Wind power operation and maintenance ship boarding and berthing system compensation control method based on active disturbance rejection control and related equipment

Abstract

The invention discloses a wind power operation and maintenance ship embarkation system compensation control method based on active disturbance rejection control and related equipment. The method comprises the following steps: predicting a system external wave disturbance variable of a six-degree-of-freedom embarkation compensation platform according to environmental parameters through a wave disturbance prediction model; the total disturbance quantity in the system is predicted through the extended state observer according to the real-time attitude information and the electric cylinder control signal, and then the total disturbance of the system is obtained; a nonlinear control quantity is calculated through an active disturbance rejection controller according to real-time attitude information, expected attitude information and a preset decoupling matrix, a feed-forward compensation quantity is calculated according to total disturbance of a system, then an output instruction of the controller is calculated, and compensation control is achieved. According to the embodiment of the invention, compensation control can be realized through the wave interference prediction model, the state expansion observer and the active disturbance rejection controller, and high precision and response speed are achieved. The method can be widely applied to the technical field of automation control.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automation control, and in particular to a wind power operation and maintenance ship berthing system compensation control method based on active disturbance rejection control and related equipment. BACKGROUND

[0002] With the rapid development of offshore wind power industry towards deep sea, the operation and maintenance ship of wind power is the key equipment for the operation and maintenance of offshore wind farm, and its operation safety and efficiency directly affect the power generation benefit of the wind farm. In the complex and changeable marine environment, the wind power operation and maintenance ship faces severe challenges when performing berthing operation. Influenced by wind, wave, swell, tidal current and other environmental factors, the ship will produce six-degree-of-freedom coupled motion (including three translational degrees of freedom of surge, sway and heave, and three rotational degrees of freedom of roll, pitch and yaw), which aggravates the relative motion between the ship body and the wind turbine foundation, and easily causes collision risk. Especially in severe sea conditions, the existing berthing compensation system is mostly idealized, relying on the accurate model under idealized conditions, and often shows problems such as response delay and insufficient compensation accuracy, which makes it difficult to realize safe and reliable berthing operation, increases the risk coefficient of operation and maintenance operation, and seriously restricts the accessibility and operation and maintenance efficiency of offshore wind farm.

[0003] In summary, the technical problems in the related art need to be improved. SUMMARY

[0004] The main purpose of the embodiments of the present application is to provide a wind power operation and maintenance ship berthing system compensation control method based on active disturbance rejection control and related equipment, which compensates the control amount of the six-degree-of-freedom berthing compensation platform according to the disturbance predicted by the wave disturbance prediction model and the state expansion observer and the actual monitoring data through the active disturbance rejection controller, has high precision and response speed, and can be used to ensure the stability and safety of the operation and maintenance personnel during the berthing wind turbine platform process.

[0005] To achieve the above purpose, one aspect of the embodiments of the present application provides a wind power operation and maintenance ship berthing system compensation control method based on active disturbance rejection control, which comprises: Obtaining environmental parameters, and predicting the system external wave disturbance amount of the six-degree-of-freedom berthing compensation platform according to the environmental parameters through a wave disturbance prediction model integrated with an online learning mechanism; Obtaining real-time attitude information, expected attitude information and electric cylinder control signals of the six-degree-of-freedom berthing compensation platform; According to the multivariable dynamics model of the six-degree-of-freedom berthing compensation platform, a multi-input multi-output expansion state observer is constructed, and the system internal total disturbance amount of the six-degree-of-freedom berthing compensation platform is predicted through the expansion state observer according to the real-time attitude information and the electric cylinder control signals; combine the system external wave disturbance and the system internal total disturbance to obtain a system total disturbance; construct a multiple-input multiple-output active disturbance rejection controller, calculate a nonlinear control quantity of the six-degree-of-freedom docking and landing compensation platform according to the real-time attitude information, the expected attitude information and a preset decoupling matrix through the active disturbance rejection controller, calculate a feedforward compensation quantity according to the system total disturbance, and calculate a controller output instruction according to the nonlinear control quantity and the feedforward compensation quantity; perform compensation control on the six-degree-of-freedom docking and landing compensation platform according to the controller output instruction.

[0006] In some embodiments, the wave disturbance prediction model is trained by the following steps: obtain historical environmental parameters and actual motion response data of the six-degree-of-freedom docking and landing compensation platform; preprocess the historical environmental parameters and the actual motion response data; determine corresponding actual values of the system external wave disturbance according to a mapping relationship between the historical environmental parameters and the actual motion response data; construct an LSTM neural network model containing several hidden layers; output predicted values of the system external wave disturbance according to the historical environmental parameters through the LSTM neural network model, calculate a loss value according to the predicted values of the system external wave disturbance and the actual values of the system external wave disturbance, optimize the LSTM neural network model according to the loss value through a gradient descent algorithm, and obtain the wave disturbance prediction model.

[0007] In some embodiments, the docking and landing compensation control method of the wind power operation and maintenance ship further comprises: calculate a predicted deviation value of the system external wave disturbance according to the environmental parameters and the real-time attitude information; determine whether the predicted deviation value continuously exceeds a preset first threshold value within a preset time window; when the predicted deviation value continuously exceeds the first threshold value within the preset time window, freeze part of parameters of the wave disturbance prediction model, and fine-tune the remaining parameters of the wave disturbance prediction model according to the environmental parameters and the real-time attitude information.

[0008] In some embodiments, the expression of the multivariate dynamic model is:

[0009] wherein, is a mass matrix, is a damping matrix, is a stiffness matrix, For attitude vector, For the control signal vector, It is a force / torque vector. This represents the total disturbance within the system.

