Motion control method and system for marine floating platform based on time sequence large model

Abstract

The invention belongs to the technical field of offshore floating platforms. The invention provides a motion control method and system for an offshore floating platform based on a time sequence large model. According to the embodiment of the invention, a time sequence prediction module is added in the floating platform control system; the time sequence large model technology can predict medium-short-term platform motion in real time, so that a more accurate control target is provided for a control system, namely, vibration of the platform is restrained to the maximum extent. The prediction controller based on the model not only has higher adaptability to the external state change of the platform and solves the problem of control action transmission and execution delay, but also considers the complex nonlinear characteristics of the floating platform, so that the control system has higher robustness. When platform parameters change due to external factors, the output of the system can be monitored in real time by using an adaptive control technology, and the parameters of the controller are adjusted on line according to errors, so that the controller can quickly adapt to the change of the model.

Description

Background Art

[0002] Wind energy plays an important role in current green energy generation, and offshore wind energy resources are far more abundant than onshore wind energy resources. Developing offshore wind energy resources also has other economic and social advantages, such as no expensive land acquisition costs, and the noise of wind turbines does not affect normal community activities. However, developing offshore wind energy resources also has thorny challenges: deep-sea wind turbines are usually installed on floating platforms, which are connected to the seabed by tethers to fix the wind turbines. Driven by tides or sea breezes, seawater will cause floating platforms to produce six degrees of freedom: forward and backward; rise and fall; left and right; pitch; roll; yaw. In extreme weather conditions such as typhoons, this six-degree-of-freedom movement will become more obvious. The violent six-degree-of-freedom movement of the platform will bring a series of problems, including increasing the fatigue load of the wind turbine, reducing the power generation efficiency of the wind turbine, and causing resonance of the wind turbine substructure. These problems can directly damage the expensive components of the wind turbine or reduce the expected life of the wind turbine. Therefore, it is urgent to develop a motion control system to stabilize the offshore floating platform and reduce the damage caused by the platform movement to the upper wind turbine.

[0003] Currently, there are two types of stability control for floating platforms: passive control and active control. Passive control means that no power module is installed on the platform, and only non-powered dampers are installed to eliminate vibration. When tides, waves or sea breezes exert external torque on the platform, causing the platform to move in six degrees of freedom, the installed dampers will generate reverse torques to offset the external torques to achieve the purpose of platform stability control. Common passive control dampers include tuned mass dampers and tuned liquid dampers. A typical tuned mass damper consists of three parts: (1) mass block (body): a relatively small mass block, usually made of steel or concrete, (2) spring: an elastic element connecting the mass block and the main structure to provide restoring force; (3) damper: provides damping and converts vibration energy into heat energy and dissipates it. The working principle of the tuned mass damper is based on the principle of dynamic vibration absorption. When the main structure is vibrated by external force, the mass block of the tuned mass damper will also vibrate. By adjusting the natural frequency of the tuned mass damper to make it close to the vibration frequency of the main structure, the tuned mass damper will generate an inertial force in the opposite direction of the vibration of the main structure, thereby offsetting part of the vibration energy and achieving the effect of vibration reduction. After optimized design, the dynamic response of the main structure under wave, wind or other environmental excitations can generally be reduced by 30%~60%. The tuned liquid damper is a new type of passive vibration reduction device. Its working principle is similar to that of the traditional tuned mass damper. Both absorb the vibration energy of the main structure by adding a mass block. The difference is that the mass block of the tuned liquid damper is a container filled with liquid. The sloshing of the liquid can generate damping force, thereby achieving the purpose of vibration reduction. A typical tuned liquid damper mainly consists of the following three parts: 1. Container: usually a rectangular or circular container, which can be made of steel, aluminum, etc.; 2. Liquid: usually water or other high-density liquids; 3. Baffle (optional): used to change the sloshing mode of the liquid and improve the damping effect. The working principle of the tuned liquid damper is mainly based on the damping force generated by the sloshing of the liquid. When the floating platform is shaken by waves or wind, the liquid in the container will also shake. The shaking of the liquid will generate inertial force, which is opposite to the direction of movement of the platform, thereby offsetting part of the vibration energy. In addition, the friction between the liquid and the container wall will also generate damping force, further consuming the vibration energy. The disadvantages of passive control systems are: 1. Narrow frequency band and poor adaptability: Passive control dampers are usually tuned for vibrations of a specific frequency. Once the external excitation frequency changes, their vibration reduction effect will be significantly reduced. The offshore environment is complex and changeable, and the wind and wave conditions are constantly changing. It is difficult for passive control dampers to adapt to such dynamic changes, resulting in unstable vibration reduction effects; 2. Significant nonlinear effects: When the vibration amplitude is large, the nonlinear characteristics of the passive control damper will become significant, affecting its vibration reduction effect. The coupling between the passive control damper and the structure will also introduce nonlinearity, making the system response complicated. Therefore, active control systems are proposed to solve such problems.

