiber to reduce the load of the UAV), which is internally integrated with: The hydrogen energy module is used to generate electricity through electrochemical reaction between the input hydrogen and oxygen in the air; The battery module is connected to the hydrogen energy module to store electrical energy and power the drone; It also integrates a central control module, which is connected to the battery module and hydrogen energy module, and integrates: an energy management unit configured to run a multi-objective optimization algorithm and dynamically allocate the output ratio of the hydrogen energy module and the battery module according to the flight phase of the UAV; a fault diagnosis unit configured to detect the operating status of the hydrogen energy module and the battery module based on sensor data and perform abnormality warning and fault-tolerant control; The multi-objective optimization algorithm is run, and its objective function J Defined as: ; in: For the comprehensive energy efficiency of hydrogen energy module and battery module, , is the total output power of the UAV, Input power to the hydrogen energy module, Input power to the battery module; is the battery life protection factor of the battery module, , SOC is the remaining battery capacity of the battery module, is the battery temperature of the battery module; is the hydrogen reactor load balancing factor of the hydrogen energy module, , is the power fluctuation standard deviation of the hydrogen energy module, is the average power of the hydrogen energy module; is a safety risk factor, , is the hydrogen pressure change rate of the hydrogen energy module, is the time interval of pressure change of hydrogen energy module, is the temperature rise of the hydrogen reactor of the hydrogen energy module, The maximum temperature allowed for the hydrogen reactor of the hydrogen energy module, and is the safety weight coefficient; ; is the stress change risk weight, For temperature rise risk weight, in real-time operation and Can be dynamically optimized according to environmental conditions; if the risk of pressure changes dominates, increase To prioritize the response to pressure change risk; if the temperature rise risk is more critical, increase To enhance sensitivity to temperature rise; and Determine the weight ratio through actual testing or simulation: Step 1: Collect the pressure change rate under different working conditions ( ) and temperature rise data ( ); Step 2: Analyze historical fault data to determine the impact of both on system safety; Step 3: Fitting by regression analysis or optimization algorithm and , so that the risk score matches the actual failure probability.

[0019] , , , It is a dynamic weight coefficient, which is adjusted in real time through the fuzzy logic rule base and deep neural network; The objective function J The constraints are as follows: The total output power of the hydrogen energy module and the battery module shall not be less than the power required by the UAV; The SOC range is limited to 20% to 80%; The hydrogen reactor temperature of the hydrogen energy module does not exceed 80°C; No more than 10% per second.

[0020] The energy management unit dynamically allocates the output ratio of the hydrogen energy module and the battery module during the UAV flight phase, specifically: Takeoff phase: The battery module provides 80% of the required power, and the hydrogen energy module provides 20% of the required power; Cruising phase: The hydrogen energy module provides 90% of the required power and charges the battery module, with the charging power accounting for 10% of the required power; Landing phase: The hydrogen energy module provides 70% of the required power, and the battery module recovers the energy corresponding to 30% of the required power (recovery efficiency is 85%).

