Unmanned ship attitude stabilization and intelligent anti-interference method and system under complex sea condition

Abstract

The invention discloses an unmanned ship attitude stabilization and intelligent anti-interference method and system under a complex sea condition, and relates to the technical field of unmanned ship intelligent control and marine environment perception, and the method comprises the steps: building a sea condition model, and judging the sea surface disturbance level; performing nonlinear adaptive control on the unmanned ship based on the sea surface disturbance level; and based on a state prediction algorithm, combined control is carried out on the attitude of the unmanned ship in combination with nonlinear adaptive control. According to the method disclosed by the invention, the accuracy of attitude control pre-judgment and the environment adaptability are improved; the comprehensive performance of the unmanned ship between energy efficiency utilization and dynamic control is improved; combined control is performed by combining a state prediction algorithm and nonlinear control, so that the control system has the ability of pre-judging the attitude change trend in advance and performing dynamic correction, the control strategy conversion from passive response to active pre-control is realized, and finally, the attitude stability, the control foresight and the task continuity of the unmanned ship under the complex sea condition are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned boat intelligent control and marine environment perception, and specifically to a method and system for unmanned boat attitude stabilization and intelligent anti-interference under complex sea conditions. Background Art

[0002] With the rapid development of artificial intelligence, advanced control theory, and multi-source perception technologies, intelligent surface platforms, particularly unmanned surface vehicles (USVs), are showing broad application prospects in tasks such as marine resource exploration, environmental monitoring, and maritime traffic management. Due to their technological advantages of autonomous navigation, remote control, and high maneuverability, USVs are gradually replacing traditional manned vessels in mission-carrying roles in high-risk, complex environments. Current research focuses on environmental perception, path planning, collaborative navigation, and optimization of adaptive control strategies for USVs. In particular, achieving attitude stability control and disturbance suppression in dynamic ocean environments has become a key research direction for intelligent surface platforms.

[0003] In typical application scenarios, unmanned boats (UAVs) often face attitude disturbances caused by wind and waves, water currents, and sudden changes in sea conditions. These factors not only affect their heading accuracy and attitude stability, but can also lead to equipment damage, mission failure, and even the risk of system loss of control. Traditional attitude control systems often use linear control methods such as PID control or robust control. Their design relies on the accuracy of the system's linear model and is difficult to effectively cope with the nonlinearity and uncertainty of sea conditions. Especially under medium and high-level disturbance conditions, they suffer from drawbacks such as adjustment delays, response lags, and control rigidity. To address these issues, nonlinear adaptive control theory has been gradually applied to marine intelligent equipment. By identifying the characteristics of external disturbances in real time and dynamically adjusting the control law, the strategy has achieved, to a certain extent, stable navigation of UAVs in changing environments.

[0004] Despite considerable progress in unmanned watercraft control technology, there is still a lack of closed-loop control strategies that integrate disturbance sensing, level determination, predictive response, and control optimization to address the uncertainty and nonlinear coupling caused by multiple disturbance environments in complex sea conditions. Existing methods face the following significant shortcomings: disturbance modeling methods lack a classification response mechanism for sea state levels, making it difficult to reflect the active regulation relationship between disturbance level and control law structure in the controller structure; while nonlinear adaptive control has certain disturbance resistance capabilities, most methods use static parameter design or weakly coupled adjustment logic, lacking deep integration with real-time prediction data, resulting in control strategy lag or overcorrection; and state prediction mechanisms, without auxiliary disturbance level classification, cannot accurately judge the severity of disturbances based solely on attitude data trends, affecting the control applicability and risk sensitivity of the predicted values. Summary of the Invention

[0005] In view of the above problems in the prior art, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: the existing unmanned boat attitude control method has the problems of inaccurate disturbance level identification, strong control strategy rigidity, delayed control response and difficulty in effectively integrating prediction information with the control mechanism under complex sea conditions, as well as how to achieve stable control and forward-looking adjustment of the unmanned boat attitude in a dynamic disturbance environment.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a method for stabilizing the attitude of an unmanned boat and intelligently rejecting disturbances under complex sea conditions, comprising: constructing a sea condition model to determine the level of sea surface disturbance; performing nonlinear adaptive control on the unmanned boat based on the level of sea surface disturbance; and jointly controlling the attitude of the unmanned boat based on a state prediction algorithm and in combination with nonlinear adaptive control.

