A UAV communication system based on Beidou messages

Abstract

The present invention relates to the field of UAV communication technology, and discloses a UAV communication system based on Beidou messages, which includes three parts: a UAV end, a communication layer, and a ground control station. The UAV end integrates modules such as flight control, data acquisition, Beidou short message communication, and communication adaptation, and can collect flight data in real time and perform two-way short message communication with the ground control station through the Beidou satellite system. The communication layer provides stable data transmission, defines the communication protocol, and encrypts and decrypts the transmitted data. The ground control station is responsible for sending control instructions, processing and analyzing the data sent back by the UAV, and uniformly managing and scheduling multiple UAV tasks. The communication system of the present invention can dynamically adjust the communication protocol parameters to adapt to different communication conditions by introducing a communication adaptation module, which significantly improves the stability and efficiency of UAV communication.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) communication technology, and in particular to a UAV communication system based on Beidou messages. Background Art

[0002] Drones are increasingly being used in various fields, such as environmental monitoring, agricultural plant protection, and logistics distribution. As a core component of drone technology, the stability and reliability of drone communication systems are crucial to safe flight and mission execution.

[0003] Existing drone communication systems mostly use traditional wireless communication methods such as Wi-Fi and 4G / 5G. However, these communication methods are susceptible to interference in complex environments (such as mountainous areas and oceans), resulting in degraded communication quality and even communication interruptions. Furthermore, existing drone communication systems lack adaptability to varying communication conditions and are unable to dynamically adjust communication protocol parameters to adapt to environmental changes, further limiting the application of drones in complex environments. Therefore, we propose a drone communication system based on BeiDou messages. Summary of the Invention

[0004] The purpose of the present invention is to provide a Beidou message-based UAV communication system to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solutions: a BeiDou message-based UAV communication system, comprising a UAV terminal, a communication layer, and a ground control station;

[0006] The UAV terminal includes a flight control module, a data acquisition module, a Beidou short message communication module and a communication adaptation module; the flight control module is used to control the flight status of the UAV according to a preset flight plan and real-time instructions; the data acquisition module is used to collect the UAV's flight data in real time, and the flight data includes the UAV's position, speed, power and communication environment parameters; the Beidou short message communication module is used to conduct two-way short message communication with the ground control station through the Beidou satellite system, transmit flight data and receive control instructions; the communication adaptation module analyzes the communication environment parameters through a machine learning algorithm and dynamically adjusts the communication protocol parameters according to the analysis results to adapt to different communication conditions;

[0007] The communication layer includes the Beidou satellite system, a communication protocol module, and a data encryption and decryption module; the Beidou satellite system is used to provide stable data transmission between the UAV end and the ground control station; the communication protocol module is used to define the communication protocol between the UAV end and the ground control station, including data format, transmission method and verification mechanism; the data encryption and decryption module is used to encrypt and decrypt the transmitted data;

[0008] The ground control station includes a command sending module, a data processing module, a task scheduling module and a user interface module; the command sending module is used to send control commands to the drone according to task requirements, including flight path, shooting parameters and return commands; the data processing module is used to receive status information and collected data sent back by the drone, and perform real-time processing and analysis; the task scheduling module is used to uniformly manage and schedule multiple drone tasks, including task allocation, priority sorting and resource allocation; the user interface module is used to display the drone's flight status and data processed and analyzed in real time by the data processing module, as well as provide operational functions to achieve flight control of the drone.

[0009] Preferably, the communication adaptive module collects the communication environment parameters of the UAV in real time, and the communication environment parameters include signal strength, noise level, channel occupancy, signal-to-noise ratio, bit error rate, delay time, packet loss rate, frequency offset and phase noise;

[0010] The collected communication environment parameters are analyzed using a pre-trained protocol parameter prediction model. The model can output optimal communication protocol parameter adjustment suggestions based on the input communication environment parameters.

[0011] Based on the analysis results of the machine learning algorithm model, the communication protocol parameters of the drone are dynamically adjusted to adapt to different communication conditions; the communication protocol parameters include modulation mode, coding rate, transmission power, data packet size, retransmission mechanism, carrier frequency and bandwidth.