[0021] The hydrogen energy module includes an air charging valve, an air release unit, an air transmission unit, a reaction unit and a hydrogen storage tank; the hydrogen storage tank and the reaction unit are both installed in the composite energy warehouse; the hydrogen storage tank is provided with an air discharge unit; the hydrogen storage tank is connected to the reaction unit through the air transmission unit; the air charging valve is connected to the hydrogen storage tank and passes through the surface of the composite energy warehouse; The deflation unit includes a deflation pipe and an intelligent deflation valve; one end of the deflation pipe is connected to the hydrogen storage tank, and the other end passes through the surface of the composite energy warehouse; the deflation pipe is equipped with an intelligent deflation valve; The gas transmission unit includes a pressure sensor, an intelligent gas transmission valve and a gas transmission pipeline; One end of the gas transmission pipeline is connected to the hydrogen storage tank, and the other end is connected to the reaction unit; The gas pipeline is equipped with pressure sensors and intelligent gas valves; The reaction unit includes a hydrogen reactor and a DC-DC converter; the hydrogen reactor is connected to the battery module through the DC-DC converter; the composite energy compartment is provided with heat dissipation holes on the side of the hydrogen reactor to facilitate heat dissipation; The intelligent air release valve, pressure sensor, intelligent gas transmission valve, hydrogen reactor and battery module are all communicatively connected to the central control module; 35MPa carbon fiber wrapped bottle, volume 2.6L, diameter 80mm, length 300mm, with pressure warning sign on the surface; in, Hydrogen storage tank: 35MPa carbon fiber wrapped bottle, volume 2.6L, diameter 80mm, length 300mm, with pressure warning sign on the surface; Deflating unit: includes a deflating pipe (inner diameter 5mm) and an intelligent deflating valve (response time ≤50ms) for emergency pressure relief; Gas transmission unit: gas transmission pipeline (pressure resistance 40MPa), pressure sensor (accuracy ±0.1MPa) and intelligent gas transmission valve (flow adjustment range 0-5L / min); Reaction unit: The hydrogen reactor adopts a proton exchange membrane fuel cell stack (rated power 2000W, efficiency ≥50%), equipped with a DC-DC converter (conversion efficiency ≥95%).

[0022] Among them, the battery module is a lithium polymer battery pack, which is equipped with a battery management system connected to the energy management unit; the lithium polymer battery pack: capacity 20000mAh (6S, voltage 22.2V), flat square design (200mm×150mm×30mm), maximum continuous discharge rate 15C, and voltage, temperature and SOC are monitored by the battery management system (BMS).

[0023] The energy management unit runs a multi-objective optimization algorithm in real time through a microcontroller, specifically an STM32F7 series, which interacts with a CAN bus communication module with a response delay of no more than 10 milliseconds. The ground station software records energy supply data and transmits it back to the cloud for continuous training of the neural network model and optimization of the rule base. The microcontroller uses STM32F767IGT6 with a main frequency of 216MHz. It communicates with sensors through the CAN bus (baud rate 1Mbps) with a response delay of ≤10m. In addition, it uses a 4G / 5G dual-mode communication module to support cloud streaming and remote command reception. The ground station software displays the remaining hydrogen, reactor temperature, battery SOC and flight trajectory in real time, supporting mission planning and secondary development.

[0024] Wherein, the fault diagnosis unit includes: Anomaly detection algorithms, based on support vector machines or random forest models, analyze hydrogen pressure, reactor temperature, and battery voltage data in the hydrogen energy module and battery module. This algorithm, primarily based on support vector machine (SVM) models, analyzes hydrogen pressure (sampling frequency 100Hz), reactor temperature (±0.5°C accuracy), and battery voltage data in real time. Fault-tolerant control strategy: when the hydrogen energy module fails, it switches to the battery module for independent power supply and reduces the drone load to less than 12 kg; when the battery module fails, it switches to full power output of the hydrogen energy module and limits maneuvering movements.

[0025] Among them, the fault diagnosis unit integrates a hydrogen leak detection sensor, specifically a MEMS hydrogen-sensitive sensor, and a distributed battery temperature monitoring node. The sampling frequency is not less than 100 Hz, and the abnormality judgment threshold is dynamically calibrated through a machine learning model.

[0026] Among them, the deep neural network model is deployed based on the TensorFlow Lite framework. The input layer contains 20-dimensional feature parameters, including the hydrogen flow in the hydrogen energy module and battery module, the remaining battery power and the ambient temperature. The output layer is the energy supply ratio weight. The model update cycle does not exceed 24 hours.

[0027] Among them, the drone or composite energy warehouse is equipped with a standardized quick-release interface to support the rapid replacement of the optoelectronic pod, cargo compartment or spraying device, and the power consumption data of the mission module is fed back to the energy management unit in real time for dynamic adjustment of the energy supply strategy.