[0008] As a preferred solution of the unmanned boat attitude stabilization and intelligent anti-interference method under complex sea conditions described in the present invention, the construction of the sea condition model includes collecting the unmanned boat attitude data and characteristic parameters of the current sea area through multi-source sensors on the unmanned boat, and using a long short-term memory neural network to predict the sea condition based on the characteristic parameters, and judging the disturbance level according to the sea condition value.

[0009] As a preferred solution of the unmanned boat attitude stabilization and intelligent anti-interference method under complex sea conditions described in the present invention, wherein: the said judging the disturbance level according to the sea state status value includes comparing the sea state status prediction value with the preset threshold value; if the sea state status prediction value is greater than or equal to the first-level preset threshold value, then the sea surface disturbance level is judged to be first level; if the sea state status prediction value is greater than or equal to the second-level preset threshold value, then the sea surface disturbance level is judged to be second level.

[0010] As a preferred solution of the method for attitude stabilization and intelligent anti-interference of unmanned boats under complex sea conditions described in the present invention, the nonlinear adaptive control of the unmanned boat includes real-time adjustment of the control gain according to the attitude error function. When the sea surface disturbance level is level one, a low-gain nonlinear adaptive control law is adopted to reduce the control action amplitude and energy consumption; when the sea surface disturbance level is level two, a high-gain nonlinear adaptive control law is adopted to improve the response speed and adjustment amplitude of the controller in real time.

[0011] As an optimal solution for the unmanned boat attitude stabilization and intelligent anti-interference method under complex sea conditions described in the present invention, the state prediction algorithm includes constructing an attitude state sequence based on the unmanned boat attitude historical data and current attitude data, predicting the unmanned boat attitude state at the next moment through the state prediction algorithm, and outputting the unmanned boat attitude prediction value.

[0012] As an optimal solution for the unmanned boat attitude stabilization and intelligent anti-interference method under complex sea conditions described in the present invention, the joint control of the unmanned boat attitude includes constructing an unmanned boat attitude joint control algorithm, performing stability evaluation on the unmanned boat attitude prediction value, performing error analysis on the unmanned boat attitude prediction value and the real-time feedback attitude data, adjusting the unmanned boat attitude joint control algorithm parameters in real time according to the error analysis results, and predicting, adjusting and stabilizing the unmanned boat attitude.

[0013] As a preferred solution of the unmanned boat attitude stabilization and intelligent anti-interference method under complex sea conditions described in the present invention, the pre-judgment adjustment and stable control of the unmanned boat attitude includes judging the changing trend of the unmanned boat attitude.

[0014] If the attitude change rate of the unmanned boat is less than the threshold, the current attitude error is controlled through the low-gain nonlinear adaptive control law.

[0015] If the attitude change rate of the unmanned boat is greater than the threshold, the high-gain nonlinear adaptive controller is triggered to intervene and perform strong control actions to avoid attitude deviation.

[0016] Another object of the present invention is to provide an unmanned boat attitude stabilization and intelligent anti-disturbance system under complex sea conditions. The system can solve the problems of the current unmanned boats lacking effective disturbance level perception, attitude control strategy rigidity, and prediction and control decoupling in complex disturbance environments through the collaborative work of the sea condition modeling and disturbance level determination module, the nonlinear adaptive attitude control module, and the attitude prediction and joint control module.

[0017] As a preferred solution of the multi-platform environment perception and fusion map construction system described in the present invention, it includes: a sea state modeling and disturbance level determination module, a nonlinear adaptive attitude control module, and an attitude prediction and joint control module; the sea state modeling and disturbance level determination module includes a multi-source sensing acquisition unit and a disturbance level identification unit, the multi-source sensing acquisition unit is used to collect the attitude data and sea surface environment characteristic parameters of the unmanned boat in real time, the disturbance level identification unit predicts the sea state state value based on the LSTM neural network, compares it with the threshold, and outputs the disturbance level determination result; the nonlinear adaptive attitude control module includes a gain adjustment control unit and a control law generation unit, the gain adjustment control unit is used to select low gain or high gain control law in real time according to the disturbance level, adjust the control response amplitude, the control law generation unit is used to construct a nonlinear control law based on the attitude error, and generate control instructions for adjusting the actuator; the attitude prediction and joint control module includes a state prediction unit and a joint control execution unit, the state prediction unit is used to construct an attitude state sequence based on historical and current attitude data, and predict the attitude change trend at the next moment, the joint control execution unit is used to fuse the predicted trend with the current error, dynamically adjust the nonlinear controller parameters, and output the joint control instruction.

