An Unmanned Aerial Vehicle Seismic Source Landing Point Prediction and Adjustment Method and System Based on a Fusion Algorithm

Abstract

The present invention discloses a method and system for predicting and adjusting the landing point of an unmanned aerial vehicle (UAV) seismic source based on a fusion algorithm, belonging to the field of seismic exploration, and comprising the following steps: S1, collecting environmental data of the flight area, as well as the position, acceleration, and attitude data of the seismic source to form multi-source data; S2, determining the initial state information of the seismic source and transmitting the multi-source data and the determined initial state information to a remote server; S3, the remote server constructs a seismic source motion model based on the adaptive Runge-Kutta algorithm combined with deep learning, and simulates and predicts the flight trajectory of the seismic source based on the constructed seismic source motion model to generate flight trajectory and landing point prediction information; S4, generating a control instruction based on the flight trajectory and landing point prediction information to optimize the state parameters. By adopting the above method and system for predicting and adjusting the landing point of an unmanned aerial vehicle seismic source based on a fusion algorithm, based on multi-source data, the flight trajectory is calculated and optimized by using the fusion algorithm, and accurate throwing of the unmanned aerial vehicle seismic source is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of seismic exploration, and particularly to a method and system for predicting and adjusting the landing point of an unmanned aerial vehicle (UAV) seismic source based on a fusion algorithm. Background Art

[0002] With the vigorous development of science and technology, geophysical exploration technology is also continuously innovating. Among them, the UAV seismic source technology, as a new force in the field of geological exploration, has shown great application potential, thus bringing new ideas and methods to geological exploration work, and is expected to break through the limitations of traditional exploration means and achieve more efficient and accurate exploration operations.

[0003] However, in actual application scenarios, especially in the face of complex and changeable environments, the UAV seismic source throwing process is significantly affected by various environmental factors, such as wind speed, wind direction, throwing angle, and initial velocity. These factors are intertwined and become the key bottleneck restricting the accuracy of UAV seismic source technology, resulting in many challenges in the wide application of existing UAV seismic source technology.

[0004] At the same time, although the UAV seismic source system has the ability to perform basic geophysical exploration tasks, it has obvious deficiencies in dealing with real-time changing environmental factors. Due to the inability to fully consider the dynamic changes of the environment, the stability of the seismic source flight trajectory is difficult to guarantee, and the throwing deviation problem occurs from time to time, seriously affecting the accuracy of exploration results.

[0005] Moreover, when obtaining high-altitude environmental conditions, existing technologies mostly rely on the measured data of ground wind speed and wind direction for indirect speculation. However, the actual situation is that there is a large difference in wind speed between the ground and high altitudes, and this indirect speculation method cannot accurately reflect the actual flight environment of the seismic source. When the high-altitude environment changes, the traditional UAV seismic source system lacks corresponding adjustment and compensation mechanisms, making it difficult for the seismic source to accurately land, thereby causing deviations in exploration results.

[0006] In addition, the reasonable selection of the throwing angle and initial velocity plays a crucial role in the seismic source trajectory. For different exploration tasks, due to the different geological characteristics and task requirements of the target areas, it is necessary to flexibly adjust the throwing angle and initial velocity. However, the traditional UAV seismic source system has limited ability to dynamically adjust these parameters and is difficult to effectively optimize the flight trajectory in complex environments, greatly restricting the effect of exploration tasks. Summary of the Invention

[0007] The purpose of the present invention is to provide a method and system for predicting and adjusting the landing point of a UAV seismic source based on a fusion algorithm to solve the above technical problems.

[0008] To achieve the above purpose, the present invention provides a method for predicting and adjusting the landing point of a UAV seismic source based on a fusion algorithm, including the following steps:

[0009] S1. Collect the environmental data of the flight area, as well as the position, acceleration, and attitude data of the seismic source to form multi-source data;

[0010] S2. After preprocessing the multi-source data, determine the initial state information of the seismic source, and transmit the multi-source data and the determined initial state information to the remote server;

[0011] S3. The remote server constructs a seismic source motion model based on the adaptive Runge-Kutta algorithm combined with deep learning, and simulates and predicts the flight trajectory of the seismic source based on the constructed seismic source motion model to generate flight trajectory and landing point prediction information;

[0012] S4. Generate control instructions based on the flight trajectory and landing point prediction information to optimize the state parameters.

