Floating photovoltaic platform ballast water and mooring tension cooperative control method and device

Abstract

The application provides a method and device for coordinated control of ballast water and mooring tension of a floating photovoltaic platform. The method obtains mooring tension data, attitude data and environmental data of the floating photovoltaic platform through a monitoring module; determines a current distribution state of mooring load and a change trend of the mooring load in a future period based on the mooring tension data and the environmental data; processes an optimization problem of a future total mooring load determined by the current distribution state and the change trend as an optimization objective under the constraint condition that the attitude data does not exceed a safe range, to obtain a water quantity adjustment scheme of each ballast water tank; and controls a ballast adjusting mechanism to adjust ballast water according to a control instruction corresponding to the water quantity adjustment scheme. The method overcomes the hysteresis of the existing passive ballast control and fundamentally optimizes the dynamic stability and safety of the platform.

Description

Technical Field

[0001] This application relates to the field of marine engineering technology, and more specifically, to a method and device for coordinated control of ballast water and mooring tension of a floating photovoltaic platform. Background Technology

[0002] Floating photovoltaic (PV) platforms typically consist of a floating platform, topside PV modules, mooring and anchoring systems, and ballast systems. Standard construction processes include platform fabrication, topside installation, sea transport, positioning and installation, anchoring, and ballast application. "Balancing" refers to increasing the platform's initial stability by applying ballast (such as gravity ballast or ballast water).

[0003] In existing technologies, platform ballast configurations are mostly one-time static counterweights applied during the initial installation phase, or simple feedback adjustments based solely on the platform's tilt angle. This passive or lagging control method cannot effectively address the dynamic redistribution of mooring tension caused by complex marine environments (wind, waves, currents). Its drawbacks include: when the environmental load on one side of the anchor chain remains consistently high, it not only accelerates fatigue damage to the anchor chain and its connecting structure, posing a risk of breakage, but may also increase the overall overturning moment of the platform, affecting the photovoltaic panel's power generation efficiency and structural safety. Existing technologies lack a collaborative control method capable of predicting tension change trends and actively and precisely adjusting ballast based on the platform's overall mechanical model, making it difficult to achieve optimal dynamic stability of the platform throughout its entire lifespan. Summary of the Invention

[0004] The purpose of this application is to provide a method and apparatus for coordinated control of ballast water and mooring tension of a floating photovoltaic platform, so as to overcome the lag of existing passive ballast control and fundamentally optimize the dynamic stability and safety of the platform.

[0005] Firstly, a method for coordinated control of ballast water and mooring tension of a floating photovoltaic platform is provided, applied to a controller on the floating photovoltaic platform. The floating photovoltaic platform also includes multiple ballast water tanks, a ballast adjustment mechanism, and a monitoring module. The method may include: The monitoring module acquires mooring tension data, attitude data, and environmental data of the floating photovoltaic platform. Based on the mooring tension data and the environmental data, the current distribution of mooring load and the trend of mooring load change in the future are determined. With the constraint that the attitude data does not exceed the safe range, the optimization problem with the future total mooring load determined by the current distribution state and the trend of change as the optimization objective is to be processed, and the water volume adjustment scheme of each ballast tank is obtained. According to the control instructions corresponding to the water volume adjustment scheme, the ballast adjustment mechanism is controlled to allocate ballast water.

[0006] In one possible implementation, based on the mooring tension data and the environmental data, the current distribution of mooring loads and the trend of mooring load changes over future periods are determined, including: The current distribution of mooring loads is determined based on the mooring tension data; Based on the current distribution status and the environmental data, the trend of the mooring load in the future period is predicted.

[0007] In one possible implementation, determining the current distribution of mooring loads based on the mooring tension data includes: The acquired mooring tension data is filtered in real time to separate the tension trend term, which characterizes the slowly changing environmental load, and the high-frequency fluctuation term caused by instantaneous waves. Based on the tension trend term, calculate the average tension and standard deviation of all anchor chains in the current sampling period; The average tension and the standard deviation of tension are used as statistical features to quantify the current distribution of mooring loads.