[0004] Active control systems for floating platforms generally use active tuned mass dampers. Active tuned mass dampers are advanced vibration control devices. Their core working principle is to suppress vibration by monitoring the vibration response of the structure in real time and actively applying control force. Compared with traditional passive tuned mass dampers, active tuned mass dampers have stronger adaptability and control capabilities and can optimize control for different excitation conditions. Active tuned mass dampers mainly consist of four parts: (1) Mass block: Similar to tuned mass dampers, active tuned mass dampers also have a mass block to absorb the vibration energy of the structure; (2) Drive device: Control force is applied to the mass block through drive devices such as motors and hydraulic cylinders. (3) Sensor: Used to monitor the vibration response of the structure in real time, such as acceleration, displacement, etc. (4) Controller: Calculate the required control force based on the signal fed back by the sensor and drive the actuator to generate the corresponding control force. The working principle of active tuned mass dampers is to generate a force opposite to the structural vibration by adjusting the position and velocity of the mass block in real time, thereby offsetting the vibration of the structure. Compared with passive tuned mass dampers, the control force of active tuned mass dampers can be adjusted according to the real-time response of the structure, thereby achieving better control effects. Active tuned mass dampers can be applied to various complex vibration environments, such as wide-band excitation, nonlinear structures, etc. Active tuned mass dampers can achieve multiple control objectives at the same time, such as reducing amplitude, shortening vibration duration, etc. However, active control systems also have disadvantages. For example, active tuned mass dampers require complex control algorithms to monitor the vibration response of the structure in real time and adjust the position of the mass block, which increases the complexity of the system. In addition, there is a certain delay in the transmission and execution of the control signal, which may affect the real-time performance of the system. Therefore, a predictive control system should be developed. In the related art, the Chinese patent application number is: CN202411123996.5, and the name is: A floating wind power generation platform with position adjustment function and its use method, which is specifically assembled together with the mounting cylinder and the adjustable support assembly, wherein the support assembly includes a buoy, a first pipeline, an anti-disturbance annular plate and a water pump. The support assembly is equipped with a component for adjusting the retraction and release of each second steel rope, and the adjustment component includes a first support wheel, a limit frame, a braking device, a retraction and release line drive assembly and a retraction automatic locking device; multiple sets of tensioning assemblies are fixed on the inner wall of the mounting cylinder; and a scraping assembly is also provided on the second steel rope. Through the design of the anti-disturbance annular plate, the impact force of the seawater inside the buoy can be effectively reduced, thereby improving the overall stability. Under strong offshore wind and wave conditions, this scheme can lower the water level and reel in the second steel rope at the same time to maintain the lateral stability of the floating platform, but there is still a lack of effective suppression means for the movement of other degrees of freedom (such as roll and pitch), and it cannot fully meet the stability requirements of the platform. Patent application number: CN202410968540.2, title: A floating platform tuned mass damper and a floating platform, and its specific method is: a tuned mass damper is installed on a floating platform, including a support frame, a guide rail, a sliding mass block, a turbine and a capacitor. The damper can be transported to a designated location after being installed on the shore. It is easy to install and has strong operability. After installing the damper, the movement within the platform plane can be effectively controlled, and the vibration amplitude of the platform can be significantly reduced, thereby providing good protection for the wind energy conversion of the superstructure and making the wind power generation device more efficient. However, under extreme sea conditions, the performance of this method is significantly reduced, and its adaptability to system changes is weak. Patent application number: CN202410317119.5, title: A floating wind turbine platform for suppressing swaying motion, and its specific method is: This method forms a sway suppression system by connecting columns and heave plates. The connecting column includes three side columns, and the side column structures are connected by cross braces; a heave plate is installed at the bottom of the lower buoy of each side column, and the connection between the structures is achieved through the connecting column. This method suppresses the swaying motion through the column structure, which belongs to the passive vibration control technology and is suitable for small floating systems, but cannot meet the application requirements of large offshore floating systems.

