Floating attitude adjusting and optimizing system for floating type offshore wind power equipment set

Abstract

The invention provides a floating attitude adjustment and optimization system for a floating type offshore wind power equipment group, and relates to the technical field of offshore wind power equipment, and the system comprises a sensing monitoring module which collects an equipment operation attitude parameter set and a marine environment data set in real time; the information is transmitted to the central control unit through the data transmission module, and is analyzed and processed by the equipment attitude prediction module to generate equipment attitude prediction information; the adjustment strategy generation module obtains a target attitude adjustment strategy based on the equipment attitude prediction information and the construction information of the buoyancy attitude adjustment device; the adjustment parameter generation module obtains attitude dynamic adjustment parameters; and the attitude adjustment execution module performs multi-point attitude adjustment and dynamic feedback optimization on the equipment group. The technical problem that an existing floating type wind power equipment set lacks a flexible floating posture adjusting means and is difficult to cope with floating posture changes caused by a complex marine environment is solved, the operation stability of the equipment set is improved, and therefore the power generation efficiency is improved, and the service life of the equipment is prolonged.

Description

Technical Field

[0001] The present application relates to the technical field of offshore wind power equipment, and in particular to a floating posture adjustment and optimization system for a floating offshore wind power equipment group. Background Art

[0002] As one of the important forms of offshore wind energy development, floating wind turbines have shown great potential in deep sea areas far from the coastline, but they also face severe challenges brought by extreme marine environments. Due to the complex and changeable marine environment, floating offshore wind turbines are often affected by various factors such as waves, tides, and wind speed. The equipment is prone to unstable posture during long-term operation, resulting in reduced power generation efficiency and even threats to the structural safety of the equipment. Existing floating wind turbines usually rely on fixed structures or simple adjustment devices to maintain the posture of the equipment. When faced with severe weather and complex marine conditions, they cannot be adjusted in time, resulting in a lag in the adjustment of the equipment posture and prone to drift or tilt, which in turn increases the risk of equipment wear and failure, seriously affecting power generation efficiency and equipment life. Summary of the invention

[0003] The present application provides a floating attitude adjustment optimization system for a floating offshore wind power equipment group, which solves the technical problem that the existing floating wind power equipment group lacks flexible floating attitude adjustment means and is difficult to cope with the floating attitude changes caused by the complex marine environment, thereby affecting the stable operation of the floating wind power equipment group. The floating attitude of the floating wind power equipment group is dynamically adjusted to improve the operating stability of the equipment group, thereby improving the power generation efficiency and extending the service life of the equipment.

[0004] In view of the above problems, the present application provides a floating attitude adjustment optimization system for a floating offshore wind power equipment group, the system comprising: a sensor monitoring module, the sensor monitoring module is used to install a sensor monitoring group on the floating offshore wind power equipment group, and the sensor monitoring group is used to collect and obtain the equipment operation attitude parameter set and the marine environment data set in real time; a data transmission module, the data transmission module is used to wirelessly transmit the equipment operation attitude parameter set and the marine environment data set to a central control unit through an Internet of Things module; an equipment attitude prediction module, the equipment attitude prediction module is used by the central control unit to call the offshore risk equipment attitude prediction model to perform Analysis and processing to generate equipment posture prediction information; an adjustment strategy generation module, the adjustment strategy generation module is used to obtain the buoyancy posture adjustment device of the floating offshore wind power equipment group, and obtain the target posture adjustment strategy based on the equipment posture prediction information and the construction information of the buoyancy posture adjustment device; an adjustment parameter generation module, the adjustment parameter generation module is used to use the target posture adjustment strategy to adjust and analyze the equipment posture prediction information to obtain posture dynamic adjustment parameters; an attitude adjustment execution module, the attitude adjustment execution module is used for the buoyancy posture adjustment device to perform multi-point attitude adjustment and dynamic feedback optimization on the floating offshore wind power equipment group based on the attitude dynamic adjustment parameters.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] The sensor monitoring module installs a sensor monitoring group on the floating offshore wind power equipment group, and obtains the equipment operation attitude parameter set and the marine environment data set in real time through the sensor monitoring group, providing an accurate real-time data basis for subsequent attitude adjustment analysis. The data transmission module wirelessly transmits the equipment operation attitude parameter set and the marine environment data set to the central control unit through the Internet of Things module, realizing instant data transmission and ensuring the real-time and accuracy of the data source of the central control unit. The equipment attitude prediction module analyzes and processes the equipment operation attitude parameter set and the marine environment data set through the central control unit calling the offshore risk equipment attitude prediction model, predicts future attitude changes, generates equipment attitude prediction information, and provides a basis for the generation of attitude adjustment strategy. The adjustment strategy generation module obtains the buoyancy attitude adjustment device of the floating offshore wind power equipment group, obtains the target attitude adjustment strategy based on the equipment attitude prediction information and the structural information of the buoyancy attitude adjustment device, and ensures the scientificity and effectiveness of the adjustment measures. The adjustment parameter generation module uses the target attitude adjustment strategy to adjust and analyze the equipment attitude prediction information, and provides specific attitude dynamic adjustment parameters for the attitude adjustment execution module to achieve precise attitude control. The attitude adjustment execution module performs multi-point attitude adjustment and dynamic feedback optimization on the floating offshore wind power equipment group based on the attitude dynamic adjustment parameters through the buoyancy attitude adjustment device to ensure that the equipment maintains the best attitude in the marine environment.