[0008] In one possible implementation, based on the current distribution state and the environmental data, predicting the changing trend of the mooring load over a future period includes: The environmental data is fused with the key features in the current distribution state to construct a multi-dimensional feature vector; wherein, the environmental data includes at least the predicted wind speed, wind direction angle, significant wave height and wave direction in the future time period, and the key features in the current distribution state include at least the current value of each anchor chain tension trend term and the standard deviation representing the tension; The multidimensional feature vector is input into a prediction model; the prediction model is a trained machine learning model or a parameterized physical model, which performs a forward calculation and outputs a change in each anchor chain tension trend term relative to the current value at the end of the future time period.

[0009] In one possible implementation, the prediction model is a physical model built based on the platform's hydrodynamic characteristics, or a machine learning model trained based on historical monitoring data.

[0010] In one possible implementation, the attitude data includes real-time draft and tilt angle; With the constraint that the attitude data does not exceed the safe range, an optimization problem is solved with the future total mooring load, determined by the current distribution state and its changing trend, as the optimization objective. This yields water volume adjustment schemes for each ballast tank, including: Based on the total future mooring load, an objective function is constructed with the core objective of minimizing the variance among the predicted total tension of all anchor chains. This objective function is used to quantitatively characterize the distribution balance of the mooring load. Based on the real-time draft and tilt angle in the attitude data, and combined with the preset platform safe operating range, a set of inequality constraints are defined. The constraints are used to ensure that the optimized water volume adjustment scheme will not cause the platform attitude to exceed the safe boundary. The configured control model is embedded into the optimization problem to establish the mathematical relationship between the water volume adjustment vector of the ballast tank and the objective function and constraints, and to calculate the changes in attitude data and mooring tension data under a specific water volume adjustment scheme. The mathematical programming problem, consisting of the objective function, constraints, and integrated system model, is solved iteratively to calculate a set of water volume adjustment amounts for each ballast tank that optimize the objective function and satisfy all constraints.

[0011] In one possible implementation, the control model is a Jacobian matrix model; The Jacobian matrix model is used to express the coupling relationship between the water volume change vector of the ballast tank, the platform attitude change vector, and the mooring tension change vector as a linear mapping relationship.

[0012] Secondly, a device for coordinated control of ballast water and mooring tension for a floating photovoltaic platform is provided. This device is applied to a controller on the floating photovoltaic platform, which also includes multiple ballast water tanks, a ballast adjustment mechanism, and a monitoring module. The device may include: The acquisition unit is used to acquire mooring tension data, attitude data, and environmental data of the floating photovoltaic platform through the monitoring module; The determining unit is used to determine the current distribution state of the mooring load and the changing trend of the mooring load in the future period based on the mooring tension data and the environmental data. The processing unit is used to process the optimization problem with the future total mooring load determined by the current distribution state and the trend of change as the optimization objective, under the constraint that the attitude data does not exceed the safe range, and to obtain the water volume adjustment scheme of each ballast tank. The control unit is used to control the ballast adjustment mechanism to allocate ballast water according to the control instructions corresponding to the water volume adjustment scheme.

[0013] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.

[0014] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.

[0015] The method and apparatus for coordinated control of ballast water and mooring tension of a floating photovoltaic platform provided in this application embodiment are applied to the controller of a floating photovoltaic platform. The floating photovoltaic platform also includes multiple ballast water tanks, a ballast adjustment mechanism, and a monitoring module. The method acquires mooring tension data, attitude data, and environmental data of the floating photovoltaic platform through the monitoring module. Based on the mooring tension data and the environmental data, it determines the current distribution state of the mooring load and the trend of its change over a future period. Using the constraint that the attitude data does not exceed a safe range, it processes the optimization problem with the future total mooring load determined by the current distribution state and the trend of change as the optimization objective, obtaining a water volume adjustment scheme for each ballast water tank. According to the control commands corresponding to the water volume adjustment schemes, it controls the ballast adjustment mechanism to allocate ballast water. This method overcomes the lag of existing passive ballast control, realizing an intelligent control method that can proactively predict the trend of mooring tension imbalance and perform precise and coordinated ballast adjustment based on the platform's spatial mechanical relationship, thereby fundamentally optimizing the platform's dynamic stability and safety. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a method for coordinated control of ballast water and mooring tension of a floating photovoltaic platform, provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a floating photovoltaic platform ballast water and mooring tension coordinated control device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by those skilled in the art. The words "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The words "comprising" or "including," etc., mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but do not exclude other elements or objects. The words "connected," "coupled," or "connected," etc., are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up," "down," "left," "right," etc., are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] The method for coordinated control of ballast water and mooring tension in a floating photovoltaic platform, provided in this application embodiment, is applied to a floating photovoltaic platform system. The system may include: (1) The main body of the floating photovoltaic platform is a floating structure (such as a rectangular or triangular float) that floats on the water surface and is used to support the photovoltaic module array.