[0018] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of any one of the methods for unmanned boat attitude stabilization and intelligent anti-interference in complex sea conditions.

[0019] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of any one of the methods for stabilizing the attitude of an unmanned boat and conducting intelligent anti-interference under complex sea conditions are implemented.

[0020] The beneficial effects of the present invention are as follows: by constructing a sea condition model and judging the disturbance level, the unmanned boat can quantitatively identify and grade the disturbance intensity in the current sea area, realize structured modeling of the disturbance environment, and ultimately improve the accuracy of the attitude control pre-judgment and the environmental adaptability; by a nonlinear adaptive control strategy based on the disturbance level, the control gain size and the control law structure are switched autonomously, and the controller realizes a dual mechanism of energy-saving fine-tuning for slight disturbances and rapid response to severe disturbances, ultimately improving the comprehensive performance of the unmanned boat between energy efficiency utilization and dynamic control; by combining the state prediction algorithm with nonlinear control for joint control, the control system has the ability to predict the attitude change trend in advance and dynamically correct it, realizing the transformation of the control strategy from passive response to active pre-control, and ultimately significantly improving the attitude stability, control foresight and mission continuity of the unmanned boat under complex sea conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A flowchart of a method for stabilizing the attitude of an unmanned boat and performing intelligent anti-interference in complex sea conditions is provided in the first embodiment of the present invention.

[0023] Figure 2 This is an overall flow chart of an unmanned boat attitude stabilization and intelligent anti-interference system under complex sea conditions provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0024] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0025] Example 1, with reference to Figure 1 , which is the first embodiment of the present invention, provides an unmanned boat attitude stabilization and intelligent anti-interference method under complex sea conditions, including:

[0026] S1: Construct a sea condition model to determine the level of sea surface disturbance.

[0027] It should be noted that constructing the sea condition model includes collecting the unmanned boat attitude data and characteristic parameters of the current sea area through multi-source sensors on the unmanned boat, predicting the sea condition based on the characteristic parameters using a long short-term memory neural network, and judging the disturbance level according to the sea condition value.

[0028] It should also be noted that the attitude data of the unmanned boat includes pitch angle, roll angle, and heave acceleration. The characteristic parameters of the current sea area include wave height, wave period, wind speed, and ocean current speed. The characteristic vector constructed based on the characteristic parameters of the current sea area is expressed as:

[0029] X(t)=[H t ,T w ,V w ,V c ]

[0030] Among them, X(t) is the characteristic parameter of the current sea area, H t Represents wave height, T w Represents the wave period, V w Indicates wind speed, V c Indicates the speed of ocean currents.

[0031] The use of long short-term memory neural network to predict sea state includes forming time series data of sea area characteristic parameters X(t) at the current moment and several previous moments, inputting it into the pre-trained LSTM model, extracting its time series features and outputting the disturbance state prediction value. The constructed sea state characteristic time series is expressed as:

[0032] X t-n:t ={X(tn),X(t-n+1),…,X(t)}

[0033] Among them, X t-n:tis the sea condition characteristic time series, and {X(tn), X(t-n+1),…, X(t)} represents the continuous sea condition characteristic vector sequence of the unmanned boat at time t and its previous n moments.

[0034] Input the time series into the LSTM network and predict the disturbance state value at the current moment as follows:

[0035] S t =LSTM(X t-n:t )

[0036] Among them, S t represents the predicted value of the disturbance state at the current moment r, and LSTM(.) represents the long short-term memory neural network.

[0037] Furthermore, judging the disturbance level according to the sea state value includes comparing the sea state prediction value with a preset threshold value. If the sea state prediction value is greater than or equal to the first-level preset threshold value, the sea surface disturbance level is judged to be first level; if the sea state prediction value is greater than or equal to the second-level preset threshold value, the sea surface disturbance level is judged to be second level.