[0013] Preferably, the environmental data described in step S1 includes the wind speed , wind direction , temperature , humidity and air pressure data, the acceleration includes the acceleration data of the seismic source on the X, Y, and Z axes , and , the attitude data includes the pitch angle , roll angle and yaw angle ;

[0014] The wind speed includes the wind speed of the flight area on the X, Y, and Z axes , and .

[0015] Preferably, the initial state information described in step S2 includes the initial velocity, initial position, throwing angle, acceleration, flight angle, and direction of the seismic source, where the flight angle is the collected pitch angle , and the direction is the collected yaw angle ;

[0016] Specifically, it includes the following steps:

[0017] S21. Use the Kalman filter algorithm to preprocess the multi-source data;

[0018] S22. Integrate the preprocessed acceleration data to obtain the initial velocity of the seismic source:

[0019] (1);

[0020] In the formula, , , respectively represent the initial velocities of the seismic source on the X, Y, and Z axes at a certain moment; represents the initial time;

[0021] Take the coordinates of the seismic source when the UAV drops it as the initial position of the seismic source ;

[0022] At the same time, use the attitude data to determine the throwing angle :

[0023] (2);

[0024] In the formula, represents the initial velocity of the seismic source, and ; represents the target direction, and , represents the target position coordinates; represents the modulus of the initial velocity, and ; represents the modulus of the target direction, and ;

[0025] S23. Transmit the preprocessed multi-source data and the determined initial state information of the seismic source to the communication chip through the UART interface or the SPI interface, and the communication chip uses the NB-IoT protocol to transmit the data to the remote server.

[0026] Preferably, step S3 specifically includes the following steps:

[0027] S31. Set the initial step size and the preset tolerance error of the Runge-Kutta algorithm according to the initial state information of the seismic source and the environmental data, where , represents the expected flight duration of the seismic source, represents the expected number of calculation steps;

[0028] S32. Consider the factors of air resistance, gravity, and thrust to construct a motion model of the seismic source:

[0029] (3);

[0030] (4);

[0031] (5);

[0032] In the formula, respectively represent the position coordinates of the seismic source in the X-axis, Y-axis, and Z-axis directions in space; , , respectively represent the components of the instantaneous velocity of the seismic source in the X-axis, Y-axis, and Z-axis directions; , and respectively represent the components of the thrust in the X-axis, Y-axis, and Z-axis directions; represents the mass of the seismic source; represents the air resistance coefficient; represents the air density based on velocity, and , represents the partial pressure of dry air, represents the molar mass of dry air, represents the saturation water vapor pressure, represents the molar mass of water vapor, represents the universal gas constant; represents the projected area of the seismic source in the direction perpendicular to the instantaneous velocity; represents the acceleration due to gravity;

[0033] S33. Numerically solve the seismic source motion model using the fourth-order Runge-Kutta algorithm to predict the state of the seismic source:

[0034] (6);

[0035] Among them,

[0036] (7);

[0037] (8);

[0038] (9);

[0039] (10);

[0040] In the formula, and respectively represent the seismic source state information at the next moment and the current moment; , , , all represent slope estimation values; represents the step size; represents constructing the seismic source motion model;

[0041] S34. Collect historical data and train a deep learning model based on the historical data. Combine the trained deep learning model with the Runge-Kutta algorithm, and use the deep learning model to capture the non-linear relationship between environmental data and the seismic source trajectory to optimize the flight trajectory prediction.

[0042] Preferably, in step S33, an adaptive strategy is adopted to dynamically adjust the step size;

[0043] It specifically includes the following steps:

[0044] S331. Calculate the error estimation between the fourth-order Runge-Kutta algorithm and the second-order Runge-Kutta algorithm :

[0045] (11);

[0046] In the formula, and respectively represent the calculation results of the fourth-order Runge-Kutta algorithm and the second-order Runge-Kutta algorithm;

[0047] S332. Based on the error estimation Adjust the step size:

[0048] (12);

[0049] In the formula, represents the adjusted step size.