[0020] (2) Multiple ballast water tanks are distributed inside or at the bottom of the platform body to store ballast water. For example, the platform can have four ballast water tanks arranged symmetrically, located at the front left, front right, rear left, and rear right positions respectively. Each tank has an independent inlet and outlet, and the volume can be designed according to the platform size (e.g., each tank has a capacity of 10-20 cubic meters).

[0021] (3) Ballast regulating mechanism, including submersible pumps or pipeline pumps and their control valves. For example, each water tank is equipped with a submersible pump, which is interconnected through a pipeline network. The pump flow rate is adjustable (e.g., 0.5-1.0 cubic meters / minute), and the start, stop and flow direction are precisely controlled by a controller.

[0022] (4) Monitoring module, including tension sensor group, attitude sensor group and environmental sensor group; wherein: Tension sensor arrays are installed at the connection points (e.g., mooring points) between each mooring anchor chain and the platform to measure the tension value F_i(t) of each anchor chain in real time (i=1,2,...,n, where n is the number of anchor chains, e.g., n=4). The sensor accuracy is typically ±1%FS, and the sampling frequency is ≥10Hz.

[0023] The attitude sensor array, including a draft sensor (such as a pressure sensor) and a tilt sensor (such as an inertial measurement unit, IMU), is installed near the platform's center of gravity to measure the real-time draft D(t) and roll / pitch angles θ_x(t) and θ_y(t). Accuracy requirements: draft ±0.01m, tilt ±0.1°.

[0024] The environmental sensor array, including anemometers and wave radar, measures parameters such as the platform's heading angle ψ(t), relative wind direction φ_wind(t), and significant wave height H_s(t). For example, the anemometer is installed on the top of the platform, and the wave radar is placed on the side of the platform.

[0025] (5) Controller, which is a programmable logic controller (PLC) or industrial computer, communicates with all sensors and actuators (e.g., via CAN bus or Ethernet). The controller has pre-stored control programs, initial values ​​of the Jacobian matrix J, platform safe operating ranges (e.g., draft safety range [D_min, D_max], tilt angle safety range θ_max), capacity limits of each ballast tank, and other parameters.

[0026] All the above components are connected by cables or pipes to form a complete monitoring-decision-execution closed-loop system. The controller, as the core, processes sensor data in real time, generates control commands, and drives the ballast regulating mechanism.

[0027] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0028] Figure 1 This is a flowchart illustrating a method for coordinated control of ballast water and mooring tension in a floating photovoltaic platform, as provided in an embodiment of this application. Figure 1 As shown, the method may include: Step S110: Obtain mooring tension data, attitude data, and environmental data of the floating photovoltaic platform through the monitoring module.

[0029] After the system starts, the controller initializes and loads preset parameters: the initial value of the Jacobian matrix J (determined through numerical simulation or experiment), the safety range (e.g., D_min=1.0m, D_max=2.0m, θ_max=5°), and the optimization algorithm parameters (e.g., the tolerance error of quadratic programming).

[0030] In practice, the following data is collected synchronously through the monitoring module: Read the instantaneous tension F_i(t) of each anchor chain from the tension sensor group (for example, the readings of the four anchor chains are: F_1=110kN, F_2=105kN, F_3=95kN, F_4=100kN).

[0031] Obtain draft D(t) (e.g., 1.5m) and tilt angles θ_x(t) and θ_y(t) (e.g., tilt θ_x = 1.0°) from the attitude sensor.

[0032] Environmental data are obtained from environmental sensors: wind angle ψ(t) (e.g., 30°), relative wind direction φ_wind(t) (e.g., 45°), significant wave height H_s(t) (e.g., 1.5m), and wave direction.

[0033] Step S120: Based on mooring tension data and environmental data, determine the current distribution of mooring load and the trend of mooring load change in the future period.