[0010] In some embodiments, the expression for the extended state observer is:

[0011] in, For the observed state vector, For the system matrix, For the input matrix, The observer gain matrix is... This is the measured output vector. This is the output matrix.

[0012] In some embodiments, the nonlinear control quantity is calculated using the following formula:

[0013] in, The nonlinear control quantity is... It is a nonlinear piecewise function. The first nonlinear coefficient, For the nonlinear coefficient, The deviation between the real-time attitude information and the desired attitude information. The parameter is of the first power. For the second power parameter, This is the segmentation threshold.

[0014] In some embodiments, the controller output command is calculated using the following formula:

[0015]

[0016]

[0017] in, Output commands to the controller. The nonlinear control quantity is... This is the feedforward compensation amount. This is a force / torque conversion function. This represents the total disturbance of the system. To control the channel gain matrix, The external wave interference amount of the system. The total disturbance within the system is denoted as .

[0018] To achieve the above objectives, another aspect of this application proposes a compensation control device for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control, the device comprising: The external disturbance prediction module is used to acquire environmental parameters and predict the amount of external wave disturbance to the six-degree-of-freedom berthing compensation platform based on the environmental parameters using a wave disturbance prediction model with an integrated online learning mechanism. The attitude information acquisition module is used to acquire the real-time attitude information, desired attitude information, and electric cylinder control signals of the six-degree-of-freedom docking compensation platform. The internal disturbance prediction module is used to construct a multi-input multi-output extended state observer based on the multivariable dynamic model of the six-degree-of-freedom docking compensation platform, and predict the total internal disturbance of the six-degree-of-freedom docking compensation platform based on the real-time attitude information and the electric cylinder control signal through the extended state observer. The total disturbance synthesis module is used to synthesize the external wave disturbance and the internal total disturbance of the system into the total system disturbance; The control quantity calculation module is used to construct a multi-input multi-output active disturbance rejection controller. The active disturbance rejection controller calculates the nonlinear control quantity of the six-degree-of-freedom landing compensation platform based on the real-time attitude information, the desired attitude information, and the preset decoupling matrix. It also calculates the feedforward compensation quantity based on the total system disturbance and calculates the controller output command based on the nonlinear control quantity and the feedforward compensation quantity. The compensation control module is used to perform compensation control on the six-degree-of-freedom docking compensation platform according to the output instructions of the controller.

[0019] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the methods described above.

[0020] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0021] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the methods described above. The embodiments of this application include at least the following beneficial effects: This application provides a compensation control method and related equipment for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control. This scheme predicts the external disturbance quantity of the system through a wave disturbance prediction model with an integrated online learning mechanism. It can adaptively adjust the model according to the current sea state, which helps to maintain high prediction accuracy in sea areas with different sea states. By predicting the internal disturbance of the system through an extended state observer and combining the prediction results of external disturbances to construct the total disturbance, it can provide more comprehensive and accurate disturbance information for the active disturbance rejection controller, and can more effectively offset the influence of various disturbances, achieving more precise compensation control. At the same time, the wave disturbance prediction model and the extended state observer can work separately and independently, reducing the real-time calculation burden and improving the system response speed. By calculating the nonlinear control quantity and feedforward compensation quantity and outputting control commands through a multi-channel active disturbance rejection controller, each channel can independently estimate the coupled disturbance and naturally decouple through nonlinear feedback. At the same time, it combines the decoupling matrix to explicitly handle the coupling effect between degrees of freedom, which performs well in multi-degree-of-freedom collaborative control, and can ensure that the platform can achieve stable and accurate control of each degree of freedom under complex sea conditions, significantly improving the overall performance and reliability of the platform. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating the steps of a compensation control method for a wind power maintenance vessel berthing system based on active disturbance rejection control, as provided in an embodiment of this application. Figure 2 This is a schematic diagram of the workflow of a wind power operation and maintenance vessel berthing system compensation control method based on active disturbance rejection control provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a wind power operation and maintenance vessel berthing system compensation control device based on active disturbance rejection control provided in an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0025] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0026] Wind turbine maintenance vessel: A vessel specifically designed to provide equipment maintenance, repair, and component replacement services for offshore wind farms. It is equipped with specialized equipment and facilities suitable for offshore operations, such as boarding equipment (gangways, cranes, etc.), tool storage, and temporary storage space for components, enabling maintenance personnel to safely and efficiently reach the offshore wind turbine platform and carry out various maintenance tasks. Its design and functionality must meet the navigation, positioning, and operational requirements under complex offshore environmental conditions, ensuring the normal operation and power generation efficiency of offshore wind power facilities.

[0027] Six degrees of freedom motion: Six degrees of freedom motion refers to the translational motion along three coordinate axes and the rotational motion about three coordinate axes when a ship is moving at sea. Specifically, it includes: translational motion along the ship's longitudinal direction (bow-stern direction), called pitch; translational motion along the ship's transverse direction (port-to-port direction), called sway; translational motion along the ship's vertical direction (vertical direction), called heave; rotational motion about the ship's longitudinal axis, called roll; rotational motion about the ship's transverse axis, called pitch; and rotational motion about the ship's vertical axis, called bow roll. These six motions are coupled together and act on the ship simultaneously in complex sea conditions, affecting the ship's stability and the safety of berthing operations.

