Long-endurance AUV (Autonomous Underwater Vehicle) and seabed data center fused intelligent cooperative monitoring method

Abstract

The invention discloses a long-endurance AUV (Autonomous Underwater Vehicle) and seabed data center fused intelligent cooperative monitoring method. According to the method, real-time monitoring, data transmission and intelligent feedback of a marine environment are realized through cooperative work of an autonomous underwater vehicle (AUV) and a submarine data center (UDC). The AUV is provided with a long-endurance gliding mode and a buoyancy adjusting system, long-time monitoring tasks can be executed with low energy consumption, and real-time transmission of data is ensured through a wireless communication module and a submarine cable communication system. Through an intelligent path planning algorithm and an external environment forecasting system, the AUV can autonomously adjust a navigation path to adapt to a complex and changeable marine environment. And meanwhile, the AUV has the functions of monitoring and maintaining the external structure of the seabed data center in real time, so that the stability and the operation efficiency of the data center are effectively improved. The system has the advantages of long endurance, high real-time performance, high autonomy and intelligent maintenance, and is suitable for large-scale marine environment monitoring and data center management.

Description

Technical Field

[0001] The present invention relates to the field of ocean monitoring and autonomous vehicle technology, and specifically to an intelligent collaborative monitoring method integrating a long-endurance AUV with a seabed data center. Background Art

[0002] With the rapid growth of global data volume, underwater data centers (UDCs) have gradually become an important choice for large-scale data storage and processing. They use the natural cooling capacity of seawater to significantly reduce energy consumption while providing higher security and stability. However, the operation of underwater data centers is affected by the complex marine environment, and its external environmental conditions pose great challenges to performance, lifespan and maintenance.

[0003] Existing ocean monitoring equipment, such as AUVs, underwater sensors and buoys, have limited endurance, narrow monitoring range and energy management issues. Traditional AUVs are difficult to conduct long-term deep-sea monitoring due to power constraints, and they need to frequently return to recharge, resulting in mission interruptions. In addition, underwater communication technology is greatly affected by the environment, radio waves are limited in propagation underwater, and acoustic communication is susceptible to interference, which cannot meet the needs of real-time data transmission.

[0004] At the same time, existing AUVs lack autonomous path planning capabilities and are difficult to adjust tasks according to real-time environmental changes, limiting their adaptability in complex marine environments. In addition, the outer shell of the submarine data center is susceptible to the attachment of marine organisms, resulting in reduced heat dissipation efficiency, and existing technologies cannot effectively monitor and maintain its external status, increasing maintenance costs and operational risks.

[0005] Therefore, there is an urgent need for an intelligent collaborative monitoring solution between AUVs and submarine data centers to achieve long-term, large-scale, real-time monitoring and intelligent maintenance of the external environment of the data center. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent collaborative monitoring method integrating long-endurance AUV and submarine data center, which has the advantages of long endurance, real-time data transmission, autonomous path optimization, and intelligent data center maintenance, and solves the problems of short endurance, data transmission delay, poor environmental adaptability and difficult maintenance of submarine data center in existing monitoring equipment.

[0007] To achieve the above object, the present invention provides the following technical solution: an intelligent collaborative monitoring method integrating a long-endurance AUV with a submarine data center, comprising the following steps:

[0008] S1: Initialization and mission planning

[0009] S1.1 Mission configuration: In the control system of the submarine data center (UDC), preset the mission parameters of the AUV, including monitoring range, monitoring cycle, path planning and target environmental variables; S1.2 Communication initialization: Establish a communication connection between the AUV and the UDC, and use the submarine cable communication system or the acoustic wave communication system to synchronize the mission instructions and system status. The submarine cable communication system is used for long-term stable data transmission, while the acoustic wave communication system is used for short-term communication tasks; S1.3 Energy configuration: Check and replenish the energy of the AUV through the energy management system of the UDC cluster to ensure that the AUV has enough power to complete the long-term monitoring mission;

[0010] S2: AUV autonomous monitoring mission execution

[0011] S2.1 Start the voyage: The AUV departs from the UDC cabin according to the predetermined path, uses the long-endurance gliding mode and buoyancy adjustment system to achieve low-energy navigation, and controls the attitude of the vehicle through the eccentric structure to ensure that it sinks or rises in a spiral manner, so as to carry out monitoring tasks in the target area; S2.2 Data acquisition: The AUV monitors the marine environment in real time through the integrated temperature sensor, pressure sensor and flow rate sensor, and detects the biological attachment and temperature distribution of the UDC shell through the camera module; S2.3 Real-time transmission and storage: Through the wireless communication module, the AUV transmits the collected monitoring data to the UDC cluster server in real time, and the monitoring data will be stored in the central server for subsequent analysis;

[0012] S3: Intelligent collaborative monitoring and feedback

[0013] S3.1 Environmental change perception: AUV uses built-in sensors to detect environmental parameters such as temperature, pressure and ocean currents in real time. When sudden environmental changes are detected, AUV feeds back data to the UDC cluster through the wireless communication module, and the UDC cluster adjusts the mission parameters and path planning of AUV accordingly; S3.2 Intelligent control: The UDC cluster uses the real-time data provided by the external environment forecasting system to dynamically control the energy distribution and heat dissipation management system of AUV through intelligent control algorithms to ensure the smooth progress of monitoring tasks in complex marine environments;

[0014] S4: Collaborative docking between AUV and UDC

[0015] S4.1 Automatic docking: After the AUV completes its mission, it will automatically return to the UDC cabin, and realize power replenishment through the power interface at the docking station, and information exchange through the data interface to ensure that the AUV has the ability to complete the next mission; S4.2 Data synchronization and storage: The AUV transmits the monitoring data to the central server of the UDC cluster, and further transmits the data to the shore-based control center through the composite cable to ensure the integrity and security of the monitoring data; S4.3 Self-inspection and maintenance: The UDC cluster conducts self-inspection of the AUV's sensors, camera modules and propulsion systems through the automatic diagnostic system, and cleans the biological attachments on the AUV shell through the cleaning module to ensure that it can work normally in the next mission;

[0016] S5: Dynamic task optimization and continuous monitoring

[0017] S5.1 Dynamic path adjustment: The UDC cluster optimizes the mission path through a dynamic path planning algorithm based on the environmental data provided by the external environment forecasting system and the shore-based control center, combined with the energy status of the AUV, to ensure that the AUV can continue to perform monitoring tasks in complex environments; S5.2 Continuous monitoring cycle: The AUV performs a new round of monitoring tasks based on the optimized mission parameters, and ensures the validity of the monitoring data and the stability of the system operation through a real-time feedback mechanism.

[0018] Preferably, the preliminary measurement calibration algorithm is used to process the monitoring data collected by the AUV, the input is temperature, pressure, and flow rate, and the output is the preliminary calibration result. The algorithm formula is: F1(x)=α1·M(x)+ε1, where: M(x) represents the sensor data obtained by the AUV, α1 is the preliminary calibration factor, and ε1 is the system error term.