[0034] Step 1: Determine the current distribution of mooring loads based on mooring tension data, including: The acquired mooring tension data is filtered in real time to separate the tension trend term, which characterizes the slowly varying environmental load, and the high-frequency fluctuation term caused by instantaneous waves. Specifically, the collected tension data F_i(t) can be filtered in real time to separate the tension trend term and the high-frequency fluctuation term. For example, a Kalman filter can be used to filter out the high-frequency components of waves with a period of less than 10 seconds, outputting a smooth tension trend term F_i,trend(t) (after filtering, F_1,trend=108kN, F_2,trend=103kN, F_3,trend=97kN, F_4,trend=99kN). Assuming that the original tension F_1(t) fluctuates between 105-115kN within 10 seconds (due to wave impact), and after filtering, F_1,trend stabilizes at 108kN, it reflects the influence of slowly varying wind load. This filtering process eliminates high-frequency noise interference, allowing subsequent decisions to be based on stable trend signals and improving control accuracy (such as avoiding false triggering of control due to a single wave peak).

[0035] Based on the tension trend term, the average tension and standard deviation of all anchor chains within the current sampling period are calculated. The average tension and standard deviation are used as statistical features to quantify the current distribution of mooring loads. Specifically, based on the tension trend term F_i,trend(t), the average tension F_avg and standard deviation σ of all anchor chains are calculated. For example: F_avg = (108 + 103 + 97 + 99) / 4 = 101.75 kN. Using F_avg and σ as statistical features, the current distribution state is quantified: a small σ value indicates a balanced load, and a large σ value indicates an imbalance (e.g., in this example, σ=4.5kN indicates a slight imbalance).

[0036] Furthermore, a dynamic imbalance judgment threshold can be preset = k × F_avg (where k is a proportionality coefficient). If k = 0.05, then the dynamic imbalance judgment threshold = 0.05 × 101.75 ≈ 5.09 kN. Subsequent prediction and optimization will only be triggered when σ continuously exceeds this dynamic imbalance judgment threshold for a preset duration (e.g., 5 minutes). For example, if σ = 4.5 kN < 5.09 kN, no trigger will be given; if σ is > 5.09 kN for 5 consecutive minutes, then a trigger will be given. If the overall load on the platform increases (F_avg = 200 kN), this threshold will be automatically adjusted to 10 kN to avoid false triggering under high load.

[0037] This dynamic threshold adapts to different load levels, avoiding under-load false alarms or high-load false alarms, reducing unnecessary computational energy consumption, and improving economic efficiency.

[0038] Step 2: Based on the current distribution status and environmental data, predict the changing trend of mooring load in the future period.

[0039] By fusing environmental data with key features of the current distribution state, a multidimensional feature vector is constructed. The environmental data includes at least the predicted wind speed, wind direction angle, significant wave height, and wave direction for the future period. The key features of the current distribution state include at least the current value of each anchor chain tension trend term and the standard deviation representing the tension. For example, the multidimensional feature vector could be: [Predicted wind speed = 15 m / s, wind direction angle = 45°, wave height = 1.5 m, F_1, trend = 108 kN, ..., σ = 4.5 kN].

[0040] A multidimensional feature vector is input into a prediction model. The prediction model is a trained machine learning model or a parametric physical model that performs a forward computation and outputs a change ΔF_i,predicted of the anchor chain tension trend term relative to the current value at the end of a future time period (e.g., 5 minutes). For example, the model predicts an increase in anchor chain tension on the windward side: ΔF_1,predicted=+8kN, ΔF_2,predicted=+5kN, ΔF_3,predicted=-2kN, ΔF_4,predicted=-1kN.

[0041] The prediction model is either a physical model built based on the platform's hydrodynamic characteristics or a machine learning model trained based on historical monitoring data.

[0042] Furthermore, the change ΔF_i, predicted, which is lower than the output, can be used for physical plausibility verification: The change ΔF_i,predicted is compared with a preset reasonable physical range (such as the maximum allowable change of a single anchor chain ±15kN); where the reasonable physical range is the maximum allowable tension change range of a single anchor chain per cycle based on the anchor chain strength and platform motion performance; if the change exceeds this range, it is corrected to the range, that is, the preset boundary value is used for amplitude limiting.

[0043] For example, if ΔF_1,predicted=+20kN exceeds the maximum allowable variation range of a single anchor chain (±15kN), then the amplitude will be limited to +15kN.

[0044] In some embodiments, if the platform experiences an increase in the quality of marine organism attachment, leading to a gradual increase in model prediction bias, online correction can progressively correct the error. In this case, the predicted value ΔF_i, predicted_prev (e.g., ΔF_1, predicted_prev = +6kN) from the previous period and the actual change ΔF_1, actual = +7kN can be recorded, and the deviation between them can be calculated as +1kN.