[0012] Preferably, a neural network algorithm is used to construct a protocol parameter prediction model, and the specific steps include:

[0013] Step 1: Construct a neural network model, which includes an input layer, a hidden layer, and an output layer. The input layer is used to receive the communication environment parameters of the drone, the hidden layer is used to perform nonlinear transformation and feature extraction, and the output layer is used to output the optimal communication protocol parameter adjustment suggestions;

[0014] Step 2: Obtain a large amount of communication environment parameter data and corresponding communication protocol parameter data from the UAV communication system to form a training data set; and preprocess the data, including normalization, removal of outliers, and filling in missing values;

[0015] Step 3: Use the training data set to train the neural network model and adjust the model parameters through an iterative optimization algorithm so that the model output gradually approaches the actual communication protocol parameter adjustment suggestions;

[0016] Step 4: Verify and test the trained neural network model.

[0017] Preferably, the training process of step 3 includes:

[0018] Step 3.1: Use the preprocessed training dataset as input and input the communication environment parameters into the input layer of the neural network;

[0019] Step 3.2: Perform nonlinear transformation and feature extraction through the hidden layer of the neural network. The output calculation formula of the hidden layer is: , where h represents the output of the hidden layer, σ represents the activation function, represents the weight matrix from the input layer to the hidden layer, x represents the input of the input layer, represents the bias of the hidden layer;

[0020] Step 3.3: Pass the output of the hidden layer to the output layer. The output calculation formula of the output layer is: , where y represents the output of the output layer, i.e. the predicted communication protocol parameter adjustment suggestions, represents the weight matrix from the hidden layer to the output layer, represents the bias of the output layer;

[0021] Step 3.4: Calculate the loss between the output of the output layer and the actual communication protocol parameter adjustment suggestion. The loss function is calculated as: , where L represents the loss and n represents the number of samples. represents the output layer output of the i-th sample, represents the real communication protocol parameter adjustment suggestion for the i-th sample;

[0022] Step 3.5: Use the gradient descent optimization algorithm to iteratively update the parameters of the neural network model according to the loss function until the preset stopping condition is met to obtain a trained neural network model.

[0023] 1. Preferably, in step 2, the Z-score normalization method is used to subtract the mean of each numerical data and divide it by its standard deviation so that the processed data conforms to the standard normal distribution. The formula for the normalization process is: ,in, is the original data, is the mean of the original data, is the standard deviation of the original data, The data are standardized.

[0024] Preferably, in step 2, for missing values, a linear interpolation algorithm is used to fill them; for outliers, a threshold judgment method is used to regard data points that exceed the preset threshold range as outliers and replace them with the mean of their neighboring points.

[0025] Preferably, the data encryption and decryption module adopts the AES symmetric encryption algorithm, the encryption key is 128 bits, which is generated by the ground control station and distributed to the drone end through a secure channel; before sending the flight data, the drone end uses the AES algorithm and encryption key to encrypt the data, and after receiving the encrypted data, the ground control station uses the same encryption key to decrypt it to restore the original flight data.

[0026] Preferably, the data verification mechanism of the communication protocol module adopts a CRC check code. The UAV end generates a CRC check code before sending data, and the ground control station performs CRC check code verification after receiving the data.

[0027] Preferably, the specific implementation of the task scheduling module is:

[0028] receiving UAV mission input from the user interface module, including mission type, mission objectives, mission priority, and resources required for the mission;

[0029] Assign the received mission to the appropriate drone based on its current status, location, battery level, and mission requirements;

[0030] Sort the tasks assigned to drones according to their priority and urgency to ensure that high-priority tasks are executed first;

[0031] Allocate necessary resources to the UAV according to mission requirements, including communication resources, computing resources, and storage resources;

[0032] Monitor the mission execution status of the drone in real time, including mission progress, drone status, and abnormal situations; dynamically adjust or reschedule the mission based on the actual execution status of the drone and changes in mission requirements.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The adaptive communication module analyzes the drone's communication environment parameters, such as signal strength and interference levels, in real time and dynamically adjusts communication protocol parameters based on the analysis results. This allows the drone to maintain stable data transmission under varying communication conditions, effectively reducing communication interruptions and bit error rates, and improving communication reliability and stability. Through continuous learning and optimization of the communication environment using machine learning algorithms, the adaptive communication module selects the transmission method and data format that best suits the current communication conditions, thereby maximizing data transmission efficiency. This not only shortens data transmission time but also reduces the overhead incurred by repeated transmissions and error checking.