[0028] Berthing operations: Berthing operations refer to the process by which a wind turbine maintenance vessel approaches an offshore wind turbine platform and safely transfers personnel and equipment from the vessel to the platform. This operation requires precise control of the vessel's position and attitude to ensure that the distance and angle between the vessel and the wind turbine platform are appropriate, while ensuring that connecting equipment (such as gangways and ramps) can be stably connected so that maintenance personnel can smoothly board the wind turbine platform with tools and equipment, or safely return to the vessel from the wind turbine platform.

[0029] Sea state: Sea state is a comprehensive description of marine meteorological and hydrological conditions, encompassing various factors such as wind speed, wind direction, wave height, wave period, ocean current speed and direction, seawater temperature, and salinity. Different sea state conditions have a significant impact on ship navigation, positioning, and berthing operations. For example, strong winds, large waves, and rapid currents exacerbate the six degrees of freedom motion of a ship, increasing the difficulty and risk of berthing; while favorable sea state facilitates stable navigation and successful berthing operations. Accurate acquisition and analysis of sea state information is a crucial foundation for ship attitude prediction and berthing compensation control.

[0030] Six-DOF (Degrees of Freedom) Docking Compensation Platform: A six-DOF docking compensation platform is a parallel active compensation device installed on a wind turbine maintenance vessel. It can actively adjust the platform's position and attitude in real time to compensate for the vessel's motion when it undergoes six degrees of freedom of motion, through its own mechanical structure and control system. This platform typically consists of multiple motion joints and drive mechanisms, capable of providing reverse motion compensation for the vessel's sway, roll, heave, pitch, and bow movements. This ensures that the docking equipment (such as the gangway) mounted on the platform maintains a relatively stable position and attitude relationship with the wind turbine platform, guaranteeing the safe docking of maintenance personnel.

[0031] MIMO-ADRC (Multi-Input Multi-Output Active Disturbance Rejection Controller) is an advanced control strategy that inherits the core idea of ​​ADRC. Its core principle is to enable the controlled object to accurately track the target command by estimating and compensating for various disturbances inside and outside the system in real time. It is suitable for strongly coupled multi-degree-of-freedom systems. Its unique feature is that it does not rely on a precise mathematical model of the controlled object, but instead treats changes in internal system parameters and external environmental disturbances as a unified "total disturbance," dynamically estimating and actively canceling them through a special observer. ADRC mainly consists of three parts: a tracking differentiator (TD) responsible for smoothing the target signal and extracting its differential signal; an extended state observer (ESO), the core component, which can observe the system's state variables in real time and extend the total disturbance into a new state for estimation; and nonlinear state error feedback (NLSEF), which generates control inputs based on the error signal.

[0032] LSTM (Long Short-Term Memory): LSTM is a special type of recurrent neural network (RNN) that effectively solves the gradient vanishing / exploding problem of traditional RNNs by introducing gating mechanisms (input gate, forget gate, output gate) and cell states. It excels at modeling long-sequence dependencies (such as speech, text, and time series prediction). Its core idea is to selectively remember important information, discard redundant information, and transmit key features over a long period of time through cell states.

[0033] Among related technologies, offshore wind power, as an important component of renewable energy, has seen continuous growth in installed capacity in recent years, placing higher demands on efficient and safe operation and maintenance. In the daily maintenance of offshore wind farms, maintenance vessels serve as a crucial link between the land and the wind turbines, but their operations face severe environmental challenges. Due to the dynamic characteristics of the marine environment, such as irregular waves, strong winds, and complex currents, maintenance vessels exhibit multi-directional complex movements when approaching wind turbines, including displacement in three directions (forward / backward, left / right, and up / down) and rotation around three axes. This complex movement pattern not only increases the difficulty of personnel transfer but also may pose a collision risk between the gangway and the wind turbine foundation, threatening operational safety.

[0034] To reduce the risks of operation and maintenance work, a berthing compensation platform is introduced. This platform actively compensates for the motion of the maintenance vessel in each degree of freedom, ensuring stability relative to the wind turbine and allowing maintenance personnel to smoothly board and alight from the turbine. The six-degree-of-freedom berthing compensation platform, a type of berthing compensation system, comprises two planes. The lower plane connects to the hull of the maintenance vessel, while the upper plane is equipped with a berthing gangway. These are connected by six electric or hydraulic cylinders. Sensors measure the vessel's pitch, sway, heave, roll, pitch, and bow movements and compensate for these movements in the opposite direction, maintaining a relatively stable position and attitude between the end of the berthing gangway on the platform and the wind turbine platform.

[0035] However, due to the influence of the physical characteristics of the actuators in actual physical systems, it is difficult to establish an accurate mathematical model for the system.

[0036] In existing technologies, the invention patent "A Wave Compensation System Control Method Based on LQR-LADRC" requires precise kinematic and dynamic modeling of a shipborne six-degree-of-freedom platform. In practical applications, the complex navigation environment of ships and the potential for changes in platform structure due to wear, deformation, and other factors alter their dynamic characteristics, making it difficult for the model to accurately reflect the real situation and thus affecting controller performance. For example, after long-term service, the connections between platform components may loosen, but the model parameters may not be updated accordingly, leading to a decrease in control accuracy. Furthermore, while LQR control can achieve optimal control, the selection of weight matrices Q and R lacks clear physical meaning and a systematic approach, heavily relying on experience and repeated trial and error. The significant differences in ship motion characteristics under different sea states necessitate frequent adjustments to the weight matrices, increasing the difficulty of engineering applications. For instance, when moving from calm seas into areas with larger waves, the original weight matrix settings may not be suitable for the new sea conditions, requiring readjustment.