[0045] The recursive least squares method is used to fine-tune the parameters of the prediction model (such as the weights of the LSTM) based on the deviation value.

[0046] Step S130: With the attitude data not exceeding the safe range as a constraint, the optimization problem with the future total mooring load determined by the current distribution state and the predicted change trend as the optimization objective is processed to obtain the water volume adjustment scheme for each ballast tank.

[0047] The attitude data includes real-time draft and inclination. The control model is a Jacobian matrix model; the Jacobian matrix model is used to express the coupling relationship between the ballast tank water volume change vector, the platform attitude change vector, and the mooring tension change vector as a linear mapping relationship.

[0048] Based on the total future mooring load, an objective function is constructed with the core objective of minimizing the variance among the predicted total tension of all anchor chains. The objective function is used to quantitatively characterize the distribution balance of the mooring load. Based on the real-time draft and tilt angle in the attitude data, and combined with the preset safe operating range of the platform, a set of inequality constraints are defined. The constraints are used to ensure that the optimized water volume adjustment scheme will not cause the platform's attitude data to exceed the safe boundary. The control model is embedded into the optimization problem to establish the mathematical relationship between the water volume adjustment vector of the ballast tank, the objective function, and the constraints. The change in attitude data and mooring tension data under a specific water volume adjustment scheme is calculated using the control model. The mathematical programming problem consisting of the objective function, constraints, and integrated system model is solved iteratively to calculate a set of water volume adjustment amounts for each ballast tank that optimize the objective function and satisfy all constraints.

[0049] In specific implementation, the objective function is defined as follows: Minimize Var(F_total), where F_total = F_i,trend(t) + ΔF_i,predicted + ΔF_i,model; F_i,trend(t) represents the tension trend term of the i-th anchor chain at the current time t. It is obtained by real-time filtering of the slowly varying environmental load components (such as tension caused by continuous wind and steady-state flow) separated from the original tension data, removing high-frequency fluctuations caused by instantaneous waves. Physically, it reflects the current steady-state load level on the anchor chain. ΔF_i,predicted is the change in the tension trend term of the i-th anchor chain within the predicted future time period. It is calculated based on environmental data (such as predicted wind speed and wave height) and the current distribution state (such as current tension value and standard deviation) through a prediction model (such as a machine learning model or a physical model). Physically, it represents the tension increase or decrease trend caused by future environmental changes. ΔF_i,model is the model-calculated change in the tension of the i-th anchor chain caused by ballast water adjustment. It is calculated using a control model (such as the Jacobian matrix model) based on the impact of water volume adjustment schemes on tension. Physically, it reflects the active adjustment effect of ballast water adjustment on mooring tension. F_total is a key variable in the optimization objective, used to quantify the future total mooring load to achieve load balancing during the control process. F_total reflects a comprehensive consideration of the current state, predicted trends, and active control, ensuring the accuracy and foresight of the decision-making.

[0050] Define constraints such as: D_min ≤ D(t) + ΔD ≤ D_max, |θ(t) + Δθ| ≤ θ_max. Where D_min is the minimum safe draft of the platform; D_max is the maximum safe draft of the platform; D(t) is the current real-time draft; ΔD is the change in draft caused by ballast water adjustment. θ(t) is the current real-time inclination angle; Δθ is the change in inclination angle caused by ballast water adjustment; θmax is the maximum safe inclination angle of the platform.

[0051] Solution: Embed the Jacobian matrix model into the optimization problem: [ΔF] = J·[ΔV], where J is a preset Jacobian matrix (e.g., determined through CFD simulation), and ΔV is the water volume adjustment vector. For example, the element J_11 of the J matrix represents the influence coefficient of the unit water volume change in tank 1 on the tension of anchor chain 1 (e.g., J_11 = 0.5 kN / m³). Iteratively solve the problem using a numerical optimization algorithm (e.g., Sequential Quadratic Programming, SQP) to calculate a set of water volume adjustment amounts for each ballast tank that optimizes the objective function and satisfies all constraints.

