Intelligent multi-adaptive solar unmanned aerial vehicle energy autonomous control system

Abstract

The invention provides an intelligent multi-adaptive solar unmanned aerial vehicle energy autonomous control system, and relates to the technical field of unmanned aerial vehicle charging and discharging control, and the system comprises a solar energy collection module, an energy storage module, an energy conversion module, a load power supply module, an environment sensing module, a flight state monitoring module, an intelligent decision module, and a control execution module. The solar energy acquisition module is electrically connected with the energy conversion module and is used for acquiring solar energy and outputting direct-current electric energy; the energy conversion module is electrically connected with the energy storage module and the load power supply module and used for converting electric energy voltage and distributing electric energy. The invention provides an intelligent multi-adaptive solar unmanned aerial vehicle energy autonomous control system for solving the problem of insufficient energy collection adaptability in an existing solar unmanned aerial vehicle energy management system, and the energy collection adaptability of the solar unmanned aerial vehicle is improved through a posture adjustment mechanism and a state monitoring unit in a solar collection module in combination with an adjustment instruction of a control execution module. And real-time dynamic adjustment of the attitude angle of the solar cell array is realized.

Description

Technical Field

[0001] This invention relates to the field of drone charging and discharging control technology, specifically to an intelligent multi-adaptive solar-powered drone energy autonomous control system. Background Technology

[0002] With the expanding applications of solar-powered drones in long-endurance reconnaissance, environmental monitoring, and disaster relief, higher demands are being placed on energy management systems. In particular, continuous power supply under complex weather conditions, energy optimization during dynamic flight, and improved system reliability have become key industry focuses. For example, high-altitude reconnaissance requires stable solar energy harvesting to support hours of flight, urban patrols need to adapt to fluctuations in sunlight to maintain sensor power, and forest rescue requires efficient energy storage to cope with low-light environments. Currently, solar-powered drone energy technology is widely used in photovoltaic cell integration and basic energy conversion circuits.

[0003] However, existing solar-powered drone energy management systems face the following key technical challenges in meeting these requirements:

[0004] The energy harvesting system lacks adaptability. Traditional systems mostly use fixed-position solar panels, which cannot adjust the angle in real time according to changes in sunlight. This results in low harvesting efficiency under cloudy or low-light conditions, with an average utilization rate of only 60%-70%, which is difficult to meet the requirements of long-term autonomous flight.

[0005] The energy storage and distribution mechanism is simple. Existing models usually rely on a single battery cell and fixed conversion parameters, without intelligent prediction and switching functions. When the flight status fluctuates, overcharging or undercharging is prone to occur, resulting in decreased system stability and a false alarm or interruption rate as high as 15%.

[0006] The lack of integrated environmental and state decision-making means that existing control methods are mostly passive and reactive, such as simple threshold triggering. They cannot integrate multi-source data for forward-looking optimization, resulting in an overall energy loss rate of over 10%, which limits the reliability and endurance of drones in dynamic environments.

[0007] Therefore, an intelligent, multi-adaptive, solar-powered drone energy autonomous control system is needed to solve the above problems. Summary of the Invention

[0008] Technical problems to be solved

[0009] To address the shortcomings of existing technologies, this invention provides an intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system, which solves the problems mentioned in the background technology.

[0010] Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solution: an intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system, comprising a solar energy acquisition module, an energy storage module, an energy conversion module, a load power supply module, an environmental perception module, a flight status monitoring module, an intelligent decision-making module, and a control execution module;

[0012] The solar energy acquisition module is electrically connected to the energy conversion module and is used to collect solar energy and output DC power.

[0013] The energy conversion module is electrically connected to the energy storage module and the load power supply module respectively, and is used to convert electrical voltage and distribute electrical energy.

[0014] The environmental perception module is data-connected to the intelligent decision-making module and is used to collect environmental data and transmit it to the intelligent decision-making module.

[0015] The flight status monitoring module is connected to the intelligent decision-making module for collecting flight status data and transmitting it to the intelligent decision-making module.

[0016] The intelligent decision-making module is connected to the control execution module and is used to generate an adaptive control strategy based on the received environmental data and flight status data using a reinforcement learning algorithm and transmit the instructions.

[0017] The control execution module is connected to the solar energy acquisition module, energy conversion module, energy storage module, and load power supply module respectively. It is used to execute adaptive control strategies to adjust the working status of each module and realize closed-loop autonomous control of energy acquisition, conversion, storage and power supply.

[0018] Preferably, the solar energy acquisition module includes a solar cell array, an attitude adjustment mechanism, and a status monitoring unit;

[0019] The solar cell array is mechanically connected to the attitude adjustment mechanism to convert solar energy into direct current and output it to the energy conversion module via an electrical connection.

[0020] The attitude adjustment mechanism is connected to the control execution module and is used to receive adjustment commands from the adaptive control strategy to adjust the attitude angle of the solar cell array to optimize the light reception efficiency.

[0021] The condition monitoring unit is connected to the solar cell array sensors to monitor voltage, current and temperature data in real time, and transmits the data to the control execution module to support attitude adjustment decisions.

[0022] Preferably, the attitude adjustment mechanism includes a rotating gimbal, a drive motor, and an angle sensor;

[0023] The rotating gimbal is fixedly connected to the solar cell array and is used to support and rotate the solar cell array;

[0024] The drive motor is connected to the rotating gimbal and is used to provide rotational torque according to the instructions of the control execution module to adjust the attitude angle;

[0025] An angle sensor is connected to the rotating gimbal to detect the current attitude angle and transmit it to the control execution module via feedback, forming a closed-loop control for attitude adjustment.

[0026] Preferably, the energy storage module includes a main battery unit, a backup battery unit, a status monitoring unit, and a switching circuit;

[0027] The main battery unit is connected to the energy conversion module for charging and storing electrical energy;

[0028] The backup battery unit is connected to the energy conversion module for charging and storing electrical energy;

[0029] The status monitoring unit is connected to the sensors of the main battery unit and the backup battery unit respectively, and is used to collect voltage, current and temperature data and transmit them to the control execution module through the data connection;

[0030] The switching circuit is electrically connected to the main battery unit, the backup battery unit, and the load power supply module, respectively, and is used to switch the power supply under the command of the control execution module to achieve seamless switching between the main battery unit and the backup battery unit.

[0031] Preferably, the energy conversion module includes a DC-DC converter, a conversion controller, and an efficiency monitoring unit;

[0032] The DC-DC converter is connected to the input of the solar energy acquisition module to convert the input DC power into the target voltage and output it to the energy storage module or load power supply module via electrical connection.