[0037] The invention patent "Control System and Method for Permanent Magnet Synchronous Motor of Shipborne Wave Compensation Platform" proposes a permanent magnet synchronous motor control system for a shipborne wave compensation platform. This system effectively suppresses multi-source interference by combining dynamic feedforward and equivalent input interference compensation in its controller design, and utilizes expert knowledge to ensure rapid convergence of the interference observer. However, its dynamic modeling based on the Newton-Euler equations requires linearization assumptions about the platform structure, including the assumption of rigid branches, neglecting joint clearances, and ideal conditions such as uniform and deformation-free materials. Under actual operating conditions, when the platform is subjected to berthing loads or high-frequency wave impacts, factors such as elastic deformation of the branches and clearance changes caused by joint wear can lead to significant deviations between the theoretically calculated driving force and actual requirements.

[0038] The invention patent "Control Method and System for Stewart Wave Compensation Platform" uses time-varying gravity estimation based on delay, followed by Kalman filtering. This process is susceptible to noise interference, and the time-varying gravity estimation itself contains inherent errors. In complex sea conditions, with violent wave fluctuations and rapid changes in time-varying gravity, estimation errors can be amplified, affecting the compensation effect. For example, in the event of giant waves, inaccurate time-varying gravity estimation can lead to over- or under-compensation by the platform. Furthermore, while non-singular terminal sliding mode controllers can achieve rapid convergence, they suffer from chattering. Chattering causes additional wear and tear on the system, reduces system reliability, and affects the stability of platform movement, adversely impacting onboard equipment. Chattering is particularly prominent in applications requiring extremely high compensation accuracy and stability.

[0039] In summary, existing berthing system compensation control technologies have significant shortcomings. Most are overly idealistic, relying on precise models under idealized conditions. They generally suffer from poor adaptability to different sea states, reduced compensation accuracy under complex conditions, high response delays, susceptibility to noise interference, and insufficient consideration of the strong coupling relationships between the joints in a six-degree-of-freedom platform. Developing intelligent compensation systems with higher accuracy and faster response speeds has become a key technological breakthrough direction for improving the safety and economy of offshore wind power operation and maintenance.

[0040] In view of this, this application provides a compensation control method and related equipment for a wind turbine maintenance vessel berthing system based on active disturbance rejection control. This scheme predicts external disturbances to the system through a wave disturbance prediction model with an integrated online learning mechanism based on data measured by real-time sensors of the berthing system, observes internal disturbances to the system through an extended state observer, and achieves active compensation control by generating multiple decoupled control signals based on the total disturbances. This provides a high-precision, high-response control strategy applicable to different sea states for the maintenance vessel berthing compensation platform, ensuring the stability and safety of maintenance personnel during the berthing process of the wind turbine platform.

[0041] This application provides a compensation control method for a wind power maintenance vessel berthing system based on active disturbance rejection control, relating to the field of information technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle-mounted terminal, but is not limited thereto. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing a compensation control method for a wind power maintenance vessel berthing system based on active disturbance rejection control, but is not limited to the above forms.

[0042] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0043] Figure 1 This is an optional flowchart of a compensation control method for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control provided in an embodiment of this application. Figure 1 The method may include, but is not limited to, steps S101 to S106.

[0044] S101. Obtain environmental parameters and predict the external wave interference of the six-degree-of-freedom berthing compensation platform based on the environmental parameters using a wave interference prediction model with an integrated online learning mechanism. Specifically, in this embodiment, real-time wave data can be collected using wave sensors and wind speed and direction sensors installed on the ship, referring to... Figure 2The acquired data may include environmental parameters such as wave height, period, wave direction, wind speed, and wind direction. The external wave interference of the six-degree-of-freedom berthing compensation platform is predicted using a wave interference prediction model. By integrating an online learning mechanism into the wave interference prediction model, the model parameters are automatically adjusted to adapt to different sea conditions when the usage scenario changes.

[0045] In some optional embodiments, the wave disturbance prediction model is trained through the following steps: S1011. Obtain historical environmental parameters and actual motion response data of the six-degree-of-freedom docking compensation platform; S1012. Preprocess historical environmental parameters and actual motion response data; S1013. Determine the actual value of the corresponding external wave disturbance of the system based on the mapping relationship between historical environmental parameters and actual motion response data. S1014. Construct an LSTM neural network model containing several hidden layers; S1015. The LSTM neural network model outputs the predicted value of the external wave interference of the system based on historical environmental parameters. The loss value is calculated based on the predicted value and the actual value of the external wave interference of the system. The LSTM neural network model is optimized based on the loss value using the gradient descent algorithm to obtain the wave interference prediction model.

[0046] Specifically, in this embodiment, it is first necessary to collect historical operational data of the vessel under different sea states, including historical environmental parameters such as wave height (m), wave period (s), wave direction (°, measured clockwise from true north), wind speed (m / s), and wind direction (°). Simultaneously, the actual motion response data of the six-degree-of-freedom platform (such as sway and roll displacement data) is recorded. The raw data is preprocessed, including cleaning, removing outliers (such as jumps caused by sensor malfunctions), and filling in missing values ​​using interpolation. Based on the mapping relationship between historical environmental parameters and platform response, the actual value of external wave interference is determined and used as a label for subsequent training.