[0052] Furthermore, during the solution process, it is monitored in real time whether intermediate solutions lead to excessive water volume in the tanks. Intermediate solutions are the temporary water volume adjustment vectors (i.e., temporary ΔV) calculated at each step of the numerical optimization algorithm during its iterative solution process. For example, if the intermediate solution requires 5 cubic meters of water to be injected into tank 2, but its remaining capacity is only 3 cubic meters, then ΔV_2 is fixed at +3 cubic meters, and the optimization problem is reconstructed to solve for the adjustment amounts of other tanks. This boundary handling ensures that feasible solutions can still be found under hardware constraints, improving solution efficiency and system robustness.

[0053] The final optimal water volume adjustment scheme can be calculated as follows: ΔV_1 = -2.5 cubic meters (drainage of compartment 1), ΔV_3 = +1.8 cubic meters (water injection of compartment 3), ΔV_2 = ΔV_4 = 0.

[0054] Step S140: Control the ballast regulating mechanism to allocate ballast water according to the control command corresponding to the water volume adjustment plan.

[0055] Based on the water volume adjustment plan and the pre-stored pump-tank mapping table, control commands are generated. For example: Command 1 (Pump 1 starts, flow direction: outward, flow rate = 0.5). (Duration = 5 minutes); Command 2 (Pump 3 starts, flow direction: inward, flow rate = 0.36) (Duration = 5 minutes).

[0056] The command is sent to the ballast regulating mechanism to control the ballast water allocation.

[0057] This application introduces a predictive feedforward model based on environmental disturbances and a ballast-tension space Jacobian mapping model, combined with a constrained optimization algorithm, to achieve active suppression and global collaborative optimization control of the mooring tension imbalance trend of floating photovoltaic platforms, significantly improving the dynamic stability, safety and durability of the platform under complex time-varying sea conditions.

[0058] Corresponding to the above method, this application also provides a device for coordinated control of ballast water and mooring tension of a floating photovoltaic platform, such as... Figure 2 As shown, the device includes: The acquisition unit 210 is used to acquire mooring tension data, attitude data and environmental data of the floating photovoltaic platform through the monitoring module; The determining unit 220 is used to determine the current distribution state of the mooring load and the changing trend of the mooring load in the future period based on the mooring tension data and the environmental data. The processing unit 230 is used to process the optimization problem with the future total mooring load determined by the current distribution state and the trend of change as the optimization objective, with the attitude data not exceeding the safe range as the constraint, and to obtain the water volume adjustment scheme of each ballast tank. The control unit 240 is used to control the ballast adjustment mechanism to perform ballast water allocation according to the control instructions corresponding to the water volume adjustment scheme.

[0059] The functions of each functional unit in the floating photovoltaic platform ballast water and mooring tension coordinated control device provided in the above embodiments of this application can be realized through the above-described methods and steps. Therefore, the specific working process and beneficial effects of each unit in the floating photovoltaic platform ballast water and mooring tension coordinated control device provided in the embodiments of this application will not be repeated here.

[0060] This application also provides an electronic device, such as... Figure 3 As shown, it includes a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340.

[0061] Memory 330 is used to store computer programs; When the processor 310 executes the program stored in the memory 330, it performs the following steps: The monitoring module acquires mooring tension data, attitude data, and environmental data of the floating photovoltaic platform. Based on the mooring tension data and the environmental data, the current distribution of mooring load and the trend of mooring load change in the future are determined. With the constraint that the attitude data does not exceed the safe range, the optimization problem with the future total mooring load determined by the current distribution state and the trend of change as the optimization objective is to be processed, and the water volume adjustment scheme of each ballast tank is obtained. According to the control instructions corresponding to the water volume adjustment scheme, the ballast adjustment mechanism is controlled to allocate ballast water.

[0062] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0063] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0064] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0065] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0066] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 1 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.

[0067] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform the ballast water and mooring tension coordinated control method for floating photovoltaic platforms as described in any of the above embodiments.

[0068] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the ballast water and mooring tension coordinated control method for floating photovoltaic platforms as described in any of the above embodiments.

[0069] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0071] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0073] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of this application.

[0074] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims in this application and their equivalents, then this application also intends to include these modifications and variations.