[0007] In summary, this application integrates multiple modules such as sensor monitoring, data transmission, equipment attitude prediction, adjustment strategy generation, adjustment parameter generation and attitude adjustment execution, monitors the marine environment and equipment operating status in real time, quickly transmits data to the central control unit, uses the prediction model to analyze data and generate accurate attitude adjustment strategies, and combines dynamic feedback optimization to achieve dynamic and intelligent adjustment of the attitude of floating offshore wind power equipment groups. The system significantly improves the adaptability of floating offshore wind power equipment groups to the frequently changing marine environment, allowing the floating offshore wind power equipment groups to always maintain the best attitude under various marine environmental conditions, effectively reducing the risk of equipment failure, thereby improving the operating stability and power generation efficiency of the wind power equipment group, extending the service life of the equipment group, and further promoting the sustainable development of offshore wind power.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the structure of a floating attitude adjustment optimization system for a floating offshore wind power equipment group provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a flow chart of generating an offshore wind power equipment attitude prediction model in a floating attitude adjustment optimization system for a floating offshore wind power equipment group provided in an embodiment of the present application;

[0011] Figure 3 A schematic diagram of a flow chart of obtaining a target attitude adjustment strategy in a floating attitude adjustment optimization system for a floating offshore wind power equipment group provided in an embodiment of the present application.

[0012] Explanation of the reference numerals: sensor monitoring module 10 , data transmission module 20 , equipment posture prediction module 30 , adjustment strategy generation module 40 , adjustment parameter generation module 50 , posture adjustment execution module 60 . DETAILED DESCRIPTION

[0013] The embodiment of the present application provides a floating attitude adjustment optimization system for a floating offshore wind power equipment group, thereby solving the technical problem that the existing floating wind power equipment group lacks flexible floating attitude adjustment means and is difficult to cope with the floating attitude changes caused by the complex marine environment, which in turn affects the stable operation of the floating wind power equipment group. The embodiment of the present application achieves the technical effect of dynamically adjusting the floating attitude of the floating wind power equipment group to improve the operating stability of the equipment group, thereby improving the power generation efficiency and extending the service life of the equipment.

[0014] like Figure 1 As shown, the embodiment of the present application provides a floating attitude adjustment optimization system for a floating offshore wind power equipment group, the system comprising:

[0015] The sensor monitoring module 10 is used to install a sensor monitoring group on a floating offshore wind power equipment group, and to obtain a device operation attitude parameter set and a marine environment data set through the sensor monitoring group in real time.

[0016] Specifically, the sensor monitoring group is a group of sensors used to monitor the operating status of the equipment (such as tilt angle, position, speed, etc.) and external environment sensors (such as wind speed, wave height, tidal changes, etc.). These sensors include attitude sensors such as accelerometers, gyroscopes, magnetometers, pressure sensors, and environmental monitoring sensors such as anemometers, water level gauges, and thermometers. The equipment operation attitude parameter set refers to key indicators such as the equipment tilt angle, rotation angle, and up and down movement amplitude recorded by the attitude sensor, while the marine environment data set is data such as wind speed, wave period, and seawater temperature recorded by the environmental monitoring sensor to reflect the marine environment conditions around the equipment group.

[0017] First, various types of sensors are installed on floating offshore wind turbines to form a monitoring group. For example, accelerometers and gyroscopes can be used to detect the tilt and rotation status of the equipment, thereby generating the equipment's operating attitude parameters; anemometers are used to measure wind speed, while underwater pressure sensors can detect the height of waves and changes in water pressure. Through the collaborative work of these sensors, multiple dimensions of equipment operating status and detailed data on the surrounding marine environment can be obtained simultaneously. Various types of sensors complement each other, providing comprehensive information on the equipment and environment, ensuring that subsequent analysis and adjustment processes can be based on real-time and reliable data.