[0005] Therefore, it is necessary to improve one or more problems existing in the above-mentioned related technical solutions.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] The purpose of the embodiments of the present disclosure is to provide a motion control method and system for an offshore floating platform based on a time-series large model, thereby overcoming one or more problems caused by limitations and defects of related technologies at least to a certain extent.

[0008] According to a first aspect of an embodiment of the present disclosure, a motion control method for an offshore floating platform based on a time series large model is provided, the method comprising: Construct a time series big model, train the model parameters according to the historical motion information to obtain the identified time series big model, and design a model prediction controller according to the identified time series big model; Predict future motion information based on the time series big model and real-time motion information; Based on the model predictive controller and future motion information, control actions are generated and executed to achieve the purpose of vibration suppression of the floating platform.

[0009] Furthermore, the step of constructing a time series large model and training model parameters according to real-time motion information to obtain an identified time series large model includes: Get the time series model; Using sensors on the floating platform to obtain real-time motion information in real time; wherein the real-time motion information at least includes wind speed, wave speed, wave height and tidal current speed; Based on the adaptive system identification method, the real-time motion information is input into the time series model for inference to obtain the current seawater movement direction and speed; The six-degree-of-freedom motion information of the floating platform is obtained according to the direction and speed of seawater movement; The model parameters are updated according to the six-degree-of-freedom motion information of the floating platform until convergence to obtain an identified time series large model.

[0010] Furthermore, the step of designing a model predictive controller according to the identification time series large model includes: Determine the prediction time domain and control time domain; Construct the cost function based on the identified large time series model, prediction time domain and control time domain; Identify constraints; Design a model predictive controller based on the cost function and constraints.

[0011] Furthermore, the step of predicting future motion information according to the time series big model and the real-time motion information includes: Acquire real-time motion information, and perform filtering, calibration and conversion processing on the real-time motion information; The processed real-time motion information is input into the time series large model for processing to obtain future motion information.

[0012] Further, the steps of generating and executing control actions according to the model predictive controller and the future motion information to achieve the purpose of suppressing the vibration of the floating platform include: Deploy the time series big model and the model predictive controller using a programmable logic controller to connect the time series big model and the model predictive controller; Use model predictive controller to solve future motion information to obtain optimal control actions; The floating platform executes optimal control actions to achieve the purpose of vibration suppression of the floating platform.

[0013] Furthermore, the method further comprises: Obtain status information of the floating platform; Online system parameter identification and controller parameter recalibration are performed based on the status information of the floating platform.

[0014] According to a second aspect of an embodiment of the present disclosure, a motion control system for an offshore floating platform based on a time series large model is provided, the system comprising: The state supervision and identification module is used to construct a time series big model, train the model parameters according to the historical motion information to obtain the identified time series big model, and design the model prediction controller according to the identified time series big model; A motion prediction module is used to predict future motion information based on a large temporal model and real-time motion information; The model predictive control module is used to generate and execute control actions based on the model predictive controller and future motion information to achieve the purpose of vibration suppression of the floating platform.

[0015] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the motion control method of an offshore floating platform based on a time-series large model are implemented in any of the above embodiments.

[0016] According to a fourth aspect of an embodiment of the present disclosure, there is provided an electronic device, including: Processor; and A memory, configured to store executable instructions of the processor; The processor is configured to execute the steps of the motion control method for an offshore floating platform based on a time series large model in any one of the above embodiments by executing the executable instructions.