[0047] Then, an LSTM neural network model with several hidden layers is constructed. For example, in this embodiment, an LSTM network with 3 hidden layers is constructed, with 128, 64, and 32 neurons in each layer, respectively, using the sigmoid function and... The function acts as an activation function to process the hidden layer output, and the output layer is mapped to τ-step perturbation predictions through a fully connected layer. The core calculation formula of LSTM is as follows: Forgotten Gate:

[0048] Input Gate:

[0049] Cell status update:

[0050] Output gates and hidden states:

[0051] in, For the input vector, For the sigmoid function, This is the hidden layer state. This is the weight matrix. For bias terms, For memory units, It is the element-wise product.

[0052] During the training of LSTM, a sliding window method is used to construct the input sequence, which contains a sequence of historical environmental parameters from the past T time points (e.g., T=60s, sampling frequency 10Hz, which contains 600 data points). As input to the LSTM, each x t The output is a vector containing 5 environmental parameters, and is a predicted value of the external wave disturbance of the system in the next τ steps (e.g., τ=10s). , This represents the amount of disturbance to the platform's motion. Based on the previously determined actual and predicted values ​​of external wave disturbance, the loss value is calculated. The parameters of the LSTM are then optimized using the inverse gradient descent algorithm to obtain the wave disturbance prediction model.

[0053] For example, the training and validation sets can be divided in a 7:3 ratio, and the Adam optimizer can be used for training, with the loss function set as the mean squared error between the predicted and actual values.

[0054] Iterate through the training until the loss on the validation set stabilizes, and save the model parameters as the initial weights for the wave disturbance prediction model.

[0055] In some optional embodiments, the wind power maintenance vessel berthing system compensation control method further includes: S1016. Calculate the predicted deviation of the external wave interference of the system based on environmental parameters and real-time attitude information. S1017. Determine whether the prediction deviation value is continuously higher than the preset first threshold within the preset time window; S1018. When the prediction deviation value continues to be higher than the first threshold within the preset time window, freeze some parameters of the wave interference prediction model, and fine-tune the remaining parameters of the wave interference prediction model according to environmental parameters and real-time attitude information.

[0056] Specifically, the core logic of the online learning mechanism of the wave disturbance prediction model is as follows: Real-time acquisition of environmental parameters of the current sea state and real-time attitude feedback data of the platform; determination of the actual disturbance based on the mapping relationship between the two; and calculation of the deviation between the predicted disturbance and the actual disturbance by the wave disturbance prediction model. When the deviation value exceeds a threshold (set according to the allowable error range, such as threshold θ=0.05m) for several consecutive time periods, the online learning mechanism will be triggered, freezing some hidden layer parameters of the model and only locally updating the weights of the output layer and the last hidden layer.

[0057] For example, during the update, a mini-batch of samples is formed using the most recently collected M time points (e.g., M=30), and gradient descent is used for 1-3 rounds of iterative training. The parameter update formula is: , ( To fine-tune the learning rate, it is set to 1 / 10 of the initial training rate (e.g., 0.001 initially, 0.0001 during online fine-tuning) to avoid drastic parameter fluctuations. Through this mechanism, the model can adaptively adjust when switching sea areas or when sea state characteristics change (e.g., wave period changes from 5s to 10s), ensuring prediction accuracy.

[0058] S102. Obtain the real-time attitude information, desired attitude information, and electric cylinder control signal of the six-degree-of-freedom docking compensation platform; Specifically, in this embodiment, referring to Figure 2 The real-time attitude information of the six-degree-of-freedom landing compensation platform can be obtained through the attitude sensor gyroscope. The desired attitude information can be calculated based on the theoretical effect of the control signal. The electric cylinder control signal corresponds to the extension and retraction command of the six electric cylinders.

[0059] S103. Construct a multi-input multi-output extended state observer based on the multivariable dynamic model of the six-degree-of-freedom docking compensation platform. Predict the total internal disturbance of the six-degree-of-freedom docking compensation platform based on real-time attitude information and electric cylinder control signals using the extended state observer. In some optional embodiments, the expression for the multivariable dynamics model is:

[0060] in, For the quality matrix, Here is the damping matrix. Here is the stiffness matrix. For attitude vector, For the control signal vector, It is a force / torque vector. This represents the total disturbance within the system.

[0061] Specifically, in this embodiment, the derivation process of the multivariable dynamics model of the six-degree-of-freedom docking compensation platform is as follows: Taking the longitudinal oscillation of a single degree of freedom as an example, the force analysis is as follows: The inertial force on the platform in the longitudinal direction is... (m1 is the equivalent mass in the longitudinal direction,) (where oscillation acceleration is), and damping force is (c1 is the oscillation damping coefficient, (where oscillation velocity is ), and stiffness force is . ( The sway stiffness coefficient is... (This refers to the swaying displacement). The driving force in the swaying direction is the force corresponding to the electric cylinder control signal. At the same time, it is affected by internal disturbances. According to Newton's second law, the equilibrium equation is:

[0062] After performing force analysis on each degree of freedom, the overall model of the six-degree-of-freedom platform can be obtained as follows:

[0063] in: These are six-degree-of-freedom attitude vectors, corresponding to sway displacement, heave displacement, roll angle, pitch angle, and bow angle, respectively.

[0064] M is a 6x6 mass matrix, C is a 6x6 damping matrix, and K is a 6x6 stiffness matrix; These are 6 control signal vectors, each representing the extension / retraction length of one of the 6 electric cylinders; It is a 6*1 force / torque vector, which is a function of the extension length of the electric cylinder. The extension length is converted into a control force / torque acting on the platform through the force-displacement characteristics of the electric cylinder. This represents the total disturbance within the system.