Claims

1. A method for coordinated control of ballast water and mooring tension in a floating photovoltaic platform, characterized in that, A controller applied to a floating photovoltaic platform, which also includes multiple ballast water tanks, a ballast adjustment mechanism, and a monitoring module, the method comprising: The monitoring module acquires mooring tension data, attitude data, and environmental data of the floating photovoltaic platform. Based on the mooring tension data and the environmental data, the current distribution of mooring load and the trend of mooring load change in the future are determined. With the constraint that the attitude data does not exceed the safe range, the optimization problem with the future total mooring load determined by the current distribution state and the trend of change as the optimization objective is to be processed, and the water volume adjustment scheme of each ballast tank is obtained. According to the control instructions corresponding to the water volume adjustment scheme, the ballast adjustment mechanism is controlled to allocate ballast water.

2. The method as described in claim 1, characterized in that, Based on the mooring tension data and the environmental data, determine the current distribution of mooring loads and their changing trends over future periods, including: The current distribution of mooring loads is determined based on the mooring tension data; Based on the current distribution status and the environmental data, the trend of the mooring load in the future period is predicted.

3. The method as described in claim 2, characterized in that, Determining the current distribution of mooring loads based on the mooring tension data includes: The acquired mooring tension data is filtered in real time to separate the tension trend term, which characterizes the slowly changing environmental load, and the high-frequency fluctuation term caused by instantaneous waves. Based on the tension trend term, calculate the average tension and standard deviation of all anchor chains in the current sampling period; The average tension and the standard deviation of tension are used as statistical features to quantify the current distribution of mooring loads.

4. The method as described in claim 2, characterized in that, Based on the current distribution status and the environmental data, predict the changing trend of the mooring load in the future, including: The environmental data is fused with the key features in the current distribution state to construct a multi-dimensional feature vector; wherein, the environmental data includes at least the predicted wind speed, wind direction angle, significant wave height and wave direction in the future time period, and the key features in the current distribution state include at least the current value of each anchor chain tension trend term and the standard deviation representing the tension; The multidimensional feature vector is input into a prediction model; the prediction model is a trained machine learning model or a parameterized physical model, which performs a forward calculation and outputs a change in each anchor chain tension trend term relative to the current value at the end of the future time period.

5. The method as described in claim 4, characterized in that, The prediction model is either a physical model built based on the platform's hydrodynamic characteristics or a machine learning model trained based on historical monitoring data.

6. The method as described in claim 1, characterized in that, The attitude data includes real-time draft and tilt angle; With the constraint that the attitude data does not exceed the safe range, an optimization problem is solved with the future total mooring load, determined by the current distribution state and its changing trend, as the optimization objective. This yields water volume adjustment schemes for each ballast tank, including: Based on the total future mooring load, an objective function is constructed with the core objective of minimizing the variance among the predicted total tension of all anchor chains. This objective function is used to quantitatively characterize the distribution balance of the mooring load. Based on the real-time draft and tilt angle in the attitude data, and combined with the preset platform safe operating range, a set of inequality constraints are defined. The constraints are used to ensure that the optimized water volume adjustment scheme will not cause the platform attitude to exceed the safe boundary. The configured control model is embedded into the optimization problem to establish the mathematical relationship between the water volume adjustment vector of the ballast tank and the objective function and constraints, and to calculate the changes in attitude data and mooring tension data under a specific water volume adjustment scheme. The mathematical programming problem, consisting of the objective function, constraints, and integrated system model, is solved iteratively to calculate a set of water volume adjustment amounts for each ballast tank that optimize the objective function and satisfy all constraints.

7. The method as described in claim 6, characterized in that, The control model is a Jacobian matrix model; The Jacobian matrix model is used to express the coupling relationship between the water volume change vector of the ballast tank, the platform attitude change vector, and the mooring tension change vector as a linear mapping relationship.

8. A device for coordinated control of ballast water and mooring tension of a floating photovoltaic platform, characterized in that, A controller for use on a floating photovoltaic platform, which also includes multiple ballast water tanks, a ballast adjustment mechanism, and a monitoring module, the device comprising: The acquisition unit is used to acquire mooring tension data, attitude data, and environmental data of the floating photovoltaic platform through the monitoring module; The determining unit is used to determine the current distribution state of the mooring load and the changing trend of the mooring load in the future period based on the mooring tension data and the environmental data. The processing unit is used to process the optimization problem with the future total mooring load determined by the current distribution state and the trend of change as the optimization objective, under the constraint that the attitude data does not exceed the safe range, and to obtain the water volume adjustment scheme of each ballast tank. The control unit is used to control the ballast adjustment mechanism to allocate ballast water according to the control instructions corresponding to the water volume adjustment scheme.

9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images