[0038] It should also be noted that the disturbance state prediction value based on the long short-term memory neural network output is compared with the preset disturbance level judgment threshold to achieve automatic classification of the disturbance level. An optimal solution for the first-level threshold is 0.35, and an optimal solution for the second-level threshold is 0.65. By performing sample cluster analysis on a large amount of historical sea state monitoring data, the disturbance state prediction value S is extracted. t The distribution range in different sea conditions, the statistical results show that when S t When the value of the disturbance state S is less than 0.35, the samples in the interval correspond to wave heights not exceeding 0.5m, wind speeds below 4m / s, stable ocean currents, and small fluctuations in attitude, which are consistent with the characteristics of stable or low-intensity disturbances. t When it is >0.65, the attitude change increases significantly, the pitch, roll and heave indicators of the unmanned boat show obvious nonlinear fluctuations, and the energy consumption level increases significantly. Therefore, this interval is used as an important dividing line for medium and high intensity disturbances.

[0039] S2: Based on the sea surface disturbance level, nonlinear adaptive control of the unmanned boat is performed.

[0040] It should be noted that the nonlinear adaptive control of the unmanned boat includes real-time adjustment of the control gain according to the attitude error function. When the sea surface disturbance level is level one, a low-gain nonlinear adaptive control law is adopted to reduce the control action amplitude and energy consumption; when the sea surface disturbance level is level two, a high-gain nonlinear adaptive control law is adopted to improve the response speed and adjustment amplitude of the controller in real time.

[0041] It should also be noted that the control gain function driven by the disturbance level is expressed as:

[0042]

[0043] Among them, γ(t) represents the control gain function, γ1 is the low gain coefficient, and γ2 is the high gain coefficient. When the sea surface disturbance level is level one, that is, L s =1, indicating that the current disturbance environment is relatively stable and the attitude error of the unmanned boat is within the stable boundary. At this time, the controller adopts a low gain coefficient to reduce the controller output amplitude, moderate the rudder angle change, and weaken the actuator power response, thereby achieving the goal of reducing the control action amplitude, energy consumption and structural stress.

[0044] When the sea surface disturbance level is level 2, that is, L s =2, indicating that the disturbance trend is increasing and the attitude deviation has the characteristics of rapid nonlinear fluctuation. At this time, the controller switches to a high gain coefficient, amplifying the response speed of the controller to the error change and improving the adjustment amplitude and frequency of the actuator, thereby achieving rapid and strong response to disturbances and anti-disturbance control.

[0045] S3: Based on the state prediction algorithm, the unmanned boat attitude is jointly controlled in combination with nonlinear adaptive control.

[0046] It should be noted that the state prediction algorithm includes constructing a posture state sequence based on the historical posture data and current posture data of the unmanned boat, predicting the posture state of the unmanned boat at the next moment through the state prediction algorithm, and outputting the posture prediction value of the unmanned boat.

[0047] It should also be noted that the posture state sequence is constructed as:

[0048] P t-n:t ={P(tn),P(t-n+1),…,P(t)}

[0049] Among them, P t-n:t represents the attitude state sequence of the unmanned boat, P(t) is the three-dimensional attitude state vector of the unmanned boat at time t, including the pitch angle, roll angle, and heave acceleration of the unmanned boat, and {P(tn), P(t-n+1),…, P(t)} represents the continuous sampling results of the attitude state of the unmanned boat in the past n+1 time steps.

[0050] Input the constructed posture state sequence into the trained state prediction model, and the posture prediction value at the next moment is expressed as:

[0051] P t =LSTM(P t-n:t )

[0052] Among them, P t It represents the predicted value of the unmanned boat posture at the current time t, and LSTM(.) represents the long short-term memory neural network.

[0053] Furthermore, the joint control of the unmanned boat attitude includes constructing an unmanned boat attitude joint control algorithm, performing stability evaluation on the unmanned boat attitude prediction value, performing error analysis on the unmanned boat attitude prediction value and the real-time feedback attitude data, adjusting the unmanned boat attitude joint control algorithm parameters in real time according to the error analysis results, and predicting, adjusting and stabilizing the unmanned boat attitude.