[0035] Because the adaptive communication module optimizes communication protocol parameters, minimizing communication failures and data transmission errors, it reduces the cost of failed or repeated drone missions due to communication issues. Furthermore, it reduces reliance on human intervention, further reducing operating and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is the overall structural diagram of the present invention;

[0037] Figure 2 This is a working step diagram of the adaptive communication module;

[0038] Figure 3 Flowchart for training the protocol parameter prediction model. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] See also Figure 1-3 The present invention provides a technical solution: a Beidou message-based UAV communication system, including a UAV terminal, a communication layer and a ground control station.

[0041] The drone side includes a flight control module, a data acquisition module, a Beidou short message communication module, and a communication adaptation module. The flight control module is responsible for precisely controlling the drone's flight status according to the preset flight plan and real-time received commands, ensuring that the drone executes according to the established route and mission requirements. The data acquisition module collects real-time flight data from the drone, including but not limited to the drone's position, speed, remaining battery life, and current communication environment parameters. The Beidou short message communication module utilizes the Beidou satellite system to enable two-way short message communication between the drone and the ground control station, ensuring reliable data transmission even in areas difficult to reach by traditional wireless communication methods, such as mountainous areas and oceans. The communication adaptation module uses a built-in machine learning algorithm to conduct in-depth analysis of collected communication environment parameters and dynamically adjusts communication protocol parameters, such as data transmission rate and encoding method, based on the analysis results to adapt to changing communication conditions, significantly improving the drone's communication stability and reliability in complex environments.

[0042] The communication layer includes the Beidou satellite system, a communication protocol module, and a data encryption and decryption module. The Beidou satellite system not only provides a stable data transmission channel between the UAV and the ground control station, but also ensures wide coverage and high reliability. The communication protocol module defines the communication specifications between the UAV and the ground control station, including unified data formats, selected transmission methods, and data verification mechanisms, ensuring accurate and efficient communication. The data encryption and decryption module is responsible for encrypting transmitted data to protect data security and prevent unauthorized interception or tampering during transmission.

[0043] The ground control station serves as the command center for the drone's communication system. It comprises a command transmission module, a data processing module, a task scheduling module, and a user interface module. The command transmission module sends control commands to the drone based on specific mission requirements, such as flight path planning, setting shooting parameters, and issuing return commands. The data processing module receives status information and collected data from the drone, performing real-time processing and analysis to provide data support for subsequent decision-making. The task scheduling module manages and schedules multiple drone missions, including the rational allocation of tasks, prioritization, and efficient resource allocation, thereby improving overall operational efficiency.

[0044] The user interface module is the window for interaction between the ground control station and the user. It is used to display the UAV's flight status, data processing results and other information in real time. It also provides a wealth of operating functions, allowing users to directly control the UAV's flight through the interface.

[0045] The present invention will be further described below in conjunction with Examples 1 to 4:

[0046] Example 1:

[0047] The flight control module uses a PID control algorithm to calculate the corresponding control outputs, including servo deflection angle and motor speed, based on the drone's real-time status (such as position, speed, and attitude) and target commands. This ensures that the drone can execute its mission according to the preset flight path and attitude. Based on the output of the flight control algorithm, the module drives actuators such as the servos and motors through PWM (pulse width modulation) signals to achieve various flight attitude and trajectory control.

[0048] The data acquisition module integrates a variety of high-precision sensors, such as GPS, IMU, barometer, and fuel meter, which are used to measure key parameters such as the drone's position, speed, attitude, altitude, and remaining power. The sensors are connected to the data acquisition module via serial communication or bus to ensure real-time transmission and accurate acquisition of data. After acquiring the data, the data is further sent to the ground control station.