[0019] Preferably, the secondary precision calibration algorithm is used to perform precision correction based on the preliminary measurement calibration algorithm. The input is the output of the preliminary measurement calibration algorithm and the external environmental conditions, and the output is the corrected calibration result. The formula is: F2(y)=β1·F1(x)+γ(T,V)+ε2, wherein: T is the ambient temperature, V is the ocean current speed, γ(T,V) is the correction factor, and ε2 is the correction error term.

[0020] Preferably, the comprehensive evaluation algorithm is used to initially measure the output results of the calibration algorithm and the secondary precision calibration algorithm to construct a performance evaluation index, and the algorithm formula is: F3(z)=λ1·log(F1(x))+λ2·exp(F2(y))+ε3, where: λ1 and λ2 are dynamic weight factors

[0021] , ε3 is the global error compensation term.

[0022] Preferably, in the energy configuration of S1.3, the UDC cluster dynamically monitors the energy demand of the AUV, including the following sub-steps:

[0023] S1.3.1 Energy evaluation: Based on the mission duration and monitoring range, the total energy required for the AUV to perform the mission is estimated, and the energy consumption rate is dynamically calculated in combination with the environmental parameters during the mission; S1.3.2 Energy replenishment strategy: By monitoring the power status of the AUV, the UDC cluster determines when the AUV needs to return to the charging station and plans the most energy-efficient path and the best charging time window; S1.3.3 Endurance optimization: Based on the urgency of the mission and the energy consumption curve in the mission path, the AUV's gliding mode and sensor operating frequency are dynamically adjusted to maximize the endurance time.

[0024] Preferably, during the start of navigation in S2.1, the AUV plans the mission and specifically includes the following sub-steps:

[0025] S2.1.1 Path initialization: The AUV starts the navigation module according to the predetermined mission path. The vehicle first adjusts its buoyancy module to reach the predetermined cruising depth, and at the same time starts the spiral diving mode, adjusts the eccentric structure and power module of the vehicle to achieve spiral sinking and obtain multi-angle monitoring perspectives; S2.1.2 Propulsion system optimization: The vehicle dynamically optimizes its propulsion efficiency by adjusting the inclination angle of the blades to cope with different water flow resistances, while maintaining energy saving, ensuring that the navigation speed and maneuverability adapt to environmental changes; S2.1.3 Monitoring system startup: When the vehicle reaches the preset monitoring area, it starts its temperature, pressure, flow rate and camera modules, collects data at predetermined intervals, and transmits monitoring data back to the UDC cluster in real time; S2.1.4 Path feedback and adjustment: During the path execution process, the vehicle provides real-time feedback on its energy consumption, environmental resistance and navigation status. The UDC cluster dynamically adjusts the vehicle's path planning based on real-time data to optimize energy consumption distribution.

[0026] Preferably, in S2.3 real-time transmission and storage, the AUV will transmit data to the UDC cluster server in real time through the wireless communication system. The data includes calibrated monitoring parameters, which specifically include the following sub-steps: S2.3.1 Data compression and preprocessing: Before transmitting the data, the AUV compresses and preprocesses the original monitoring data to remove noise and redundant information to reduce transmission delay and improve transmission efficiency; S2.3.2 Real-time transmission mechanism: Through the wireless communication module, the compressed and calibrated monitoring data is transmitted to the UDC cluster in real time to ensure the real-time and integrity of the data; S2.3.3 Data backup and distribution: The UDC cluster backs up the received data in multiple nodes, and distributes some key data to the shore-based control center in real time for analysis and task adjustment.

[0027] Preferably, in the environmental change perception S3.1, the AUV can detect the temperature changes and ocean current changes in the environment, and transmit the data to the UDC cluster through the feedback mechanism, which specifically includes the following sub-steps: S3.1.1 Environmental data acquisition: The AUV regularly collects environmental parameters through the installed temperature sensors and ocean current sensors, and increases the collection frequency when a sudden change occurs; S3.1.2 Data anomaly detection: The AUV performs real-time analysis on the collected data to determine whether there is an abnormal situation that does not match the expected value; S3.1.3 Feedback mechanism: Once abnormal data is detected, the AUV immediately sends feedback to the UDC cluster through wireless communication. The UDC cluster adjusts the AUV's mission parameters in real time according to the feedback, and plans a path to avoid areas of environmental abnormality.

[0028] Preferably, in the self-inspection and maintenance S4.3, the UDC cluster cleans the camera and sensors of the AUV and handles external biological attachments, which specifically includes the following sub-steps: S4.3.1 Sensor self-inspection: After returning to the UDC cabin, the AUV automatically detects the status of each sensor, including the clarity of the camera, the response sensitivity of the pressure sensor, and generates a self-inspection report; S4.3.2 Biological attachment cleaning: The UDC cluster uses automated cleaning equipment to clean biological attachments on the AUV outer shell and key sensor areas to ensure the accuracy of the monitoring data; S4.3.3 Equipment maintenance and care: Perform routine inspections and maintenance on key components of the AUV to ensure that the equipment can operate normally in the next mission.

[0029] Preferably, in S5.1 dynamic path adjustment, the following sub-steps are specifically included:

[0030] S5.1.1 Data fusion and analysis: The UDC cluster analyzes the environmental monitoring data sent back by the AUV, including real-time changes in temperature, pressure and flow rate, and combines these data with the external environment forecasting system to generate a complete environmental model to determine the necessity of adjusting the navigation path; S5.1.2 Energy and efficiency evaluation: Combined with the current energy level of the AUV and the obstacles and environmental conditions in the navigation path, the optimal energy consumption curve is calculated, and the navigation path is optimized to ensure that the vehicle can maximize the use of its energy to complete the monitoring task; S5.1.3 Obstacle avoidance path planning: The UDC cluster generates an obstacle avoidance path in real time by comprehensively analyzing the obstacle data in the monitoring area, ensuring that the vehicle can safely bypass potential obstacles, and dynamically updates the obstacle avoidance strategy according to the real-time position of the obstacles; S5.1.4 Real-time path update and feedback: When the current path of the vehicle is no longer suitable for continued advancement, the UDC cluster transmits the adjusted path to the vehicle through the wireless communication module, and the vehicle adjusts its navigation direction and speed in real time according to the instructions to adapt to the new monitoring needs.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. The present invention realizes low-energy consumption and long-term monitoring of AUV by setting a long-endurance gliding mode and a buoyancy adjustment system, thereby achieving the effect of extending the endurance of the monitoring equipment and reducing energy consumption, thereby solving the problem of insufficient endurance of existing equipment.

[0033] 2. The present invention ensures the real-time transmission and feedback of monitoring data by combining the wireless communication module with the submarine cable communication system, thereby achieving the advantages of improving data transmission speed and reducing communication delay, and solving the problem of untimely data transmission in the prior art.

[0034] 3. The present invention realizes real-time dynamic adjustment of the AUV mission path by combining an intelligent path planning algorithm with an external environment forecasting system, thereby achieving the effect of improving environmental adaptability and optimizing mission execution efficiency, and solving the problem that traditional equipment cannot cope with complex marine environment changes.