[0054] It should also be noted that the joint control algorithm of the unmanned boat attitude is expressed as:

[0055]

[0056] in, represents the joint control output signal, η(t) is the prediction adjustment weight coefficient, which is used to control the influence of the prediction item on the joint controller.

[0057] The error vector of the unmanned boat attitude is constructed as:

[0058]

[0059] Among them, ΔP(t) represents the attitude error vector of the unmanned boat, are the predicted values ​​of the pitch angle, roll angle and heave acceleration of the unmanned boat, θ(t), φ(t), a z (t) represents the current feedback values ​​of the pitch angle, roll angle and heave acceleration of the unmanned boat respectively.

[0060] The error analysis between the predicted attitude value of the unmanned boat and the real-time feedback attitude data is performed. A preferred solution for the preset threshold ε of the unmanned boat attitude error is:

[0061]

[0062] Among them, ε is the preset threshold of the unmanned boat attitude error, Δθ(t) is the preset threshold of the unmanned boat pitch angle error, Δφ(t) is the preset threshold of the unmanned boat roll angle error, Δa z (t) is the preset threshold value of the unmanned boat heave acceleration error.

[0063] In low to medium sea conditions, the natural fluctuation amplitude of the pitch angle of the unmanned boat usually does not exceed 2 degrees. Setting the threshold to 2.5 degrees can effectively filter out invalid intervention caused by small fluctuations, ensuring that the system will trigger enhanced control actions only when there is a significant deviation trend in the pitch attitude, thereby taking into account both system stability and response sensitivity. The roll angle is more sensitive to the heading stability of the unmanned boat. Too small or too large a roll offset may cause the track to deviate. Therefore, setting the threshold to 2.0 degrees can make timely corrections when there is a small disturbance in the heading, which helps to improve the accuracy of track control and navigation efficiency. The heave acceleration reflects the degree of vertical dynamic disturbance and is set to 0.8m / s2 It can effectively identify vertical disturbances of medium intensity or above, and promptly trigger the controller to adjust the thrust compensation and attitude stabilization strategies to prevent structural fatigue and inertial drift caused by vertical oscillations, thereby improving navigation safety and system robustness. When ΔP(t) ≥ ε, the prediction item weight η(t) is automatically amplified to enhance the controller's feedforward response capability; when ΔP(t) < ε, the prediction weight is kept low to reduce unnecessary intervention intensity, thereby realizing trend perception-driven controller dynamic gain distribution.

[0064] Furthermore, predictive adjustment and stable control of the unmanned boat's posture include judging the changing trend of the unmanned boat's posture.

[0065] If the attitude change rate of the unmanned boat is less than the threshold, the current attitude error is controlled through the low-gain nonlinear adaptive control law.

[0066] If the attitude change rate of the unmanned boat is greater than the threshold, the high-gain nonlinear adaptive controller is triggered to intervene and perform strong control actions to avoid attitude deviation.

[0067] It should also be noted that the attitude feedback values ​​of the unmanned boat at the current moment are collected, including the pitch angle, roll angle and heave acceleration, and the attitude feedback values ​​of the previous moment are recorded synchronously to form a data sequence of continuous time steps. Based on the time step Δt, the change amount of each attitude parameter between two adjacent moments is calculated respectively, that is, the attitude difference between the current moment and the previous moment. The above attitude difference is divided by the time step Δt to obtain the corresponding attitude change rate. The pitch angle change rate, roll angle change rate and heave acceleration change rate correspond to the change amplitude of the pitch angle, roll angle and heave acceleration in unit time respectively. A preferred solution for the pitch angle change rate is 25%, a preferred solution for the roll angle change rate is 30%, and a preferred solution for the heave acceleration change rate is 20%. Setting the pitch angle change rate to 25% can respond in time when identifying large longitudinal waves or sudden changes in sea conditions at an early stage, while not being too sensitive to avoid frequent disturbances caused by small disturbances. Setting the roll angle change rate to 30% effectively balances heading tracking stability with navigation energy optimization, preventing ineffective control caused by small lateral sway while ensuring rapid response when dangerous sway occurs. Setting the heave acceleration change rate to 20% effectively detects sudden vertical disturbances, avoiding sensor drift, navigation error accumulation, and system response lag caused by failure to promptly identify heave disturbances. When the UAV's attitude change rate is less than a preset threshold, indicating that the current sea disturbance is mild and the attitude change trend is gentle, a low-gain nonlinear adaptive control law is adopted, making fine adjustments based on the attitude error function, appropriately reducing the controller output amplitude and energy consumption, maintaining system stability and efficiency, and avoiding overcontrol caused by minor disturbances. When the UAV's attitude change rate exceeds the preset threshold, indicating that the current sea disturbance is intensifying or the UAV's attitude is deviating significantly, the high-gain nonlinear adaptive controller's rapid intervention mechanism is triggered, automatically increasing the controller's dynamic response rate and adjustment amplitude, executing strong control actions, and increasing the ability to suppress attitude errors in real time, preventing the attitude from further deviating from the expected trajectory, thereby improving the UAV's anti-disturbance stability and navigation safety in complex sea conditions.