[0017] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects: In the embodiments of the present disclosure, a time series prediction module is added to the floating platform control system through the above-mentioned motion control method and device for offshore floating platforms based on a time series large model; the time series large model technology can predict the medium- and short-term platform motion in real time, thereby providing a more accurate control target for the control system, namely, maximizing the suppression of platform vibration. The use of a model-based predictive controller not only has higher adaptability to changes in the external state of the platform, solving the problem of control action transmission and execution delay, but also takes into account the complex nonlinear characteristics of the floating platform, thereby making the control system more robust. When the platform parameters change due to external factors, the present application uses adaptive control technology to monitor the output of the system in real time, and adjust the parameters of the controller online according to the error, so that the controller can quickly adapt to changes in the model.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0020] Figure 1 A step diagram showing a motion control method for an offshore floating platform based on a time series large model in an exemplary embodiment of the present disclosure; Figure 2 A flow chart showing online identification of time series large model parameters in an exemplary embodiment of the present disclosure is shown; Figure 3 A schematic diagram showing the structure of a floating platform in an exemplary embodiment of the present disclosure and a motion control system of an offshore floating platform based on a time series large model; Figure 4 An operation flow chart of a motion control system of an offshore floating platform based on a time series large model in an exemplary embodiment of the present disclosure is shown; Figure 5 A schematic diagram showing a program product in an exemplary embodiment of the present disclosure; Figure 6 A schematic diagram showing an electronic device in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0022] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0023] In this example implementation, a motion control method for an offshore floating platform based on a time series large model is first provided. The method can be applied to a terminal device, such as a mobile phone, a personal digital assistant, a laptop, a tablet computer, a smart watch, or other mobile terminal [flexibly adjusted according to specific circumstances, such as the terminal device is a server, etc.]. Figure 1 As shown in , the method may include the following steps: Step S101: constructing a time series large model, training model parameters according to historical motion information to obtain an identified time series large model, and designing a model prediction controller according to the identified time series large model; Step S102: predicting future motion information based on the time series large model and real-time motion information; Step S103: Generate and execute control actions based on the model prediction controller and future motion information to achieve the purpose of suppressing the vibration of the floating platform.

[0024] Through the above-mentioned motion control method of offshore floating platform based on large time series model, a time series prediction module is added to the floating platform control system; the large time series model technology can predict the medium- and short-term platform motion in real time, thereby providing a more accurate control target for the control system, that is, maximizing the suppression of platform vibration. The use of a model-based predictive controller not only has higher adaptability to changes in the external state of the platform, solving the problem of control action transmission and execution delay, but also takes into account the complex nonlinear characteristics of the floating platform, so that the control system has higher robustness. When the platform parameters change due to external factors, the present application uses adaptive control technology to monitor the output of the system in real time, and adjust the parameters of the controller online according to the error, so that the controller can quickly adapt to changes in the model.

[0025] Next, we will refer to Figure 1 to Figure 2 Each step of the above method in this example implementation is described in more detail.

[0026] In step S101, a time series large model is constructed, model parameters are trained according to historical motion information to obtain an identified time series large model, and a model prediction controller is designed according to the identified time series large model.

[0027] For example, a time series large model is trained to realize the floating platform motion prediction function. The role of the time series large model is to predict the future wave velocity based on the wave velocity around the floating platform in the past, thereby predicting the movement of the floating platform. The area around the floating platform can be divided into grids using 1m*1m grids, and a flow sensor is installed in each grid to measure the wave velocity in each grid. Therefore, the input and output of the time series large model are gridded wave velocity data. When training the time series large model, training is not started from scratch, that is, the weights of the neural network are not randomly initialized, because this training method is more expensive. Instead, the weights of the fluid pre-trained model (such as the FLUID-LLM model) are used to initialize the weights of the neural network. Then collect less wave velocity data from around the floating platform, and use these data to fine-tune the large model so that it can adapt to the wave prediction task and improve its prediction accuracy. Suppose the adjustable parameter matrix of the time series model (M) is , the input wave velocity sequence of the time series model is , the time series model predicts the wave velocity to be , and its corresponding true value is , the following loss function can be used to calculate the gradient of the time series model parameter matrix, thereby updating the model to achieve the purpose of model fine-tuning:

[0028] in is the number of training samples in a batch, is the gradient operator.