[0035] 4. Through the collaborative work of AUV and submarine data center, the present invention has the ability to monitor the external environment of the submarine data center in real time, and can perform intelligent maintenance on the temperature changes and biological attachment of the data center, thereby reducing manual intervention and improving the stability of the data center, and solving the problem of difficult maintenance of the submarine data center. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of the intelligent collaborative monitoring method integrating the long-endurance AUV and the submarine data center of the present invention;

[0037] Figure 2 This is a flow chart of the preliminary measurement calibration algorithm of the present invention;

[0038] Figure 3 It is a flow chart of the secondary precision calibration algorithm of the present invention;

[0039] Figure 4 This is a flow chart of the comprehensive evaluation algorithm of the present invention;

[0040] Figure 5 This is a flow chart of energy configuration and battery life optimization of the present invention;

[0041] Figure 6 This is a flowchart of the AUV starting navigation of the present invention;

[0042] Figure 7 This is a real-time transmission and storage flow chart of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0044] See also Figures 1 to 7 The present invention provides an intelligent collaborative monitoring method integrating a long-endurance AUV (autonomous underwater vehicle) and a submarine data center (UDC). The method can perform long-term, large-scale marine monitoring tasks in a complex marine environment, and solve the problems of short endurance of existing monitoring equipment, communication delays, and difficult maintenance of submarine data centers.

[0045] S1: Initialization and mission planning,Before the monitoring mission begins, the AUV and UDC cluster need to be initialized and,planned to ensure efficient collaboration of the system.

[0046] S1.1 Mission configuration: In the UDC control system, the mission parameters of the AUV are pre-configured, including the sea area to be monitored, the execution cycle of the mission, the planning of the navigation path, and the environmental variables of the monitoring target (such as temperature, pressure, ocean currents, etc.). Through this configuration, the AUV can perform a variety of tasks in different monitoring areas. For example, the AUV can be assigned to monitor changes in certain specific water environments, or it can perform monitoring in different depth ranges according to mission requirements.

[0047] S1.2 Communication initialization: Establish a communication connection between the AUV and the UDC. In long-distance communication, the AUV can use the submarine cable communication system to achieve long-term and stable data transmission; in short-term monitoring or data exchange, the AUV can synchronize mission instructions and update status through the acoustic communication system. This dual communication method ensures that the AUV can maintain efficient data interaction with the UDC at different mission stages. S1.3 Energy configuration: Through the energy management system of the UDC cluster, the AUV performs energy inspection and power replenishment before the mission begins. Since ocean monitoring is usually a long-term mission, the AUV needs to have sufficient power. The UDC will intelligently allocate and replenish power according to the energy consumption of the AUV to ensure that it can complete the entire monitoring mission.

[0048] S2: AUV autonomous monitoring mission execution. After completing mission planning and energy preparation, the AUV enters the autonomous monitoring mission phase.

[0049] S2.1 Start the voyage: The AUV departs from the UDC cabin and uses its long-endurance gliding mode and buoyancy adjustment system to achieve low-energy gliding navigation. During the voyage, the AUV controls its attitude by adjusting the eccentric structure, slowly sinking or rising in a spiral manner. This method not only improves the stability of the voyage, but also expands the coverage of the monitoring. The gliding mode saves a lot of energy by reducing the use of the electric propulsion system. S2.2 Data acquisition: During the voyage, the AUV monitors the changes in the marine environment in real time through the integrated temperature sensor, pressure sensor and flow rate sensor. At the same time, the AUV's camera module is used to detect the biological adhesion and temperature distribution of the shell of the submarine data center. These data will help the UDC understand the impact of the external environment on the operation of the equipment in real time. S2.3 Real-time transmission and storage: Through the wireless communication module, the AUV transmits the real-time monitored data to the central server of the UDC cluster to ensure that the data can be analyzed and stored immediately. In this way, the monitoring results can be quickly transmitted to the control center and used for subsequent task adjustments.

[0050] S3: Intelligent collaborative monitoring and feedback. In the present invention, the AUV can not only perform tasks, but also collaborate intelligently with the UDC to optimize task execution through a real-time feedback mechanism. S3.1 Perception of environmental changes: The AUV uses built-in sensors to detect parameters such as temperature, pressure, and ocean currents in the marine environment in real time. When sudden environmental changes are detected, such as sudden changes in ocean currents or abnormal temperatures, the AUV immediately feeds back the data to the UDC cluster through the wireless communication module. The UDC cluster will adjust the AUV's mission parameters based on these environmental changes, including changes in the monitoring area or adjustments to task priorities. S3.2 Intelligent regulation: The UDC cluster not only responds to environmental changes, but also dynamically regulates the AUV's energy distribution and heat dissipation management system through intelligent control algorithms based on data provided by the external environment forecasting system. This intelligent regulation mechanism can ensure that the AUV can efficiently perform tasks even in complex marine environments.

[0051] S4: AUV and UDC coordinate docking. After the mission is completed, the AUV needs to dock with the UDC for data transmission, equipment maintenance and energy replenishment.

[0052] S4.1 Automatic docking: After the AUV mission is completed, it will automatically return to the UDC cabin and replenish power for the AUV through the power interface of the docking station. At the same time, the monitoring data is transmitted through the data interface to ensure that the data can be stored and backed up after the mission is completed. S4.2 Data synchronization and storage: Through the composite cable, the data monitored by the AUV will be transmitted from the UDC central server to the shore-based control center to ensure the integrity and security of the data. The composite cable provides a high-bandwidth data transmission path to ensure that large amounts of data can be transmitted quickly and reliably. S4.3 Self-inspection and maintenance: The UDC cluster uses an automatic diagnostic system to check various sensors, camera modules and propulsion systems of the AUV, and uses a cleaning module to clean biological attachments on the AUV's outer shell to ensure its normal operation in the next mission.

[0053] S5: Dynamic mission optimization and continuous monitoring. The AUV in the present invention has the ability of dynamic mission optimization, ensuring that it can continuously and efficiently perform monitoring tasks over a long period of time.