[0033] The conversion controller is connected to the control execution module and is used to receive adjustment instructions from the adaptive control strategy to modify the conversion parameters;

[0034] The efficiency monitoring unit is connected to the DC-DC converter sensor to monitor the conversion efficiency and feed the data back to the control execution module to achieve dynamic optimization of the conversion parameters.

[0035] Preferably, the intelligent decision-making module includes a data fusion unit, an energy prediction unit, and a strategy generation unit;

[0036] The data fusion unit is connected to the environmental perception module and the flight status monitoring module respectively, and is used to integrate environmental data and flight status data to form a unified dataset and transmit it to the energy prediction unit through an internal data stream.

[0037] The energy prediction unit and the data fusion unit are connected by an internal data stream. This is used to analyze a unified dataset and predict energy demand and environmental changes using a long short-term memory network algorithm. The prediction results are then transmitted to the strategy generation unit via the internal data stream.

[0038] The strategy generation unit is connected to the energy prediction unit via internal data flow. It is used to generate an adaptive control strategy based on the prediction results using a genetic algorithm, and then transmits the strategy to the control execution module via an instruction connection.

[0039] Preferably, the control execution module includes a data acquisition control unit, a conversion control unit, a storage control unit, and a power supply control unit;

[0040] The data acquisition and control unit is connected to the solar energy acquisition module and is used to execute attitude adjustment commands in the adaptive control strategy;

[0041] The conversion control unit is connected to the energy conversion module and is used to execute conversion parameter adjustment commands in the adaptive control strategy;

[0042] The storage control unit is connected to the energy storage module and is used to execute storage switching commands in the adaptive control strategy;

[0043] The power supply control unit is connected to the load power supply module and is used to execute the power distribution instructions in the adaptive control strategy;

[0044] The data acquisition control unit, conversion control unit, storage control unit, and power supply control unit are connected to the internal bus of the intelligent decision module to receive adaptive control strategy instructions and provide feedback on the execution status, thereby coordinating the control flow and data flow.

[0045] Preferably, the control method corresponding to the system includes the following steps:

[0046] S1. The environmental perception module collects environmental data and transmits it to the data fusion unit of the intelligent decision-making module through a data connection; the flight status monitoring module collects flight status data and transmits it to the data fusion unit through a data connection.

[0047] S2. The data fusion unit integrates environmental data and flight status data to form a unified dataset and transmits it to the energy prediction unit through an internal data stream. The energy prediction unit uses a long short-term memory network algorithm to analyze the unified dataset and predict energy demand and environmental changes. The prediction results are transmitted to the strategy generation unit through an internal data stream. The strategy generation unit uses a genetic algorithm to generate an adaptive control strategy based on the prediction results and transmits it to the control execution module through an instruction connection.

[0048] S3. The acquisition control unit of the control execution module executes an adaptive control strategy to adjust the attitude of the solar energy acquisition module, and the conversion control unit executes an adaptive control strategy to adjust the parameters of the energy conversion module.

[0049] S4. The storage control unit of the control execution module executes an adaptive control strategy based on the data fed back by the status monitoring unit of the energy storage module, allocating electrical energy to the energy storage module for storage or directly to the load power supply module.

[0050] S5, the status monitoring unit of the energy storage module collects data and feeds it back to the intelligent decision-making module through data connection, so as to realize the dynamic adjustment of the adaptive control strategy and the autonomous energy control.

[0051] Preferably, in step S3, the acquisition control unit, based on the light prediction data in the adaptive control strategy, controls the drive motor of the attitude adjustment mechanism to rotate the gimbal, while the angle sensor transmits the current attitude angle data to the control execution module through a feedback connection, forming a closed-loop control to maximize the solar energy acquisition efficiency.

[0052] Preferably, in step S4, the storage control unit receives voltage and temperature data transmitted by the status monitoring unit through the data connection, combines it with the energy demand prediction information in the adaptive control strategy, and activates the switching circuit through the control connection to switch between the main battery unit and the backup battery unit. At the same time, the power supply control unit adjusts the output ratio of the load power supply module through the control connection to achieve energy distribution optimization.

[0053] Beneficial effects

[0054] This invention provides an intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system. It has the following beneficial effects:

[0055] 1. This invention addresses the problem of insufficient energy harvesting adaptability in existing solar-powered drone energy management systems by providing an intelligent multi-adaptive solar-powered drone energy autonomous control system. Through the attitude adjustment mechanism and status monitoring unit in the solar energy harvesting module, combined with the adjustment commands of the control execution module, the system can realize real-time dynamic adjustment of the attitude angle of the solar cell array. This enables the system to adaptively optimize the receiving efficiency according to changes in illumination, thereby significantly improving the stability and continuity of energy harvesting under complex conditions such as cloudy or low light conditions, and meeting the needs of long-term autonomous flight.

[0056] 2. This invention addresses the problem of the single energy storage and distribution mechanism in existing solar-powered drone energy management systems. By combining the main battery unit, backup battery unit, status monitoring unit, and switching circuit in the energy storage module with the conversion controller and efficiency monitoring unit in the energy conversion module, seamless switching between the main and backup batteries and dynamic modification of conversion parameters are achieved. This enables the system to avoid overcharging or undercharging when flight status fluctuates, improves the overall system stability and power supply reliability, and reduces the risk of interruption.

[0057] 3. This invention addresses the problem of the lack of environmental and state fusion decision-making in existing solar-powered drone energy management systems. By integrating the data fusion unit, energy prediction unit, and strategy generation unit in the intelligent decision-making module, reinforcement learning algorithm, long short-term memory network algorithm, and genetic algorithm to generate adaptive control strategies from multi-source data, it achieves forward-looking optimization and closed-loop autonomous control, thereby reducing overall energy loss and improving the reliability and endurance of drones in dynamic environments. Attached Figure Description

[0058] Figure 1 This is a system framework diagram of the present invention;

[0059] Figure 2 This is a system flowchart of the present invention;

[0060] Figure 3 This is a schematic diagram of the system of the present invention in a static state;

[0061] Figure 4 This is a schematic diagram of the interface during system operation according to the present invention. Detailed Implementation

[0062] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Specific Implementation Example 1:

[0064] like Figures 1-4 As shown, this is an intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system. This system aims to achieve autonomous management of energy harvesting, conversion, storage, and power supply for solar-powered UAVs, in order to cope with energy fluctuations in complex flight environments and ensure long-term autonomous flight. The system includes a solar energy harvesting module, an energy storage module, an energy conversion module, a load power supply module, an environmental perception module, a flight status monitoring module, an intelligent decision-making module, and a control execution module.