[0049] The communication adaptation module collects the communication environment parameters of the UAV in real time. The communication environment parameters include signal strength, noise level, channel occupancy, signal-to-noise ratio, bit error rate, delay time, packet loss rate, frequency offset and phase noise, etc. These parameters reflect the current communication environment status of the UAV.

[0050] The communication adaptation module analyzes these collected communication environment parameters using a pre-trained protocol parameter prediction model. This model, built on a neural network algorithm, can output optimal communication protocol parameter adjustment recommendations based on the input communication environment parameters.

[0051] In order to train the neural network model, it is necessary to obtain a large amount of communication environment parameter data and corresponding communication protocol parameter data from the UAV communication system to form a training data set.

[0052] The communication adaptation module can dynamically adjust the communication protocol parameters of the drone according to the current communication environment, including modulation mode, coding rate, transmission power, data packet size, retransmission mechanism, carrier frequency and bandwidth, so as to adapt to different communication conditions and ensure stable communication of the drone in complex environments.

[0053] The steps to construct a protocol parameter prediction model using a neural network algorithm are as follows:

[0054] Step 1: Build a neural network model. This model is designed to consist of an input layer, hidden layers, and an output layer. The input layer receives the drone's communication environment parameters, which describe the drone's current communication environment. The hidden layer performs nonlinear transformation and feature extraction, deeply processing the input data to extract features useful for predicting communication protocol parameter adjustment recommendations. The output layer, based on the hidden layer's processing results, outputs the optimal communication protocol parameter adjustment recommendations.

[0055] 2. Step 2: Prepare the training data set. Obtain a large amount of communication environment parameter data and corresponding communication protocol parameter data from the UAV communication system. Through this data, the model can learn the mapping relationship between the communication environment parameters and the communication protocol parameters. After obtaining the data, preprocessing is required, including normalization, removal of outliers, and filling in missing values ​​to ensure the accuracy and consistency of the data, thereby improving the training effect of the model. Using the Z-score standardization method, each numerical data is subtracted from its mean and divided by its standard deviation so that the processed data conforms to the standard normal distribution. The formula for standardization is: ,in, is the original data, is the mean of the original data, is the standard deviation of the original data, The data are standardized.

[0056] For missing values, linear interpolation algorithm is used to fill them; for outliers, threshold judgment method is used to regard data points that exceed the preset threshold range as outliers and replace them with the mean of their neighboring points.

[0057] Step 3: Train the neural network model. Use the preprocessed training dataset to train the neural network model. Through iterative optimization algorithms, continuously adjust the model parameters so that the model output gradually approaches the actual communication protocol parameter adjustment recommendations. During the training process, it is necessary to monitor the model performance to ensure that the model's performance on the training set gradually improves and that there is no overfitting or underfitting. The specific steps are:

[0058] Step 3.1: Use the preprocessed training dataset as input and input the communication environment parameters into the input layer of the neural network.

[0059] Step 3.2: Perform nonlinear transformation and feature extraction through the hidden layer of the neural network. The output calculation formula of the hidden layer is: , where h represents the output of the hidden layer, σ represents the activation function, represents the weight matrix from the input layer to the hidden layer, x represents the input of the input layer, represents the bias of the hidden layer.

[0060] Step 3.3: Pass the output of the hidden layer to the output layer. The output calculation formula of the output layer is: , where y represents the output of the output layer, i.e. the predicted communication protocol parameter adjustment suggestions, represents the weight matrix from the hidden layer to the output layer, represents the bias of the output layer.

[0061] Step 3.4: Calculate the loss between the output of the output layer and the actual communication protocol parameter adjustment suggestion. The loss function is calculated as: , where L represents the loss and n represents the number of samples. represents the output layer output of the i-th sample, represents the actual communication protocol parameter adjustment suggestion for the i-th sample.

[0062] Step 3.5: Use the gradient descent optimization algorithm to iteratively update the parameters of the neural network model according to the loss function until the preset stopping condition is met to obtain a trained neural network model.

[0063] Step 4: Validate and test the neural network model. The trained neural network model is validated and tested to ensure its performance in real-world applications. The purpose of validation and testing is to evaluate the model's performance on unknown data to examine its generalization capabilities. If the model performs well on the validation and test sets and accurately outputs optimal communication protocol parameter adjustment recommendations based on the communication environment parameters, the model is considered valid and can be deployed in a real-world drone communication system.