[0054] S5.1 Dynamic path adjustment: The UDC cluster combines the data provided by the external environment forecasting system and the analysis of the environment by the shore-based control center to adjust the AUV's monitoring path in real time. Through the dynamic path planning algorithm, the AUV can avoid complex underwater environments, optimize navigation efficiency, and minimize energy consumption. S5.2 Continuous monitoring cycle: After completing the mission path optimization, the AUV can perform new monitoring tasks. In this process, through the real-time feedback mechanism, the monitoring data can be continuously transmitted back to the UDC to ensure the monitoring efficiency of the entire system and the validity of the data;

[0055] The preliminary measurement calibration algorithm is used to process the monitoring data collected by the AUV. The input parameters include temperature, pressure, and flow rate, and the output is the result after preliminary calibration. The formula of the algorithm is as follows: F1(x) = α1·M(x) + ε1, F1(x) is the output result of the preliminary measurement calibration, which represents the monitoring data after preliminary error correction. This output is used for subsequent accuracy calibration or directly transmitted to the UDC cluster for storage and analysis. As the basic data for further processing and calibration, it ensures that the original sensor data has a high accuracy when entering the next step of processing, reducing the impact of subsequent errors;

[0056] M(x) represents the raw monitoring data collected by the AUV through sensors, including marine environmental parameters such as temperature, pressure and flow rate. When performing monitoring tasks, the AUV collects this data from the environment through integrated temperature sensors, pressure sensors and flow rate sensors. The selection of specific sensor types depends on the specific needs of the monitoring area. For example, deep sea areas require higher pressure sensor accuracy, while shallow sea areas may pay more attention to changes in temperature gradients. In gliding mode, the AUV performs fixed-point or continuous data collection through a set path and depth. The data collection frequency can be adjusted according to the mission requirements. For example, when monitoring sensitive areas, the data collection frequency is higher;

[0057] α1 is a preliminary calibration factor used to adjust errors in raw sensor data. This factor is set primarily based on sensor characteristics, environmental conditions, and historical data from equipment calibration. This factor is usually obtained through laboratory calibration before system deployment and is dynamically adjusted based on the sensor's long-term usage record. Different sensors will have different calibration factors. For example, a temperature sensor may exhibit a different response than under standard conditions in a high-pressure deep-sea environment, so it will be calibrated experimentally before the mission begins to determine the applicable calibration factor; the α1 calibration factor is determined by minimizing the difference between the measured data and the true value. This is usually done through repeated testing with a series of known environmental conditions and known data, and the resulting calibration coefficient is used to correct the measurement deviation of the device in the actual environment.

[0058] ε1 is the systematic error term, which represents the noise or systematic error that cannot be avoided during the sensor data acquisition process. The systematic error term usually comes from the noise of the sensor itself, environmental interference (such as ocean currents, temperature differences), sensor wear, etc. This error is inevitable in the sensor design and manufacturing process, but its impact can be minimized through filtering algorithms or signal processing technology; in practical applications, the systematic error can be estimated and compensated through certain statistical models, such as through noise filtering algorithms or time series analysis to reduce the impact of the error and minimize its impact on the final monitoring results.

[0059] Algorithm execution process: Raw data acquisition: The AUV collects temperature, pressure and flow rate data in the marine environment through sensors, and these data will first enter the preliminary calibration module. The system adjusts the raw data M(x) through the calibration factor α1 based on the historical data of the sensor and the environmental characteristics of the mission area to generate a preliminary calibration result F1(x). During the data calibration process, the system will also compensate with the error term ε1 to reduce errors caused by sensor noise or system interference. The data F1(x) after preliminary calibration will be used as output for subsequent precision calibration or directly for analysis and decision-making.

[0060] The secondary precision calibration algorithm is used to perform precision correction based on the preliminary measurement calibration and combined with external environmental conditions. The input is the output result of the preliminary calibration algorithm and the external environmental parameters, and the output is a more accurate calibration result after correction. The formula is as follows: F2(y) = β1·F1(x) + γ(T,V) + ε2, F2(y) is the output result of the secondary precision calibration algorithm, which represents the calibration data after error correction under the influence of the external environment. This output result is more accurate and suitable for further analysis or transmission to the control center for decision-making. Through secondary correction, the influence of environmental factors (such as temperature and ocean currents) is eliminated to ensure the consistency of data accuracy in complex marine environments;

[0061] F1(x) is the result output from the preliminary calibration algorithm. It represents the data after the preliminary calibration and serves as the basic input for the secondary calibration. After the preliminary calibration, F1(x) has eliminated the system error of the sensor itself and is the first stage output of the sensor data.

[0062] β1 is a secondary calibration factor, which is mainly used to adjust the weight of the preliminary calibration result F1(x). This factor takes into account the impact of environmental conditions on the preliminary calibration results and is obtained through experiments and simulations.

[0063] Source: This factor is usually determined by analyzing the response of the sensor under different environmental conditions. For example, in low temperature or strong ocean current areas, the sensor data may be affected to varying degrees, so the value of β1 will also be adjusted according to these environmental conditions. β1 is determined by analyzing experimental data and the historical response curve of the sensor, with the aim of optimizing the data accuracy of the final output by adjusting the weight of the preliminary calibration data. γ(T,V) is a correction factor, which represents the correction result based on the external environmental temperature T and the ocean current velocity V. The temperature and ocean current velocity of the external environment are very critical parameters in ocean monitoring and directly affect the sensor readings. For example, temperature changes may cause deviations in the sensor's measurement accuracy, while the ocean current velocity will affect the motion stability of the AUV, which in turn affects the sensor's data acquisition. The correction factor γ(T,V) further corrects the preliminary calibration results by combining these environmental data. The correction factor γ(T,V) is based on the response characteristics of the sensor at different temperatures and ocean current velocities, and is obtained through experimental data modeling. This correction factor can dynamically adjust the calibration results to make the data more adaptable to the current environmental conditions.

[0064] ε2 is the correction error term, which represents the residual system error in the secondary precision calibration process. Similar to the error in the initial calibration, ε2 comes from environmental conditions, equipment noise, and approximate errors in the algorithm. This error is difficult to completely eliminate, but it can be minimized through error estimation and compensation methods. The system estimates ε2 through a statistical model and filters the data according to the actual situation to minimize its impact on the calibration results.

[0065] Algorithm execution process: Preliminary calibration result input: After completing the preliminary calibration, the AUV uses F1(x) as the input of the secondary calibration algorithm. Environmental parameter acquisition: The system obtains the current external environmental parameters through sensors, including ambient temperature T and ocean current speed V. Secondary calibration factor adjustment: Through the secondary calibration factor β1, the system adjusts the weight of the preliminary calibration results to adapt to different environmental conditions. Environmental correction: The system further corrects the preliminary calibration results through the correction factor γ(T,V) according to the temperature of the external environment and the ocean current speed to reduce the impact of the environment on the sensor data. Error compensation: After completing the correction, the system will combine the correction error term ε2 to perform the final error compensation and output more accurate calibration data F2(y).

[0066] The comprehensive evaluation algorithm is used to combine the output results of the preliminary measurement calibration algorithm and the secondary precision calibration algorithm to construct a performance evaluation index. This index is used to comprehensively evaluate the execution of the AUV's monitoring task and serves as an important basis for optimizing subsequent monitoring tasks. The formula is as follows: F3(z) = λ1·log(F1(x))+λ2·exp(F2(y))+ε3, where F3(z) is the output result of the comprehensive evaluation algorithm and represents the comprehensive performance evaluation index of the AUV monitoring task. This index combines the results of the preliminary calibration and the secondary calibration, and provides a basis for subsequent decision-making by evaluating the accuracy and reliability of the current data. This evaluation index can reflect the accuracy, environmental adaptability and error compensation effect of the sensor data, and can be used to monitor the overall performance of the task execution. λ1 and λ2 are dynamic weight factors used to balance the influence of the preliminary calibration data and the secondary precision calibration data in the evaluation index. These weight factors are dynamically adjusted according to the monitoring task requirements of the AUV and the current environmental conditions. For example, when the external environment changes drastically, the importance of the secondary precision calibration data increases, so the value of λ2 will also increase accordingly; while in the case of small environmental changes, the weight λ1 of the preliminary calibration result will be higher. By analyzing historical mission data and real-time environmental trends, the weight factor will dynamically adjust its contribution in the formula. The basis for adjustment includes the response time of the sensor, the fluctuation range of data accuracy, and the environmental disturbances that occur during the mission execution.

