A method and system for marine wave compensation for vessel stabilization

Abstract

The present application relates to the technical field of wave compensation, and particularly relates to a marine wave compensation method and system for ship stability, which comprises the following steps: collecting all-around marine wave monitoring parameters, and performing multi-time window period division processing and wave energy density quantification analysis to generate wave energy density of each time window; performing nonlinear dynamics behavior mining and dynamic sea wave digital perception modeling according to the wave energy density of each time window to construct a sea wave field dynamics model; performing multi-scale wave feature analysis based on the sea wave field dynamics model, and performing wave trend evolution prediction to construct a wave trend prediction map; and identifying current ship state parameters. The present application realizes automatic adjustment of the center of gravity position according to real-time monitoring data, and realizes adaptive stability optimization of the ship attitude under different wave conditions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wave compensation, in particular to a marine wave compensation method and system for ship stability. BACKGROUND

[0002] With the continuous development of global shipping industry, ships as an important means of transportation, bear the heavy responsibility of global cargo transportation. In harsh marine environment, the stability of the ship is directly related to the safety of navigation and transportation efficiency. Especially in complex sea conditions, waves, wind waves and other factors have a great impact on the swing, tilt and swing of the ship, which brings not small challenges to the normal operation of the ship. With the continuous progress of modern ship technology, the requirements for ship stability are becoming more and more stringent, and how to improve the stability of the ship under the influence of waves has become a technical problem to be solved in the shipping industry.

[0003] The traditional ship stability method mainly relies on the center of gravity control, ballast water adjustment and passive stability technology such as stabilization tank. Although these methods can improve the stability of the ship to a certain extent, they are often limited by the change of sea conditions and cannot cope with instantaneous wave impact or dynamic changes of marine environment, and need to rely on manual intervention or regular adjustment, which has certain limitations. At the same time, when facing large-scale changes of ocean waves, the traditional method lacks real-time dynamic adaptability and cannot achieve accurate and effective wave compensation, especially in complex marine environment, which may lead to poor stability of the ship and increase the risk of navigation.

[0004] With the rapid development of intelligent technology, Internet of Things, big data analysis and other technologies, the field of ship stability has also ushered in new opportunities. By introducing advanced sensor technology, real-time monitoring system and intelligent algorithm, the ocean waves can be accurately perceived and the dynamic changes of the waves can be analyzed in real time, so as to intelligently adjust the attitude, center of gravity and other parameters of the ship. This intelligent and real-time wave compensation method is expected to greatly improve the stability of the ship in complex sea conditions, reduce the need for human intervention and improve the safety of ship navigation.

[0005] However, the existing wave compensation technology mostly only compensates for single wave period or is based on simple model prediction, without considering various wave types, complex sea conditions with dynamic changes and real-time response of the ship. Although these methods improve the stability of the ship to a certain extent, they often lack forward-looking analysis of wave changes and intelligent dynamic adjustment mechanism, and cannot realize real-time warning and adaptive compensation. Therefore, a new marine wave compensation method with high intelligence and real-time performance is needed to solve the shortcomings of the existing technology and better adapt to the rapidly changing marine environment. SUMMARY

[0006] The application is a marine wave compensation method and system for ship stability to solve at least one of the above technical problems.

[0007] To achieve the above object, the application provides a marine wave compensation method for ship stability, comprising the following steps:

[0008] Step S1: Collect omnidirectional marine wave monitoring parameters, and perform multi-time window period division processing and wave energy density quantification analysis to generate wave energy density of each time window.

[0009] Step S2: Perform nonlinear dynamics behavior mining and dynamic sea wave digital perception modeling according to the wave energy density of each time window to construct a sea wave field dynamics model.

[0010] Step S3: Perform multi-scale wave feature analysis based on the sea wave field dynamics model, and perform wave trend evolution prediction to construct a wave trend prediction map.

[0011] Step S4: Identify the current ship state parameters; calculate the real-time roll and pitch angles of the ship according to the current ship state parameters, and perform wave action motion characteristic modeling to construct a ship dynamics stability model.

[0012] Step S5: Perform dynamic navigation simulation on the ship dynamics stability model based on the wave trend prediction map, and perform inclination amplitude analysis to calculate the current ship center of gravity position.

[0013] Step S6: Adjust the adaptive ship center of gravity distribution of the current ship center of gravity position according to the center of gravity adjustable dynamic ballast device, and then perform reinforcement learning to construct an intelligent wave compensation engine.

[0014] The present application collects all-around ocean wave data (wave height, wave period, wave speed, wave direction, etc.) in real time through various sensors (such as buoys, radars, sonars, satellite remote sensing, etc.), ensuring comprehensive and accurate monitoring data, providing detailed marine environment information, and providing reliable basic data for subsequent analysis. By dividing the wave data into time windows, the changes in wave signals are divided into multiple periods for processing. This method can capture the detailed changes under different wave periods, effectively improving the accuracy of wave change trend analysis. Based on the combined analysis of wave height, wavelength, and wave period, the wave energy density in each time window is quantified. Energy density is a key indicator of the impact of waves on ships, reflecting the strength and impact range of waves, and is helpful for further analyzing the effect of waves on ship stability. The behavior of waves often exhibits nonlinear characteristics, such as wave resonance, breaking, and other nonlinear phenomena. Through the analysis of wave energy density, the nonlinear dynamics of waves can be explored, providing more accurate data support for ship stability analysis. A sea wave model with dynamic perception capability is constructed, which can adjust and adapt to changes in wave conditions in real time. This model can accurately simulate the dynamic characteristics of the wave field, enhancing the adaptability of ships to waves, and laying the foundation for subsequent wave prediction and compensation strategies. By establishing a comprehensive sea wave field dynamics model, the evolution and propagation process of sea waves can be accurately described. This model provides a theoretical basis for ship wave compensation design, enabling optimization of ship motion under complex wave conditions. Through multi-scale analysis, key features of waves (such as wave peaks, troughs, bandwidth, etc.) can be extracted from multiple time scales, which can accurately capture the change trend under different wave periods and optimize the ship stability evaluation model. Based on the sea wave field dynamics model, the trend evolution of waves is predicted, and a wave trend prediction map is generated. By predicting the future trend of waves, ships can take appropriate stability measures in advance to avoid damage or instability caused by changes in waves. The generation of the wave trend prediction map is to provide intuitive wave dynamic change information to ship operators, helping them judge the intensity, direction, and period of the upcoming waves, and providing support for ship navigation decisions. Through real-time monitoring of ship speed, acceleration, inclination angle, and other state parameters, the current motion state of the ship can be accurately identified, which is crucial for evaluating the stability of the ship in waves. According to the real-time state of the ship, the roll and pitch angles of the ship are accurately calculated, which are key indicators in ship stability evaluation, helping to analyze the dynamic response of the ship after being affected by waves. Combined with real-time wave data and ship state, a ship motion characteristic model under wave action is constructed. Through this model, the behavior of the ship in waves can be accurately simulated, providing a basis for stability analysis and compensation. By establishing a dynamic stability model of the ship body, the stability of the ship in wave environments can be evaluated in real time, and scientific basis is provided for subsequent wave compensation and dynamic adjustment.By means of dynamic navigation simulation based on wave trend prediction map, the motion performance of the ship in different wave environments is simulated, which can identify the possible stability problems of the ship in future wave conditions in advance and provide guidance for navigation strategy. According to the dynamic response of the ship, the inclination amplitude and its change are calculated, which helps to grasp the stability of the ship in real time and take necessary measures to prevent the ship from tilting too much and causing instability. Through monitoring and simulation of the ship's motion state, the center of gravity position of the ship body is accurately calculated. The change of the center of gravity position is crucial to the stability of the ship, and the calculation of this parameter helps to further carry out dynamic compensation and stability optimization. Through the adjustable ballast system, the center of gravity distribution of the ship is dynamically adjusted according to the real-time center of gravity position of the ship body, and the stability of the ship body is optimized. The device can effectively reduce the instability of the ship caused by waves, especially in complex marine environments. The system can automatically adjust the center of gravity position according to the real-time monitoring data to realize adaptive stability optimization of the ship in different wave conditions, which can improve the safety of the ship and reduce manual intervention. Through reinforcement learning algorithm, the system can continuously optimize the wave compensation strategy according to the actual navigation situation. The compensation engine can automatically learn the optimal stability compensation strategy during the ship's navigation process, improve the adaptability of the ship, and gradually improve the stability of the ship in different sea conditions.

[0015] In the present specification, a marine wave compensation system for ship stability is provided for performing the marine wave compensation method for ship stability as described above, comprising:

[0016] A data processing module is used to collect all-around marine wave monitoring parameters, and perform multi-time window period division processing and wave energy density quantification analysis to generate wave energy density of each time window.

[0017] A nonlinear dynamics analysis module is used to perform nonlinear dynamics behavior mining and dynamic sea wave digital perception modeling according to the wave energy density of each time window, and construct a sea wave field dynamics model.

[0018] A wave trend prediction module is used to perform multi-scale wave feature analysis based on the sea wave field dynamics model, and perform wave trend evolution prediction to construct a wave trend prediction map.

[0019] A ship attitude module is used to identify current ship state parameters; calculate real-time roll and pitch angles of the ship according to the current ship state parameters, and perform wave action motion characteristic modeling to construct a ship body dynamics stability model.

[0020] A dynamic navigation simulation module is used to perform dynamic navigation simulation on the ship body dynamics stability model based on the wave trend prediction map, and perform inclination amplitude analysis to calculate the current ship body center of gravity position.

[0021] The ship center of gravity adjusting module is used for adjusting the current ship center of gravity position according to the center of gravity adjustable dynamic ballast device, and then performing reinforcement learning to construct an intelligent wave compensation engine.