[0065] In this embodiment, to improve the accuracy of the model, the parameters in the model are identified. The motion response of the platform under different working conditions is tested experimentally, and relevant data are collected. The maximum likelihood method is used to estimate and optimize parameters such as mass, moment of inertia, elastic coefficient, and friction coefficient in the model, so that the established dynamic model can more accurately reflect the actual dynamic characteristics of the platform.

[0066] In some optional embodiments, the expression for the extended state observer is:

[0067] in, For the observed state vector, For the system matrix, For the input matrix, The observer gain matrix is... This is the measured output vector. This is the output matrix.

[0068] Specifically, the input of MESO (Multi-Input Multi-Output Extended State Observer) includes two types of signals: one is the 6-channel electric cylinder control signal output by MIMO-ADRC. (Corresponding to the extension and retraction commands of 6 electric cylinders); secondly, the real-time feedback of the upper platform's attitude information from the six-degree-of-freedom platform gyroscope. (These represent the real-time values ​​for sway, heave, roll, pitch, and bow roll, respectively). The observer, based on a multivariable dynamic model of a six-degree-of-freedom platform, estimates the total internal disturbance of the system in real time by comparing the theoretical attitude under control signals with the gyroscope-measured attitude. (Including internal perturbations of each degree of freedom).

[0069] The equation of state for MESO is:

[0070] in: The observed state vector (containing attitude, velocity, and corresponding internal perturbations for 6 degrees of freedom); A is the system matrix, with dimensions 18×18, and the diagonal blocks are... ( (This is the disturbance attenuation coefficient). B is the input matrix with dimensions 18×6. Rows 2, 5, 8, 11, 14, and 17 correspond to 1 / m1, 1 / m2, 1 / m3, 1 / m4, 1 / m5, and 1 / m6, respectively (reflecting the influence of force / torque after the conversion of the electric steel's expansion and contraction length on the acceleration of each degree of freedom). L is an 18×6 observer gain matrix (designed using the pole placement method to ensure that the observer convergence speed meets the control requirements). y=q is the measured output vector, and C is a 6×18 output matrix (only attitude components are extracted).

[0071] S104. Combine the external wave disturbance and the total internal disturbance of the system into the total disturbance of the system. Specifically, in this embodiment, more accurate disturbance information is obtained by combining the external wave interference and the total internal disturbance into the total system disturbance, thereby achieving higher precision compensation control.

[0072] For example, the formula for the synthesis of the total system disturbance is:

[0073]

[0074]

[0075] in, The external wave disturbance amount predicted by the wave disturbance prediction model for the future τ-step is mapped to each control cycle (e.g., 10ms) through time interpolation. This represents the total internal disturbance observed by the observer.

[0076] S105. Construct a multi-input multi-output active disturbance rejection controller. The active disturbance rejection controller calculates the nonlinear control quantity of the six-degree-of-freedom landing compensation platform based on the real-time attitude information, the desired attitude information and the preset decoupling matrix. It calculates the feedforward compensation quantity based on the total system disturbance and calculates the controller output command based on the nonlinear control quantity and the feedforward compensation quantity. In some optional embodiments, the nonlinear control quantity is calculated using the following formula:

[0077] in, It is a nonlinear control quantity. It is a nonlinear piecewise function. The first nonlinear coefficient, For the nonlinear coefficient, The deviation between real-time attitude information and desired attitude information The parameter is of the first power. For the second power parameter, This is the segmentation threshold.

[0078] Specifically, in this embodiment, the multiple-input multiple-output active disturbance rejection controller (MIMO-ADRC) uses the extension and retraction length of six electric cylinders as the control output to determine the desired attitude of the platform relative to the wind turbine foundation. (The target is zero deviation) The error e=rq between the actual attitude q and the target attitude is used as the feedback input, while the total disturbance D(t) is introduced as a feedforward compensation term. (Refer to...) Figure 2 The controller comprises six parallel ADRC submodules, each corresponding to one degree of freedom, connected by a decoupling matrix. Addressing the coupling effects between degrees of freedom ( It is a 6×6 matrix, and the off-diagonal elements are labeled according to the coupling strength.

[0079] For example, the key parameters of each component in MIMO-ADRC are set as follows: Tracking Differentiator (TD): The filter factor r is set according to the response speed requirement (e.g., r=50). Extended State Observer (ESO): Bandwidth (k=3~5), To control bandwidth, such as =10 rad / s then =30rad / s); Nonlinear State Error Feedback (NLSEF): , in .

[0080] In some optional embodiments, the controller output command is calculated using the following formula:

[0081]

[0082]

[0083] in, Output commands to the controller. It is a nonlinear control quantity. This is the feedforward compensation amount. This is a force / torque conversion function. For the total system disturbance, To control the channel gain matrix, This refers to the amount of external wave interference to the system. This represents the total disturbance within the system.

[0084] Specifically, in this embodiment, the controller's output command u consists of two parts: one is a nonlinear control quantity based on error feedback. (Electric cylinder extension / retraction length) is generated by processing the error signal using the aforementioned NLSEF; secondly, it is based on the total system disturbance. Feedforward compensation (Electric cylinder extension / retraction length compensation amount), through The conversion yields ( The control channel gain matrix is ​​6×6 (calibrated experimentally). The final control signal is: , refer to Figure 4 The signal, after being converted from digital to analog, drives the electric cylinder to perform extension and retraction actions, thereby offsetting the attitude deviation caused by the ship's movement in real time and ensuring the stability of the platform.