[0018] The data transmission module 20 is used to wirelessly transmit the device operation attitude parameter set and the marine environment data set to the central control unit through the Internet of Things module.

[0019] Specifically, the IoT module is a part of the data transmission module 20, which connects physical devices and sensors through the Internet to achieve wireless data transmission. The central control unit is used to receive, process and analyze the data from the sensors and generate subsequent control decisions. It can be a high-performance computer or cloud computing platform that can process a large amount of real-time data.

[0020] Floating offshore wind power equipment groups are usually located in sea areas far from the coast, and traditional wired transmission methods will be difficult to achieve. In this case, the data transmission module 20 uses the Internet of Things technology, such as 4G / 5G network or satellite communication, to transmit the equipment operation attitude parameter set and marine environment data set monitored by the sensor monitoring module 10 to the central control unit, providing real-time data support for the adjustment and decision-making of the central control unit. For example, the data transmission module 20 may use a satellite communication module to send the equipment's operating data to the central control system via a satellite. In offshore wind farms, cellular networks (such as 5G) may be used for high-speed wireless data transmission to ensure that the equipment attitude data and marine environment data collected by the sensors can be delivered in a timely manner.

[0021] The equipment posture prediction module 30 is used by the central control unit to call the offshore risk equipment posture prediction model to analyze and process the equipment operation posture parameter set and the marine environment data set to generate equipment posture prediction information.

[0022] Specifically, the offshore risk equipment attitude prediction model is a trained algorithm model used to predict the risks that floating offshore wind turbines may encounter and their future attitude changes, which is usually established based on historical data and physical principles. The equipment attitude prediction information is the specific result output by the model, which includes the expected tilt angle, swing amplitude and other attitude parameters of the equipment in the future.

[0023] First, load the latest equipment operation attitude parameter set and marine environment data set from the data pool, including the current tilt angle, wind speed, wave height, water flow, etc. Then, input these data into the pre-trained offshore risk equipment attitude prediction model. The model is trained with a large amount of historical data and uses advanced prediction algorithms such as neural networks, random forests or support vector machines to analyze the input data and output the possible attitude changes of the equipment in the future, that is, the equipment attitude prediction information. This information is used to guide the generation of attitude adjustment strategies to avoid affecting power generation efficiency or equipment safety due to unstable attitude.

[0024] The adjustment strategy generation module 40 is used to obtain the buoyancy attitude adjustment device of the floating offshore wind power equipment group, and obtain the target attitude adjustment strategy based on the equipment attitude prediction information and the construction information of the buoyancy attitude adjustment device.

[0025] Specifically, the buoyancy attitude adjustment device is a physical device used to adjust the attitude of the floating wind turbine group, and maintains the balance and stability of the wind turbine group by adjusting the buoyancy or ballast, such as an adjustable buoyancy device or a counterweight system. The target attitude adjustment strategy is a specific adjustment plan formulated based on the prediction information and the structural information of the buoyancy attitude adjustment device, which guides the equipment on how to adjust its buoyancy or attitude to cope with changes in the external environment and ensure the smooth operation of the equipment.

[0026] This module receives the device attitude prediction information from the attitude prediction module, which contains the attitude change trend of the device in the future. For example, the prediction may show that the device will tilt due to the increase of waves and wind speed in the next 30 minutes. Then, the adjustment strategy generation module 40 obtains the structural information of the buoyancy attitude adjustment device of the wind power equipment. This information includes the position, capacity, reaction time and operating limit of each adjustment element. For example, the size and position of the buoy, the water tank capacity of the ballast system, and the response time and adjustment range of these adjustment devices. Based on the device attitude prediction information and the structure of the adjustment device, the adjustment strategy generation module 40 determines the attitude adjustment strategy through a mathematical model or optimization algorithm, such as PID control, or a more complex adaptive control algorithm. The adjustment strategy includes increasing the buoyancy of the buoyancy device or adjusting the position of the counterweight system to reduce swaying and maintain the stability of the equipment. This strategy ensures that the floating offshore wind power equipment group can maintain a stable posture in a complex and changeable marine environment, avoid problems such as tilting and drifting, and ensure the efficient and safe operation of the equipment.

[0027] The adjustment parameter generation module 50 is used to adopt the target posture adjustment strategy to adjust and analyze the device posture prediction information to obtain posture dynamic adjustment parameters.