[0022] The application ensures that comprehensive and accurate wave information is collected by the data processing module through comprehensive collection of ocean wave parameters such as wave height, wave period, wave speed, and wave direction, providing sufficient input data for subsequent analysis. By using multiple sensors (such as buoys, radars, sonars, etc.), real-time monitoring of changes in the ocean waves around the ship can be achieved, enhancing the reliability of the data. The data is divided into multiple time windows to allow for more detailed period analysis. Analysis of different time windows can help capture the instantaneous changes in the sea waves, reflect the wave behavior at different time scales, and improve the accuracy and real-time nature of the analysis. Through comprehensive analysis of parameters such as wave height, wave period, and wave speed, the wave energy density in each time window is quantified, providing a reliable wave energy model for subsequent wave trend prediction and dynamic stability analysis, allowing the impact of ocean waves to be clearly quantified and providing basic data support for ship stability optimization. Waves have complex nonlinear characteristics, such as resonance, wave interaction, and breaking. Through the nonlinear dynamics analysis module, the complex behavior of waves can be explored to provide more accurate dynamic characteristics for ship stability evaluation. This deep exploration can reveal wave characteristics that traditional linear models cannot capture, providing a new perspective for wave compensation. The nonlinear dynamics analysis module helps establish a multidimensional sea wave field dynamics model to simulate wave behavior in different sea wave environments. This model can accurately predict the evolution of sea waves and provide scientific basis for ship stability prediction and compensation schemes. By analyzing the multi-scale characteristics of sea waves (such as wave crest, wave trough, period, amplitude, etc.), the module can extract key features of waves from multiple dimensions. This multi-scale analysis can capture the changing trends of waves in the short term (such as a few hours) and the long term (such as a few days), helping to better understand wave dynamics at different time scales. Based on the sea wave field dynamics model, the evolution of future wave trends is predicted. This module can predict wave changes (such as wave intensity, direction, period, etc.) in the future for a certain period of time, providing information support for ships to take stability measures in advance. By generating wave trend prediction charts, ship operators can visually see the future wave trends, including the direction, intensity, and period of the waves. This visual prediction chart helps crew members make more intelligent decisions in complex sea conditions, improving navigation safety. The ship attitude module obtains real-time ship motion state parameters (such as ship speed, acceleration, ship body angle, etc.), accurately describing the ship's state under the action of waves. Through these parameters, the module can monitor the ship's stability in real time and provide feedback for dynamic compensation. The module can accurately calculate the roll angle and pitch angle of the ship under different wave conditions, which are important parameters for analyzing ship stability and helping crew members judge the stability changes of the ship and take timely measures. By modeling the ship's motion characteristics under the action of waves, the module can simulate the ship's response under different wave conditions, providing a scientific basis for subsequent stability optimization and dynamic compensation strategies.Based on the wave trend prediction map, the dynamic navigation simulation module can simulate the actual navigation of the ship under different wave conditions. The simulation results can help the crew to predict the stability problems that may be encountered during navigation and provide support for taking appropriate compensation measures. By accurately calculating the real-time center of gravity position of the ship, the module can provide stability data of the ship to help evaluate whether the center of gravity needs to be adjusted and provide data support for subsequent compensation strategies. The ship center of gravity adjustment module adjusts the center of gravity of the ship through dynamic ballast devices. According to the real-time center of gravity position, the system adjusts the liquid ballast distribution of the ship to achieve the best distribution of the ship's center of gravity, thereby improving the stability. Through the reinforcement learning algorithm, the module can continuously optimize the compensation strategy of the ship's stability. Through the accumulation of experience in actual navigation, the system can continuously learn and adjust the compensation algorithm to always maintain the best state under different wave conditions. The system gradually optimizes the wave compensation strategy through reinforcement learning to adapt to different wave conditions in real time. Finally, an intelligent wave compensation engine is formed through self-learning and self-optimization, which effectively improves the dynamic stability of the ship, reduces manual intervention, and improves the safety and efficiency of navigation. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 A step flow diagram of a marine wave compensation method for ship stability is provided.

[0024] Figure 2 A detailed implementation step flow diagram of step S1 is provided.

[0025] Figure 3 A detailed implementation step flow diagram of step S2 is provided.

[0026] Figure 4 A detailed implementation step flow diagram of step S3 is provided. DETAILED DESCRIPTION

[0027] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0028] The present application provides a marine wave compensation method and system for ship stability. The execution subject of the marine wave compensation method and system for ship stability includes but is not limited to mechanical equipment, data processing platform, cloud server node, network upload device, etc. which can be regarded as general computing nodes of the present application, and the data processing platform includes but is not limited to audio image management system, information management system, cloud data management system, at least one of which.

[0029] Please refer to Figures 1 to 4 The present application provides a marine wave compensation method for ship stability, which includes the following steps:

[0030] Step S1: Collecting all-around ocean wave monitoring parameters, and performing multi-time window period division processing and wave energy density quantification analysis to generate wave energy density of each time window;

[0031] Step S2: According to the wave energy density of each time window, nonlinear dynamics behavior mining and dynamic sea wave digital perception modeling are performed to construct a sea wave field dynamics model;

[0032] Step S3: Based on the sea wave field dynamics model, multi-scale wave feature analysis is performed, and wave trend evolution prediction is performed to construct a wave trend prediction map;

[0033] Step S4: Identifying the current ship state parameters; calculating the real-time roll and pitch angles of the ship according to the current ship state parameters, and performing wave action motion characteristic modeling to construct a ship dynamics stability model;

[0034] Step S5: Based on the wave trend prediction map, the ship dynamics stability model is simulated for dynamic navigation, and the inclination amplitude is analyzed to calculate the current ship center of gravity position;

[0035] Step S6: According to the center of gravity adjustable dynamic ballast device, the current ship center of gravity position is adjusted for adaptive ship center of gravity distribution, and reinforcement learning is performed to construct an intelligent wave compensation engine.

[0036] The present application collects all-around ocean wave data (wave height, wave period, wave speed, wave direction, etc.) in real time through various sensors (such as buoys, radars, sonars, satellite remote sensing, etc.), ensuring comprehensive and accurate monitoring data, providing detailed marine environment information, and providing reliable basic data for subsequent analysis. By dividing the wave data into time windows, the changes in wave signals are divided into multiple periods for processing. This method can capture the detailed changes under different wave periods, effectively improving the accuracy of wave change trend analysis. Based on the combined analysis of wave height, wavelength and wave period, the wave energy density in each time window is quantified. Energy density is a key indicator of the impact of waves on ships, which can reflect the intensity and impact range of waves, and is helpful for further analyzing the effect of waves on ship stability. The behavior of waves usually exhibits nonlinear characteristics, such as wave resonance, breaking, and other nonlinear phenomena. Through the analysis of wave energy density, the nonlinear dynamics of waves can be explored, providing more accurate data support for ship stability analysis. A sea wave model with dynamic perception capability is constructed, which can adjust and adapt to changes in wave conditions in real time. This model can accurately simulate the dynamic characteristics of the wave field, enhancing the adaptability of the ship to waves, and laying the foundation for subsequent wave prediction and compensation strategies. By establishing a comprehensive sea wave field dynamics model, the evolution and propagation process of sea waves can be accurately described. This model provides a theoretical basis for ship wave compensation design, which can optimize ship motion under complex wave conditions. Through multi-scale analysis, key features of waves (such as wave peaks, troughs, bandwidth, etc.) can be extracted from multiple time scales, which can accurately capture the change trend under different wave periods and optimize the ship stability evaluation model. Based on the sea wave field dynamics model, the trend evolution of the wave is predicted, and a wave trend prediction map is generated. By predicting the future trend of the wave, the ship can take appropriate stability measures in advance to avoid damage or instability caused by changes in the wave. The generation of the wave trend prediction map is to provide intuitive wave dynamic change information to ship operators, helping them judge the intensity, direction and period of the upcoming wave, and providing support for ship navigation decision-making. Through real-time monitoring of ship speed, acceleration, inclination angle and other state parameters, the current motion state of the ship can be accurately identified, which is crucial for evaluating the stability of the ship in waves. According to the real-time state of the ship, the roll and pitch angles of the ship are accurately calculated, which are key indicators in ship stability evaluation, helping to analyze the dynamic response of the ship after being affected by waves. Combined with real-time wave data and ship state, a ship motion characteristic model under wave action is constructed. Through this model, the behavior of the ship in waves can be accurately simulated, providing a basis for stability analysis and compensation. By establishing a dynamic stability model of the ship body, the stability of the ship in the wave environment can be evaluated in real time, and scientific basis is provided for subsequent wave compensation and dynamic adjustment.By means of dynamic navigation simulation based on wave trend prediction map, the motion performance of the ship in different wave environments is simulated, which can identify the possible stability problems of the ship in future wave conditions in advance and provide guidance for navigation strategy. According to the dynamic response of the ship, the inclination amplitude and its change are calculated, which helps to grasp the stability of the ship in real time and take necessary measures to prevent the ship from tilting too much and causing instability. Through monitoring and simulation of the ship's motion state, the center of gravity position of the ship body is accurately calculated. The change of the center of gravity position is crucial to the stability of the ship, and the calculation of this parameter helps to further carry out dynamic compensation and stability optimization. Through the adjustable ballast system, the center of gravity distribution of the ship is dynamically adjusted according to the real-time center of gravity position of the ship body, and the stability of the ship body is optimized. The device can effectively reduce the instability of the ship caused by waves, especially in complex marine environments. The system can automatically adjust the center of gravity position according to the real-time monitoring data to realize adaptive stability optimization of the ship under different wave conditions, which can improve the safety of the ship and reduce manual intervention. Through reinforcement learning algorithm, the system can continuously optimize the wave compensation strategy according to the actual navigation situation. The compensation engine can automatically learn the optimal stability compensation strategy during the ship's navigation process, improve the adaptability of the ship, and gradually improve the stability of the ship in different sea conditions.