[0029] In step S102, future motion information is predicted based on the time series big model and the real-time motion information.

[0030] For example, online model identification and model predictive controller design. First, by analyzing the input and output data of the system in real time, using methods such as the least squares method, the parameters of the system model are continuously updated to better reflect the current state of the system. Figure 2As shown in the figure, the specific steps of online identification of model parameters using the recursive square method are listed. Based on the updated model, the optimization algorithm of model predictive control (MPC) is used to predict the system output in the future and calculate the optimal control action sequence that enables the system output to track the desired trajectory. The state space model of the floating system identified in the previous step is:

[0031]

[0032] is the state vector, is the control input, is the output. is the transfer matrix, is the state input matrix, is the output matrix. Then, the model predictive controller needs to be designed based on the identified model. First, the prediction time domain and control time domain need to be determined. Np : Indicates the length of time to predict future states. Control time domain Nc : represents the time length for optimizing the control input. Then construct the cost function. The design goal of the cost function is to minimize the error between the predicted output and the reference trajectory, while considering the rate of change of the control input and the constraints of the control amount. For the floating platform stabilization system, the cost function can be expressed as:

[0033] in, For at the moment Predicted Moment The output, is the reference trajectory, and is the weight matrix. Next, we need to determine the constraints on the system state, input and output to meet the physical limitations of the system and ensure system safety. The constraints of the floating platform control system are:

[0034]

[0035] Under the constraints, the cost function is minimized to obtain the optimal control sequence.

[0036] In step S103, a control action is generated and executed based on the model predictive controller and the future motion information to achieve the purpose of suppressing the vibration of the floating platform.

[0037] For example, the time series big model and the optimal controller are deployed to the floating control system. The first step and the second step respectively optimize the floating platform motion prediction big model and the optimal floating platform controller. These two models need to be deployed to the programmable logic controller of the floating platform in the form of functions. Specifically, the input data interface of the floating platform motion prediction model is the data sensed by the flow sensor, and the output is the flow velocity data of future waves. The input interface of the optimal controller function is the platform motion state, and the output is the control signal.

[0038] The perception module uses floating system sensors to sense the environmental status. First, the sensors on the floating platform are used to collect data. The specific data collected include environmental parameters such as wind speed, wind direction, wave height, wave period, water temperature, air temperature, humidity, etc. Due to sensor errors and failures, the collected data may be erroneous, incomplete, or abnormal. Therefore, the collected raw data needs to be filtered, calibrated, converted, etc. to make it more accurate and reliable. The processed data is then transmitted to the deployed model.

[0039] The deployed time series model predicts seawater movement based on recorded environmental status information. Input: The real-time collected environmental status data (such as wind speed, air pressure, water temperature, etc.) is used as the input of the model. Model calculation: The model calculates the input data according to the rules established by historical data to obtain the prediction results. Output: The model outputs the predicted seawater movement parameters, such as wave height, wave period, water flow speed, etc.

[0040] The optimal controller solves the optimal control action based on the future movement of the seawater. When the time series model predicts the future movement state of the seawater, the movement of the platform can be solved based on the state. The control goal of the floating platform is to suppress such movement by controlling the parameters of the tunable mass damper. Therefore, when the platform movement state is input to the model predictive controller, the model predictive controller solves the optimal control action sequence based on the control goal.

[0041] Execute the optimal control action to achieve the goal of controlling the platform vibration. In step 6, the model-based predictive controller has solved the optimal control action sequence to suppress the platform vibration based on the future motion state of the seawater predicted by the time series model. Therefore, the actuator of the active tuned damper needs to strictly execute the control action sequence generated by the optimal controller to achieve the goal of stable, accurate and fast.

[0042] Feedback platform status information to the control system. After the control action sequence is executed, it is very important to evaluate the execution effect of the execution action. Therefore, it is necessary to feed back the platform status information to the control system. The control system can use this information to complete two important tasks. The first task is online system parameter re-identification: Due to seawater erosion, component failure or aging, the parameters of the floating platform may change over time. This increase in uncertainty will lead to a decrease in the execution effect of the actuator. Therefore, the control system needs to use the feedback platform status information to correct the parameters of the model, thereby reducing the model error and enhancing the control performance. The second task is controller parameter recalibration. When the system model changes, the controller parameters need to be recalculated to realize the change in the environment, while reducing the control error and improving the control effect of the platform.