[0085] S106. Perform compensation control on the six-degree-of-freedom docking compensation platform according to the controller output instructions.

[0086] It can be recognized that, in the embodiments of the present invention, the total external disturbance predicted by the wave disturbance prediction model and the total internal disturbance observed by MESO are accurately synthesized to form the total system disturbance, providing more comprehensive and accurate disturbance information for MIMO-ADRC. This more effectively offsets the impact of various disturbances on the platform, achieving more precise wave compensation control. Each channel of MIMO-ADRC independently estimates coupled disturbances, and through nonlinear feedback, natural decoupling allows for early disturbance compensation, improving response speed. Simultaneously, the wave disturbance prediction model predicts external disturbances in advance, while MESO focuses on unmodeled disturbances within the system. This division of labor reduces the real-time computational burden, further improving response speed. Furthermore, MIMO-ADRC itself has strong robustness and is insensitive to model uncertainties and external disturbances. By handling the coupling effects between degrees of freedom through a decoupling matrix, it performs better in multi-degree-of-freedom collaborative control, ensuring that the platform can achieve stable and accurate control of each degree of freedom under complex sea conditions, significantly improving the overall performance and reliability of the platform. By combining long-term predictions from wave disturbance prediction models with instantaneous observations from MESO, both periodic and sudden disturbances can be taken into account, significantly improving control robustness under complex sea conditions.

[0087] The present invention will be further described in conjunction with a specific embodiment.

[0088] Reference Figure 2 In this embodiment, real-time wave data, including wave height, period, wave direction, wind speed, and wind direction, is first collected using wave sensors and wind speed and direction sensors installed on the ship. A Long Short-Term Memory (LSTM) neural network model is then used to train a wave disturbance prediction model. An online learning mechanism is embedded within the LSTM to automatically fine-tune parameters as the usage scenario changes. Based on the wave disturbance prediction model, wave disturbances within a future timeframe are predicted. Based on real-time attitude information collected by the attitude sensor gyroscope, an Extended State Observer (MESO) is used to observe internal system disturbances. The wave disturbances predicted by the LSTM are superimposed with the internal system disturbances observed by the MESO to obtain the total internal and external disturbances for the berthing system. A Multiple-Input Multiple-Output (MIMO-ADRC) active disturbance rejection controller generates the attitude control target Position, which is then input into the Controller to generate control commands that can be executed by the permanent magnet synchronous motors (PMSM1-6). Feedback control is achieved by collecting operating parameters through an encoder. It can be recognized that this embodiment, through the complementary use of long-term prediction by the LSTM and instantaneous observation by the MESO, can take into account both periodic disturbances and sudden dynamics, significantly improving control robustness under complex sea conditions. The method described in this embodiment can accurately estimate the total disturbance of the system. Combined with the MIMO-ADRC mechanism for early disturbance compensation, it can significantly improve the compensation control accuracy of the berthing system under complex sea conditions, providing a safe and stable working environment for offshore wind power operation and maintenance personnel.

[0089] Please see Figure 3 This application also provides a compensation control device for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control, which can implement the above-mentioned method. The device includes: The external disturbance prediction module is used to acquire environmental parameters and predict the amount of external wave disturbance to the six-degree-of-freedom berthing compensation platform based on the environmental parameters through a wave disturbance prediction model with an integrated online learning mechanism. The attitude information acquisition module is used to acquire the real-time attitude information, desired attitude information, and electric cylinder control signals of the six-degree-of-freedom landing compensation platform. The internal disturbance prediction module is used to construct a multi-input multi-output extended state observer based on the multivariable dynamic model of the six-degree-of-freedom docking compensation platform. The extended state observer predicts the total internal disturbance of the six-degree-of-freedom docking compensation platform based on real-time attitude information and electric cylinder control signals. The total disturbance synthesis module is used to synthesize the external wave disturbance and the internal total disturbance of the system into the total system disturbance; The control quantity calculation module is used to construct a multi-input multi-output active disturbance rejection controller. The active disturbance rejection controller calculates the nonlinear control quantity of the six-degree-of-freedom landing compensation platform based on real-time attitude information, desired attitude information and preset decoupling matrix. It also calculates the feedforward compensation quantity based on the total system disturbance and calculates the controller output command based on the nonlinear control quantity and the feedforward compensation quantity. The compensation control module is used to perform compensation control on the six-degree-of-freedom docking compensation platform according to the output instructions of the controller.

[0090] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0091] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0092] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0093] Please see Figure 4 , Figure 4 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 using the methods described in the embodiments of this application. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0094] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0095] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0096] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0097] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0098] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0099] This application provides a compensation control method and related equipment for a wind power maintenance vessel berthing system based on active disturbance rejection control (ADRC). The method utilizes a wave disturbance prediction model with an integrated online learning mechanism to predict external disturbances. This model can adaptively adjust itself according to the current sea state, helping to maintain high prediction accuracy in different sea conditions. Furthermore, by predicting internal disturbances using an extended state observer and combining the prediction results with external disturbances to construct the total disturbance, the method provides more comprehensive and accurate disturbance information to the ADRC controller, enabling more effective... It effectively counteracts the effects of various disturbances, achieving more precise compensation control. Meanwhile, the wave disturbance prediction model and the extended state observer can work independently, reducing the real-time computation burden and improving the system's response speed. The multi-channel active disturbance rejection controller calculates nonlinear control quantities and feedforward compensation quantities and outputs control commands. Each channel can independently estimate coupled disturbances and naturally decouple through nonlinear feedback. At the same time, it combines decoupling matrix to explicitly handle the coupling effect between degrees of freedom. It performs excellently in multi-degree-of-freedom cooperative control, ensuring that the platform can achieve stable and accurate control of each degree of freedom under complex sea conditions, significantly improving the overall performance and reliability of the platform.