[0037] In the embodiment of the present application, referring to Figure 1 The present application is a method for stabilizing a ship in ocean waves. The steps of the method include:

[0038] Step S1: Collect all-around ocean wave monitoring parameters, and perform multi-time window period division processing and wave energy density quantification analysis to generate the wave energy density of each time window;

[0039] In this embodiment, suitable monitoring devices (such as wave buoys, sonar sensors, accelerometers, etc.) are selected that can comprehensively capture the dynamic characteristics of ocean waves. Wave buoys can measure wave height, wavelength, and wave period in real time. Multiple buoys are arranged in a certain sea area to ensure wide coverage and obtain monitoring data under various wave conditions. Factors such as water depth, tidal changes, and ocean currents should be considered when arranging to obtain more accurate data. According to the rate of change of wave characteristics, a reasonable data acquisition frequency is set. It is generally recommended to sample once every second to ensure that subtle changes in waves can be captured. Sampling at a frequency of 1 per second for 2 hours will ultimately result in 7200 data points, ensuring data continuity and integrity. The collected wave monitoring data is stored in real time into the data server and undergoes preliminary data cleaning and preprocessing. The cleaning process includes removing outliers and filling missing values to ensure data quality. If an abnormal wave height is detected for a certain data point (such as exceeding a reasonable range), it is removed and the missing data point is filled using interpolation. According to the purpose of wave monitoring, appropriate time windows are selected for division. A 10-minute, 15-minute, or 30-minute time window is usually used to analyze the changes in wave characteristics. The 2-hour monitoring data is divided into 8 15-minute time windows to ensure that the wave data in each window can be analyzed independently. The data in each time window is organized to ensure that relevant wave parameters (such as wave height, wave period, etc.) can be extracted. In each time window, the data integrity should be ensured, and any missing or abnormal values should be removed. If there are missing data points in a 15-minute window, the average value of the previous and subsequent data is used to fill them, so that there are 900 data points in each window (if the sampling frequency is 1 Hz). The monitoring data of each time window is recorded in the database for subsequent analysis and processing. The record format should include "time window, wave height, wave period, wave speed" and other information. Wave energy density (E) refers to the energy possessed by waves per unit area. If the average wave height in a certain time window is 1.5 meters, the energy density of that window is calculated as E = 0.5 x 1000 x 9.81 x (1.5 2 ), and the energy density value is obtained. The calculated wave energy density of each time window is recorded in the database for subsequent analysis, and these records should include the time window identifier and the corresponding energy density value.

[0040] Step S2: Nonlinear dynamic behavior mining and dynamic sea wave digital perception modeling are performed according to the wave energy density of each time window to construct a sea wave field dynamics model.

[0041] In this embodiment, wave energy density data for each time window is obtained from step S1, which should include time window identification, wave energy density value, and related parameters (such as wave height, wave period, etc.). Assuming that in 2 hours of monitoring, 8 15-minute time windows are divided, the wave energy density of each window has been calculated and stored, and the record format is "time window, wave height, wave energy density". The collected wave energy density data is cleaned to remove outliers and missing values. Statistical methods such as Z-score or IQR (interquartile range) can be used to identify and remove abnormal data points. If the energy density value of a certain time window is significantly higher than other values (such as more than 3 times the standard deviation), the value should be removed, and the missing value should be filled using linear interpolation to ensure data integrity. Nonlinear time series analysis methods (such as phase space reconstruction, Lyapunov exponent calculation, fractal dimension, etc.) are used to analyze wave energy density data, which can reveal the complexity and nonlinear characteristics of wave behavior. Through phase space reconstruction, the wave energy density time series is converted into a phase space graph, from which the dynamic characteristics of the wave signal are identified. The Lyapunov exponent is calculated to assess the chaotic characteristics of the wave signal. A positive Lyapunov exponent indicates that the system has chaotic characteristics, while a negative one indicates that the system tends to be stable. If the calculated Lyapunov exponent is 0.1, it indicates that the wave behavior has certain chaotic characteristics, which needs to be further analyzed for its impact on ship stability. The fractal dimension of wave energy density data is analyzed through fractal theory to quantify the complexity of wave signals. Higher fractal dimension indicates more complex wave behavior. If the fractal dimension of wave energy density is 1.5, it indicates that the wave behavior has high complexity and its impact on the ship needs attention. Based on the mined nonlinear dynamic characteristics, select appropriate models (such as nonlinear time series models, neural network models, stochastic process models, etc.) to construct the sea wave field dynamics model. The model should be able to reflect the dynamic changes of waves and their impact on ships. Select the long short-term memory (LSTM) model, which performs well in handling time series data and can capture long-term dependencies of waves. Use the wave energy density data collected earlier to train the dynamic sea wave model. Divide the data into training and validation sets, set reasonable training parameters (such as learning rate, batch size, etc.) to optimize model performance. Set 80% of the data for training and 20% for validation to ensure the model can accurately predict wave behavior. Evaluate the model's predictive ability by calculating indicators such as root mean square error (RMSE) and mean absolute error (MAE). Ensure that the model can effectively reflect the dynamic characteristics of waves and provide accurate support for ship stability. Apply the constructed sea wave field dynamics model to the real-time wave monitoring system to predict wave behavior in real time and provide feedback. Adjust the ship's navigation strategy based on real-time data to optimize stability.If the wave energy density is monitored to rise rapidly in a short time, the model will automatically adjust the ship's heading and speed to maintain stability.

[0042] Step S3: Perform multi-scale wave feature analysis based on the sea wave field dynamics model and conduct wave trend evolution prediction to construct a wave trend prediction map.

[0043] In this embodiment, wave monitoring data is extracted from the sea wave field dynamics model, with particular attention paid to wave energy density, wave height, wave period, and other parameters. These data will be used for multi-scale analysis to obtain different characteristics of the waves. It is assumed that wave energy density data for 10 time windows has been obtained, with energy densities of 1.2 kJ / m 2 , 1.5 kJ / m 2 , etc. in each window, which will serve as the basis for analysis. Wavelet transform is used to perform multi-scale analysis on the wave data. Wavelet transform can analyze signals in both time and frequency domains simultaneously, revealing the multi-level characteristics of wave signals. Daubechies wavelet (such as db4) is selected as the base wavelet to decompose the wave energy density data and extract wave features in different frequency ranges, such as low-frequency waves (long waves) and high-frequency waves (short waves). The main wave features are extracted from the wavelet transform results, including energy distribution, amplitude, and period at each scale. By comparing the characteristics at different scales, the change pattern of the waves is understood. By analyzing the wavelet coefficients, it is found that the energy proportion of low-frequency waves is 60% and that of high-frequency waves is 40% in a certain time window, indicating that the waves in this time period are dominated by low-frequency waves. A suitable time series prediction model (such as ARIMA model, LSTM model, etc.) is selected for wave trend prediction. This model should be able to capture the evolution characteristics and dynamic changes of the waves. The LSTM model is chosen because it performs well in handling time series data and can effectively capture the non-linear characteristics and long-term dependencies of the waves. Historical wave data extracted from the sea wave field dynamics model is used to train the trend prediction model. The data should be divided into training and validation sets to ensure that the model accurately reflects the evolution trend of the waves. Set 70% of the data for model training and 30% for validation. If the wave energy density of the training data changes from 1.2 kJ / m 2 to 1.8 kJ / m 2 in the past 10 minutes, this range of change should be considered during training. Input real-time monitoring data into the wave trend prediction model to predict the change trend of wave energy density in the future. A wave trend prediction map is generated based on the results output by the model. If the model predicts that the wave energy density will rise from 1.5 kJ / m 2 to 2.0 kJ / m 2 in the next 15 minutes, the ship's heading and speed will be automatically adjusted to maintain stability.If the trend is recorded and a corresponding prediction graph is generated. Visualize the prediction results and construct a wave trend prediction graph. The graph should include a time axis, wave energy density and its predicted value, which can help analyze the changing trend of waves intuitively. Create a line chart with time on the horizontal axis and wave energy density on the vertical axis, and mark the actual monitoring value and model prediction value in the graph for comparison and analysis. Analyze the wave change law shown in the wave trend prediction graph and apply it to ship stability design and operation strategy formulation. By identifying the rising and falling trend of waves, scientific basis is provided for ship operation. If the prediction graph shows that the wave energy density will rise sharply in the next 30 minutes, the ship's heading or speed can be adjusted in advance to reduce the impact of waves on the ship.

[0044] Step S4: Identify the current ship state parameters; calculate the real-time roll and pitch angles of the ship according to the current ship state parameters, and model the wave action motion characteristics to build a ship dynamics stability model;

[0045] In this embodiment, a variety of sensors (such as inertial measurement unit (IMU), accelerometer, gyroscope, GPS, etc.) are arranged on the ship to monitor the state parameters of the ship in real time. The sensors should be able to capture the key information of the ship's speed, acceleration, heading, roll angle and pitch angle, etc. 3D acceleration and angular velocity data are obtained using IMU, collected once per second to ensure that the dynamic response of the ship under wave action can be reflected. The collected sensor data is monitored and processed in real time through data processing algorithms. Use filters (such as Kalman filter) to remove noise and ensure the accuracy and stability of the data. Kalman filter can be used to smooth the IMU data and reduce the influence of noise on the calculation of roll and pitch angles, thereby providing more accurate attitude parameters. Record the real-time calculated ship state parameters in the database for subsequent analysis and modeling, which should include timestamp, ship speed, acceleration, roll angle and pitch angle. If the recorded ship state at a certain time is "timestamp: T1, ship speed: 8 m / s, roll angle: 4°, pitch angle: 2°", these data are saved for subsequent use. The roll angle refers to the rotation angle of the ship around its longitudinal axis, which is usually calculated from the accelerometer and gyroscope data of the ship. The pitch angle refers to the rotation angle of the ship around its transverse axis, reflecting the degree of forward and backward inclination of the ship. If the lateral acceleration measured by the accelerometer is 0.5 m / s 2, the current roll angle can be calculated by integration. The angular velocity is integrated using the integral method to calculate the current roll and pitch angles. By updating the angle value in real time, the dynamic changes of the ship under the action of waves are reflected. The roll and pitch angles are updated regularly, and these data are recorded in the database. Ensure that the angle change at each time point is recorded for subsequent analysis and modeling. If the roll angle recorded after 1 second is 4.2° and the pitch angle is 2.1°, update and save these two values. Analyze the influence of waves on ship motion, especially how wave energy density, wave height, and wave period affect the roll and pitch behavior of the ship. Use the collected wave data to perform correlation analysis. If the wave height is 1.5 meters and the wave period is 6 seconds in a certain wave event, and the ship roll angle is observed to increase significantly, the relationship between waves and ship motion needs to be modeled. Based on the motion characteristics under the action of waves, a ship hull dynamics stability model is constructed. The model should consider factors such as the mass distribution of the ship hull, the center of gravity position, buoyancy, and resistance to achieve accurate description of the dynamic behavior of the ship. Use the Lagrange equation to construct the ship hull dynamics model, considering the dynamic response of the ship under the action of waves. Set model parameters such as ship hull mass of 5000 kg, center of gravity height of 1.5 m, etc. Use the measured data to verify the constructed dynamics model to ensure that the model can accurately reflect the stability of the ship under the action of waves. Evaluate the model by calculating its fitting degree and prediction ability. If the model predicts the roll angle consistent with the actual measured roll angle (e.g., model prediction is 4.1°, actual is 4.2°), the model verification is considered successful; if the deviation is large, adjust the model parameters to optimize the prediction results.