[0065] The solar energy harvesting module and the energy conversion module are connected via an electrical connection (such as copper wires or dedicated cables) to collect solar energy and convert it into direct current (DC) electricity. Specifically, the solar energy harvesting module receives solar radiation, generates DC electricity through the photovoltaic effect, and outputs it to the energy conversion module via the electrical connection. The core function of this module is to maximize solar energy utilization and avoid energy waste.

[0066] The energy conversion module is electrically connected (e.g., via a power line) to both the energy storage module and the load power supply module. It converts electrical voltage and distributes electrical energy. The energy conversion module receives DC power from the solar energy harvesting module, adjusts the voltage level according to system requirements (e.g., reducing from high to low voltage or vice versa), and distributes the converted energy to the energy storage module for storage or directly to the load power supply module for use by the drone's payload (e.g., motors, sensors). This module ensures efficient power transmission and matching, avoiding losses caused by voltage mismatch.

[0067] The environmental sensing module and the intelligent decision-making module are connected via a data link (such as a serial bus or wireless data link) to collect environmental data (such as light intensity, wind speed, temperature, humidity, etc.) and transmit it to the intelligent decision-making module. The specific data collection process involves integrating sensors (such as light sensors, anemometers, temperature and humidity sensors) to sample environmental parameters in real time and send them to the intelligent decision-making module in the form of digital signals through the data link to provide external environmental information to support decision-making.

[0068] The flight status monitoring module and the intelligent decision-making module are connected via a data link (such as CAN bus or Ethernet) to collect flight status data (such as UAV speed, altitude, attitude angle, power consumption, etc.) and transmit it to the intelligent decision-making module. Specifically, the data collection process uses built-in sensors (such as an IMU inertial measurement unit, GPS module, and power meter) to continuously monitor the UAV's dynamic parameters and transmit data packets to the intelligent decision-making module via the data link to reflect the UAV's real-time operating status.

[0069] The intelligent decision-making module is connected to the control execution module via an instruction connection (such as a digital command bus). It generates adaptive control strategies based on received environmental and flight status data using reinforcement learning algorithms and transmits the commands. The intelligent decision-making module first integrates the input data, then applies a reinforcement learning algorithm (such as Q-learning or a variant of Deep Q-Network) to learn and optimize the strategy through a state-action-reward mechanism. This algorithm uses environmental and flight status data as state inputs, calculates actions (such as attitude adjustment or switching storage), and iteratively optimizes based on a reward function (such as maximizing energy efficiency), ultimately generating an adaptive control strategy (such as attitude adjustment commands, parameter setting conversions, etc.), which is then transmitted to the control execution module via the instruction connection. The core of this module is to achieve intelligent adaptability of the system, ensuring that the strategy dynamically adjusts with changes in the environment.

[0070] The control execution module is connected to the solar energy acquisition module, energy conversion module, energy storage module, and load power supply module via control connections (such as PWM signal lines or digital control interfaces). It executes adaptive control strategies to adjust the operating states of each module, achieving closed-loop autonomous control of energy acquisition, conversion, storage, and power supply. Specifically, the control execution module receives strategy instructions, parses and distributes them to the corresponding sub-units, adjusts module parameters in real time (such as adjusting the solar energy acquisition angle, conversion voltage, storage switching, and power supply allocation), and verifies the execution effect through feedback loops (such as obtaining data from the status monitoring unit), forming a closed-loop control. This closed loop ensures that the system prioritizes energy storage when energy is insufficient and directly supplies power when energy is sufficient, achieving overall autonomy.

[0071] The solar energy harvesting module includes a solar cell array, an attitude adjustment mechanism, and a status monitoring unit. The solar cell array and attitude adjustment mechanism are connected mechanically (e.g., by bolts or brackets) to convert solar energy into direct current (DC) power, which is then output to the energy conversion module via an electrical connection. The array consists of multiple photovoltaic cell units, using monocrystalline or polycrystalline silicon materials, arranged in series and parallel for efficient conversion. The output voltage is typically in the range of 12V-48V, and the power is transmitted via an electrical connection (e.g., a DC power line).

[0072] The attitude adjustment mechanism is connected to the control execution module via a control connection (such as a servo control line) to receive adjustment commands from the adaptive control strategy and adjust the attitude angle of the solar cell array to optimize light reception efficiency. Specifically, the attitude adjustment mechanism calculates the target angle (e.g., perpendicular to sunlight) based on the command, drives the mechanical components to rotate the array, and optimizes the incident angle to improve conversion efficiency by more than 20%.

[0073] The condition monitoring unit is connected to the solar array via sensors (such as voltage / current probes and thermistors) to monitor voltage, current, and temperature data in real time. This data is then transmitted to the control execution module via a data connection (such as an I2C bus) to support attitude adjustment decisions. The monitoring process involves periodic sampling (e.g., 10 times per second), and the data includes output voltage (in V), current (in A), and temperature (in °C). After transmission, this data is used as algorithm input to prevent overheating or inefficient operation.

[0074] The attitude adjustment mechanism includes a gimbal, a drive motor, and an angle sensor. The gimbal is connected to the solar array via a fixed connection (such as welding or clips) and is used to support and rotate the solar array. The gimbal adopts a dual-axis or tri-axis design, supports horizontal and vertical rotation, and can support a weight of over 5 kg.

[0075] The drive motor is connected to the rotating gimbal via a transmission connection (such as gears or belts) and is used to provide rotational torque according to the instructions of the control execution module to adjust the attitude angle. The specific driving process is as follows: the motor receives a PWM signal, generates torque (such as 0.5-2Nm), and drives the gimbal to rotate to a specified angle with an accuracy of 0.1 degrees.

[0076] An angle sensor is connected to the rotating gimbal via a connection (such as integrated installation) to detect the current attitude angle and transmit it to the control execution module via a feedback connection (such as an analog signal line) to form a closed-loop control for attitude adjustment. The specific feedback process is as follows: the sensor (such as an encoder or gyroscope) outputs angle data (such as 0-360 degrees) in real time, the control execution module compares the target angle with the actual angle, adjusts the motor commands, and realizes PID closed-loop control.

[0077] The energy storage module includes a main battery unit, a backup battery unit, a status monitoring unit, and a switching circuit. The main battery unit is connected to the energy conversion module via a charging connection (such as a charging circuit board) and is used to store electrical energy. This unit uses a lithium-ion battery with a capacity of, for example, 100Wh, supports fast charging, and has a storage efficiency of >95%.