[0043] In one embodiment, the six-degree-of-freedom motion of the platform is predicted in the short and medium term based on the historical state information of the platform based on the time series large model. The state of the platform includes wind speed information, wave information, tidal current information, etc. around the platform.

[0044] In one embodiment, based on the principle of fluid mechanics, the Navier-Stokes formula is used to describe the movement of seawater. The Navier-Stokes formula shows that the movement of seawater is caused by the coupling of tidal motion and wave motion dragged by wind. Therefore, a time series large model is designed based on this principle to predict the movement of seawater. The input information of the time series model is the historical wind speed, wave speed, wave height, tidal speed, etc. around the platform, and the output is the direction and speed of seawater movement in the short and medium term. Finally, the six-degree-of-freedom motion information of the platform can be settled according to the direction and speed of seawater movement.

[0045] In one embodiment, a predictive control technology based on a floating platform model is used to achieve the effect of optimal control of platform vibration, wherein the model of the floating platform is a six-degree-of-freedom motion model, and the controller is an optimal predictive controller based on the six-degree-of-freedom model.

[0046] In one embodiment, the optimal controller is proposed to solve the delay problem of control action transmission and execution according to the optimal control theory. Specifically, the time series large model can predict the future motion information of the platform, and the optimal control theory can establish the optimization target according to the future motion information of the platform and the delay limit of the control system. Solving this optimization problem can obtain the current optimal control action, and then executing this action can achieve the effect of suppressing the vibration of the platform.

[0047] In one embodiment, an adaptive control method is combined with a model-based predictive controller to enhance the robustness of the controller to model changes.

[0048] In one embodiment, adaptive system identification technology is used to adjust system parameters in real time according to the actual input and output of the floating platform, thereby achieving the purpose of online model update. The updated model is then used to adjust the parameters of the model predictive controller to reduce its control error, so that the system can better track the desired trajectory. The designed controller can adapt to model uncertainties and external disturbances, improving the robustness of the system.

[0049] In a specific embodiment, in the preferred implementation of the present application, it is considered that the existing floating platform vibration control system does not include platform motion prediction technology. Therefore, when the surrounding fluid environment changes drastically (such as wind speed, wave speed, wave height), the system cannot respond quickly to stabilize the platform. The present application proposes a motion prediction technology based on a time series large model, and the time series large model can predict the six-degree-of-freedom motion of the platform in the short and medium term based on the historical state information of the platform. The state of the platform includes wind speed information, wave information, tidal current information, etc. around the platform. The vibration of the floating platform is mainly affected by the movement of seawater. That is, the external force on the floating platform is mainly the thrust exerted by the movement of seawater, and the thrust of different directions and intensities at different positions causes the vibration of the floating platform. According to the principle of fluid mechanics, the present application uses the Navier-Stokes formula to describe the movement of seawater. According to the Navier-Stokes formula, the movement of seawater is generated by the coupling of tidal motion and wave motion dragged by wind. Therefore, the present application designs a time series large model based on this principle to predict the movement of seawater. The information input to the time series model is the historical wind speed, wave speed, wave height, tidal current speed, etc. around the platform, and the output is the direction and speed of seawater movement in the short and medium term. Finally, the platform's six-degree-of-freedom motion information can be calculated based on the direction and speed of seawater movement.

[0050] In a specific embodiment, the existing active control technology only senses the current state of the platform and applies control actions to reduce the current vibration, without considering the impact of the control action on the future, nor considering the delay in the transmission and execution of the control action, so the control effect needs to be improved. The present application uses a predictive control technology based on a floating platform model to achieve the effect of optimal control of platform vibration. The model of the floating platform is a six-degree-of-freedom motion model, and the controller is an optimal predictive controller based on the six-degree-of-freedom model. In order to solve the transmission and delay problems of control actions and enhance the adaptability of the control system to drastic changes in the environment, the present application proposes to use an optimal controller to solve this problem based on the optimal control theory. Specifically, the large time series model can predict the motion information of the future platform, and the optimal control theory can establish an optimization target based on the future motion information of the platform and the delay limit of the control system. Solving this optimization problem can obtain the current optimal control action, and then controlling the active tuned damper to perform this action can achieve the effect of suppressing the vibration of the platform.