[0064] The following is a simplified code example of training and building a neural network model using the Python programming language:

[0065]

[0066] The main steps and functions of the above code are as follows:

[0067] Data preparation and preprocessing: Use the numpy library to generate simulated communication environment parameter (X) and communication protocol parameter (y) data. Use the StandardScaler class to perform Z-score normalization on the data to ensure data accuracy and consistency, thereby improving model training results.

[0068] Split the data into training and test sets: Use the train_test_split function to split the data into training and test sets so that the performance of the model can be evaluated during the training process.

[0069] Building a Neural Network Model: A Sequential model was used to construct a neural network consisting of an input layer, a hidden layer, and an output layer. The hidden layer used 64 neurons and the ReLU activation function for nonlinear transformation and feature extraction. The output layer used 7 neurons and a linear activation function to predict communication protocol parameters.

[0070] Compile model: Use the Adam optimizer and mean squared error loss function to compile the model for training.

[0071] Training model: Use the fit function to train the model, specifying the training set, training rounds (epochs), batch size (batch_size), and the ratio of the validation set.

[0072] Evaluate the model: Use the evaluate function to evaluate the performance of the model on the test set and print out the test loss.

[0073] Example 2:

[0074] As the core of the communications layer, the BeiDou satellite system primarily provides a stable data transmission channel between drones and ground control stations. Utilizing satellite communication technology, drones can maintain reliable communication with ground control stations even when far from base stations or in complex terrain. Through the BeiDou satellite system, drones can transmit flight data and status information to ground control stations in real time, while also receiving commands and control information from the ground.

[0075] The communication protocol module is responsible for defining the communication protocol between the UAV end and the ground control station. The communication protocol covers multiple aspects such as data format, transmission mode and verification mechanism to ensure that both parties can exchange information accurately and efficiently. The data format specifies the encoding method, structure and meaning of each field of the data, so that the UAV and the ground control station can correctly parse and understand the information sent by each other. The transmission mode defines the way data is sent and received, including synchronous, asynchronous, serial, parallel and other modes to adapt to different communication needs and scenarios. The verification mechanism is used to ensure the integrity and accuracy of the data, and detects and corrects errors that may occur during data transmission by adding check codes, performing cyclic redundancy checks, etc. The data verification mechanism of the communication protocol module of the present invention adopts CRC check code. The UAV end generates a CRC check code before sending data, and the ground control station verifies the CRC check code after receiving the data.

[0076] The data encryption and decryption module uses the AES symmetric encryption algorithm, and the encryption key length is set to 128 bits, which not only ensures the security of the encryption, but also ensures the efficiency of the encryption and decryption process.

[0077] The ground control station is responsible for generating and managing encryption keys. The ground control station uses a secure random number generation algorithm to generate a 128-bit encryption key and distributes the key to the drone via a secure channel, such as a dedicated encrypted communication link. This ensures the security of the key during transmission, preventing it from being intercepted or tampered with by third parties. Before sending flight data, the drone preprocesses the data to ensure that the format and size meet the requirements of the AES algorithm. The drone then encrypts the data using the AES algorithm and the encryption key received from the ground control station. The encryption process involves multiple rounds of data substitution and permutation to convert the original data into ciphertext that cannot be directly deciphered. The encrypted flight data is then transmitted to the ground control station via a wireless channel. Upon receiving the encrypted data, the ground control station decrypts it using the same encryption key as the drone. The decryption process is the reverse of the encryption process, using multiple rounds of data substitution and permutation to restore the ciphertext to the original flight data.

[0078] Suppose a drone needs to send flight data containing altitude, speed, and direction to a ground control station. First, the ground control station generates a 128-bit encryption key and distributes it to the drone over a secure channel. Before sending the flight data, the drone uses the AES algorithm and this key to encrypt the data, generating a ciphertext that cannot be directly deciphered. The drone then sends this encrypted ciphertext to the ground control station. Upon receiving the ciphertext, the ground control station decrypts it using the same encryption key, successfully recovering the original flight data, including altitude, speed, and direction.