[0046] Step S5: Based on the wave trend prediction chart, perform dynamic navigation simulation on the ship hull dynamics stability model, and perform inclination amplitude analysis to calculate the current ship center of gravity position.

[0047] In this embodiment, the input parameters for dynamic navigation simulation are set based on the wave trend prediction chart generated in step S3. The wave trend prediction chart should include information such as wave energy density, wave height, and wave period, which will directly affect the dynamic response of the ship. Assuming the prediction chart shows that the wave height will reach 1.8 meters and the wave period is 5 seconds in the next 30 minutes, these data will be used as the basic parameters for dynamic navigation simulation. Using the previously constructed ship dynamics stability model, integrate the wave characteristics data to accurately simulate the dynamic behavior of the ship under the action of waves. The model should reflect the key factors such as the mass, buoyancy, and center of gravity position of the ship. Set the mass of the ship body to 6000 kg, the center of gravity height to 1.5 meters, and consider the geometric shape and hydrodynamic characteristics of the ship to ensure the accuracy of the model. Build a dynamic navigation environment in the computer simulation software, combine the wave characteristics in the wave trend prediction chart with the ship dynamics model, and prepare for dynamic navigation simulation. Ensure that the simulation environment can reflect the real sea conditions. Use the MATLAB / Simulink platform to build the ship model and input the wave data to ensure that the system can respond to the changes in the waves in real time. Start the dynamic navigation simulation program and monitor the ship's motion state under the action of waves in real time. Record the ship's speed, acceleration, roll angle, and pitch angle to facilitate subsequent analysis. Set the simulation time to 30 minutes and record the ship's motion parameters every second to ensure the continuity and integrity of the data. During the simulation process, monitor the ship's dynamic response in real time, including changes in roll and pitch angles. The dynamic response data will be used for subsequent inclination amplitude analysis and center of gravity calculation. If the maximum roll angle is 5.5° and the pitch angle is 3.2° during the simulation process, record these data for subsequent analysis. Organize all the data collected during the simulation and store them in the database to ensure that the dynamic response at each time point is recorded. The record format should include "timestamp, roll angle, pitch angle, speed, acceleration," etc. The inclination amplitude refers to the maximum inclination of the ship under the action of waves, usually determined by the roll and pitch angles. The analysis of inclination amplitude is crucial for evaluating the stability of the ship. If the roll angle is 5.5° and the pitch angle is 3.2°, the total inclination amplitude can be calculated. By combining the changes in roll and pitch angles, the inclination amplitude of the ship can be calculated. The vector composition method can be used to combine the roll and pitch angles to obtain the actual inclination angle. The current center of gravity position of the ship refers to the actual center of gravity under the action of waves. The change in the center of gravity position has an important influence on the stability of the ship. When calculating, the influence of inclination amplitude on the center of gravity position should be considered. Assuming that the initial center of gravity position of the ship body is 1.5 meters, it needs to be adjusted according to the inclination amplitude. Based on the inclination amplitude, adjust the center of gravity position of the ship body. The vertical position offset of the center of gravity can be calculated through simple geometric relationships. The adjustment value of the center of gravity position is ΔCG = h·sin( inclination amplitude), where h is the center of gravity height (1.5 meters).The calculated current ship center of gravity position is recorded in the database for subsequent stability analysis. The record format should include "time stamp, current center of gravity position". If the calculated current center of gravity position is 1.45 meters, it is recorded as "time stamp: T1, current center of gravity position: 1.45 meters".

[0048] Step S6: According to the center of gravity adjustable dynamic ballast device, the adaptive ship center of gravity distribution adjustment is performed on the current ship center of gravity position, and reinforcement learning is performed to construct an intelligent wave compensation engine.

[0049] In this embodiment, the current ship's center of gravity position calculated from the previous step is used to assess the stability of the ship under wave action. This position is crucial for subsequent dynamic ballast adjustments. If the current center of gravity position is 1.45 meters, it needs to be compared with the standard center of gravity position (e.g., 1.5 meters) to calculate the center of gravity deviation. The center of gravity deviation can be calculated using the formula ΔCG = CG(standard) - CG(current), and the impact of the center of gravity deviation on the ship's stability can be assessed. Based on the change in the center of gravity position, it is determined whether the ship is within a safe range. If the deviation is too large, appropriate adjustments need to be made. If the center of gravity deviation exceeds 0.1 meters, it indicates that the ship is at risk of significant tilting, and measures need to be taken to adjust it. Based on the center of gravity deviation, the adjustable dynamic ballast device is activated, which automatically adjusts the distribution of the ship's center of gravity based on real-time monitoring data to compensate for the center of gravity deviation. If 200 liters of water need to be compensated, the dynamic ballast device will start and adjust the distribution of these water to achieve the optimal center of gravity position. The amount of water needed for compensation is calculated, and the water injection or discharge location is determined. The dynamic ballast device is activated to perform water injection or discharge operations, and the ship's center of gravity position is adjusted in real time. The process needs to be fast and accurate to respond to changes in waves. If it is decided to inject 50 liters of water at the rear of the ship, the dynamic ballast device will quickly complete this operation and update the ship's center of gravity position. Real-time data generated during the dynamic ballast adjustment process, including center of gravity position, roll angle, pitch angle, and water volume change, are collected and used to train the reinforcement learning model. The state parameters of the ship after each dynamic adjustment and the corresponding wave environment are recorded to build a training set. Suitable reinforcement learning algorithms, such as Q-learning or deep Q-network (DQN), are selected to train the model to learn the optimal center of gravity adjustment strategy. The model should be able to adaptively adjust the ship's center of gravity based on the current state and environmental changes. DQN is used to process the state space, including the current center of gravity position, roll and pitch angles, and wave state, so that the model can develop appropriate water volume adjustment strategies in different situations. The collected data is used to train the reinforcement learning model, and the decision-making strategy is continuously optimized through trial and error learning. A reward mechanism is set up to encourage the model to reduce center of gravity adjustments when stability is achieved. If the model's adjustment under the current state reduces the ship's roll angle, a positive reward is given; if it increases the tilt angle, a negative reward is given, prompting the model to learn a better adjustment strategy. The trained intelligent wave compensation engine is applied to the ship's real-time navigation monitoring system to respond to wave changes and adjust the center of gravity in real time. The system should be able to quickly respond under different wave conditions. If the wave height is found to suddenly rise, the system will automatically calculate the required water volume adjustment based on the current state and activate the dynamic ballast device for compensation. The performance of the intelligent wave compensation engine is evaluated based on actual navigation data, and the stability performance under different environmental conditions is checked. Based on the evaluation results, the model parameters are continuously optimized to improve the compensation effect.If the system successfully controls the roll angle within 3° in a certain voyage, it is considered to perform well; if the control fails, the reasons need to be analyzed and the model needs to be adjusted. According to the real-time feedback and voyage data, the reinforcement learning model is periodically iteratively optimized to improve the decision quality and compensation effect. Ensure that the system is always adapted to the changing marine environment. If the performance of the model under certain wave conditions is found to be poor, special retraining can be carried out for these conditions to improve the adaptability and stability of the system.

[0050] In this embodiment, referring to Figure 2 , the detailed implementation steps of step S1 include:

[0051] Based on the multi-sensor acquisition of the full-range marine wave monitoring parameters;

[0052] The raw noise of the full-range marine wave monitoring parameters is identified, and the marine raw noise points are marked;

[0053] The marine raw noise points are adaptively digitally filtered to obtain digital filter denoising monitoring parameters;

[0054] The data missing detection is performed on the digital filter denoising monitoring parameters, and the data missing position is extracted;

[0055] According to the data missing position, the mean filling optimization is performed, so as to optimize the marine wave monitoring parameters;

[0056] Based on the optimized marine wave monitoring parameters, the multi-time window period division processing and wave energy density quantization analysis are performed, and the wave energy density of each time window is generated.

[0057] In this embodiment, multiple types of sensors (such as accelerometers, pressure sensors, and sonar sensors) are deployed within the monitoring area to comprehensively capture the dynamic characteristics of ocean waves. These sensors should cover different water depths and locations to ensure data diversity and representativeness. Ten sensors are set up at different locations in the water area to record wave parameters such as wave height, wave frequency, wave speed, etc. The sampling frequency is set to 100 times per second to ensure the timeliness of the data. During the operation of the sensors, real-time data collection is carried out, and the data is stored in the central data management system. This process must ensure data integrity and accuracy to avoid false records caused by signal interference. The output signals of each sensor are transmitted to the data center in real time using a data logger, and the storage format is CSV or database for subsequent analysis. Signal processing techniques such as short-time Fourier transform and waveform analysis are used to analyze the collected wave monitoring data to identify original noise points. These noises may be caused by environmental interference (such as passing ships, weather changes, etc.). A threshold is set, and points with signal amplitude exceeding the threshold are marked as noise points. The sliding window method is used to analyze the energy distribution of the signal to ensure the accuracy of noise identification. The identified noise points are marked and recorded in the database for subsequent processing. These marks should include the timestamp and amplitude information of the noise points to facilitate tracing and analysis. If 10 noise points are found within a certain time period, the recording format is "timestamp, noise amplitude, noise type", which provides a basis for subsequent filtering processing. Based on the identified noise characteristics, adaptive digital filtering algorithms such as Kalman filtering and least mean square error filtering are selected for noise suppression processing. The design of the filter should consider the frequency spectrum characteristics of the noise to effectively remove interference signals. The state equation and observation equation of the Kalman filter are set to ensure that the filter can effectively estimate the true wave signal and reduce the impact of noise. The adaptive filtering algorithm is applied to the original wave monitoring data, and each data point is filtered. The processed data can accurately reflect the true characteristics of ocean waves. The identified noise points are interpolated to fill the noise affected area with surrounding valid data to generate smooth wave monitoring parameters. The filtered wave monitoring data is subjected to data integrity detection to identify data missing positions. Statistical methods such as Z-score detection and missing value analysis can be used to determine missing data points. The missing value determination criteria are set, and if the data is NaN for three consecutive time points, it is marked as missing data. The location of the identified missing data points is recorded in the database to ensure that the subsequent mean value filling optimization can accurately locate the missing values. The recording format should include "timestamp, missing type, missing position" to provide a basis for subsequent data filling. A mean value filling strategy is developed for the identified missing data positions. The surrounding valid data mean value can be used for filling to ensure that the filled data maintains a certain continuity and consistency.If there are 5 valid data points before and after the missing value, calculate the mean of these 10 points and fill in the missing position. Perform mean filling operation and verify the filled data to ensure that the filling effect meets the expected. Linear regression or other regression models can be used to verify the reasonableness of the filled data. Record the comparison of data before and after filling to ensure that the filled data can reflect the true wave characteristics and avoid deviation caused by filling. Divide the optimized wave monitoring data into multiple time windows to ensure that the calculation of energy density can cover the wave characteristics of different time periods. A fixed time window (such as every 10 minutes) can be set for division. Divide 1 hour of monitoring data into 6 10-minute time windows to ensure that the data in each window is complete. Quantitative analysis of wave energy density is performed on the wave data in each divided time window. The square average of wave height can be used to calculate the wave energy density of each window. The calculation formula is set as follows: where H(t) is the wave height data and T is the time window length. Record the wave energy density results of each time window in the database for subsequent analysis and visualization. Ensure that the energy density results of each window can be clearly identified.