[0051] In a specific embodiment, the existing active control technology has high requirements for the accuracy of the system model. Therefore, when the model parameters change (for example, component damage or aging), the control system has low adaptability to this change, resulting in reduced control system performance. The present application combines an adaptive control method with a model-based predictive controller to enhance the robustness of the controller to model changes. Adaptive system identification technology can adjust system parameters in real time according to the actual input and output of the floating platform, thereby achieving the purpose of updating the model online. The updated model is then used to adjust the parameters of the model predictive controller to reduce its control error, so that the system can better track the desired trajectory. Therefore, combining adaptive system identification technology with model-based predictive control technology can enable the designed controller to adapt to model uncertainties and external disturbances, thereby improving the robustness of the system.

[0052] It should be noted that, although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc. In addition, it is also easy to understand that these steps may be, for example, executed synchronously or asynchronously in multiple modules / processes / threads.

[0053] Furthermore, in this example implementation, a motion control system for an offshore floating platform based on a time series large model is also provided. The motion control system for an offshore floating platform based on a time series large model may include a state monitoring and identification module, a motion prediction module, and a model prediction control module. Among them: The state supervision and identification module is used to construct a time series big model, train the model parameters according to the historical motion information to obtain the identified time series big model, and design the model prediction controller according to the identified time series big model; A motion prediction module is used to predict future motion information based on a large temporal model and real-time motion information; The model predictive control module is used to generate and execute control actions based on the model predictive controller and future motion information to achieve the purpose of vibration suppression of the floating platform.

[0054] Specifically, the structural diagram of the vibration suppression system for the floating platform of an offshore wind turbine generator in this embodiment is as follows: Figure 3 As shown in Figure 1, it is mainly composed of three parts: system state monitoring and identification module, motion prediction module, and model prediction control module. The system state monitoring and identification module can use the installed sensors to monitor the motion information of the system in real time, identify the parameters of the model based on the motion information, and then update the model in time to reduce the uncertainty of the model caused by various reasons. The flowchart of updating the model is shown in Figure 1. Figure 4 As shown in the figure. The motion prediction module is responsible for predicting future motion information based on the historical motion information measured and recorded by the system state supervision module, thereby providing a state trajectory for designing the optimal controller. This part mainly includes a large time series model based on deep learning, that is, using the powerful learning ability of the deep learning model to accurately predict the future short-term environmental state and provide a basis for decision-making. The model predictive control module generates control actions based on the environmental state predicted by the motion prediction module using the optimal control method to achieve the purpose of suppressing the vibration of the floating platform.

[0055] Through the above-mentioned motion control method and device for offshore floating platforms based on a large time series model, a time series prediction module is added to the floating platform control system; the large time series model technology can predict the medium- and short-term platform motion in real time, thereby providing a more accurate control target for the control system, that is, maximizing the suppression of platform vibration. The use of a model-based predictive controller not only has higher adaptability to changes in the external state of the platform, solving the problem of control action transmission and execution delay, but also takes into account the complex nonlinear characteristics of the floating platform, so that the control system has higher robustness. When the platform parameters change due to external factors, the present application uses adaptive control technology to monitor the output of the system in real time, and adjust the parameters of the controller online according to the error, so that the controller can quickly adapt to changes in the model.

[0056] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0057] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of a module or unit described above can be further divided into multiple modules or units for concretization. The components displayed as modules or units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0058] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, and when the program is included in a processor and executed, the steps of the motion control method for an offshore floating platform based on a time-series large model described in any of the above embodiments can be implemented. In some possible implementations, various aspects of the present application can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present application described in the above-mentioned motion control method for an offshore floating platform based on a time-series large model section of this specification.