[0079] Example 3:

[0080] The specific implementation of the task scheduling module is as follows:

[0081] The task scheduling module receives the UAV task input from the user interface module. The task input information describes the task requirements, including the task type (such as reconnaissance, strike, rescue, etc.), the task objective (such as image acquisition at a specific location, destruction of enemy targets, etc.), the task priority (used to determine the urgency of task execution), and the resources required for task execution (such as specific communication equipment, computing power, storage space, etc.).

[0082] The task scheduling module intelligently assigns received tasks to the most suitable drone based on its current status, location, battery level, and specific mission requirements. This assignment takes into account factors such as drone availability, distance to the mission target, and remaining battery life to ensure efficient and reliable execution of tasks.

[0083] After the task allocation is completed, the task scheduling module will also sort the tasks assigned to the drone according to the priority and urgency of the tasks to ensure that high-priority tasks can be executed first, thereby meeting the urgency of task execution.

[0084] To meet the resource requirements during mission execution, the mission scheduling module also allocates necessary resources to the drone based on the specific mission requirements. These resources may include communication resources (to ensure stable communication between the drone and the ground control station), computing resources (to process and analyze data collected by the drone), and storage resources (to store data generated during mission execution).

[0085] During mission execution, the Task Scheduling module monitors the drone's mission status in real time. This includes mission progress (e.g., completion percentage), the drone's current status (e.g., altitude, speed, battery level), and any anomalies (e.g., equipment failure, communication interruption, etc.). This real-time monitoring allows the Task Scheduling module to promptly identify and address any issues encountered during mission execution.

[0086] Finally, the task scheduling module dynamically adjusts or reschedules tasks based on the actual performance of the drones and changes in mission requirements. For example, if a drone encounters an unexpected situation (such as sudden weather changes or equipment failure) while performing a mission, the task scheduling module may reassign the drone's mission to another available drone or adjust the execution order and priority of the tasks to ensure smooth execution and efficient completion of the overall mission.