[0050] Preferably, step S34 specifically includes the following steps:

[0051] S341. During the process of calculating the seismic source movement trajectory by the Runge-Kutta algorithm, input the environmental data and seismic source state information at the current moment into the trained deep learning model to obtain the predicted correction value of the seismic source state at the next moment;

[0052] S342. Fuse the predicted correction value of the deep learning model with the calculation result of the Runge-Kutta algorithm to generate the final flight trajectory and landing point prediction information:

[0053] (13);

[0054] In the formula, represents the seismic source state generated after fusion; represents the predicted correction value of the seismic source state predicted by the deep learning model; represents the weight of the predicted correction value of the deep learning model.

[0055] Preferably, step S4 specifically includes the following steps:

[0056] S41. The remote server transmits the prediction result of the seismic source flight trajectory, the landing point prediction information, and the target information to the ground station. The ground station optimizes the seismic source state parameters through an optimization algorithm and generates a control instruction;

[0057] S42. The ground station transmits the control instruction back to the remote server through an encrypted communication protocol, and the remote server then transmits the control instruction to the microcontroller of the UAV through the cellular network;

[0058] S43. After the microcontroller decrypts the control instruction, it adjusts the state of the seismic source according to the control instruction.

[0059] Preferably, in step S41, a model predictive control algorithm is used to calculate the flight adjustment parameters of the UAV, and the flight adjustment parameters include the throwing angle adjustment amount and the initial velocity adjustment amount;

[0060] It specifically includes the following steps:

[0061] S411. Consider a discrete-time linear time-varying system to describe the motion of the seismic source and the UAV, and its state-space equation expression is:

[0062] (14);

[0063] In the formula, , , respectively represent the system matrix, the input matrix and the noise vector; represents the control input vector, and includes the throwing angle adjustment amount and the initial velocity adjustment amount ;

[0064] S412. Define a quadratic objective function to measure the deviation between the predicted state and the target state, as well as the change amount of the control input:

[0065] (15);

[0066] In the formula, represents the seismic source state predicted at the -th moment based on the information at the -th moment; represents the target state at the -th moment; represents the state weight matrix; represents the control input at the -th moment determined based on the information at the -th moment; represents the seismic source state predicted at the -th moment based on the information at the -th moment; represents the target state at the -th moment;

[0067] At the same time, add the following constraint conditions:

[0068] (16);

[0069] (17);

[0070] Wherein, and respectively represent the minimum and maximum values of the throwing angle; and respectively represent the minimum and maximum values of the initial velocity;

[0071] S413. Solve the quadratic objective function to determine the control input vector .

[0072] A UAV seismic source landing point prediction and adjustment system based on a fusion algorithm, which is used to execute a UAV seismic source landing point prediction and adjustment method based on a fusion algorithm, including:

[0073] A data acquisition module, which is used to acquire the environmental data of the flight area, as well as the acceleration and attitude data of the seismic source;

[0074] A microcontroller, which is used to determine the initial state information of the seismic source after preprocessing multi-source data, and adjust the flight parameters according to the control instructions fed back by the remote server;

[0075] A communication chip, which is used to upload the initial state information to the remote server;

[0076] A cellular module, which is used to configure network connection parameters and establish a cellular network connection between the communication chip and the remote server;

[0077] A remote server, which is used to generate flight trajectory and landing point prediction information according to the initial state information;

[0078] A ground station, which is used to generate control instructions based on the flight trajectory and landing point prediction information, optimize the flight parameters of the UAV and feed them back to the microcontroller;

[0079] The data acquisition module is connected to the microcontroller, the microcontroller communicates with the communication chip through the UART interface or the SPI interface, the communication chip communicates with the remote server bidirectionally through the cellular module, and the remote server communicates with the ground station bidirectionally.