[0028] In the present invention, the drone uses a composite energy synergistic power supply mechanism to significantly improve the drone's endurance, specifically: Hydrogen energy module: The hydrogen storage tank (35MPa carbon fiber wrapped bottle) stores high-pressure hydrogen and transmits it to the proton exchange membrane fuel cell stack (rated power 2000W) through the gas transmission unit (pressure sensor, smart valve); Hydrogen fuel cells generate direct current through electrochemical reactions (H2+O2→H2O+electricity) and output it stably through a DC-DC converter (efficiency ≥ 95%) to provide continuous power for drones. Battery Module: A lithium polymer battery pack (20,000 mAh, 15C discharge) serves as an auxiliary energy source, supporting instantaneous high power demands (such as takeoff and maneuvering). The battery management system (BMS) monitors voltage, temperature, and SOC in real time. Central control module: Energy management unit: Runs a multi-objective optimization algorithm to dynamically allocate the energy supply ratio of hydrogen fuel and lithium batteries: Takeoff phase: lithium batteries provide 80% of the power (high-rate discharge), and hydrogen fuel provides 20%; Cruising phase: Hydrogen fuel provides 90% of the power (efficient and stable output) and charges the lithium battery (10% of the power); Landing phase: Hydrogen fuel provides 70% of the power, and lithium batteries recover 30% of the energy (through the motor's back electromotive force, with a recovery efficiency of 85%). The present invention runs a multi-objective optimization algorithm to improve and optimize the dynamic performance of the UAV. The algorithm objective function J Defined as: ; Maximum improvement in overall energy efficiency ( ), give priority to the energy supply combination with the highest overall efficiency; Battery life protection ( ), limit the charge and discharge rate, avoid high temperature and overcharge / overdischarge; Load Balancing ), smoothing hydrogen reactor power fluctuations, i.e. limiting hydrogen reactor power fluctuations (standard deviation / mean ≤ 10%), extending fuel cell life by more than 30%; Safety Risk Control ( ), real-time monitoring of pressure mutations and temperature rise, and dynamic adjustment of safety weight coefficients; , , , Dynamic weight coefficients are adjusted in real time through fuzzy logic rule base and deep neural network to adapt to complex environments (such as high temperature and high pressure fluctuations); The reliability of the present invention is enhanced, and the specific configurations include: Fault diagnosis unit: Based on the support vector machine (SVM) model, it analyzes hydrogen pressure, reactor temperature, and battery status in real time, and triggers fault-tolerant control (such as switching energy sources and limiting loads) when an abnormality occurs.

[0029] Example 1: Long-duration power line inspection mission: Scenario description: A power company needed to conduct a three-hour continuous inspection of high-voltage transmission lines in a mountainous area. This required a drone with long-duration flight capabilities and the ability to transmit high-definition image data in real time. Implementation details Drone configuration: Hydrogen energy module: The hydrogen storage tank (35MPa, 2.6L) provides the main energy source, and the fuel cell stack power is 2000W; Battery module: lithium polymer battery pack (20000mAh) as auxiliary energy source; Mission module: equipped with a 4K electro-optical pod (50W power consumption) and a laser radar (30W power consumption); Energy distribution strategy: Cruising phase: The hydrogen energy module provides 90% power (1800W) and the lithium battery charges 10% (200W); Sudden climb (altitude adjustment required in case of strong wind): lithium battery instantly replenishes 80% of power requirement (1600W), hydrogen fuel provides 20% (400W); Performance data: Endurance: 3.2 hours (after the hydrogen fuel is exhausted, the lithium battery can independently power the aircraft for 5 minutes to complete the landing); Energy efficiency: overall efficiency , an improvement of 15% compared to a single hydrogen fuel system; Fault response: During inspection, abnormal temperature rise of hydrogen reactor was detected ( ), the fault diagnosis unit switches to lithium battery power supply within 2 seconds to ensure the completion of the task.