[0067] log(F1(x)) takes the logarithm of the preliminary calibration result F1(x). This is to smooth the fluctuations in sensor data and reduce the impact of noise on the evaluation results. In the evaluation algorithm, the use of logarithmic functions helps to reduce large data differences, making the data smoother and avoiding excessive impact of extreme values ​​on the evaluation results.

[0068] exp(F2(y)) performs an exponential operation on the result of the secondary precision calibration F2(y) to amplify the weight of the high-precision data after the secondary correction. After the secondary correction, the data has a higher accuracy, so its influence is amplified by exponential operation to ensure that more accurate data is given priority in task evaluation. Exponential amplification is suitable for monitoring scenarios in mission-critical areas to ensure priority processing of key data; ε3 is a global error compensation term, which represents the system error or calculation error that exists in the entire comprehensive evaluation process. The error compensation term mainly comes from sensor response delay, algorithm approximation error, and environmental interference. These errors are difficult to completely eliminate, but they can be compensated by a comprehensive error model. Through the analysis of historical data and modeling of error distribution, the system can estimate ε3 and then compensate for the final evaluation result to ensure that it is closer to the actual situation.

[0069] Algorithm execution process: Data input: The preliminary calibration result F1(x) and the secondary precision calibration result F2(y) are both used as inputs to the comprehensive evaluation algorithm. Weight factor adjustment: According to the environmental status of the current task, the system dynamically adjusts λ1 and λ2 to ensure that the most important calibration results dominate the comprehensive evaluation. Data processing: The system performs logarithmic operations on the preliminary calibration result F1(x) to smooth its data fluctuations; at the same time, it performs exponential operations on the secondary precision calibration result F2(y) to amplify its higher-precision monitoring data. Error compensation: Finally, the system performs global error compensation on the evaluation results through ε3 to further improve the credibility of the data. Evaluation result output: After the above steps, the system generates a comprehensive evaluation index F3(z), which is used to evaluate the execution effect of the current monitoring task and provide a reference for subsequent path optimization or task adjustment.

[0070] Furthermore, in S1.3 Energy Configuration, when the UDC cluster monitors the AUV to perform tasks, it not only needs to ensure that it completes the task, but also dynamically manages its energy consumption to improve task efficiency and extend the endurance of the equipment. Through the detailed description of this step, it can ensure that the AUV continues to maintain efficient energy utilization and maximize the completion of the task when performing long-term monitoring tasks.

[0071] S1.3.1 Energy assessment, energy assessment is a key step before mission execution. According to the duration of the AUV's monitoring mission, the monitoring range, and changes in the ocean environment, the UDC cluster can accurately estimate the total energy required for the AUV to complete the mission. The specific steps are as follows:

[0072] Mission duration and scope assessment: Estimated total energy demand: Before the mission begins, the system calculates the basic energy required for the AUV to complete the mission by analyzing the total mission duration and the geographical scope of monitoring. If the mission area is large or the execution time is long, the system will automatically increase the backup energy demand.

[0073] Dynamic evaluation of environmental parameters: The impact of environmental parameters on energy: The system dynamically adjusts the energy demand according to the environmental conditions in which the AUV operates (such as ocean current speed, temperature, etc.). For example, in areas with strong ocean currents, the AUV may need more thrust, so the system will increase the energy budget for that mission area accordingly.

[0074] Energy consumption rate calculation: Dynamic calculation of energy consumption rate: By combining the real-time operating status of the AUV and the environmental data collected by the sensor, the UDC cluster can dynamically estimate the energy consumption rate of the AUV. For example, in low-temperature waters, the energy consumption rate of the battery may accelerate. The system will update the consumption rate in real time according to such environmental changes to ensure the accuracy of energy assessment;

[0075] S1.3.2 Energy replenishment strategy. During the AUV's mission, the UDC cluster needs to monitor the AUV's power status in real time to ensure that it can be replenished in time when the energy is insufficient to prevent mission interruption. This strategy ensures the continuity of the mission by planning the charging time and path. Real-time power monitoring: Power status monitoring: The UDC cluster can monitor the AUV's power status in real time through the wireless communication module, calculate the remaining power and the current energy consumption rate. If the system detects that the power drops to a certain critical value (such as 30%), the energy replenishment program will be started.

[0076] Charging time and path planning: Planning the optimal path: In order to reduce the time and energy consumed in returning to the charging station, the system will dynamically plan the most energy-efficient path to return to the charging station based on the AUV's current position, mission priority, and remaining energy.

[0077] Optimize the charging time window: During the charging process, the system will select the best charging time window according to the urgency of the task. For example, if the task is very urgent, the system will arrange a quick charge and return to work quickly after charging enough energy; in a lighter task, the system can arrange a longer full charge. Mission uninterrupted: Parallel task processing: When the AUV returns to the charging station, the system can start the backup AUV to continue the task, ensuring that the entire monitoring process is not interrupted. Through the collaborative work of multiple AUVs, the continuity of the mission and the integrity of data collection can be ensured.

[0078] S1.3.3 Endurance Optimization,During the mission execution, endurance optimization is a key step to ensure that the AUV can maximize the use of its energy.,The UDC cluster combines the mission urgency and energy consumption curve,,dynamically adjusts the AUV's working mode and sensor frequency to extend the,AUV's working time.

[0079] Glide Mode and Thrust Management: Dynamically Adjust Glide Mode: The AUV's glide mode reduces energy consumption by adjusting buoyancy. In low energy situations, the system increases the frequency of glide mode use and reduces the use of the electric propulsion system. Glide mode is particularly suitable for mission areas with low energy consumption, such as areas with stable ocean currents. Through glide mode, the AUV can operate longer without consuming too much energy.

[0080] Sensor operating frequency adjustment: Energy-saving sensor management: In non-critical mission areas, the system can reduce the operating frequency of sensors and reduce unnecessary data collection, thereby saving energy. For example, when the AUV is in a sea area where there is no urgent need for data, the collection frequency of sensors such as temperature and flow rate can be reduced to reduce power consumption; when entering a key monitoring area, the operating frequency of these sensors will be increased to ensure accurate data collection.

[0081] Energy consumption curve and task adjustment: Task urgency assessment: The system adjusts the AUV's task execution according to the energy consumption curve and task priority. In the case of urgent tasks, the system can temporarily increase energy consumption to ensure that the task is completed on time; in the case of relatively loose tasks, the system will give priority to energy saving and extend the AUV's endurance.