[0100] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0101] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0102] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0103] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0104] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0105] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0106] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0107] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0108] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0109] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0110] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A compensation control method for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control, characterized in that, include: The system acquires environmental parameters and uses a wave interference prediction model with an integrated online learning mechanism to predict the amount of external wave interference to the six-degree-of-freedom berthing compensation platform based on these environmental parameters. Acquire the real-time attitude information, desired attitude information, and electric cylinder control signals of the six-degree-of-freedom docking compensation platform; Based on the multivariable dynamics model of the six-degree-of-freedom docking compensation platform, a multi-input multi-output extended state observer is constructed. The extended state observer predicts the total internal disturbance of the six-degree-of-freedom docking compensation platform based on the real-time attitude information and the electric cylinder control signal. The external wave disturbance and the total internal disturbance of the system are combined into the total system disturbance. A multi-input multi-output active disturbance rejection controller is constructed. The active disturbance rejection controller calculates the nonlinear control quantity of the six-degree-of-freedom landing compensation platform based on the real-time attitude information, the desired attitude information, and the preset decoupling matrix. It also calculates the feedforward compensation quantity based on the total system disturbance and calculates the controller output command based on the nonlinear control quantity and the feedforward compensation quantity. The controller outputs instructions to perform compensation control on the six-degree-of-freedom docking compensation platform.

2. The compensation control method for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control according to claim 1, characterized in that, The wave interference prediction model is trained using the following steps: Acquire historical environmental parameters and actual motion response data of the six-degree-of-freedom docking compensation platform; The historical environmental parameters and the actual motion response data are preprocessed; The actual value of the external wave interference of the system is determined based on the mapping relationship between the historical environmental parameters and the actual motion response data. Construct an LSTM neural network model containing several hidden layers; The LSTM neural network model outputs a predicted value of the external wave interference based on the historical environmental parameters. A loss value is calculated based on the predicted value and the actual value of the external wave interference. The LSTM neural network model is then optimized using a gradient descent algorithm based on the loss value to obtain the wave interference prediction model.

3. The compensation control method for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control according to claim 1, characterized in that, The compensation and control method for the wind power maintenance vessel berthing system also includes: The predicted deviation of the external wave interference of the system is calculated based on the environmental parameters and the real-time attitude information. Determine whether the prediction deviation value remains higher than a preset first threshold within a preset time window; If the prediction deviation value remains higher than the first threshold within a preset time window, some parameters of the wave interference prediction model are frozen, and the remaining parameters of the wave interference prediction model are fine-tuned based on the environmental parameters and the real-time attitude information.

4. The compensation control method for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control according to claim 1, characterized in that, The expression for the multivariable dynamics model is: in, For the quality matrix, Here is the damping matrix. Here is the stiffness matrix. For the attitude vector, For the control signal vector, It is a force / torque vector. This represents the total disturbance within the system.

5. The compensation control method for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control according to claim 1, characterized in that, The expression for the extended state observer is: in, For the observed state vector, For the system matrix, For the input matrix, The observer gain matrix is... This is the measured output vector. This is the output matrix.

6. The compensation control method for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control according to claim 1, characterized in that, The nonlinear control quantity is calculated using the following formula: in, The nonlinear control quantity is... It is a nonlinear piecewise function. The first nonlinear coefficient, For the nonlinear coefficient, The deviation between the real-time attitude information and the desired attitude information. The parameter is of the first power. For the second power parameter, This is the segmentation threshold.

7. A compensation control method for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control as described in claim 1, characterized in that, The controller output command is calculated using the following formula: in, Output commands to the controller. The nonlinear control quantity is... This is the feedforward compensation amount. This is a force / torque conversion function. The total disturbance of the system is given. To control the channel gain matrix, The external wave interference amount of the system. The total disturbance within the system is denoted as .

8. A compensation control device for a wind power operation and maintenance vessel berthing system based on active disturbance rejection control, characterized in that, The device includes: The external disturbance prediction module is used to acquire environmental parameters and predict the amount of external wave disturbance to the six-degree-of-freedom berthing compensation platform based on the environmental parameters using a wave disturbance prediction model with an integrated online learning mechanism. The attitude information acquisition module is used to acquire the real-time attitude information, desired attitude information, and electric cylinder control signals of the six-degree-of-freedom docking compensation platform. The internal disturbance prediction module is used to construct a multi-input multi-output extended state observer based on the multivariable dynamic model of the six-degree-of-freedom docking compensation platform, and predict the total internal disturbance of the six-degree-of-freedom docking compensation platform based on the real-time attitude information and the electric cylinder control signal through the extended state observer. The total disturbance synthesis module is used to synthesize the external wave disturbance and the internal total disturbance of the system into the total system disturbance; The control quantity calculation module is used to construct a multi-input multi-output active disturbance rejection controller. The active disturbance rejection controller calculates the nonlinear control quantity of the six-degree-of-freedom landing compensation platform based on the real-time attitude information, the desired attitude information, and the preset decoupling matrix. It also calculates the feedforward compensation quantity based on the total system disturbance and calculates the controller output command based on the nonlinear control quantity and the feedforward compensation quantity. The compensation control module is used to perform compensation control on the six-degree-of-freedom docking compensation platform according to the output instructions of the controller.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images