[0078] The backup battery unit is connected to the energy conversion module via a charging connection and is used to store electrical energy. This unit uses a supercapacitor or a backup lithium battery, with a capacity of, for example, 50Wh, for emergency replenishment.

[0079] The status monitoring unit is connected to the main battery unit and the backup battery unit via sensors (such as voltage dividers, current transformers, and NTC thermistors) to collect voltage, current, and temperature data, which is then transmitted to the control execution module via a data connection (such as an SPI bus). Specifically, the data is collected once per minute, with data ranges such as voltage 3.7-4.2V, current 0-10A, and temperature -20-60℃, for health assessment.

[0080] The switching circuit is electrically connected (e.g., to the main battery unit, backup battery unit, and load power supply module) to the main battery unit, backup battery unit, and load power supply module respectively. It is used to switch power supplies under the command of the control execution module, achieving seamless switching between the main battery unit and backup battery unit. The specific switching process is as follows: according to the command (e.g., digital high / low level), the circuit disconnects one unit and connects to another, with a switching time of <1ms, avoiding power interruption.

[0081] The energy conversion module includes a DC-DC converter, a conversion controller, and an efficiency monitoring unit. The DC-DC converter is connected to the solar energy harvesting module via an input connection (such as an input terminal) to convert the input DC power into a target voltage and output it to the energy storage module or load power supply module via an electrical connection. This converter adopts a buck-boost topology, supports a wide input range (such as 5-60V), outputs a stable voltage such as 12V, and has an efficiency >90%.

[0082] The conversion controller and the control execution module are connected via a control connection (such as a GPIO interface) to receive adjustment instructions from the adaptive control strategy to modify conversion parameters (such as duty cycle and frequency). The specific modification process is as follows: the controller parses the instructions, adjusts the PWM signal, and achieves dynamic voltage / current matching.

[0083] The efficiency monitoring unit is connected to the DC-DC converter via a sensor (such as a power metering chip) to monitor the conversion efficiency and feed the data back to the control execution module, enabling dynamic optimization of the conversion parameters. Specifically, the monitoring process involves calculating the input / output power ratio (e.g., efficiency = output power / input power), and using the feedback data for algorithm optimization to reduce losses.

[0084] The intelligent decision-making module includes a data fusion unit, an energy prediction unit, and a strategy generation unit. The data fusion unit is connected to the environmental perception module and the flight status monitoring module via data links. It integrates environmental data and flight status data to form a unified dataset and transmits it to the energy prediction unit via internal data flow (such as memory sharing). This unit uses Kalman filtering or similar algorithms to fuse multi-source data and generate a standardized dataset (such as in vector form).

[0085] The energy prediction unit and the data fusion unit are connected via an internal data stream. The fusion unit uses a Long Short-Term Memory (LSTM) network algorithm to analyze a unified dataset and predict energy demand and environmental changes. The prediction results are then transmitted to the policy generation unit via the internal data stream. Specifically, the LSTM model takes time-series data (such as light intensity and velocity over the past hour) as input, uses a gating mechanism to capture long-term dependencies, and outputs future energy demand (power prediction for the next hour, in W) and environmental changes (such as light intensity decay rate), achieving an accuracy >85%.

[0086] The strategy generation unit and the energy prediction unit are connected via an internal data stream. The strategy generation unit uses a genetic algorithm to generate an adaptive control strategy based on the prediction results and transmits it to the control execution module via an instruction connection. The specific generation process is as follows: the genetic algorithm initializes the population (e.g., a random strategy set), iterates and optimizes it through selection, crossover, and mutation (e.g., the fitness function is energy efficiency), and outputs the optimal strategy (e.g., attitude angle = 30 degrees, conversion voltage = 24V).

[0087] The control execution module includes a data acquisition control unit, a conversion control unit, a storage control unit, and a power supply control unit. The data acquisition control unit is connected to the solar energy acquisition module via a control connection and is used to execute attitude adjustment commands in the adaptive control strategy. This unit parses the commands and generates drive signals to adjust the attitude.

[0088] The conversion control unit is connected to the energy conversion module via a control connection and is used to execute conversion parameter adjustment commands in the adaptive control strategy. This unit adjusts the converter parameters to ensure matching.

[0089] The storage control unit is connected to the energy storage module via a control connection and is used to execute storage switching commands in the adaptive control strategy. This unit controls the switching circuit to achieve primary / standby switching.

[0090] The power supply control unit is connected to the load power supply module via a control connection and is used to execute the power distribution instructions in the adaptive control strategy. This unit adjusts the output ratio, such as storing 70% and supplying 30%.

[0091] The data acquisition control unit, conversion control unit, storage control unit, and power supply control unit are connected to the intelligent decision-making module via an internal bus (such as I2C or UART) to receive adaptive control strategy commands and provide feedback on the execution status, thereby coordinating the control flow (such as command issuance) and data flow (such as status reporting). The specific coordination process involves: command transmission via the bus, followed by feedback from the unit after execution (such as success / failure) to ensure synchronization. Specific Implementation Example 2:

[0093] like Figures 1-4 As shown below, the control method of the intelligent multi-adaptive solar-powered UAV energy autonomous control system is described in detail:

[0094] This method achieves energy autonomy for solar-powered drones through closed-loop control. Specifically, it includes the following steps:

[0095] S1. The environmental perception module collects environmental data and transmits it to the data fusion unit of the intelligent decision-making module via a data connection. The flight status monitoring module collects flight status data and transmits it to the data fusion unit via a data connection. Specifically, the environmental perception module uses sensors to sample environmental parameters (such as light intensity, collected once per second, ranging from 0-1000 W / m²), forms data packets (such as JSON format), and sends them via the data connection; the flight status monitoring module samples flight parameters (such as speed, collected once every 0.5 seconds, in m / s), and also packages and transmits them to the data fusion unit. This step ensures the real-time nature and accuracy of the input data, providing a basis for subsequent decision-making.