[0059] refer to Figure 5 As shown, a program product 300 for implementing the above method according to an embodiment of the present application is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0060] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0061] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0062] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0063] In an exemplary embodiment of the present disclosure, an electronic device is also provided, which may include a processor and a memory for storing executable instructions of the processor. The processor is configured to execute the steps of the motion control method of an offshore floating platform based on a time series large model in any of the above embodiments by executing the executable instructions.

[0064] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0065] Refer to the following Figure 6 The electronic device 600 according to this embodiment of the present application is described. Figure 6 The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0066] like Figure 6 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0067] The storage unit stores a program code, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present application described in the motion control method of an offshore floating platform based on a time series large model in the above-mentioned specification. For example, the processing unit 610 can execute the following steps: Figure 1 Follow the steps shown in .

[0068] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0069] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0070] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0071] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 650. In addition, the electronic device 600 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 through a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0072] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server or a network device, etc.) to execute the above-mentioned motion control method of the offshore floating platform based on the timing large model according to the implementation of the present disclosure.

[0073] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A motion control method for an offshore floating platform based on a time series large model, characterized in that: The method includes: Construct a time series big model, train the model parameters according to the historical motion information to obtain the identified time series big model, and design a model prediction controller according to the identified time series big model; Predict future motion information based on the time series big model and real-time motion information; Based on the model predictive controller and future motion information, control actions are generated and executed to achieve the purpose of vibration suppression of the floating platform.

2. According to claim 1, the motion control method of an offshore floating platform based on a time series large model is characterized in that: The steps of constructing a time series large model and training model parameters according to real-time motion information to obtain an identified time series large model include: Get the time series model; Using sensors on the floating platform to obtain real-time motion information in real time; wherein the real-time motion information at least includes wind speed, wave speed, wave height and tidal current speed; Based on the adaptive system identification method, the real-time motion information is input into the time series model for inference to obtain the current seawater movement direction and speed; The six-degree-of-freedom motion information of the floating platform is obtained according to the direction and speed of seawater movement; The model parameters are updated according to the six-degree-of-freedom motion information of the floating platform until convergence to obtain an identified time series large model.

3. The motion control method of an offshore floating platform based on a time series large model according to claim 2 is characterized in that: The steps of designing a model predictive controller based on the identification time series large model include: Determine the prediction time domain and control time domain; Construct the cost function based on the identified large time series model, prediction time domain and control time domain; Identify constraints; Design a model predictive controller based on the cost function and constraints.

4. The motion control method of an offshore floating platform based on a time series large model according to claim 1 is characterized in that: The steps of predicting future motion information based on the time series big model and real-time motion information include: Acquire real-time motion information, and perform filtering, calibration and conversion processing on the real-time motion information; The processed real-time motion information is input into the time series large model for processing to obtain future motion information.

5. The motion control method of an offshore floating platform based on a time series large model according to claim 4 is characterized in that: The steps of generating and executing control actions based on the model predictive controller and future motion information to achieve the purpose of vibration suppression of the floating platform include: Deploying the time series big model and the model predictive controller using a programmable logic controller to connect the time series big model and the model predictive controller; Use model predictive controller to solve future motion information to obtain optimal control actions; The floating platform executes optimal control actions to achieve the purpose of vibration suppression of the floating platform.

6. The motion control method of an offshore floating platform based on a time series large model according to claim 1 is characterized in that: The method further includes: Obtain status information of the floating platform; Online system parameter identification and controller parameter recalibration are performed based on the status information of the floating platform.

7. A motion control system for an offshore floating platform based on a time series large model, characterized in that: The system includes: The state supervision and identification module is used to construct a time series big model, train the model parameters according to the historical motion information to obtain the identified time series big model, and design the model prediction controller according to the identified time series big model; A motion prediction module is used to predict future motion information based on a large temporal model and real-time motion information; The model predictive control module is used to generate and execute control actions based on the model predictive controller and future motion information to achieve the purpose of vibration suppression of the floating platform.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the motion control method for an offshore floating platform based on a time-series large model as described in any one of claims 1 to 7 are implemented.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the steps of the motion control method of an offshore floating platform based on a time-series large model according to any one of claims 1 to 7 by executing the executable instructions.

Images