[0080] Preferably, the data acquisition module includes a wind speed sensor, a wind direction sensor, a temperature and humidity sensor, and a barometer installed on the UAV, as well as a three-axis acceleration sensor, an attitude sensor, and a GPS integrated inside the seismic source;

[0081] Both the wind speed sensor and the wind direction sensor are connected to the microcontroller through a digital communication interface; the temperature and humidity sensor and the barometer are connected to the microcontroller through a digital interface.

[0082] Therefore, the present invention adopts the above-mentioned method and system for predicting and adjusting the landing point of an unmanned aerial vehicle (UAV) seismic source based on a fusion algorithm, and the beneficial effects are as follows:

[0083] 1. Accuracy: By integrating real-time environmental data, flight data, status data, and historical data, it can effectively reduce the prediction errors caused by factors such as wind speed, wind direction, and throwing angle, significantly improve the accuracy of seismic source placement, and provide accurate landing point prediction for the UAV seismic source.

[0084] 2. Real-time performance: Based on the continuously changing environmental data during flight, the prediction results can be updated in real time. The UAV can perform precise control accordingly to ensure that the landing point of the seismic source meets the target requirements, improving the flexibility and response speed of the system.

[0085] 3. Adaptability: The system fully considers the complex changes in different environmental conditions such as wind speed, wind direction, temperature, and humidity. In different environments such as mountains and coastal areas, it can optimize the flight trajectory to ensure the accurate placement of the seismic source.

[0086] 4. Multi-model fusion: Combining physical models, numerical integration methods, and machine learning techniques, where the physical model provides a theoretical basis and the machine learning algorithm processes complex non-linear relationships, improving the comprehensive performance of prediction and enabling the system to have high-precision theoretical analysis capabilities.

[0087] 5. Real-time monitoring and feedback: Real-time monitoring of the UAV flight trajectory, environmental changes, etc., and providing adjustment information for real-time adjustment of the flight mission through a feedback mechanism, improving the control accuracy and flight safety.

[0088] Next, through the drawings and embodiments, the technical solutions of the present invention will be further described in detail. Description of the Drawings

[0089] Figure 1 It is a flowchart of a method for predicting and adjusting the landing point of an unmanned aerial vehicle (UAV) seismic source based on a fusion algorithm according to the present invention. Detailed Embodiments

[0090] To make the objectives, technical solutions and advantages of the embodiments of the present invention more clearly understood, the following further describes the embodiments of the present invention in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention, and are not used to limit the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end.

[0091] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0092] The following describes in detail the embodiments of the present invention in conjunction with the accompanying drawings.

[0093] As Figure 1 shown, a method for predicting and adjusting the landing point of an unmanned aerial vehicle seismic source based on a fusion algorithm includes the following steps:

[0094] S1. Collect environmental data of the flight area, as well as the position, acceleration and attitude data of the seismic source to form multi-source data;

[0095] The environmental data described in step S1 includes the wind speed , wind direction , temperature , humidity and air pressure data. The acceleration includes the acceleration data of the seismic source on the X, Y, and Z axes , and . The attitude data includes the pitch angle , roll angle and yaw angle of the seismic source;

[0096] The wind speed includes the wind speed on the X, Y, and Z axes of the flight area , and .

[0097] S2. After preprocessing the multi-source data, determine the initial state information of the seismic source, and transmit the multi-source data and the determined initial state information to the remote server;

[0098] The initial state information described in step S2 includes the initial velocity, initial position, throwing angle, acceleration, flight angle, and direction of the seismic source, where the flight angle is the collected pitch angle and the direction is the collected yaw angle ;

[0099] It specifically includes the following steps:

[0100] S21. Preprocess the multi-source data using the Kalman filtering algorithm;

[0101] S22. Integrate the preprocessed acceleration data to obtain the initial velocity of the seismic source:

[0102] (1);

[0103] In the formula, , , respectively represent the initial velocities of the seismic source on the X, Y, and Z axes at time represents the initial time;

[0104] Take the coordinates of the UAV when it drops the seismic source as the initial position of the seismic source ;

[0105] At the same time, use the attitude data to determine the throwing angle :

[0106] (2);

[0107] In the formula, represents the initial velocity of the seismic source, and ; represents the target direction, and , represents the target position coordinates; represents the modulus of the initial velocity, and ; represents the modulus of the target direction, and ;

[0108] S23. Transmit the preprocessed multi-source data and the determined initial state information of the seismic source to the communication chip through the UART interface or SPI interface, and the communication chip uses the NB-IoT protocol to transmit the data to the remote server.