[0096] S2. The data fusion unit integrates environmental data and flight status data to form a unified dataset, which is then transmitted to the energy prediction unit via an internal data stream. The energy prediction unit uses a long short-term memory network algorithm to analyze the unified dataset and predict energy demand and environmental changes. The prediction results are transmitted to the policy generation unit via the internal data stream. The policy generation unit uses a genetic algorithm to generate an adaptive control policy based on the prediction results and transmits it to the control execution module via a command connection. The specific fusion process is as follows: The data fusion unit uses a weighted average or sensor fusion algorithm (such as extended Kalman filtering) to merge data, forming a unified time-series dataset (e.g., in matrix form, where rows represent timestamps and columns represent parameters). The energy prediction unit inputs this dataset into an LSTM model, which includes an input gate, a forget gate, and an output gate. This model processes the sequence data to capture trends and predicts, for example, energy demand (in Wh) and environmental changes (e.g., a 10% decrease in light intensity) for the next 30 minutes. The prediction results (e.g., numerical vectors) are then transmitted to the policy generation unit. The strategy generation unit initializes the genetic algorithm population (e.g., 100 policy individuals), defines a fitness function (e.g., energy balance score), and optimizes iteratively (selecting elite individuals, crossover gene exchange, and random adjustment through mutation) to generate an adaptive control strategy (e.g., a specific instruction set). This strategy is then sent to the control execution module via an instruction connection (e.g., a serial port protocol). The core of this step is algorithm-driven prediction and optimization, ensuring the policy's forward-looking nature.

[0097] S3. The acquisition control unit of the control execution module executes an adaptive control strategy to adjust the attitude of the solar energy acquisition module, and the conversion control unit executes an adaptive control strategy to adjust the parameters of the energy conversion module. Specifically, the acquisition control unit parses the attitude command (e.g., target angle 45 degrees) in the strategy and sends a drive signal to the attitude adjustment mechanism through the control connection to achieve array rotation; the conversion control unit parses the conversion command (e.g., voltage ratio 1:2) and adjusts the DC-DC converter parameters (e.g., duty cycle 50%) to ensure output matching. This step improves response speed and optimizes acquisition and conversion efficiency through parallel execution.

[0098] S4. The storage control unit of the control execution module executes an adaptive control strategy based on data fed back from the status monitoring unit of the energy storage module, allocating electrical energy to the energy storage module for storage or directly to the load power supply module. The specific allocation process is as follows: The storage control unit receives feedback from the status monitoring unit (e.g., main battery voltage 4.0V, temperature 25℃), combines it with the strategy (e.g., if storage > 80%, then directly supply power), activates the switching circuit to allocate a ratio (e.g., 60% storage, 40% power supply), and realizes the energy flow through electrical connections. This step is based on dynamic balancing of feedback data to avoid overcharging or undercharging.

[0099] S5, the state monitoring unit of the energy storage module collects data and feeds it back to the intelligent decision-making module via a data connection, enabling dynamic adjustment of the adaptive control strategy and autonomous energy control. The specific feedback process is as follows: the state monitoring unit periodically collects data (e.g., voltage / current / temperature every 10 seconds) and uploads it to the intelligent decision-making module via the data connection; the intelligent decision-making module compares the actual data with the predictions, triggering reinforcement learning updates (e.g., adjusting the reward function), thus achieving strategy iteration. This step forms a complete closed loop, ensuring long-term system autonomy. Specific Implementation Example 3:

[0101] like Figures 1-4 As shown, this embodiment provides a detailed hardware composition description of each module of the intelligent multi-adaptive solar-powered UAV energy autonomous control system, and elaborates on its application logic, steps, input-output relationships, and data transmission paths to ensure close collaboration between modules and the formation of a unified energy autonomous system. Specifically, the entire system hardware is integrated on the UAV's fuselage circuit board, using an Advanced Reduced Instruction Set Machine (ARSI) processor as the central computing unit, running an embedded operating system, and supporting multi-threaded processing of environmental data, flight status, and control commands. The hardware components of the solar energy acquisition module include a solar cell array, high-efficiency monocrystalline silicon photovoltaic panels (the array consists of four to six panels connected in series), a maximum power point tracking chip integration, an attitude adjustment mechanism including a dual-axis rotating gimbal, a stepper motor as the drive motor, a high-precision encoder as the angle sensor, a status monitoring unit, and integrated voltage, current, and temperature sensors. The module's inputs are solar radiation and adjustment commands from the control execution module, as well as pulse-width modulated signals transmitted through general-purpose input / output pins. The outputs are DC power, monitoring data, and digital signals for voltage, current, and temperature. The data transmission path involves the status monitoring unit directly sending monitoring data to the acquisition and control unit of the control execution module via an integrated circuit bus. Simultaneously, power is connected to the DC-to-DC converter input of the energy conversion module via a power line, forming a closed-loop path for acquisition, monitoring, and adjustment. This avoids independence and instead dynamically adjusts the array angle through feedback commands from the control execution module. The logical steps involve the acquisition and control unit receiving strategy commands, calculating the target angle, driving the motor, and comparing the actual angle with the angle sensor feedback to adjust the deviation, ensuring optimal matching between the input sunlight data and the output power.

[0102] The hardware components of the energy storage module include a main battery unit, a lithium polymer battery pack, a backup battery unit, a supercapacitor pack, a state monitoring unit, and an integrated battery management chip containing voltage, current, and temperature sensors and a switching circuit. It utilizes metal-oxide-semiconductor field-effect transistor switches and high-frequency relays. The input is the charging current from the energy conversion module, transmitted via a DC line connected to the charging terminal. The output is a stable supply voltage, output and status data to the load power supply module, and analog signals collected through sensor connections converted to digital. The data transmission path involves the state monitoring unit transmitting voltage, current, and temperature data to the storage control unit of the control execution module via a serial peripheral interface bus. Simultaneously, the switching circuit receives digital instructions from the storage control unit to switch between the main and backup units. The application logic involves the storage control unit analyzing the input status data; if the main battery voltage is below a threshold, it instructs the switch to the backup output path, ensuring coordination with the energy conversion module's distribution. The steps involve the energy conversion module outputting energy, the storage control unit evaluating the demand allocation ratio, and providing feedback on status data to update the strategy.

[0103] The hardware components of the energy conversion module include a DC-DC converter, a boost / buck converter, a conversion controller, a microcontroller subunit integrating an analog-to-digital converter (ADC) and a digital-to-analog converter (DAC), an efficiency monitoring unit, and a power metering sensor. The input is DC power from the solar energy acquisition module, connected via a power line. The output is the converted voltage, connected via an electrical connection to the energy storage module's charging line or the load power supply module's power line. The data transmission path involves the efficiency monitoring unit collecting the power difference before and after conversion through a sensor connection, calculating the efficiency, and feeding it back to the conversion control unit of the control execution module. The application logic involves the conversion controller receiving adjustment instructions from the adaptive control strategy and modifying parameters such as the duty cycle. The steps involve receiving the input power, the efficiency monitoring unit calculating in real time, and if the efficiency is below a threshold, the conversion control unit adjusting parameters to optimize the output voltage, ensuring it matches the charging needs of the storage module and avoiding independent optimization through a feedback path to dynamically optimize the overall energy flow.