[0030] Example 2: Emergency relief supplies delivery: Scenario Description Roads in a disaster area were blocked, and a drone was needed to quickly deliver medical supplies (10kg payload). The drone was required to take off, fly, and deliver the supplies accurately within a short timeframe. Implementation details: Drone configuration: Standardized quick-release interface for mounting cargo compartment (total load 12kg); Powertrain: Four electric motors with a total power of 6.1kW (peak); Energy distribution strategy: Takeoff: Lithium batteries provide 80% power (4880W), and hydrogen fuel provides 20% (1220W); Cruise phase: Hydrogen fuel provides 90% power (5490W), lithium battery charges 10% (610W); Landing phase: Hydrogen fuel provides 70% of the power (4270W), and lithium batteries recover 30% of the energy; Performance data: Mission time: 25 minutes in total (including 10km round trip); Dynamic response: The lithium battery achieves 15C discharge during takeoff to meet instantaneous power requirements; Safety redundancy: Hydrogen pressure drops suddenly during delivery ( ), the central control module system automatically limits the hydrogen fuel output and switches to the lithium battery full power mode.

[0031] Comparative Example 1: Traditional lithium battery drone performs the same task: Scenario description: A drone powered by a single lithium battery (with a capacity of 20,000 mAh) was used to perform the power line inspection task of Example 1. Implementation details: Energy configuration: It relies solely on lithium batteries for power supply and has no hydrogen fuel system; Mission module: Same 4K electro-optical pod and lidar; Performance data: Flight time: After 1.1 hours, the battery power dropped to 20% and was forced to return; Efficiency drawback: During continuous high-power flight, the battery temperature rises to 60°C, triggering BMS protection and forcing frequency reduction. Failure risk: There is no fault tolerance mechanism, and the drone may lose control and crash after the battery is over-discharged.

[0032] Comparative Analysis

[0033] Conclusion: The present invention significantly improves endurance, dynamic performance and system reliability through hydrogen-electric synergistic energy supply and intelligent optimization algorithm, and is suitable for complex mission scenarios.

[0034] This invention solves the pain points of traditional drones such as short flight time, poor dynamic performance, and low reliability through the intelligent collaboration of hydrogen fuel and lithium batteries, multi-objective optimization algorithm and modular design. It is suitable for complex scenarios such as power inspection, agricultural plant protection, and emergency disaster relief. It is efficient, safe, and environmentally friendly, and has significant technical advantages and market competitiveness.

[0035] It should be noted that the computer-readable medium described in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0036] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0037] The modules described in the embodiments of the present application may be implemented in software or hardware. The modules described may also be provided in a processor. For example, they may be described as: a processor including a determination module, an extraction module, a training module, and a screening module. The names of these modules do not, in some cases, limit the modules themselves. For example, the determination module may also be described as a "module for determining a candidate user set."

[0038] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0039] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A composite energy collaborative power supply UAV, comprising a UAV fuselage, the fuselage being equipped with a composite energy compartment, the interior of which is integrated with: The hydrogen energy module is used to generate electricity through electrochemical reaction between the input hydrogen and oxygen in the air; The battery module is connected to the hydrogen energy module to store electrical energy and power the drone; Its characteristics are: It also integrates a central control module, which is connected to the battery module and hydrogen energy module, and integrates: an energy management unit configured to run a multi-objective optimization algorithm and dynamically allocate the output ratio of the hydrogen energy module and the battery module according to the flight phase of the UAV; The fault diagnosis unit is configured to detect the operating status of the hydrogen energy module and the battery module based on sensor data, and perform abnormal warning and fault-tolerant control.

2. The composite energy collaborative power supply UAV according to claim 1, characterized in that: The multi-objective optimization algorithm is run, and its objective function J Defined as: ； in: For the comprehensive energy efficiency of hydrogen energy module and battery module, , is the total output power of the UAV, Input power to the hydrogen energy module, Input power to the battery module; is the battery life protection factor of the battery module, , SOC is the remaining battery capacity of the battery module, is the battery temperature of the battery module; is the hydrogen reactor load balancing factor of the hydrogen energy module, , is the power fluctuation standard deviation of the hydrogen energy module, is the average power of the hydrogen energy module; is a safety risk factor, , is the hydrogen pressure change rate of the hydrogen energy module, is the time interval of pressure change of hydrogen energy module, is the temperature rise of the hydrogen reactor of the hydrogen energy module, The maximum temperature allowed for the hydrogen reactor of the hydrogen energy module, and is the safety weight coefficient; , , , It is a dynamic weight coefficient, which is adjusted in real time through the fuzzy logic rule base and deep neural network.