[0109] S3. The remote server constructs a seismic source motion model based on the adaptive Runge-Kutta algorithm combined with deep learning, and simulates and predicts the flight trajectory of the seismic source based on the constructed seismic source motion model to generate flight trajectory and landing point prediction information;

[0110] Step S3 specifically includes the following steps:

[0111] S31. Set the initial step size and preset tolerance error of the Runge-Kutta algorithm according to the initial state information of the seismic source and environmental data wherein, wherein, , represents the expected flight duration of the seismic source, represents the expected number of calculation steps;

[0112] S32. Construct a seismic source motion model considering air resistance, gravity, and thrust factors:

[0113] (3);

[0114] (4);

[0115] (5);

[0116] In the formula, respectively represent the position coordinates of the seismic source in the X-axis, Y-axis, and Z-axis directions in space; , , respectively represent the components of the instantaneous velocity of the seismic source in the X-axis, Y-axis, and Z-axis directions; , and respectively represent the components of the thrust in the X-axis, Y-axis, and Z-axis directions; represents the mass of the seismic source; represents the air resistance coefficient; represents the air density based on velocity, and , represents the partial pressure of dry air, represents the molar mass of dry air, represents the saturation water vapor pressure, represents the molar mass of water vapor, represents the universal gas constant; represents the projected area of the seismic source in the direction perpendicular to the instantaneous velocity; represents the acceleration due to gravity;

[0117] S33. Numerically solve the seismic source motion model using the fourth-order Runge-Kutta algorithm to predict the state of the seismic source:

[0118] (6);

[0119] wherein,

[0120] (7);

[0121] (8);

[0122] (9);

[0123] (10);

[0124] Wherein, and respectively represent the source state information at the next moment and the current moment; , , , all represent slope estimation values; represents the step size; represents constructing a source motion model;

[0125] In step S33, an adaptive strategy is adopted to dynamically adjust the step size;

[0126] It specifically includes the following steps:

[0127] S331. Calculate the error estimation between the fourth-order Runge-Kutta algorithm and the second-order Runge-Kutta algorithm :

[0128] (11);

[0129] Wherein, and respectively represent the calculation results of the fourth-order Runge-Kutta algorithm and the second-order Runge-Kutta algorithm;

[0130] S332. Based on the error estimation adjust the step size:

[0131] (12);

[0132] Wherein, represents the adjusted step size.

[0133] S34. Collect historical data, and train a deep learning model based on the historical data. Combine the trained deep learning model with the Runge-Kutta algorithm, and use the deep learning model to capture the non-linear relationship between environmental data and the source trajectory to optimize the flight trajectory prediction.

[0134] Step S34 specifically includes the following steps:

[0135] S341. During the process of calculating the source motion trajectory by the Runge-Kutta algorithm, input the environmental data and source state information at the current moment into the trained deep learning model to obtain a predicted correction value for the source state at the next moment;

[0136] S342. Fusion of the predicted correction value of the deep learning model with the calculation result of the Runge-Kutta algorithm to generate the final flight trajectory and landing point prediction information:

[0137] (13);

[0138] In the formula, represents the source state generated after fusion; represents the corrected value of the source state predicted by the deep learning model; represents the weight of the predicted correction value of the deep learning model.

[0139] S4. Generate control commands based on the flight trajectory and landing point prediction information to optimize the state parameters.