[0058] In this embodiment, the specific steps of generating wave energy density of each time window based on the multi-time window period division processing and wave energy density quantitative analysis of the optimized ocean wave monitoring parameters are as follows:

[0059] Define the periodic observation time range;

[0060] According to the periodic observation time range, the optimized ocean wave monitoring parameters are divided into multiple time windows, and the ocean wave monitoring parameters of multiple time windows are obtained;

[0061] The wave height and wave speed of each time window are extracted by calculating the ocean wave monitoring parameters of multiple time windows one by one;

[0062] Calculate the adjacent wave peak time interval of the ocean wave monitoring parameters of the multiple time windows;

[0063] Based on the adjacent wave peak time interval, the average wave period is calculated to obtain the wave period of each time window;

[0064] The wave energy density of each time window is generated by performing wave energy density quantitative analysis on the wave period, wave height and wave speed.

[0065] In this embodiment, the time range for observation is defined according to the research purpose and monitoring needs, which should consider the changing period of wave characteristics, usually selecting a time period of 1 hour, 2 hours or longer to ensure that the typical characteristics of the wave can be captured. The observation time range is set to 2 hours to facilitate the observation of wave changes and trends during this period, ensuring that different wave events can be covered. Within the defined time range, the time points for data collection are reasonably selected. The sampling frequency should be high enough to capture the subtle changes of the wave, usually selecting 1 second or 5 seconds for each sampling. Within the 2-hour observation time, if sampling is performed at a frequency of 1 second, a total of 7200 data points need to be collected to ensure the continuity and integrity of the data. According to the defined periodic observation time range, the optimized marine wave monitoring parameters are processed by multi-time window division. The length of each time window should be reasonably set according to the wave characteristics and data density, usually selecting a window of 10 minutes, 15 minutes or 30 minutes. The 2-hour observation data is divided into 8 time windows of 15 minutes each to facilitate the analysis of wave characteristics in each time period. The data in each time window is sorted to ensure that relevant wave parameters (such as wave height, wave speed, etc.) can be extracted. In each time window, the integrity of the data should be ensured, and any missing or abnormal values should be removed. Each 15-minute window should contain 900 data points (if the sampling frequency is 1 second per second), providing sufficient sample data for subsequent calculations. In each time window, the maximum wave height (Hmax) and the average wave height (Havg) are extracted by analyzing the wave monitoring parameters. Wave height is usually defined as the vertical distance from the wave crest to the wave trough. Peak detection algorithms are used to identify the wave crest and wave trough in each time window, and the wave height is calculated. If the highest wave crest in a certain time window is 2 meters and the lowest wave trough is 0.5 meters, the wave height of that time window is 1.5 meters. According to the wave frequency and wave height, the wave speed (C) in each time window is calculated. Wave speed can be calculated by wave length (λ) and wave period (T), the formula is C = λ / T. If the wave length is calculated to be 30 meters and the wave period is 5 seconds in a certain time window, the wave speed of that window is 6 meters / second. In each time window, the wave crest detection is performed on the extracted wave data, and the time interval between adjacent wave crests is recorded. Threshold method or quadratic function fitting method can be used to identify the wave crest. If the wave crest times identified in a certain time window are 0 seconds and 5 seconds, the time interval between them is 5 seconds. The time intervals of all adjacent wave crests in each time window are counted, and the average value of the adjacent wave crest time interval of each window is calculated, which will be used for subsequent wave period calculation. If 3 adjacent wave crest time intervals of 5 seconds, 7 seconds and 4 seconds are recorded in a certain time window, the average wave crest time interval of that window is 5.33 seconds. The average wave period (T) is calculated according to the time interval of adjacent wave crests. Wave period refers to the time interval between two consecutive wave crests, usually represented by the average value.If the average adjacent peak time interval is calculated to be 5.33 seconds within a certain time window, the wave period of the window is 5.33 seconds. The wave period of each time window is recorded in the data table for subsequent analysis, which should include the time window identifier and the corresponding wave period value. The record format is "time window, wave period", ensuring the traceability and integrity of the data. Wave energy density (E) is usually quantified by wave height and wave period, and energy density can be calculated by the formula E = 1 / 2pgH. 2 where p is the density of water, g is the acceleration of gravity. If the wave height is 1.5 meters, the wave energy density of the window is calculated as E = 1 / 2 x 1000 x 9.81 x (1.5 2 ), resulting in an energy density value.

[0066] In this embodiment, referring to Figure 3 , the detailed implementation steps of step S2 include:

[0067] The wave energy density of each time window is analyzed for temporal variation, and the wave energy density variation characteristics in different windows are identified;

[0068] The transient wave frequency of the marine wave monitoring parameters of the plurality of time windows is calculated;

[0069] The frequency characteristics of the transient wave frequency are mined, thereby generating wave transient propagation frequency characteristics;

[0070] Based on the wave energy density variation characteristics and the wave transient propagation frequency characteristics in different windows, nonlinear dynamics behavior mining is performed to obtain wave nonlinear dynamics behavior rules;

[0071] According to the wave nonlinear dynamics behavior rules, dynamic sea wave digital perception modeling is performed to construct a sea wave field dynamics model.

[0072] In this embodiment, the wave energy density data within each time window is organized into time series data to ensure that the data reflects continuous temporal trends. This process involves arranging the wave energy density data in chronological order for subsequent analysis. If the time window is 15 minutes, the wave energy density records for each window are organized into a series of time series data to facilitate subsequent time series analysis. Statistical analysis methods such as moving average and standard deviation analysis are used to analyze the time series changes in wave energy density and identify the characteristics of wave energy density changes within different windows. Moving average can smooth the data and help identify long-term trends. A 5-minute moving window is set to calculate the average wave energy density, and the changing trend of wave energy density in different time periods is observed to identify the peak and valley values of wave intensity. The identified wave energy density change characteristics, including peak, valley, and change rate, are recorded in the database. Through visualization means such as line charts, the changes of wave energy density in each time window are displayed. If the peak value of wave energy density in a certain time period is 3.5 kJ / m 2 , and the valley value is 1.0 kJ / m 2, record these features, and calculate the rate of change for subsequent analysis. The transient wave frequency refers to the frequency change of the wave within each time window, usually calculated by the time interval between the wave crest and trough. This can be calculated using the extracted wave period data. If the wave period is calculated to be 5.33 seconds within a certain time window, the transient wave frequency can be calculated by the formula f = 1 / T, resulting in a frequency of 0.187 Hz. Record the transient wave frequency within each time window to form a time series data of frequency, ensuring the integrity of the data and avoiding errors in frequency calculation due to data loss. The record format should include "time window, transient wave frequency" to ensure the completeness and traceability of the frequency information of each window. Use statistical methods (such as spectral analysis, Fourier transform) to analyze the transient wave frequency to identify the characteristics and trends of frequency change, which can help understand the dynamic behavior of ocean waves under different conditions. Use fast Fourier transform (FFT) to analyze the transient wave frequency data, extract the principal components and spectral characteristics of the frequency. Use feature extraction techniques (such as principal component analysis, feature selection algorithms) to deeply mine the transient wave frequency data, extract key frequency features, which will be used for subsequent analysis of wave dynamic behavior. Use principal component analysis (PCA) to reduce the dimensionality of the data and extract the main frequency components to more clearly identify the propagation characteristics of the wave. Record the extracted wave transient propagation frequency characteristics, including the main frequency components and their corresponding energy density. Through these characteristics, we can better understand the propagation behavior and influencing factors of the wave. The record format should include "time window, frequency component, related energy density" to ensure the integrity and traceability of the data. Use nonlinear dynamics theory to analyze the dynamic behavior of the wave and identify the nonlinear characteristics of the wave under different conditions. Common methods include phase space reconstruction, Lyapunov exponent calculation, etc. Use the phase space reconstruction method to construct the phase space graph of the wave monitoring parameters and analyze the nonlinear characteristics of the wave dynamic behavior. Evaluate the analysis results and identify the nonlinear dynamic behavior of the wave, which may include the chaotic characteristics of the wave, bifurcation phenomenon, etc., to help understand the complex behavior of ocean waves. If the wave shows chaotic behavior in a certain time period, record these rules and conduct further analysis. According to the extracted nonlinear dynamic behavior of the wave, select appropriate modeling methods (such as neural networks, system dynamics models, etc.) to build a dynamic sea wave model, which should be able to reflect the dynamic change characteristics of the wave. Choose long short-term memory network (LSTM) for modeling, as it performs well in time series prediction and is suitable for handling the time series characteristics of wave data. Use historical wave monitoring data to train the dynamic sea wave model and adjust the model parameters to optimize the prediction effect. Ensure that the model can accurately reflect the dynamic behavior of the wave and perform cross-validation to evaluate the performance of the model.The model's root mean square error (RMSE) is calculated using 80% of the data for training and 20% for validation to assess the model's predictive ability. The constructed dynamic sea wave model is applied to actual wave monitoring, predicting wave behavior in real-time and making dynamic adjustments to optimize the stability of the ship. Through a feedback mechanism, the model is continuously optimized to improve its prediction accuracy. If there is a deviation between the model's predicted wave energy density and the actual monitoring data, the model parameters are adjusted to improve the accuracy of the prediction.