[0068] Example 2, reference Figure 2 , which is an embodiment of the present invention, provides an unmanned boat attitude stabilization and intelligent anti-disturbance system under complex sea conditions, including a sea condition modeling and disturbance level determination module 100, a nonlinear adaptive attitude control module 200, and an attitude prediction and joint control module 300.

[0069] Among them, S4: sea condition modeling and disturbance level determination module 100 includes a multi-source sensing acquisition unit 101 and a disturbance level identification unit 102. The multi-source sensing acquisition unit 101 is used to collect the posture data of the unmanned boat and the characteristic parameters of the sea surface environment in real time. The disturbance level identification unit 102 predicts the sea condition state value based on the LSTM neural network, compares it with the threshold, and outputs the disturbance level determination result.

[0070] It should also be noted that the multi-source sensing acquisition unit 101 collects the posture data of the unmanned boat and the characteristic parameters of the sea surface environment, and transmits them to the disturbance level identification unit 102. The disturbance level identification unit 102 predicts the sea state based on the LSTM network and outputs the disturbance level determination result.

[0071] S5: The nonlinear adaptive posture control module 200 includes a gain adjustment control unit 201 and a control law generation unit 202. The gain adjustment control unit 201 is used to select a low-gain or high-gain control law in real time according to the disturbance level and adjust the control response amplitude. The control law generation unit 202 is used to construct a nonlinear control law based on the posture error and generate control instructions for adjusting the actuator.

[0072] It should also be noted that the gain adjustment control unit 201 receives the disturbance level determination result, dynamically selects a low-gain or high-gain control law according to the disturbance level, and transmits the selection result to the control law generation unit 202, which generates a nonlinear adaptive control instruction according to the posture error.

[0073] S6: The posture prediction and joint control module 300 includes a state prediction unit 301 and a joint control execution unit 302. The state prediction unit 301 is used to construct a posture state sequence based on historical and current posture data and predict the posture change trend at the next moment. The joint control execution unit 302 is used to fuse the predicted trend with the current error, dynamically adjust the nonlinear controller parameters, and output joint control instructions.

[0074] It should also be noted that the state prediction unit 301 predicts the posture change trend at the next moment based on historical and current posture data, and the joint control execution unit 302 combines the posture prediction results with the current error to dynamically adjust the nonlinear control parameters to form a joint control instruction.

[0075] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0076] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0077] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0078] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0079] 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 the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for stabilizing the attitude of an unmanned boat and intelligently rejecting disturbances in complex sea conditions, characterized by: include: Construct sea condition models to determine the level of sea surface disturbance; Based on the sea surface disturbance level, nonlinear adaptive control of the unmanned boat is performed; Based on the state prediction algorithm, the unmanned boat's attitude is jointly controlled in combination with nonlinear adaptive control.

2. The method for stabilizing the attitude of an unmanned boat and performing intelligent anti-interference in complex sea conditions according to claim 1, wherein: The sea condition model is constructed by collecting the attitude data of the unmanned boat and the characteristic parameters of the current sea area through the multi-source sensors on the unmanned boat, predicting the sea condition based on the characteristic parameters using a long short-term memory neural network, and judging the disturbance level according to the sea condition value.