[0140] Step S4 specifically includes the following steps:

[0141] S41. The remote server transmits the prediction result of the source flight trajectory, the landing point prediction information, and the target information to the ground station. The ground station optimizes the source state parameters through an optimization algorithm and generates control commands;

[0142] In step S41, the model predictive control algorithm is used to calculate the flight adjustment parameters of the UAV, and the flight adjustment parameters include the throwing angle adjustment amount and the initial velocity adjustment amount;

[0143] It specifically includes the following steps:

[0144] S411. Consider a discrete-time linear time-varying system to describe the motion of the source and the UAV. Its state space equation expression is:

[0145] (14);

[0146] In the formula, , , respectively represent the system matrix, the input matrix, and the noise vector; represents the control input vector, and includes the throwing angle adjustment amount and the initial velocity adjustment amount ;

[0147] S412. Define a quadratic objective function to measure the deviation between the predicted state and the target state, as well as the change in the control input:

[0148] (15);

[0149] In the formula, represents based on the The source state at the moment predicted from the information at that moment; Indicates the target state at the moment; Indicates the state weight matrix; Indicates based on the information at the moment, the control input at the moment; The source state at the moment predicted from the information at that moment; Indicates the target state at the moment;

[0150] At the same time, add the following constraint conditions:

[0151] (16);

[0152] (17);

[0153] In the formula, and respectively represent the minimum and maximum values of the throwing angle; and respectively represent the minimum and maximum values of the initial velocity;

[0154] S413. Solve the quadratic objective function to determine the control input vector .

[0155] S42. The ground station transmits the control command back to the remote server through an encrypted communication protocol, and the remote server then transmits the control command to the microcontroller of the UAV through the cellular network. Among them, the remote server transmits information such as the real-time calculated flight trajectory, landing point offset, and control command to the ground station through protocols such as HTTP, MQTT, or WebSocket;

[0156] S43. After decrypting the control command, the microcontroller adjusts the source state according to the control command.

[0157] A UAV source landing point prediction and adjustment system based on a fusion algorithm, used to execute a UAV source landing point prediction and adjustment method based on a fusion algorithm, including:

[0158] A data acquisition module, used to acquire the environmental data of the flight area, as well as the acceleration and attitude data of the source;

[0159] A microcontroller, used to determine the initial state information of the source after preprocessing multi-source data, and adjust the flight parameters according to the control command feedback by the remote server;

[0160] A communication chip for uploading initial status information to a remote server;

[0161] A cellular module for configuring network connection parameters (such as APN, authentication key, etc.) and establishing a cellular network (such as 4G / 5G) connection between the communication chip and the remote server;

[0162] A remote server for generating flight trajectory and landing point prediction information based on the initial status information;

[0163] A ground station for generating control commands based on the flight trajectory and landing point prediction information, optimizing the flight parameters of the UAV and feeding them back to the microcontroller;

[0164] The data acquisition module is connected to the microcontroller. The microcontroller communicates with the communication chip via the UART interface or SPI interface. The communication chip communicates bidirectionally with the remote server via the cellular module. The remote server communicates bidirectionally with the ground station.

[0165] The data acquisition module includes a wind speed sensor, a wind direction sensor, a temperature and humidity sensor, and a barometer installed on the UAV, as well as a three-axis acceleration sensor, an attitude sensor, and a GPS integrated inside the vibration source. Both the wind speed sensor and the wind direction sensor are connected to the microcontroller through a digital communication interface. The temperature and humidity sensor and the barometer are connected to the microcontroller through a digital interface.