[0073] In this embodiment, referring to Figure 4 For the detailed implementation step flowchart of step S3, in this embodiment, the detailed implementation steps of step S3 include:

[0074] Based on the sea wave field dynamics model, multi-scale wave feature analysis is performed to obtain multi-scale wave feature data;

[0075] The multi-scale wave feature data is subjected to time-frequency decomposition to obtain wave frequency domains of multiple frequency components;

[0076] The wave frequency domains are subjected to dynamic time series change analysis to obtain wave signal dynamic time series change features;

[0077] The time-frequency difference value of the wave signal dynamic time series change features is identified;

[0078] Wave trend mining is performed according to the time-frequency difference value to generate wave trend features at different time points;

[0079] Wave trend evolution prediction is performed according to the wave trend features at different time points to construct a wave trend prediction map.

[0080] In this example, a dynamic model of the sea wave field is established based on previous analysis results. The model should consider multiple influencing factors of waves, including wind speed, tides, topography, etc., to ensure the accuracy of the simulation. The input parameters of the model are set as wind speed (10 m / s), water depth (20 m), and wave frequency range (0.05-0.5 Hz) to capture wave characteristics of different scales. After running the model, multi-scale analysis is performed on the sea wave field data to extract wave characteristics at different wavelengths and frequencies. Methods such as wavelet transform can be used for multi-scale decomposition of the data. Through wavelet transform, the wave signal is decomposed into different scales, and characteristic data such as short waves, high-frequency waves, and long waves are extracted for subsequent analysis. Select appropriate time-frequency decomposition methods such as short-time Fourier transform (STFT) or wavelet transform to perform time-frequency analysis on multi-scale wave characteristics data. These methods can provide both time and frequency information, helping to understand the changes in wave signals. Use wavelet transform to decompose wave data to extract time-varying characteristics of different frequency components. During time-frequency decomposition, extract each frequency component and its corresponding time information. Ensure that the extracted data can reflect the dynamic changes of the wave signal, especially under the influence of wind waves, tidal waves, and other factors. If the extracted frequency components include 0.1 Hz, 0.3 Hz, and 0.5 Hz, record the changes of these components in the time series for subsequent analysis. Organize the extracted frequency components into a time-frequency matrix and display the characteristic changes of the wave signal at different times and frequencies through visualization methods such as time-frequency graphs, which will help analyze the dynamic characteristics of the wave. Through the time-frequency graph, the energy distribution of different frequency components is displayed, and the frequency changes in a certain time period are identified. Perform dynamic time series analysis on the extracted wave frequency domain data to identify the change characteristics of frequency components at different time points. Statistical analysis methods such as analysis of variance can be used to evaluate the dynamic changes of wave frequency. Set the analysis window to 5 minutes and calculate the standard deviation of frequency components in each window to identify the volatility and dynamic characteristics of frequency. Record the identified dynamic characteristics in the database, including frequency change rate, frequency fluctuation range, etc., for subsequent trend mining and prediction analysis. The record format should include "time window, frequency change rate, fluctuation range" to ensure the completeness and traceability of the results. Based on the dynamic time series change characteristics of the wave signal, calculate the time-frequency difference between adjacent time points. The change trend of the wave signal can be identified by calculating the absolute difference or relative difference of the frequency change. If the frequency at a certain time point is 0.1 Hz and the next time point is 0.12 Hz, the difference is calculated as 0.02 Hz. Record the calculated time-frequency difference in the database for subsequent wave trend mining. The record should include the time point, frequency difference, and change trend.Based on the identified time-frequency difference values, time series analysis methods such as moving average, exponential smoothing, etc. are used to mine wave trends. These methods can help identify long-term trends and potential patterns in wave changes. Moving average method is used to smooth the time-frequency difference values to extract the main direction of wave trend. Based on the mined wave trend characteristics, suitable prediction models such as ARIMA model, LSTM model, etc. are selected for wave trend evolution prediction. These models should be able to handle time series data and provide future trends of wave trends. LSTM model is selected for training due to its superior performance in capturing long-term dependencies in time series. Historical wave data is used for model training, and model parameters are adjusted to optimize prediction results. Ensure that the model can accurately reflect the wave trend, and perform cross-validation to evaluate the performance of the model. Use 80% of the data for training and 20% of the data for validation, calculate the root mean square error (RMSE) of the model to evaluate the accuracy of the prediction. Visualize the prediction results and construct a wave trend prediction chart to show the wave trend characteristics at future time points. Through the chart, the changing trend of the wave can be analyzed intuitively to assist the ship stability design.

[0081] In this embodiment, step S4 includes the following steps:

[0082] Identify the current ship state parameters; calculate the ship speed and acceleration according to the current ship state parameters;

[0083] Calculate the relative speed between the ship and the wave according to the ship speed and acceleration, and obtain the relative speed;

[0084] Calculate the real-time roll and pitch angles of the ship based on the current ship state parameters, and extract the dynamic ship attitude parameters;

[0085] Time-synchronize the dynamic ship attitude parameters according to the wave energy density of each time window, and evaluate the ship interaction stability based on the relative speed to obtain the ship dynamics stability evaluation value;

[0086] Model the wave action motion characteristics according to the ship dynamics stability evaluation value, and construct the ship dynamics stability model.

[0087] In this embodiment, multiple sensors such as GPS, accelerometer, gyroscope, etc. are used to monitor the state parameters of the ship in real time. The state parameters include the speed, acceleration, heading, roll and pitch angles of the ship, which provide basic data support for subsequent analysis. The position information of the ship is obtained through GPS, and combined with the accelerometer data, the current speed and acceleration of the ship are calculated in real time. The collected ship state parameters are arranged in a structured format to ensure parameter integrity and traceability. The record format should include timestamp, speed, acceleration, heading, roll and pitch angles, etc. The record format is "timestamp, speed (m / s), acceleration (m / s 2 ), heading (°), roll angle (°), pitch angle (°)", ensuring that each data point has a clear identification. The speed of the ship is calculated by the change of position and time interval. The speed can be calculated by a simple difference formula, V = ΔD / ΔT, where ΔD is the displacement of the ship in time ΔT. If the ship moves 10 meters in 1 second, the calculated speed is 10 m / s. The acceleration of the ship is calculated according to the rate of change of speed. The acceleration can also be calculated by the difference formula, A = ΔV / ΔT, where ΔV is the change of speed in time ΔT. If the speed of the ship increases from 10 m / s to 12 m / s in 1 second, the acceleration is 2 m / s. Through the previous wave monitoring analysis, the speed of the current wave is obtained. The wave speed is usually determined by the wavelength and period of the wave, and the calculation formula is C = λ / T. The relative speed is calculated according to the speed of the ship and the speed of the wave. The relative speed can be calculated by the formula V rel = V ship -V wave , where V ship is the speed of the ship, V waveFor wave velocity, if the ship speed is 10 m / s and the wave velocity is 6 m / s, the relative velocity is 10-6 = 4 m / s. Based on the acceleration and angular velocity data of the ship, the real-time roll angle and pitch angle of the ship are calculated. Roll and pitch angles are usually obtained from gyro or IMU (Inertial Measurement Unit) data. If the change of roll angle is 0.5° / s and the change of pitch angle is 0.2° / s, then in 1 second, the roll and pitch angles are 0.5° and 0.2° respectively. Based on the wave energy density data of each time window, the dynamic ship attitude parameters are time-synchronized and matched. Ensure that the wave monitoring data and ship attitude data are aligned in time for analysis. If the time interval of wave energy density data is 10 seconds, then the ship attitude parameters are also sampled at 10 second intervals to ensure the time consistency of the data. The dynamic model is used to analyze the stability of the ship interaction. The model should consider the dynamic behavior of the ship under the action of waves, and evaluate it by calculating dynamic stability indicators (such as GM value, transient stability, etc.). By calculating the height of the center of gravity and the position of the floating center of the ship, the stability of the ship under the action of waves is evaluated. The calculated ship dynamics stability evaluation value is recorded in the database, including relative velocity, stability indicators, etc. for subsequent analysis and model construction. According to the ship dynamics stability evaluation value, select the appropriate modeling method (such as finite element method, fluid dynamics model, etc.) to construct the ship dynamics stability model, which should be able to reflect the influence of waves on ship motion. Use the finite element method to model the ship structure, considering the dynamic response under the action of waves. Use historical data to verify the constructed dynamics model to ensure that the model can accurately reflect the stability of the ship under the action of waves. Adjust the model parameters to optimize the prediction effect. By comparing with the actual monitoring data, calculate the prediction error of the model, adjust the model parameters to improve the accuracy of stability evaluation. Apply the constructed ship dynamics stability model to the real-time wave monitoring system to evaluate the stability of the ship in real time and provide feedback. By dynamically adjusting the attitude of the ship, optimize the performance of the ship in waves. If the model predicts that the stability of the ship under certain wave conditions decreases, the system can issue an alarm and suggest adjusting the heading or speed.

[0088] In this embodiment, the specific steps of step S5 are:

[0089] Based on the wave trend prediction map, dynamic navigation simulation is performed on the ship dynamics stability model to obtain dynamic ship simulation data;

[0090] Calculate the ship oscillation frequency and ship swing angle of the dynamic ship simulation data;

[0091] Based on the ship oscillation frequency and ship swing angle, the tilt amplitude is analyzed, and the ship tilt amplitude value is obtained;

[0092] The current ship center of gravity position is calculated based on the ship inclination amplitude value.