[0082] S2.1 Start the navigation. The process of starting the navigation module of the AUV (autonomous underwater vehicle) is crucial and directly determines the efficiency of the subsequent monitoring tasks. Through a series of dynamic adjustments and path optimization, the AUV can efficiently complete the path planning while minimizing energy consumption, ensuring the best state when entering the monitoring area.

[0083] S2.1.1 Path initialization, path initialization is the first step for AUV to start sailing. The system starts the navigation module according to the predetermined path of the mission planning. The specific implementation steps are as follows: Buoyancy adjustment and depth control: Adjustment of the buoyancy module: Before starting the voyage, the AUV first needs to adjust its buoyancy through the buoyancy adjustment module to reach the predetermined cruising depth. The control of buoyancy is achieved by adjusting the compressed air bag or buoyancy adjustment cabin inside the AUV, so that the AUV can reach the monitoring waters in the most energy-efficient way.

[0084] Predetermined depth: According to the mission plan, the AUV will be assigned to different depths for monitoring. For example, in a deep-sea environment, the system will set the appropriate cruising depth based on water pressure, temperature and other environmental conditions. By precisely controlling buoyancy, the AUV can reach this depth quickly and smoothly.

[0085] Spiral diving mode: Implementation of spiral diving: In order to better adapt to the complex marine environment, the AUV starts the spiral diving mode. By adjusting the eccentric structure and power module of the vehicle, the AUV can sink in a spiral manner. This sinking method can not only increase the stability of navigation, but also allow the AUV to scan and monitor the waters from multiple angles, providing more comprehensive data.

[0086] Multi-angle viewing angle: Spiral diving allows the AUV to observe the target area from a wider angle, especially in complex terrain or ocean current environments. This mode can help the AUV better locate and avoid obstacles.

[0087] S2.1.2 Propulsion system optimization,During navigation, the optimization of the propulsion system is crucial to maintaining efficient and energy-saving navigation.,Through dynamic adjustment of the blades, the AUV can maintain a stable speed and maneuverability under different water flow conditions.

[0088] Dynamic adjustment of blade inclination: The role of the propulsion system: The propulsion system of the AUV controls its forward speed and direction through one or more pairs of blades. According to the change of water flow resistance, the system will adjust the inclination of the blades in real time to ensure the optimal propulsion efficiency. Dealing with water flow resistance: When the AUV enters waters with strong or complex ocean currents, water flow resistance will significantly affect the propulsion efficiency. In order to reduce energy consumption, the system detects the speed and direction of the current water flow through sensors, automatically adjusts the angle of the blades, reduces unnecessary resistance and improves propulsion efficiency. Energy-saving navigation mode: Energy-saving strategy: When the mission is not urgent, the AUV will give priority to the propulsion method with lower energy consumption and extend the endurance by reducing the propulsion power. Only when the mission is urgent or it is necessary to enter a certain area quickly, the system will increase the propulsion power to ensure the efficiency of the mission. Maneuverability optimization: By optimizing the dynamic adjustment of the propulsion system, the AUV can maintain good maneuverability in complex marine environments, not only can it quickly adjust the navigation direction, but also can avoid obstacles or potential dangerous areas when necessary.

[0089] S2.1 Start the navigation. The process of starting the navigation module of the AUV (autonomous underwater vehicle) is crucial and directly determines the efficiency of the subsequent monitoring tasks. Through a series of dynamic adjustments and path optimization, the AUV can efficiently complete the path planning while minimizing energy consumption, ensuring the best state when entering the monitoring area.

[0090] S2.1.1 Path initialization: Path initialization is the first step for AUV to start navigation. The system starts the navigation module according to the predetermined path planned by the mission. The specific implementation steps are as follows:

[0091] Buoyancy adjustment and depth control: Adjustment of the buoyancy module: Before starting the voyage, the AUV first needs to adjust its buoyancy through the buoyancy adjustment module to reach the predetermined cruising depth. The control of buoyancy is achieved by adjusting the compressed air bag or buoyancy adjustment cabin inside the AUV, so that the AUV can reach the monitoring waters in the most energy-efficient way. Predetermined depth: According to the mission plan, the AUV will be assigned to different depths for monitoring. For example, in a deep-sea environment, the system will set the appropriate cruising depth based on water pressure, temperature and other environmental conditions. By precisely controlling buoyancy, the AUV can reach that depth quickly and smoothly.

[0092] Spiral diving mode: Implementation of spiral diving: In order to better adapt to the complex marine environment, the AUV starts the spiral diving mode. By adjusting the eccentric structure and power module of the vehicle, the AUV can sink in a spiral manner. This sinking method can not only increase the stability of navigation, but also allow the AUV to scan and monitor the waters from multiple angles, providing more comprehensive data.

[0093] Multi-angle viewing angle: Spiral diving allows the AUV to observe the target area from a wider angle, especially in complex terrain or ocean current environments. This mode can help the AUV better locate and avoid obstacles.

[0094] S2.1.2 Propulsion system optimization,During navigation, the optimization of the propulsion system is crucial to maintaining efficient and energy-saving navigation.,Through dynamic adjustment of the blades, the AUV can maintain a stable speed and maneuverability under different water flow conditions.

[0095] Dynamic adjustment of blade inclination: The role of the propulsion system: The propulsion system of the AUV controls its forward speed and direction through one or more pairs of blades. According to the changes in water flow resistance, the system will adjust the blade inclination in real time to ensure the optimal propulsion efficiency.

[0096] Dealing with water resistance: When the AUV enters waters with strong or complex ocean currents, water resistance will significantly affect propulsion efficiency. In order to reduce energy consumption, the system detects the current speed and direction of the water through sensors and automatically adjusts the angle of the blades to reduce unnecessary resistance and improve propulsion efficiency.

[0097] Energy-saving navigation mode: Energy-saving strategy: When the mission is not urgent, the AUV will give priority to the propulsion mode with lower energy consumption, and extend the endurance time by reducing the propulsion power. Only when the mission is urgent or needs to enter a certain area quickly, the system will increase the propulsion power to ensure the efficiency of mission completion.

[0098] Maneuverability optimization: By optimizing the dynamic adjustment of the propulsion system, the AUV can maintain good maneuverability in complex marine environments, not only can it quickly adjust the direction of navigation, but also can avoid obstacles or potential dangerous areas when necessary. S2.1.3 Monitoring system startup: When the AUV reaches the predetermined monitoring area, the monitoring system automatically starts and begins to collect environmental data. The startup of the monitoring system is crucial for obtaining environmental information in real time, ensuring that the system can collect accurate data according to the preset tasks.

[0099] Activation of temperature, pressure and flow rate sensors: Sensor activation: When the AUV reaches the monitoring area, its integrated sensor modules (including temperature, pressure and flow rate sensors) will start collecting environmental data at preset time intervals. These sensors play an important role in high-precision environmental monitoring and can reflect the marine environment status of the monitoring area in real time.

[0100] Data collection frequency: The operating frequency of the sensor can be dynamically adjusted according to the mission requirements. For example, in relatively stable sea areas, the system will reduce the sampling frequency to save energy; while when monitoring sensitive areas, the system will increase the sampling frequency to ensure that sufficient environmental data is obtained.