[0087] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0088] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A Beidou message-based UAV communication system, characterized by: It includes the drone side, the communication layer and the ground control station; The UAV terminal includes a flight control module, a data acquisition module, a Beidou short message communication module and a communication adaptive module; the flight control module is used to control the flight state of the UAV according to a preset flight plan and real-time instructions; the data acquisition module is used to collect the flight data of the UAV in real time, and the flight data includes the position, speed, power and communication environment parameters of the UAV; the Beidou short message communication module is used to perform two-way short message communication with the ground control station through the Beidou satellite system, transmit flight data and receive control instructions; the communication adaptive module analyzes the communication environment parameters through a machine learning algorithm, and dynamically adjusts the communication protocol parameters according to the analysis results to adapt to different communication conditions; The communication layer includes a Beidou satellite system, a communication protocol module and a data encryption and decryption module; the Beidou satellite system is used to provide stable data transmission between the UAV terminal and the ground control station; the communication protocol module is used to define the communication protocol between the UAV terminal and the ground control station, including data format, transmission mode and verification mechanism; the data encryption and decryption module is used to encrypt and decrypt the transmitted data; The ground control station includes a command sending module, a data processing module, a task scheduling module and a user interface module; the command sending module is used to send control commands to the drone according to task requirements, including flight paths, shooting parameters and return commands; the data processing module is used to receive status information and collected data sent back by the drone, and perform real-time processing and analysis; the task scheduling module is used to uniformly manage and schedule multiple drone tasks, including task allocation, priority sorting and resource allocation; the user interface module is used to display the flight status of the drone and the data processed and analyzed in real time by the data processing module, and provide operation functions to realize flight control of the drone; The communication adaptive module collects the communication environment parameters of the UAV in real time, and the communication environment parameters include signal strength, noise level, channel occupancy, signal-to-noise ratio, bit error rate, delay time, packet loss rate, frequency offset and phase noise; The collected communication environment parameters are analyzed through a pre-trained protocol parameter prediction model, which can output the optimal communication protocol parameter adjustment suggestions based on the input communication environment parameters; According to the analysis results of the machine learning algorithm model, the communication protocol parameters of the UAV are dynamically adjusted to adapt to different communication conditions; the communication protocol parameters include modulation mode, coding rate, transmission power, data packet size, retransmission mechanism, carrier frequency and bandwidth; A neural network algorithm is used to build a protocol parameter prediction model. The specific steps include: Step 1: Construct a neural network model, which includes an input layer, a hidden layer, and an output layer. The input layer is used to receive the communication environment parameters of the drone, the hidden layer is used to perform nonlinear transformation and feature extraction, and the output layer is used to output the optimal communication protocol parameter adjustment suggestions; Step 2: Obtain a large amount of communication environment parameter data and corresponding communication protocol parameter data from the UAV communication system to form a training data set; and preprocess the data, including normalization, removal of outliers, and filling in missing values; Step 3: Use the training data set to train the neural network model, and adjust the model parameters through an iterative optimization algorithm so that the model output gradually approaches the actual communication protocol parameter adjustment suggestions; Step 4: Verify and test the trained neural network model; The training process of step 3 includes: Step 3.1: Using the preprocessed training dataset as input, input the communication environment parameters into the input layer of the neural network; Step 3.2: Perform nonlinear transformation and feature extraction through the hidden layer of the neural network. The output calculation formula of the hidden layer is: , where h represents the output of the hidden layer, σ represents the activation function, represents the weight matrix from the input layer to the hidden layer, x represents the input of the input layer, represents the bias of the hidden layer; Step 3.3: Pass the output of the hidden layer to the output layer. The output calculation formula of the output layer is: , where y represents the output of the output layer, i.e., the predicted communication protocol parameter adjustment suggestions, represents the weight matrix from the hidden layer to the output layer, represents the bias of the output layer; Step 3.4: Calculate the loss between the output of the output layer and the actual communication protocol parameter adjustment suggestion. The loss function calculation formula is: , where L represents the loss and n represents the number of samples. represents the output layer output of the i-th sample, represents the real communication protocol parameter adjustment suggestion for the i-th sample; Step 3.5: Use the gradient descent optimization algorithm to iteratively update the parameters of the neural network model according to the loss function until the preset stop condition is met to obtain a trained neural network model; In step 2, the Z-score standardization method is used to subtract the mean of each numerical data and divide it by its standard deviation so that the processed data conforms to the standard normal distribution. The formula for standardization is: ,in, is the original data, is the mean of the original data, is the standard deviation of the original data, is the standardized data.

2. The Beidou message-based unmanned aerial vehicle communication system according to claim 1, characterized in that: In step 2, for missing values, linear interpolation algorithm is used to fill them; for outliers, threshold judgment method is used to regard data points beyond the preset threshold range as outliers and replace them with the mean of their neighboring points.

3. The Beidou message-based unmanned aerial vehicle communication system according to claim 1, characterized in that: The data encryption and decryption module adopts the AES symmetric encryption algorithm, and the encryption key is 128 bits, which is generated by the ground control station and distributed to the drone end through a secure channel; before sending the flight data, the drone end uses the AES algorithm and encryption key to encrypt the data, and after receiving the encrypted data, the ground control station uses the same encryption key to decrypt the data to restore the original flight data.

4. The Beidou message-based unmanned aerial vehicle communication system according to claim 1, characterized in that: The data verification mechanism of the communication protocol module adopts CRC check code. The UAV end generates CRC check code before sending data, and the ground control station verifies the CRC check code after receiving the data.

5. The Beidou message-based unmanned aerial vehicle communication system according to claim 4, characterized in that: The specific implementation of the task scheduling module is as follows: receiving UAV mission input from the user interface module, including mission type, mission objectives, mission priority, and resources required for the mission; Assign the received tasks to the appropriate drone based on the drone’s current status, location, battery level, and mission requirements; Sort the tasks assigned to drones according to their priority and urgency to ensure that high-priority tasks are executed first; Allocate necessary resources to the UAV according to mission requirements, including communication resources, computing resources, and storage resources; Monitor the mission execution status of the drone in real time, including mission progress, drone status and abnormal situations; dynamically adjust or reschedule the mission according to the actual execution status of the drone and changes in mission requirements.

Images