[0093] In this embodiment, the wave trend prediction chart obtained through preliminary analysis is used to set the simulation conditions, which include the amplitude, period, direction, and wave speed of the waves, to ensure the authenticity and effectiveness of the simulation. If the prediction chart shows that the wave height is 1.5 meters and the wave period is 6 seconds within a certain time period, these parameters will be used as input conditions for dynamic simulation. In the dynamic navigation simulation, a ship dynamics stability model is used for motion simulation. This model should consider factors such as the ship's geometry, mass distribution, buoyancy, and resistance to ensure that it can accurately reflect the dynamic behavior of the ship under the action of waves. A finite element analysis (FEA) software is used to construct the ship model, input the detailed parameters of the ship (such as length, width, and center of gravity position), and set the wave conditions for dynamic simulation. The simulation program is run, and dynamic navigation simulation is performed according to the set wave trend prediction chart. The motion state of the ship under different wave conditions is recorded, including speed, acceleration, roll angle, and oscillation frequency. During the simulation process, the ship's motion parameters are recorded every 0.1 seconds to ensure the continuity and completeness of the data, which facilitates subsequent analysis. The displacement data of the ship body are extracted from the dynamic simulation data, and the FFT (Fast Fourier Transform) method is used to calculate the oscillation frequency of the ship body. The oscillation frequency refers to the periodic motion frequency of the ship under the action of waves, reflecting the dynamic response characteristics of the ship. If the recorded displacement data shows periodic changes within a certain time period, the main oscillation frequency is 0.25 Hz through FFT analysis. Through analysis of the dynamic simulation data, the roll angle of the ship is calculated. The roll angle is usually obtained from the acceleration and angular velocity data of the ship, reflecting the inclination state of the ship in waves. If the maximum inclination angle of the ship within a certain wave period during the simulation process is 5°, the roll angle is recorded as the basis data for subsequent analysis. According to the calculated roll angle, the inclination amplitude analysis is performed. The inclination amplitude usually refers to the maximum inclination degree of the ship under the action of waves, affecting the stability and safety of the ship. If the maximum roll angle is 5° during the simulation process, the inclination amplitude can be directly recorded as the dynamic response characteristics of the ship. The calculated inclination amplitude is recorded in the database to ensure that the results of each time window are saved. The recording format should include "time stamp, inclination amplitude (°)". If the inclination amplitude is recorded as 5° at a certain time point, the format is "time stamp, inclination amplitude" to ensure the integrity and traceability of the data. Based on the inclination amplitude and design parameters of the ship body, the current center of gravity position of the ship body is calculated. The center of gravity position is usually closely related to the stability of the ship and affects its performance in waves. The formula CG = h / cos(θ) is used, where h is the design waterline height of the center of gravity and θ is the inclination angle, to calculate the new center of gravity position of the ship body under a certain inclination amplitude. The calculated center of gravity position of the ship body is recorded in the database to ensure that the center of gravity position of each time window is saved. The recording format should include "time stamp, center of gravity position (m)".

[0094] In this embodiment, the specific steps of step S6 are:

[0095] According to the preset standard center of gravity position, the center of gravity deviation of the current ship body center of gravity position is calculated, so as to obtain the ship body center of gravity deviation value;

[0096] Based on the center of gravity adjustable dynamic ballast device, the intelligent center of gravity deviation compensation calculation is performed on the ship body center of gravity deviation value, so as to obtain the center of gravity deviation compensation value;

[0097] According to the center of gravity deviation compensation value, the self-adaptive ship body center of gravity distribution adjustment is performed on the ship by the center of gravity adjustable dynamic ballast device, so as to obtain the center of gravity distribution adjustment parameter;

[0098] The ship body posture parameter after the center of gravity adjustment is monitored;

[0099] The ship body stability quantification evaluation is performed on the ship body posture parameter, so as to obtain the center of gravity compensation effect evaluation value;

[0100] Based on the center of gravity compensation effect evaluation value, the stability index judgment is performed, when the stability index judgment is unqualified, the iterative compensation calculation is performed on the center of gravity distribution adjustment parameter, so as to obtain the iterative compensation optimization parameter;

[0101] According to the iterative compensation optimization parameter, the reinforcement learning is performed on the center of gravity adjustable dynamic ballast device, so as to construct the intelligent wave compensation engine.

[0102] In this embodiment, the standard center of gravity position is preset according to the ship design parameters and operating conditions, which is usually determined during the design phase as a reference value for the ship's normal operation. The standard center of gravity position is set to 1.5 meters, indicating that the center of gravity of the ship should be located 1.5 meters below the waterline. The current center of gravity position is monitored in real time using sensors such as accelerometers and gyroscopes. The current center of gravity position may change due to the cargo state, fuel consumption, and wave effects. The current center of gravity position is monitored to be 1.3 meters, and this data is recorded for subsequent analysis. By comparing the current center of gravity position with the standard center of gravity position, the center of gravity deviation value is calculated. If the standard center of gravity position is 1.5 meters and the current center of gravity position is 1.3 meters, the center of gravity deviation value is 1.5-1.3=0.2 meters, indicating that the center of gravity is low. Based on the center of gravity deviation value, intelligent center of gravity deviation compensation calculation is performed using the center of gravity adjustable dynamic ballast device. This device adjusts the position and amount of ballast water to dynamically adjust the center of gravity. The maximum adjustment capacity of the dynamic ballast device is set to 5000 liters of water to quickly adjust the center of gravity position when needed. According to the center of gravity deviation value, the required compensation water volume is calculated. The compensation value can be calculated by the formula V(comp)=k x ΔCG, where k is the adjustment coefficient, reflecting the sensitivity of the ballast device to the center of gravity adjustment. If k=1000 liters / meter, the compensation water volume is =1000 x 0.2=200 liters, indicating that 200 liters of water need to be added to adjust the center of gravity. According to the water volume calculated by compensation, adaptive center of gravity distribution adjustment is performed through the dynamic ballast device. The adjustment parameters should consider the water distribution position to achieve the best center of gravity adjustment effect. If 200 liters of water need to be added, the supplement can be selected in the front or rear of the ship, depending on the current wave and ship motion state. Start the center of gravity adjustable dynamic ballast device and inject or discharge water according to the calculated center of gravity distribution adjustment parameters. Ensure the real-time and accuracy of the adjustment to quickly respond to wave changes. If 200 liters of water is selected to be injected in the rear, the dynamic ballast device will start and complete the water injection within a few seconds. After the center of gravity adjustment, the ship's attitude parameters are monitored in real time, including roll angle, pitch angle, and heading, etc. These data are continuously recorded using sensors for subsequent evaluation of the ship's stability. The roll angle is monitored by the gyroscope to be 3° and the pitch angle to be 2° after adjustment, and these attitude data are recorded. Based on the ship attitude parameters, the stability of the ship is quantitatively evaluated. The stability evaluation indicators usually include GM value (initial stability), dynamic stability, and inclination recovery force. The standard for stability evaluation is set, and if the GM value is above 0.5 meters, the ship's stability is good. Calculate the stability evaluation value according to the monitored attitude parameters. If the ship's GM value is calculated to be 0.6 meters after adjustment, record this value as the center of gravity compensation effect evaluation value. The record format should be "timestamp, stability evaluation value" to ensure the integrity and traceability of the data.According to the stability index obtained by evaluation, if the stability index is unqualified (such as the GM value is less than 0.5 meters), iteration compensation calculation is needed. If the GM value is 0.4 meters, it is judged as unqualified, and the center of gravity needs to be further adjusted. According to the center of gravity deviation compensation value and the current stability evaluation value, iteration compensation calculation is carried out. Control algorithm (such as PID control) can be used to optimize the center of gravity adjustment parameters. If further adjustment of water quantity is needed, a new compensation water quantity of 300 liters can be set to recalculate and implement. According to the iteration compensation optimization parameters, they are applied to the reinforcement learning model to realize the adaptive wave compensation mechanism. The model should be able to automatically adjust the center of gravity distribution according to real-time data. Q-learning or deep Q network (DQN) is used for model training to optimize the center of gravity adjustment under different wave conditions. Historical data and simulation data are used to train the reinforcement learning model to evaluate the stability and response ability of the model. Ensure that the model can effectively adjust the center of gravity of the ship under various wave conditions. Through multiple simulation training, the model parameters are optimized so that the stability index reaches the expected standard under wave disturbance. The built intelligent wave compensation engine is applied to the real-time monitoring system to respond to wave changes and adjust the center of gravity of the ship in real time. Ensure that the stability of the ship under the action of waves is maximized. When the wave height is monitored to exceed the preset value, the center of gravity adjustment program is automatically started to ensure that the ship remains in a stable state.

[0103] In this embodiment, a marine wave compensation system for ship stability is provided for performing the marine wave compensation method for ship stability as described above, comprising:

[0104] A data processing module is used to collect all-around marine wave monitoring parameters, perform multi-time window period division processing and wave energy density quantization analysis, and generate wave energy density of each time window.

[0105] A nonlinear dynamics analysis module is used to perform nonlinear dynamics behavior mining and dynamic sea wave digital perception modeling based on the wave energy density of each time window, and construct a sea wave field dynamics model.

[0106] A wave trend prediction module is used to perform multi-scale wave feature analysis based on the sea wave field dynamics model, and perform wave trend evolution prediction, and construct a wave trend prediction map.

[0107] A ship attitude module is used to identify current ship state parameters; calculate real-time roll and pitch angles of the ship based on the current ship state parameters, and perform wave action motion characteristic modeling, and construct a ship dynamics stability model.

[0108] A dynamic navigation simulation module is used to perform dynamic navigation simulation on the ship dynamics stability model based on the wave trend prediction map, and perform inclination amplitude analysis, and calculate the current ship center of gravity position.

[0109] A ship center of gravity adjustment module is used to adjust the current ship center of gravity position according to the center of gravity adjustable dynamic ballast device, and then perform reinforcement learning to construct an intelligent wave compensation engine.