[0104] The hardware components of the load power supply module include a voltage regulator circuit, a low-dropout regulator, an output and power distribution switch, and a multi-channel relay module. The input is electrical energy from the energy conversion module or energy storage module, which is connected via electrical connection. The output is a stable power supply to the UAV load, such as motors, sensors, and communication modules. The data transmission path is to receive the distribution instructions from the power supply control unit through the control connection. The application logic is that the power supply control unit adjusts the output ratio based on the strategy. The steps are that the power supply control unit receives the strategy, evaluates the load demand, and switches the power supply path to ensure cooperation with the conversion and storage module, forming a complete energy chain from data collection to the load.

[0105] The hardware components of the environmental perception module include a light sensor, a wind speed sensor, and a temperature and humidity sensor, all integrated on a sensor board. The input is external environmental signals, and the output is digital environmental data, which is transmitted to the data fusion unit of the intelligent decision-making module via a data connection. The application logic is real-time sampling and transmission, supporting decision input. The path is that the sensor-collected data fusion unit integrates and transmits the data to the energy prediction unit.

[0106] The hardware components of the flight status monitoring module include an inertial measurement unit sensor, an accelerometer gyroscope for acquiring data, a global positioning system module, and a power meter. The input is the UAV dynamic signal, and the output is flight status data, which is transmitted to the data fusion unit via a data connection. The application logic is to continuously monitor and provide attitude, velocity, and power consumption data, and supports predictive input. The path is the data fusion unit and the prediction unit for analysis.

[0107] The hardware components of the intelligent decision-making module include a main processor, a reinforcement learning framework, a data fusion unit, software implementation on the processor hardware supporting multiple analog-to-digital conversion inputs, an energy prediction unit, a long short-term memory network model deployed on the processor's neural network accelerator, a policy generation unit, and an integrated genetic algorithm library. The input is environmental flight data, which enters the fusion unit through a data connection. The output is an adaptive control strategy, which is transmitted to the control execution module through an instruction connection. The application logic steps are as follows: the data fusion unit receives the input data and integrates it into a unified dataset; the path is multi-source data fusion, with the internal data flow to the prediction unit; the energy prediction unit uses a long short-term memory network to analyze the sequence and predict the demand; the input dataset processing gating mechanism captures trends and outputs prediction vectors; the internal data flow to the policy generation unit; the policy generation unit uses a genetic algorithm to optimize the initial population, iteratively selects crossover mutations, and outputs a strategy, ensuring that the computing module and the perception execution module work together to form a decision-making closed loop.

[0108] The hardware components of the control execution module include a microcontroller, integrated multi-general-purpose input / output and sub-control units, and dedicated input / output groups for data acquisition, conversion, storage, and power supply. The input is a strategy command, received from the intelligent decision-making module via an internal bus. The output is an adjustment signal, connected to each module via a control connection. The application logic is to parse the strategy, distribute the command, and provide feedback on the status. The path is for the receiving command sub-unit to execute the feedback data and return it to the decision-making module, thus avoiding independence and coordinating the data flow of the entire system through the bus. Specific Implementation Example 4:

[0110] like Figures 1-4As shown, this embodiment details the input data, output results, and specific applications of reinforcement learning, long short-term memory (LSTM) network, and genetic algorithms in the intelligent decision-making module, including a description of the computation process. The reinforcement learning algorithm is applied to the intelligent decision-making module as a whole to generate adaptive control strategies. Its input data includes environmental data such as light intensity and wind speed, and flight status data such as speed, altitude, and power consumption. This data is transmitted from the environmental perception module and flight status monitoring module to the data fusion unit for integration. The computation process involves first treating the input data as a system state, such as the current energy level, and combining it with environmental conditions to form a state vector. Then, the algorithm learns the optimal action sequence by repeatedly experimenting with actions such as trying different attitude angles or switching storage. Based on reward feedback (positive reward for high energy efficiency, negative reward for low energy efficiency), the algorithm gradually learns the optimal action sequence. Specific steps include initializing an action state table, selecting actions to execute from the current state, observing new states and rewards, updating the table to favor high-reward actions, and iterating multiple times until convergence. The output result is an optimized adaptive control strategy, such as a set of instructions including attitude adjustment values ​​and conversion parameters. In the system, this strategy is applied to the control execution module to implement adjustments, achieving dynamic adaptation of the entire energy chain, such as prioritizing energy storage when light intensity is low.

[0111] Long Short-Term Memory (LSTM) network algorithms are applied in the energy prediction unit to predict energy demand and environmental changes. The input data is a unified dataset received from the data fusion unit's internal data stream, including time-series environmental and flight data such as the past hour's illumination and velocity sequences. The computation process involves the algorithm processing the sequence data, using an input gate to determine which new information to retain, a forget gate to discard old information, and an output gate to control the final output. This layered processing of the sequence captures long-term patterns, such as identifying a weakening illumination trend. Specific steps include feeding the input sequence into the network in segments, updating the internal memory unit at each time step, filtering irrelevant noise using a gating mechanism, and finally aggregating the predictions. The output is a prediction vector, such as the energy demand value and illumination change rate for the next thirty minutes. This vector is used in the system's policy generation unit as a basis to help generate forward-looking policies, such as adjusting attitude in advance when energy shortages are predicted.

[0112] Genetic algorithms are applied in the policy generation unit to generate adaptive control policies based on prediction results. The input data is the prediction results from the energy prediction unit, such as the demand prediction vector. The computation process simulates an evolutionary process. First, an initial policy group is created, such as randomly generating one hundred possible instruction combinations. Then, the fitness of each policy is evaluated, such as the energy balance score after simulation execution. High-fitness policies are selected as parents, and a new generation is generated through crossover and random mutation. This process is repeated iteratively until the group converges to the optimal policy. Specific steps include population initialization, fitness sorting, elite retention, crossover and mutation, and new population evaluation. The output is an optimized adaptive control policy, such as a specific attitude angle conversion voltage storage ratio. In the system, this is applied to the control execution module to distribute instructions, achieving a closed-loop application from prediction to execution, such as increasing acquisition efficiency during high demand prediction. Specific Implementation Example 5:

[0114] like Figures 1-4 As shown, the following are specific use cases of the entire solution:

[0115] This embodiment provides specific use cases of the intelligent multi-adaptive solar-powered drone energy autonomous control system, covering different scenarios to demonstrate its adaptability. Each case describes the entire process in detail.