[0101] Camera module startup: Environment and target scanning: The camera module is mainly used to detect the state of the UDC shell, changes in the target object or environment. The camera module starts working when it reaches the target area, and can capture images at regular intervals and feed them back to the UDC cluster in real time for monitoring changes in the external environment, detecting biological attachment, etc. S2.1.4 Path feedback and adjustment. In order to ensure high efficiency during navigation, the AUV needs to provide real-time feedback on its navigation status and energy consumption when performing tasks. The UDC cluster will dynamically adjust the path planning based on the feedback information to optimize the distribution of energy.

[0102] Energy consumption feedback: Real-time energy feedback: AUV detects energy consumption status through sensors and transmits data back to the UDC cluster in real time through wireless communication modules. The system can dynamically adjust navigation strategies according to changes in energy consumption to ensure that AUV can complete tasks efficiently.

[0103] Path planning optimization: According to the current energy status of the AUV, the system can adjust the navigation path. For example, when insufficient energy is detected, the system can plan a shorter path to reduce energy consumption, or decide whether to return to the charging station midway according to the urgency of the mission.

[0104] Environmental resistance and navigation status feedback: Environmental parameter feedback: Through the environmental resistance information detected by the sensor, the AUV can perceive the impact of environmental factors such as ocean currents and temperature changes in real time. The system will transmit this data to the UDC cluster so that the path can be adjusted in time.

[0105] Navigation status optimization: Through path feedback and adjustment, the AUV's navigation route can be more adapted to the current environment and reduce unnecessary energy consumption. For example, in areas with strong ocean currents, the system will avoid areas with the strongest currents and choose a navigation path with less resistance.

[0106] During the mission, the AUV transmits the collected monitoring data to the UDC cluster through the wireless communication system. This step includes:

[0107] Data compression and preprocessing: Before transmission, the AUV will compress the data to remove noise and redundant information to reduce bandwidth usage and transmission delay. Real-time transmission mechanism: Through the wireless communication module, the compressed and calibrated data is transmitted to the UDC cluster in real time to ensure the real-time and integrity of the data. Data backup and distribution: The UDC cluster backs up the received data and transmits key data to the shore-based control center in real time for subsequent analysis and task adjustment.

[0108] The AUV uses sensors to monitor changes in temperature and ocean currents in the environment, and transmits them to the UDC cluster in a timely manner through a feedback mechanism. This step includes:

[0109] Environmental data collection: Collect environmental parameters regularly, and increase the collection frequency if a sudden change occurs. Data anomaly detection: Analyze data in real time to determine whether an abnormal situation occurs. Feedback mechanism: Once abnormal data is detected, the AUV immediately transmits feedback to the UDC cluster via wireless communication to adjust the mission parameters and path.

[0110] After the AUV completes its mission, it will perform self-inspection and maintenance through the UDC cluster to ensure the normal operation of the equipment. This step includes: Sensor self-inspection: The AUV automatically detects the status of equipment such as cameras and sensors and generates a self-inspection report. Biological attachment cleaning: The automated cleaning equipment is used to remove biological attachments on the AUV shell and sensors to ensure monitoring accuracy. Equipment maintenance and care: Regularly check key components such as the propulsion system and batteries to ensure that the AUV is in good condition.

[0111] The UDC cluster dynamically adjusts the navigation path of the AUV based on the AUV's real-time monitoring data and external environmental information. This step includes: Data fusion and analysis: Analyze the environmental data sent back by the AUV, and combine it with the external environmental forecast to generate an environmental model to decide whether to adjust the path. Energy and efficiency evaluation: Calculate the optimal path for energy consumption based on the current energy level and environmental conditions. Obstacle avoidance path planning: Generate an obstacle avoidance path in real time to ensure that the AUV bypasses obstacles. Real-time path update and feedback: According to the new path instructions, the AUV adjusts the navigation direction and speed in real time

[0112] Although 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 the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent collaborative monitoring method integrating long-endurance AUV and submarine data center, characterized by: The following steps are involved: S1: Initialization and mission planning S1.1 Mission configuration: In the UDC control system, preset the mission parameters of the AUV, including monitoring range, monitoring cycle, path planning, and target environmental variables; S1.2 Communication initialization: Establish a communication connection between the AUV and the UDC, and use the submarine cable communication system or the acoustic wave communication system to synchronize mission instructions and system status. The submarine cable communication system is used for long-term stable data transmission, while the acoustic wave communication system is used for short-term communication tasks. S1.3 Energy configuration: The energy management system of the UDC cluster is used to check and recharge the AUV to ensure that the AUV has enough power to complete long-term monitoring tasks; S2: AUV autonomous monitoring mission execution S2.1 Start navigation: The AUV departs from the UDC cabin according to the predetermined path, uses the long-endurance gliding mode and buoyancy adjustment system to achieve low-energy navigation, and controls the attitude of the vehicle through the eccentric structure to ensure that it sinks or rises in a spiral manner, thereby carrying out monitoring tasks in the target area; S2.2 Data acquisition: The AUV monitors the marine environment in real time through integrated temperature sensors, pressure sensors, and flow rate sensors, and detects the biological attachment and temperature distribution of the UDC shell through the camera module; S2.3 Real-time transmission and storage: Through the wireless communication module, the AUV transmits the collected monitoring data to the UDC cluster server in real time, and the monitoring data will be stored in the central server for subsequent analysis; S3: Intelligent collaborative monitoring and feedback S3.1 Environmental change perception: AUV uses built-in sensors to detect environmental parameters such as temperature, pressure and ocean currents in real time. When sudden environmental changes are detected, AUV feeds back data to the UDC cluster through the wireless communication module, and the UDC cluster adjusts the AUV's mission parameters and path planning accordingly. S3.2 Intelligent Control: The UDC cluster uses the real-time data provided by the external environment forecasting system to dynamically control the energy distribution and heat dissipation management system of the AUV through intelligent control algorithms to ensure the smooth progress of monitoring tasks in complex marine environments; S4: Collaborative docking between AUV and UDC S4.1 Automatic docking: After the AUV completes its mission, it automatically returns to the UDC cabin and realizes power replenishment through the power interface at the docking station and information exchange through the data interface to ensure that the AUV has the ability to complete the next mission; S4.2 Data synchronization and storage: The AUV transmits the monitoring data to the central server of the UDC cluster, and further transmits the data to the shore-based control center via a composite cable to ensure the integrity and security of the monitoring data; S4.3 Self-inspection and maintenance: The UDC cluster performs self-inspection on the AUV’s sensors, camera modules, and propulsion systems through the automatic diagnostic system, and cleans the AUV’s outer shell of biological attachments through the cleaning module to ensure that it can work normally in the next mission; S5: Dynamic task optimization and continuous monitoring S5.1 Dynamic path adjustment: The UDC cluster optimizes the task path through a dynamic path planning algorithm based on the environmental data provided by the external environment forecasting system and the shore-based control center, combined with the energy status of the AUV, to ensure that the AUV can continue to perform monitoring tasks in complex environments; S5.2 Continuous monitoring cycle: The AUV performs a new round of monitoring tasks according to the optimized mission parameters, and ensures the validity of the monitoring data and the stability of the system operation through a real-time feedback mechanism.

2. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 1 is characterized by: The preliminary measurement calibration algorithm is used to process the monitoring data collected by the AUV. The input is temperature, pressure, and flow rate, and the output is the preliminary calibration result. The algorithm formula is: F1(x)=α1·M(x)+ε1, where: M(x) represents the sensor data obtained by the AUV, α1 is the preliminary calibration factor, and ε1 is the system error term.

3. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 2 is characterized by: The secondary precision calibration algorithm is used to perform precision correction on the basis of the preliminary measurement calibration algorithm. The input is the output of the preliminary measurement calibration algorithm and the external environmental conditions. The output is the corrected calibration result. The formula is: F2(y)=β1·F1(x)+γ(T,V)+ε2, where: T is the ambient temperature, V is the ocean current velocity, γ(T,V) is the correction factor, and ε2 is the correction error term.

4. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 3 is characterized by: The comprehensive evaluation algorithm is used to preliminarily measure the output results of the calibration algorithm and the secondary precision calibration algorithm to construct a performance evaluation index. The algorithm formula is: F3(z)=λ1·log(F1(x))+λ2·exp(F2(y))+ε3, where: λ1 and λ2 are dynamic weight factors, and ε3 is the global error compensation term.

5. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 4 is characterized by: In the energy configuration of S1.3, the UDC cluster dynamically monitors the energy demand of the AUV, including the following sub-steps: S1.3.1 Energy evaluation: based on the mission duration and monitoring range, the total energy required for the AUV to perform the mission is estimated, and the energy consumption rate is dynamically calculated in combination with the environmental parameters during the mission; S1.3.2 Energy Recharge Strategy: By monitoring the AUV’s power status, the UDC cluster decides when the AUV needs to return to the charging station and plans the most energy-efficient path and the best charging time window; S1.3.3 Endurance optimization: Combine the urgency of the mission with the energy consumption curve in the mission path to dynamically adjust the AUV’s gliding mode and sensor operating frequency to maximize endurance.

6. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 5 is characterized by: During the S2.1 start-up navigation, the AUV plans the mission according to the following sub-steps: S2.1.1 Path initialization: The AUV starts the navigation module according to the predetermined mission path. The vehicle first reaches the predetermined cruising depth by adjusting its buoyancy module, and starts the spiral diving mode at the same time, adjusting the eccentric structure and power module of the vehicle to achieve spiral sinking and obtain multi-angle monitoring perspectives; S2.1.2 Propulsion system optimization: The vehicle dynamically optimizes its propulsion efficiency by adjusting the inclination angle of the blades to cope with different water flow resistances, while maintaining energy saving, ensuring that the navigation speed and maneuverability adapt to environmental changes; S2.1.3 Monitoring system startup: When the vehicle reaches the preset monitoring area, its temperature, pressure, flow rate and camera modules are started, data is collected at predetermined intervals, and monitoring data is transmitted back to the UDC cluster in real time; S2.1.4 Path feedback and adjustment: During the path execution process, the vehicle feeds back its energy consumption, environmental resistance and navigation status in real time. The UDC cluster dynamically adjusts the vehicle's path planning according to real-time data to optimize the energy consumption distribution.

7. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 6 is characterized by: In S2.3 real-time transmission and storage, the AUV will transmit data to the UDC cluster server in real time through the wireless communication system. The data includes calibrated monitoring parameters, which specifically includes the following sub-steps: S2.3.1 Data compression and preprocessing: Before transmitting the data, the AUV compresses and preprocesses the original monitoring data to remove noise and redundant information to reduce transmission delay and improve transmission efficiency; S2.3.2 Real-time transmission mechanism: The compressed and calibrated monitoring data is transmitted to the UDC cluster in real time through the wireless communication module to ensure the real-time and integrity of the data; S2.3.3 Data backup and distribution: The UDC cluster will back up the received data in multiple nodes and distribute some key data to the shore-based control center in real time for analysis and task adjustment.

8. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 7 is characterized by: In S3.1 environmental change perception, the AUV can detect temperature changes and ocean current changes in the environment, and transmit the data to the UDC cluster through a feedback mechanism, which specifically includes the following sub-steps: S3.1.1 Environmental data acquisition: The AUV regularly collects environmental parameters through the installed temperature sensors and ocean current sensors, and increases the collection frequency when a sudden change occurs; S3.1.2 Data anomaly detection: The AUV performs real-time analysis on the collected data to determine whether there are any abnormal situations that do not match the expected values; S3.1.3 Feedback mechanism: Once abnormal data is detected, the AUV immediately sends feedback to the UDC cluster through wireless communication. The UDC cluster adjusts the AUV's mission parameters in real time based on the feedback, and plans paths to avoid areas of environmental anomalies.

9. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 8 is characterized by: In the self-inspection and maintenance of S4.3, the UDC cluster cleans the camera and sensor of the AUV and processes the external biological attachment, which specifically includes the following sub-steps: S4.3.1 Sensor self-test: After returning to the UDC cabin, the AUV automatically detects the status of each sensor, including the clarity of the camera and the response sensitivity of the pressure sensor, and generates a self-test report; S4.3.2 Biological attachment cleaning: The UDC cluster uses automated cleaning equipment to clean biological attachments on the AUV shell and key sensor areas to ensure the accuracy of monitoring data; S4.3.3 Equipment maintenance and care: Perform routine inspection and maintenance on key components of the AUV to ensure that the equipment can operate normally in the next mission.

10. The intelligent collaborative monitoring method of the long-endurance AUV and the submarine data center according to claim 9 is characterized by: In S5.1 dynamic path adjustment, the following sub-steps are specifically included: S5.1.1 Data fusion and analysis: The UDC cluster analyzes the environmental monitoring data sent back by the AUV, including real-time changes in temperature, pressure, and flow rate, and combines these data with the external environmental forecasting system to generate a complete environmental model to determine the necessity of adjusting the navigation path; S5.1.2 Energy and efficiency assessment: Based on the current energy level of the AUV and the obstacles and environmental conditions in the navigation path, calculate the optimal energy consumption curve and optimize the navigation path to ensure that the vehicle can maximize its energy to complete the monitoring task; S5.1.3 Obstacle avoidance path planning: The UDC cluster generates an obstacle avoidance path in real time by comprehensively analyzing the obstacle data in the monitoring area to ensure that the vehicle can safely bypass potential obstacles and dynamically update the obstacle avoidance strategy based on the real-time location of the obstacles; S5.1.4 Real-time path update and feedback: When the current path of the aircraft is no longer suitable for continued advancement, the UDC cluster transmits the adjusted path to the aircraft through the wireless communication module. The aircraft adjusts its navigation direction and speed in real time according to the instructions to adapt to the new monitoring requirements.

Images