[0110] The application ensures that comprehensive and accurate wave information is collected by the data processing module through comprehensive collection of ocean wave parameters such as wave height, wave period, wave speed, and wave direction, providing sufficient input data for subsequent analysis. By using multiple sensors (such as buoys, radars, sonars, etc.), real-time monitoring of changes in the ocean waves around the ship can be achieved, enhancing the reliability of the data. The data is divided into multiple time windows to allow for more detailed period analysis. Analysis of different time windows can help capture the instantaneous changes in the sea waves, reflect the wave behavior at different time scales, and improve the accuracy and real-time nature of the analysis. Through comprehensive analysis of parameters such as wave height, wave period, and wave speed, the wave energy density in each time window is quantified, providing a reliable wave energy model for subsequent wave trend prediction and dynamic stability analysis, allowing the impact of ocean waves to be clearly quantified and providing basic data support for ship stability optimization. Waves have complex nonlinear characteristics, such as resonance, wave interaction, and breaking. Through the nonlinear dynamics analysis module, the complex behavior of waves can be explored to provide more accurate dynamic characteristics for ship stability evaluation. This deep exploration can reveal wave characteristics that traditional linear models cannot capture, providing a new perspective for wave compensation. The nonlinear dynamics analysis module helps establish a multi-dimensional sea wave field dynamics model to simulate wave behavior in different sea wave environments. This model can accurately predict the evolution of sea waves and provide scientific basis for ship stability prediction and compensation schemes. By analyzing the multi-scale characteristics of sea waves (such as wave crest, wave trough, period, amplitude, etc.), the module can extract key features of waves from multiple dimensions. This multi-scale analysis can capture the changing trends of waves in the short term (such as a few hours) and the long term (such as a few days), helping to better understand wave dynamics at different time scales. Based on the sea wave field dynamics model, the evolution of future wave trends is predicted. This module can predict wave changes (such as wave intensity, direction, period, etc.) in the future for a certain period of time, providing information support for ships to take stability measures in advance. By generating wave trend prediction charts, ship operators can visually see the future wave trends, including the direction, intensity, and period of the waves. This visual prediction chart helps crew members make more intelligent decisions in complex sea conditions, improving navigation safety. The ship attitude module obtains real-time ship motion state parameters (such as ship speed, acceleration, ship body angle, etc.), accurately describing the ship's state under the action of waves. Through these parameters, the module can monitor the ship's stability in real time and provide feedback for dynamic compensation. The module can accurately calculate the roll angle and pitch angle of the ship under different wave conditions, which are important parameters for analyzing ship stability and helping crew members judge the stability changes of the ship and take timely measures. By modeling the ship's motion characteristics under the action of waves, the module can simulate the ship's response under different wave conditions, providing a scientific basis for subsequent stability optimization and dynamic compensation strategies.Based on the wave trend prediction chart, the dynamic navigation simulation module can simulate the actual navigation of the ship under different wave conditions. The simulation results can help the crew to predict the stability problems that may be encountered during navigation and provide support for taking appropriate compensation measures. By accurately calculating the real-time center of gravity position of the ship, the module can provide stability data of the ship to help evaluate whether the center of gravity needs to be adjusted and provide data support for subsequent compensation strategies. The ship center of gravity adjustment module adjusts the center of gravity of the ship through dynamic ballast devices. According to the real-time center of gravity position, the system adjusts the liquid ballast distribution of the ship to achieve the optimal distribution of the ship's center of gravity, thereby improving the stability. Through the reinforcement learning algorithm, the module can continuously optimize the compensation strategy of the ship's stability. Through the accumulation of experience in actual navigation, the system can continuously learn and adjust the compensation algorithm, so that it can always maintain the best state under different wave conditions. The system gradually optimizes the wave compensation strategy through reinforcement learning to adapt to different wave conditions in real time. Finally, an intelligent wave compensation engine is formed, which can self-learn and self-optimize, effectively improve the dynamic stability of the ship, reduce manual intervention, and improve the safety and efficiency of navigation.

[0111] Therefore, embodiments should be considered in all respects as illustrative and not restrictive, the scope of the application being defined by the appended claims rather than the description preceding them, and all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

[0112] The foregoing merely illustrates the principles of the application and application of its principles. Various modifications can be made by those skilled in the art utilizing the conception of the present application as defined by the scope of the claims appended hereto, without departing from the spirit and scope of the application. Accordingly, the application is not to be limited by the above description, but is to be given full scope in the appended claims.

Claims

1. A method of marine wave compensation for ship stabilization, characterized in that, The ship is internally provided with a gravity-adjustable dynamic ballast device, including the following steps: Step S1: Collecting all-directional ocean wave monitoring parameters, and performing multi-time window period division processing and wave energy density quantification analysis to generate wave energy density of each time window; Step S2: According to the wave energy density of each time window, nonlinear dynamic behavior mining and dynamic sea wave digital perception modeling are performed to construct a sea wave field dynamics model; Step S3: Based on the sea wave field dynamics model, multi-scale wave feature analysis is performed, and wave trend evolution prediction is performed to construct a wave trend prediction map, specifically including: based on the sea wave field dynamics model, multi-scale wave feature analysis is performed to obtain multi-scale wave feature data; the multi-scale wave feature data is subjected to time-frequency decomposition to obtain wave frequency domain of multiple frequency components; the wave frequency domain is subjected to dynamic time sequence change analysis to obtain wave signal dynamic time sequence change feature; the time-frequency difference value of the wave signal dynamic time sequence change feature is identified; according to the time-frequency difference value, wave trend mining is performed to generate wave trend features at different time points; according to the wave trend features at different time points, wave trend evolution prediction is performed to construct a wave trend prediction map; Step S4: Identifying the current ship state parameters; calculating the real-time roll and pitch angles of the ship according to the current ship state parameters, and performing wave action motion characteristic modeling to construct a ship dynamics stability model; Step S5: Based on the wave trend prediction map, the ship dynamics stability model is subjected to dynamic navigation simulation, and the tilt amplitude is analyzed to calculate the current ship gravity center position; Step S6: According to the gravity-adjustable dynamic ballast device, the current ship gravity center position is subjected to adaptive ship gravity center distribution adjustment, and then reinforcement learning is performed to construct an intelligent wave compensation engine.

2. Marine wave-compensation method for ship stabilization according to claim 1, characterized in that, The specific steps of step S1 are: Collecting all-directional ocean wave monitoring parameters based on multiple sensors; Identifying original noise of the all-directional ocean wave monitoring parameters, and marking ocean original noise points; Performing adaptive digital filtering processing on the ocean original noise points to obtain digital filtering and noise reduction monitoring parameters; Performing data missing detection on the digital filtering and noise reduction monitoring parameters to extract data missing positions; According to the data missing positions, mean filling optimization is performed to optimize the ocean wave monitoring parameters; Based on the optimized ocean wave monitoring parameters, multi-time window period division processing and wave energy density quantification analysis are performed to generate wave energy density of each time window.

3. Marine wave-compensation method for ship stabilization according to claim 2, characterized in that, The specific steps of the step of generating wave energy density of each time window based on the optimized ocean wave monitoring parameters are: Defining a period observation time range; According to the period observation time range, the optimized ocean wave monitoring parameters are subjected to multi-time window period division processing to obtain ocean wave monitoring parameters of multiple time windows; The ocean wave monitoring parameters of multiple time windows are calculated one by one to extract wave height and wave speed of each time window; The adjacent wave peak time intervals of the ocean wave monitoring parameters of the multiple time windows are calculated; Based on the adjacent wave peak time interval, the average wave period is calculated, and the wave period of each time window is obtained. The wave energy density of each time window is calculated based on the wave period, wave height and wave speed.

4. Marine wave-compensation method for ship stabilization according to claim 3, characterized in that, The specific steps of step S2 are: The time sequence change of the wave energy density of each time window is analyzed, and the wave energy density change characteristics in different windows are identified. The transient wave frequency of the marine wave monitoring parameters of the plurality of time windows is calculated. The frequency characteristics of the transient wave frequency are mined, and the wave transient propagation frequency characteristics are generated. Based on the wave energy density change characteristics in different windows and the wave transient propagation frequency characteristics, the nonlinear dynamics behavior is mined, and the wave nonlinear dynamics behavior law is obtained. According to the wave nonlinear dynamics behavior law, the dynamic sea wave digital perception modeling is carried out, and the sea wave field dynamics model is constructed.

5. Marine wave-compensation method for ship stabilization according to claim 3, characterized in that, The specific steps of step S4 are: The current ship state parameters are identified, and the ship speed and acceleration are calculated according to the current ship state parameters. The relative speed between the ship and the wave is calculated based on the ship speed and acceleration, and the relative speed is obtained. The real-time roll and pitch angles of the ship are calculated based on the current ship state parameters, and the dynamic ship attitude parameters are extracted. The dynamic ship attitude parameters are time-synchronized matched according to the wave energy density of each time window, and the ship interaction stability is evaluated based on the relative speed, so as to obtain the ship dynamics stability evaluation value. According to the ship dynamics stability evaluation value, the wave action motion characteristic modeling is carried out, and the ship dynamics stability model is constructed.

6. Marine wave-compensation method for ship stabilization according to claim 1, characterized in that, The specific steps of step S5 are: Based on the wave trend prediction map, the dynamic navigation simulation of the ship dynamics stability model is carried out, and the dynamic ship simulation data is obtained. The ship oscillation frequency and ship rolling angle of the dynamic ship simulation data are calculated. Based on the ship oscillation frequency and ship rolling angle, the inclination amplitude analysis is carried out, and the ship inclination amplitude value is obtained. The current ship gravity center position is calculated based on the ship inclination amplitude value.

7. Marine wave-compensation method for ship stabilization according to claim 1, characterized in that, The specific steps of step S6 are: According to the preset standard gravity center position, the gravity center deviation of the current ship gravity center position is calculated, and the ship gravity center deviation value is obtained. Based on the gravity adjustable dynamic ballast device, the intelligent gravity center deviation compensation calculation of the ship gravity center deviation value is carried out, and the gravity center deviation compensation value is obtained. According to the gravity center deviation compensation value, the adaptive ship gravity center distribution adjustment of the ship is carried out through the gravity adjustable dynamic ballast device, and the gravity center distribution adjustment parameter is obtained. The ship attitude parameters after gravity adjustment are monitored. The ship stability quantitative evaluation of the ship attitude parameters is carried out, and the gravity compensation effect evaluation value is obtained. Based on the gravity compensation effect evaluation value, the stability index judgment is carried out, and when the stability index judgment is unqualified, the iteration compensation calculation of the gravity center distribution adjustment parameter is carried out, and the iteration compensation optimization parameter is obtained. According to the iteration compensation optimization parameter, the gravity adjustable dynamic ballast device is strengthened, and the intelligent wave compensation engine is constructed.

8. A marine wave compensating system for vessel stabilization, characterized in that, The method for ship stability of the marine wave compensation method for ship stability according to claim 1 is used to execute, comprising: A data processing module is configured to collect omni-directional marine wave monitoring parameters, perform multi-time window period division processing and wave energy density quantification analysis, and generate wave energy density of each time window; A nonlinear dynamics analysis module is configured to perform nonlinear dynamics behavior mining and dynamic sea wave digital perception modeling according to the wave energy density of each time window, and construct a sea wave field dynamics model; A wave trend prediction module is configured to perform multi-scale wave feature analysis based on the sea wave field dynamics model, perform wave trend evolution prediction, and construct a wave trend prediction map; A ship attitude module is configured to identify current ship state parameters, calculate real-time roll and pitch angles of the ship according to the current ship state parameters, perform wave action motion characteristic modeling, and construct a ship dynamics stability model; A dynamic navigation simulation module is configured to perform dynamic navigation simulation on the ship dynamics stability model based on the wave trend prediction map, perform inclination amplitude analysis, and calculate a current ship center of gravity position; A ship center of gravity adjustment module is configured to perform adaptive ship center of gravity distribution adjustment on the current ship center of gravity position according to the center of gravity adjustable dynamic ballast device, and perform reinforcement learning, thereby constructing an intelligent wave compensation engine.

Images