3. The composite energy collaborative power supply UAV according to claim 2, characterized in that: The objective function J The constraints are as follows: The total output power of the hydrogen energy module and the battery module shall not be less than the power required by the UAV; The SOC range is limited to 20% to 80%; The hydrogen reactor temperature of the hydrogen energy module does not exceed 80°C; No more than 10% per second.

4. The composite energy collaborative power supply UAV according to claim 1, characterized in that: The energy management unit dynamically allocates the output ratio of the hydrogen energy module and the battery module during the UAV flight phase, specifically: Takeoff phase: The battery module provides 80% of the required power, and the hydrogen energy module provides 20% of the required power; Cruising phase: The hydrogen energy module provides 90% of the required power and charges the battery module, with the charging power accounting for 10% of the required power; Landing phase: The hydrogen energy module provides 70% of the required power, and the battery module recovers energy corresponding to 30% of the required power.

5. The composite energy collaborative power supply UAV according to claim 1, characterized in that: The hydrogen energy module includes an inflation valve, an air release unit, a gas transmission unit, a reaction unit and a hydrogen storage tank; the hydrogen storage tank and the reaction unit are both installed in the composite energy warehouse; the hydrogen storage tank is provided with an air release unit; the hydrogen storage tank is connected to the reaction unit through the gas transmission unit; the inflation valve is connected to the hydrogen storage tank and passes through the surface of the composite energy warehouse; The deflation unit includes a deflation pipe and an intelligent deflation valve; one end of the deflation pipe is connected to the hydrogen storage tank, and the other end passes through the surface of the composite energy warehouse; the deflation pipe is equipped with an intelligent deflation valve; The gas transmission unit includes a pressure sensor, an intelligent gas transmission valve and a gas transmission pipeline; One end of the gas transmission pipeline is connected to the hydrogen storage tank, and the other end is connected to the reaction unit; The gas pipeline is equipped with pressure sensors and intelligent gas valves; The reaction unit includes a hydrogen reactor and a DC-DC converter; the hydrogen reactor is connected to the battery module via the DC-DC converter; The intelligent air release valve, pressure sensor, intelligent gas transmission valve, hydrogen reactor and battery module are all communicatively connected with the central control module.

6. The composite energy collaborative power supply UAV according to claim 1, characterized in that: The battery module is a lithium polymer battery pack, which is equipped with a battery management system connected to an energy management unit.

7. The composite energy collaborative power supply UAV according to claim 1, characterized in that: The energy management unit runs a multi-objective optimization algorithm in real time through a microcontroller. The microcontroller is specifically an STM32F7 series, which interacts with the CAN bus communication module. The response delay does not exceed 10 milliseconds, and the ground station software records the energy supply data and transmits it back to the cloud for continuous training of the neural network model and optimization of the rule base.

8. The composite energy collaborative power supply UAV according to claim 1, characterized in that: The fault diagnosis unit includes: Anomaly detection algorithms, based on support vector machines or random forest models, analyze hydrogen pressure, reactor temperature, and battery voltage data in the hydrogen energy module; Fault-tolerant control strategy: when the hydrogen energy module fails, it switches to the battery module for independent power supply and reduces the drone load to less than 12 kg; when the battery module fails, it switches to full power output of the hydrogen energy module and limits maneuvering movements.

9. The composite energy collaborative power supply UAV according to claim 1, characterized in that: The fault diagnosis unit integrates a hydrogen leak detection sensor, specifically a MEMS hydrogen-sensitive sensor, and a distributed battery temperature monitoring node. The sampling frequency is not less than 100 Hz, and the abnormality judgment threshold is dynamically calibrated through a machine learning model.

10. The composite energy collaborative power supply UAV according to claim 1, characterized in that: The deep neural network model is deployed based on the TensorFlow Lite framework. The input layer contains 20-dimensional feature parameters, including the hydrogen flow rate in the hydrogen energy module and battery module, the remaining battery power and the ambient temperature. The output layer is the energy supply ratio weight. The model update cycle does not exceed 24 hours.

Images