[0028] Specifically, the dynamic attitude adjustment parameters are specific control instructions or parameters, such as how much water needs to be injected or discharged, how to adjust the buoyancy of the float, or how to change the tilt angle of the equipment, etc., which directly guide the execution device to make adjustments. The adjustment parameter generation module 50 receives the target attitude adjustment strategy from the adjustment strategy generation module 40. These strategies usually exist in the form of high-level solutions, such as "If the tilt angle of the equipment exceeds 5 degrees, the ballast system needs to be adjusted to increase buoyancy." This strategy itself is an overall adjustment direction, but does not contain specific execution details. Next, the adjustment parameter generation module 50 calls the equipment attitude prediction information, that is, the possible attitude changes of the equipment in different sea conditions in the future. Combined with these prediction information, further analysis is performed on how to operate the buoyancy adjustment device.

[0029] For example, the forecast results show that the upcoming southeast wind will cause the equipment to tilt 10° to the east, and the rotation speed will exceed the safety threshold. The adjustment strategy generation module 40 immediately enters the working state, first determining that the left ballast water tank needs to be supplemented with about 200 tons of water to increase the weight to counter the wind; at the same time, it orders the west ballast water tank to discharge the same amount of water to reduce the burden and achieve left-right balance. In addition, in order to speed up the recovery process, the module will also mobilize the east propeller to work briefly to generate reverse torque to help the equipment correct its posture faster and ensure that it returns to the safe range before the wind strengthens.

[0030] In this way, the adjustment parameter generation module 50 converts the macro strategy into micro execution instructions, ensuring that the floating offshore wind power equipment can respond accurately and promptly to maintain stable operation when facing a complex marine environment.

[0031] The attitude adjustment execution module 60 is used for the buoyancy attitude adjustment device to perform multi-point attitude adjustment and dynamic feedback optimization on the floating offshore wind power equipment group based on the attitude dynamic adjustment parameters.

[0032] Specifically, the attitude adjustment execution module 60 receives the attitude dynamic adjustment parameters from the adjustment parameter generation module 50, and controls the buoyancy attitude adjustment device to act according to these adjustment parameters. The adjustment process will be carried out at multiple key points of the equipment at the same time. For floating offshore wind power equipment, there are usually multiple adjustment points, such as multiple buoys or multiple ballast water tanks. Each point needs to be adjusted individually or jointly according to different situations to maintain the overall attitude stability. For example, when changes in wind speed and wave height cause the front and left side of the equipment to tilt, the buoyancy attitude adjustment device needs to adjust the buoys or ballast water systems on the front and left sides at the same time to ensure the overall balance of the equipment.

[0033] While performing adjustments, the module monitors the device's attitude changes and adjustment effects in real time through the sensor monitoring group. If the adjustment operation does not achieve the expected effect, the system will immediately adjust the adjustment strategy. For example, if the device is still tilted too much after adjustment, the system will recalculate the required buoyancy or ballast adjustment and perform the correction operation again. This dynamic feedback mechanism enables the system to respond quickly to changing environmental conditions, ensuring the accuracy and continuous optimization of attitude adjustments.

[0034] Furthermore, the data transmission module 20 in the embodiment of the present application is also used to perform the following steps:

[0035] The ocean environment data set is subjected to sea condition analysis through the Internet of Things module to obtain data transmission sea condition information; the data transmission impact assessment is performed on the data transmission sea condition information to obtain a data transmission impact coefficient; a wireless transmission link set is acquired according to the Internet of Things module, and the data transmission impact coefficient is matched with the wireless transmission link set to obtain a target transmission link; the target transmission link is used to wirelessly transmit the device operation attitude parameter set and the ocean environment data set to the central control unit.

[0036] Specifically, data transmission sea condition information refers to a real-time assessment of the quality of the communication link based on the analysis of the marine environment data set, covering factors that affect the stability of wireless transmission, such as wind speed, waves, and electromagnetic interference. The data transmission impact assessment is to quantify and analyze the above sea condition information to obtain an assessment result of the degree of interference that data transmission may be subject to, which is specifically expressed as a data transmission impact coefficient. The higher the coefficient, the worse the transmission conditions. The wireless transmission link set refers to the set of all available wireless communication paths, including LoRa, NB-IoT, Wi-Fi, satellite links, etc. Each link has a different transmission distance, bandwidth, and anti-interference capability. The target transmission link is the most suitable communication path matched according to the data transmission impact coefficient and link characteristics to ensure that data can be transmitted stably and efficiently under the current sea conditions.