3. The method for stabilizing the attitude of an unmanned boat and performing intelligent anti-interference in complex sea conditions according to claim 1 or 2, characterized in that: The method of determining the disturbance level according to the sea state value includes comparing the predicted sea state value with a preset threshold value. If the predicted sea state value is greater than or equal to the first-level preset threshold value, the sea surface disturbance level is determined to be first level. If the predicted sea state value is greater than or equal to the second-level preset threshold value, the sea surface disturbance level is determined to be second level.

4. The method for stabilizing the attitude of an unmanned boat and performing intelligent anti-interference in complex sea conditions according to claim 3, wherein: The nonlinear adaptive control of the unmanned boat includes real-time adjustment of the control gain according to the attitude error function. When the sea surface disturbance level is level one, a low-gain nonlinear adaptive control law is adopted to reduce the control action amplitude and energy consumption; when the sea surface disturbance level is level two, a high-gain nonlinear adaptive control law is adopted to improve the response speed and adjustment amplitude of the controller in real time.

5. The method for stabilizing the attitude of an unmanned boat and performing intelligent anti-interference in complex sea conditions according to claim 4, characterized in that: The state prediction algorithm includes constructing a posture state sequence based on the historical posture data and current posture data of the unmanned boat, predicting the posture state of the unmanned boat at the next moment through the state prediction algorithm, and outputting the posture prediction value of the unmanned boat.

6. The method for stabilizing the attitude of an unmanned boat and performing intelligent anti-interference in complex sea conditions according to any one of claims 1, 2, 4, or 5, wherein: The joint control of the unmanned boat attitude includes constructing an unmanned boat attitude joint control algorithm, performing stability evaluation on the unmanned boat attitude prediction value, performing error analysis between the unmanned boat attitude prediction value and the real-time feedback attitude data, adjusting the parameters of the unmanned boat attitude joint control algorithm in real time according to the error analysis results, and predicting, adjusting and stabilizing the unmanned boat attitude.

7. The method for stabilizing the attitude of an unmanned boat and performing intelligent anti-interference in complex sea conditions according to claim 6, wherein: The predictive adjustment and stable control of the unmanned boat's attitude includes judging the changing trend of the unmanned boat's attitude; If the attitude change rate of the unmanned boat is less than the threshold, the current attitude error is controlled through the low-gain nonlinear adaptive control law; If the attitude change rate of the unmanned boat is greater than the threshold, the high-gain nonlinear adaptive controller is triggered to intervene and perform strong control actions to avoid attitude deviation.

8. An unmanned boat attitude stabilization and intelligent anti-interference system under complex sea conditions, characterized by: It includes a sea state modeling and disturbance level determination module (100), a nonlinear adaptive attitude control module (200), and an attitude prediction and joint control module (300); The sea state modeling and disturbance level determination module (100) comprises a multi-source sensing acquisition unit (101) and a disturbance level identification unit (102). The multi-source sensing acquisition unit (101) is used to collect the attitude data of the unmanned boat and the characteristic parameters of the sea surface environment in real time. The disturbance level identification unit (102) predicts the sea state value based on the LSTM neural network, compares it with the threshold value, and outputs the disturbance level determination result. The nonlinear adaptive attitude control module (200) comprises a gain adjustment control unit (201) and a control law generation unit (202), wherein the gain adjustment control unit (201) is used to select a low-gain or high-gain control law in real time according to the disturbance level and adjust the control response amplitude, and the control law generation unit (202) is used to construct a nonlinear control law according to the attitude error and generate a control instruction for adjusting the actuator; The posture prediction and joint control module (300) comprises a state prediction unit (301) and a joint control execution unit (302). The state prediction unit (301) is used to construct a posture state sequence based on historical and current posture data and predict the posture change trend at the next moment. The joint control execution unit (302) is used to fuse the predicted trend with the current error, dynamically adjust the nonlinear controller parameters, and output a joint control instruction.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the unmanned boat attitude stabilization and intelligent anti-interference method under complex sea conditions described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the unmanned boat attitude stabilization and intelligent anti-interference method under complex sea conditions described in any one of claims 1 to 7 are implemented.

Images