[0116] In high-altitude long-endurance reconnaissance scenarios, UAVs deployed in plateau regions perform surveillance missions. First, the system initializes. The solar energy acquisition module receives intense sunlight through a solar array and converts it into DC power. The environmental perception module collects data on high light intensity and wind speed, which is then transmitted to the data fusion unit of the intelligent decision-making module. Simultaneously, the flight status monitoring module collects stable altitude and speed data, which is transmitted to the same unit. The data fusion unit integrates these data to form a unified dataset, which is then transmitted to the energy prediction unit. A long short-term memory network algorithm analyzes and predicts future energy demands, such as sustained high consumption. The prediction results are transmitted to the strategy generation unit, where a genetic algorithm generates adaptive control strategies, such as adjusting attitude to align with sunlight and allocating 80% of the electrical energy directly to power the system. The control execution module receives the strategy, the acquisition control unit drives the attitude adjustment mechanism to rotate the gimbal for optimized reception, the conversion control unit adjusts the parameters of the energy conversion module to match the voltage, the storage control unit switches the main battery to replenish remaining energy, and the power supply control unit distributes power to the load power supply module to drive the camera equipment. The status monitoring unit feeds back data to the intelligent decision-making module to dynamically adjust the strategy, ensuring continuous flight for more than eight hours without external charging. The entire process, from perception to execution, forms a closed loop, achieving energy autonomy.

[0117] In urban low-altitude inspection scenarios, drones are used to inspect buildings. The system first starts up, and the environmental perception module detects intermittent light shading caused by buildings, transmitting this data to the data fusion unit. The flight status monitoring module collects attitude changes and power consumption data, transmitting this data to the same unit. The data fusion unit integrates the unified dataset and transmits it to the energy prediction unit. A long short-term memory network algorithm predicts peak demand periods, such as high sensor power consumption periods. The prediction results are transmitted to the strategy generation unit, where a genetic algorithm generates strategies such as tracking the light source attitude and optimizing voltage. The control execution module executes the process: the acquisition control unit adjusts the attitude mechanism to track the light source and maximize acquisition; the conversion control unit modifies conversion parameters for efficient output; the storage control unit uses a backup unit to buffer transients and avoid interruptions; and the power supply control unit distributes power to the load power supply module to support the inspection sensors. The status monitoring unit provides real-time feedback to adjust the strategy. The entire process ensures uninterrupted inspection with an energy autonomy rate of 95%.

[0118] In wilderness search and rescue scenarios, when a drone traverses a forested area, the system is first activated. The environmental perception module collects low-light data and transmits it to the data fusion unit. The flight status monitoring module monitors frequent attitude changes and speed changes and transmits the data to the same unit. The data fusion unit forms a unified dataset and transmits it to the energy prediction unit. The long short-term memory network algorithm analyzes and predicts the low energy availability period, and the prediction results are transmitted to the strategy generation unit. The genetic algorithm generates strategies such as prioritizing storage and reducing output. The control execution module implements the strategy: the data acquisition control unit adjusts the attitude to capture scattered light, the conversion control unit reduces the conversion output to the minimum, the storage control unit switches the main battery to store excess energy, and the power supply control unit allocates minimum power to support hovering. The status monitoring unit provides feedback data to dynamically optimize the strategy. The entire process achieves energy balance and supports long-term search and rescue operations. Specific Implementation Example Six:

[0120] like Figures 1-4 As shown, this embodiment designs a comparative experiment to verify the performance advantages of the intelligent multi-adaptive solar-powered UAV energy autonomous control system. The comparison object is a traditional fixed-attitude solar-powered UAV system without intelligent decision-making and adaptive adjustment. The experiment is set with the same hardware foundation, such as the same solar array and battery capacity, and tested under three conditions in a simulated environment chamber: constant illumination, intermittent illumination, and low illumination. Each system runs for two hours, and the measured indicators include energy harvesting efficiency (harvested electrical energy divided by the theoretical maximum and multiplied by 100%), storage utilization rate (effective storage divided by the total capacity and multiplied by 100%), overall autonomous time (continuous flight time without external power supply), and energy loss rate (conversion and distribution loss divided by the total input and multiplied by 100%).

[0121] The following experimental data are derived from the average values ​​of multiple repeated simulation experiments. Ten independent operation tests were conducted on both the system and the traditional system under the same control conditions. A professional light source simulator was used to precisely control the light intensity and fluctuation mode. Data was collected in real time using a high-precision power meter, voltage and current recorder, and flight simulation platform. All measuring equipment was calibrated by the national metrology institution. The experimental environment temperature was controlled at 25 degrees Celsius ± 1 degree Celsius, and the humidity was controlled at 50% ± 5% to ensure high consistency and repeatability of experimental conditions. This proves that the obtained data is objective and reliable and can effectively reflect the performance advantages of the system under different lighting conditions.

[0122] The following are the specific experimental data for this scheme:

[0123] condition System type Energy harvesting efficiency (%) Storage utilization % Self-governance time (minutes) Energy loss rate (%) Constant illumination This system 92 85 150 5 Constant illumination Traditional system 85 70 120 10 Intermittent light This system 88 80 140 6 Intermittent lighting Traditional system 70 50 90 15 Low light This system 75 75 110 8 Low light Traditional system 60 40 70 20

[0124] The results show that the system improves efficiency by an average of 15%, utilization rate by 25%, autonomous time by 30 minutes, and reduces losses by 8%, proving that the intelligent multi-adaptation mechanism significantly improves energy autonomy performance.

[0125] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a reference structure" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0126] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system, characterized in that: It includes a solar energy acquisition module, an energy storage module, an energy conversion module, a load power supply module, an environmental perception module, a flight status monitoring module, an intelligent decision-making module, and a control execution module; The solar energy acquisition module is electrically connected to the energy conversion module and is used to collect solar energy and output DC power. The energy conversion module is electrically connected to the energy storage module and the load power supply module respectively, and is used to convert electrical voltage and distribute electrical energy. The environmental perception module is data-connected to the intelligent decision-making module and is used to collect environmental data and transmit it to the intelligent decision-making module. The flight status monitoring module is connected to the intelligent decision-making module for collecting flight status data and transmitting it to the intelligent decision-making module. The intelligent decision-making module is connected to the control execution module and is used to generate an adaptive control strategy based on the received environmental data and flight status data using a reinforcement learning algorithm and transmit the instructions. The control execution module is connected to the solar energy acquisition module, energy conversion module, energy storage module, and load power supply module respectively. It is used to execute adaptive control strategies to adjust the working status of each module and realize closed-loop autonomous control of energy acquisition, conversion, storage and power supply.