[0166] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for predicting and adjusting the landing point of an unmanned aerial vehicle seismic source based on a fusion algorithm, characterized in that: The steps include the following: S1. Collect the environmental data of the flight area, as well as the position, acceleration, and attitude data of the seismic source to form multi-source data; S2. After preprocessing the multi-source data, determine the initial state information of the seismic source, and transmit the multi-source data and the determined initial state information to the remote server; S3. The remote server constructs a seismic source motion model based on the adaptive Runge-Kutta algorithm combined with deep learning, and simulates and predicts the flight trajectory of the seismic source based on the constructed seismic source motion model to generate flight trajectory and landing point prediction information; Step S3 specifically includes the following steps: S31. Set the initial step size of the Runge-Kutta algorithm according to the initial state information of the seismic source and the environmental data and the preset tolerance error , where , represents the expected flight duration of the seismic source, represents the expected number of calculation steps; S32. Consider the factors of air resistance, gravity, and thrust to construct a seismic source motion model; S33. Use the fourth-order Runge-Kutta algorithm to numerically solve the seismic source motion model and predict the state of the seismic source; In step S33, an adaptive strategy is adopted to dynamically adjust the step size; It specifically includes the following steps: S331. Calculate the error estimation between the fourth-order Runge-Kutta algorithm and the second-order Runge-Kutta algorithm : （11）； In the formula, and represent the calculation results of the fourth-order Runge-Kutta algorithm and the second-order Runge-Kutta algorithm, respectively; S332. Error Estimation Based Adjust the step size: （12）； In the formula, represents the step size; represents the adjusted step size; S34. Collect historical data, train a deep learning model based on the historical data, combine the trained deep learning model with the Runge-Kutta algorithm, and use the deep learning model to capture the non-linear relationship between the environmental data and the seismic source trajectory to optimize the flight trajectory prediction; Step S34 specifically includes the following steps: S341. During the process of the Runge-Kutta algorithm calculating the seismic source motion trajectory, input the environmental data and seismic source state information at the current moment into the trained deep learning model to obtain the predicted correction value of the seismic source state at the next moment; S342. Integrate the predicted correction value of the deep learning model with the calculation result of the Runge-Kutta algorithm to generate the final flight trajectory and landing point prediction information: （13）； In the formula, represents the seismic source state generated after fusion; represents the correction value of the seismic source state predicted by the deep learning model; represents the weight of the correction value predicted by the deep learning model; represents the seismic source state information at the next moment; S4. Generate control instructions based on the flight trajectory and landing point prediction information to optimize the state parameters.

2. The method for predicting and adjusting the landing point of a drone seismic source based on a fusion algorithm according to claim 1, wherein: The environmental data described in step S1 includes the wind speed in the flight area , wind direction , temperature , humidity and air pressure data. The acceleration includes the acceleration data of the seismic source on the X, Y, and Z axes , and . The attitude data includes the pitch angle , roll angle and yaw angle ; Wind speed including the wind speeds in the X, Y, and Z axes of the flight area , and .

3. A method for predicting and adjusting the landing point of an unmanned aerial vehicle seismic source based on a fusion algorithm according to claim 2, characterized in that: The initial state information described in step S2 includes the initial velocity, initial position, throwing angle, acceleration, flight angle, and direction of the seismic source, where the flight angle is the collected pitch angle , and the direction is the collected yaw angle ; It specifically includes the following steps: S21. Use the Kalman filter algorithm to preprocess the multi-source data; S22. Integrate the preprocessed acceleration data to obtain the initial velocity of the seismic source: （1）； In the formula, , , respectively represent the initial velocities of the seismic source on the X, Y, and Z axes at the moment; represents the initial time; Use the coordinates when the drone drops the seismic source as the initial position of the seismic source ; At the same time, use the attitude data to determine the throwing angle : （2）； In the formula, represents the initial velocity of the seismic source, and ; represents the target direction, and , represents the target position coordinates; represents the modulus of the initial velocity, and ; represents the modulus of the target direction, and ; S23. Transmit the preprocessed multi-source data and the determined initial state information of the seismic source to the communication chip through the UART interface or SPI interface, and the communication chip uses the NB-IoT protocol to transmit the data to the remote server.

4. A method for predicting and adjusting the landing point of an unmanned aerial vehicle seismic source based on a fusion algorithm according to claim 3, characterized in that: The expression for constructing the seismic source motion model considering the factors of air resistance, gravity, and thrust described in step S32 is as follows: （3）； （4）； （5）； In the formula, respectively represent the position coordinates of the seismic source along the X-axis, Y-axis, and Z-axis directions in space; , , respectively represent the components of the instantaneous velocity of the seismic source in the X-axis, Y-axis, and Z-axis directions; , and respectively represent the components of the thrust force in the X-axis, Y-axis, and Z-axis directions; represents the mass of the seismic source; represents the air resistance coefficient; represents the air density based on velocity, and , represents the partial pressure of dry air, represents the molar mass of dry air, represents the saturation water vapor pressure, represents the molar mass of water vapor, represents the universal gas constant; represents the projected area of the seismic source in the direction perpendicular to the instantaneous velocity; represents the acceleration due to gravity; The expression for numerically solving the seismic source motion model using the fourth-order Runge-Kutta algorithm and predicting the state of the seismic source described in step S33 is as follows: （6）； Wherein, （7）； （8）； （9）； （10）； Wherein, and respectively represent the source state information at the next moment and the current moment; , , , all represent the slope estimation values; represents constructing a source motion model.

5. A method for predicting and adjusting the landing point of an unmanned aerial vehicle seismic source based on a fusion algorithm according to claim 4, characterized in that: Step S4 Specifically includes the following steps: S41. The remote server transmits the prediction result of the seismic source flight trajectory, the landing point prediction information, and the target information to the ground station. The ground station optimizes the state parameters of the seismic source through an optimization algorithm and generates control instructions; S42. The ground station transmits the control instructions back to the remote server through an encrypted communication protocol, and the remote server then transmits the control instructions to the microcontroller of the unmanned aerial vehicle through the cellular network; S43. After decrypting the control instructions, the microcontroller adjusts the state of the seismic source according to the control instructions.

6. The method for predicting and adjusting the landing point of a drone seismic source based on a fusion algorithm according to claim 5, characterized in that: In step S41, a model predictive control algorithm is used to calculate the flight adjustment parameters of the unmanned aerial vehicle, and the flight adjustment parameters include the throwing angle adjustment amount and the initial velocity adjustment amount; It specifically includes the following steps: S411. Consider a discrete-time linear time-varying system to describe the motion of the seismic source and the UAV. The expression of its state-space equation is as follows: （14）； In the formula, , , represent the system matrix, the input matrix, and the noise vector respectively; represents the control input vector, and includes the throwing angle adjustment amount and the initial velocity adjustment amount ; S412. Define a quadratic objective function to measure the deviation between the predicted state and the target state, as well as the change in the control input: （15）； Wherein, represents the source state at the th moment predicted based on the information at the th moment; represents the target state at the th moment; represents the state weight matrix; represents the control input at the th moment determined based on the information at the th moment; represents the source state at the th moment predicted based on the information at the th moment; represents the target state at the th moment; Meanwhile, add the following constraint conditions: （16）； （17）； In the formula, and respectively represent the minimum and maximum values of the throwing angle; and respectively represent the minimum and maximum values of the initial velocity; S413. Solve the quadratic objective function Determine the control input vector .

7. A UAV seismic source landing point prediction and adjustment system based on a fusion algorithm, which is used to execute the method for predicting and adjusting the landing point of a UAV seismic source based on a fusion algorithm according to claim 6, and is characterized in that: Including: A data acquisition module, which is used to acquire the environmental data of the flight area, as well as the acceleration and attitude data of the seismic source; A microcontroller, which is used to determine the initial state information of the seismic source after preprocessing multi-source data, and adjust the flight parameters according to the control instructions fed back by the remote server; A communication chip, which is used to upload the initial state information to the remote server; A cellular module, which is used to configure the network connection parameters and establish a cellular network connection between the communication chip and the remote server; A remote server, which is used to generate flight trajectory and landing point prediction information according to the initial state information; A ground station, which is used to generate control instructions based on the flight trajectory and landing point prediction information, optimize the flight parameters of the UAV and feed them back to the microcontroller; The data acquisition module is connected to the microcontroller. The microcontroller communicates with the communication chip through the UART interface or the SPI interface. The communication chip communicates bidirectionally with the remote server through the cellular module. The remote server communicates bidirectionally with the ground station.

8. A drone seismic source landing point prediction and adjustment system based on a fusion algorithm according to claim 7, characterized in that: The data acquisition module includes a wind speed sensor, a wind direction sensor, a temperature and humidity sensor, and a barometer installed on the UAV, as well as a three-axis acceleration sensor, an attitude sensor, and a GPS integrated inside the seismic source; Both the wind speed sensor and the wind direction sensor are connected to the microcontroller through a digital communication interface; the temperature and humidity sensor and the barometer are connected to the microcontroller through a digital interface.

Images