2. The intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system according to claim 1, characterized in that, The solar energy acquisition module includes a solar cell array, an attitude adjustment mechanism, and a status monitoring unit; The solar cell array is mechanically connected to the attitude adjustment mechanism to convert solar energy into direct current and output it to the energy conversion module via an electrical connection. The attitude adjustment mechanism is connected to the control execution module and is used to receive adjustment commands from the adaptive control strategy to adjust the attitude angle of the solar cell array to optimize the light reception efficiency. The condition monitoring unit is connected to the solar cell array sensors to monitor voltage, current and temperature data in real time, and transmits the data to the control execution module to support attitude adjustment decisions.

3. The intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system according to claim 2, characterized in that, The attitude adjustment mechanism includes a rotating gimbal, a drive motor, and an angle sensor; The rotating gimbal is fixedly connected to the solar cell array and is used to support and rotate the solar cell array; The drive motor is connected to the rotating gimbal and is used to provide rotational torque according to the instructions of the control execution module to adjust the attitude angle; An angle sensor is connected to the rotating gimbal to detect the current attitude angle and transmit it to the control execution module via feedback, forming a closed-loop control for attitude adjustment.

4. The intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system according to claim 1, characterized in that, The energy storage module includes a main battery unit, a backup battery unit, a status monitoring unit, and a switching circuit. The main battery unit is connected to the energy conversion module for charging and storing electrical energy; The backup battery unit is connected to the energy conversion module for charging and storing electrical energy; The status monitoring unit is connected to the sensors of the main battery unit and the backup battery unit respectively, and is used to collect voltage, current and temperature data and transmit them to the control execution module through the data connection; The switching circuit is electrically connected to the main battery unit, the backup battery unit, and the load power supply module, respectively, and is used to switch the power supply under the command of the control execution module to achieve seamless switching between the main battery unit and the backup battery unit.

5. The intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system according to claim 1, characterized in that, The energy conversion module includes a DC-DC converter, a conversion controller, and an efficiency monitoring unit; The DC-DC converter is connected to the input of the solar energy acquisition module to convert the input DC power into the target voltage and output it to the energy storage module or load power supply module via electrical connection. The conversion controller is connected to the control execution module and is used to receive adjustment instructions from the adaptive control strategy to modify the conversion parameters; The efficiency monitoring unit is connected to the DC-DC converter sensor to monitor the conversion efficiency and feed the data back to the control execution module to achieve dynamic optimization of the conversion parameters.

6. The intelligent multi-adaptive solar-powered unmanned aerial vehicle energy autonomous control system according to claim 1, characterized in that, The intelligent decision-making module includes a data fusion unit, an energy prediction unit, and a strategy generation unit. The data fusion unit is connected to the environmental perception module and the flight status monitoring module respectively, and is used to integrate environmental data and flight status data to form a unified dataset and transmit it to the energy prediction unit through an internal data stream. The energy prediction unit and the data fusion unit are connected by an internal data stream. This is used to analyze a unified dataset and predict energy demand and environmental changes using a long short-term memory network algorithm. The prediction results are then transmitted to the strategy generation unit via the internal data stream. The strategy generation unit is connected to the energy prediction unit via internal data flow. It is used to generate an adaptive control strategy based on the prediction results using a genetic algorithm, and then transmits the strategy to the control execution module via an instruction connection.

7. The intelligent multi-adaptive solar-powered unmanned aerial vehicle (UAV) energy autonomous control system according to claim 1, characterized in that, The control execution module includes a data acquisition control unit, a conversion control unit, a storage control unit, and a power supply control unit; The data acquisition and control unit is connected to the solar energy acquisition module and is used to execute attitude adjustment commands in the adaptive control strategy; The conversion control unit is connected to the energy conversion module and is used to execute conversion parameter adjustment commands in the adaptive control strategy; The storage control unit is connected to the energy storage module and is used to execute storage switching commands in the adaptive control strategy; The power supply control unit is connected to the load power supply module and is used to execute the power distribution instructions in the adaptive control strategy; The data acquisition control unit, conversion control unit, storage control unit, and power supply control unit are connected to the internal bus of the intelligent decision module to receive adaptive control strategy instructions and provide feedback on the execution status, thereby coordinating the control flow and data flow.

8. The control method corresponding to the intelligent multi-adaptive solar-powered unmanned aerial vehicle energy autonomous control system according to any one of claims 1-7, characterized in that, Includes the following steps: S1. The environmental perception module collects environmental data and transmits it to the data fusion unit of the intelligent decision-making module through a data connection; the flight status monitoring module collects flight status data and transmits it to the data fusion unit through a data connection. S2. The data fusion unit integrates environmental data and flight status data to form a unified dataset and transmits it to the energy prediction unit through an internal data stream. The energy prediction unit uses a long short-term memory network algorithm to analyze the unified dataset and predict energy demand and environmental changes. The prediction results are transmitted to the strategy generation unit through an internal data stream. The strategy generation unit uses a genetic algorithm to generate an adaptive control strategy based on the prediction results and transmits it to the control execution module through an instruction connection. S3. The acquisition control unit of the control execution module executes an adaptive control strategy to adjust the attitude of the solar energy acquisition module, and the conversion control unit executes an adaptive control strategy to adjust the parameters of the energy conversion module. S4. The storage control unit of the control execution module executes an adaptive control strategy based on the data fed back by the status monitoring unit of the energy storage module, allocating electrical energy to the energy storage module for storage or directly to the load power supply module. S5, the status monitoring unit of the energy storage module collects data and feeds it back to the intelligent decision-making module through data connection, so as to realize the dynamic adjustment of the adaptive control strategy and the autonomous energy control.

9. The control method corresponding to the intelligent multi-adaptive solar-powered unmanned aerial vehicle energy autonomous control system according to claim 8, characterized in that, In step S3, the acquisition control unit, based on the light prediction data in the adaptive control strategy, controls the drive motor of the attitude adjustment mechanism to rotate the gimbal. At the same time, the angle sensor transmits the current attitude angle data to the control execution module through the feedback connection, forming a closed-loop control to maximize the solar energy acquisition efficiency.

10. The control method corresponding to the intelligent multi-adaptive solar-powered unmanned aerial vehicle energy autonomous control system according to claim 8, characterized in that, In step S4, the storage control unit receives voltage and temperature data transmitted by the status monitoring unit through the data connection, and combines it with the energy demand prediction information in the adaptive control strategy. It then activates the switching circuit through the control connection to switch between the main battery unit and the backup battery unit. At the same time, the power supply control unit adjusts the output ratio of the load power supply module through the control connection to achieve energy distribution optimization.

Images