[0037] The data transmission module 20 first calls the Internet of Things module to analyze the marine environment data set, evaluates the complexity of the current sea conditions, and generates data transmission sea condition information. Then, the data transmission impact coefficient is calculated based on this information to quantify the challenges faced by data transmission under the current sea conditions. Subsequently, the module will select the link that best matches the current impact coefficient from the wireless transmission link set, that is, the target transmission link. The device operation attitude parameter set and the marine environment data set are wirelessly transmitted to the central control unit through the target transmission link to ensure that the data is transmitted in the best state. For example, when the sea conditions are bad, the wind speed and wave height may increase significantly, resulting in electromagnetic wave scattering and attenuation, and the data transmission impact coefficient at this time will be high. The data transmission module 20 will give priority to satellite links with strong anti-interference and long transmission distance as the target transmission link to ensure stable data transmission. On the contrary, when the sea conditions are relatively stable, the impact coefficient is low, and the module may choose a LoRa link with lower power consumption and faster transmission rate to achieve the dual goals of energy saving and efficient transmission.

[0038] Through this intelligent matching mechanism, the data transmission module 20 can ensure that data can be transmitted through the most suitable link under various sea conditions, thereby ensuring that the central control unit obtains real-time data.

[0039] Furthermore, the device posture prediction module 30 of the embodiment of the present application is also used to perform the following steps:

[0040] A floating offshore wind power equipment attitude database is acquired through data mining technology; the attitude data in the floating offshore wind power equipment attitude database is marked, and the marked floating offshore wind power equipment attitude database is used as model training sample information; deep network model training and verification optimization are performed based on the model training sample information to generate an offshore wind power equipment attitude prediction model; the offshore wind power equipment attitude prediction model is stored in the central control unit.

[0041] Specifically, the historical operating data of floating offshore wind power equipment is collected through data mining technology and stored in the floating offshore wind power equipment attitude database. The database records the operating status of the equipment under different environmental conditions, such as the tilt angle and floating status of the equipment under strong winds, big waves or normal weather. The data in the database is marked with attitude data, that is, each group of data is assigned a label. When the equipment is in different tilt states, it is marked as "normal", "slightly tilted", "severely tilted", etc. So that the model can better understand the operation of the equipment under different conditions in the subsequent training process.

[0042] The marked data is used as the model training sample information and input into the deep network model for training. The deep learning model learns the equipment's posture change rules under different environmental conditions through a large amount of historical data, and verifies the model's performance through data that is not involved in the training. The model parameters are adjusted according to the verification results to improve its prediction accuracy. After multiple rounds of training and optimization, the offshore wind power equipment posture prediction model is obtained, and the trained model is stored in the central control unit so that the central control unit can call the model in daily operation and monitor the equipment's operating posture in real time.

[0043] By training the offshore wind turbine equipment posture prediction model, the module can accurately predict the posture of wind turbine equipment in complex marine environments, thereby determining the adjustment strategy in advance and ensuring the operational stability of the wind turbine equipment group.

[0044] Further, such as Figure 2 As shown, the device posture prediction module 30 in the embodiment of the present application is also used to perform the following steps:

[0045] Based on the model training sample information, deep network model training is performed to obtain an initial equipment posture prediction model; performance verification is performed on the initial equipment posture prediction model to obtain model performance verification feedback data; loss analysis is performed on the model performance verification feedback data to obtain predicted loss data; performance optimization is performed on the initial equipment posture prediction model based on the predicted loss data to generate the offshore wind power equipment posture prediction model.

[0046] Specifically, first, based on the model training sample information, the initial device posture prediction model is trained through the deep learning framework. At this stage, the model continuously adjusts the weights and biases through the back-propagation algorithm to minimize the prediction error. Subsequently, the module uses an independent validation data set to perform performance tests on the model, collecting the model's prediction results on unseen data to evaluate its generalization ability. Based on the test results, the module generates model performance verification feedback data, including prediction accuracy, recall rate, F1 score and other indicators.

[0047] Next, we conduct an in-depth loss analysis on the feedback data of model performance verification, and identify the main sources of error in model prediction, such as prediction bias under certain environmental conditions, by drawing loss function curves, calculating mean square error (MSE) or root mean square error (RMSE), etc. Based on the analysis results, we optimize the performance of the initial device posture prediction model in a targeted manner, such as adjusting the network structure, introducing regularization terms, or changing optimizer parameters, so as to improve the prediction ability and robustness of the model.

[0048] For example, through loss analysis, it was found that the initial equipment attitude prediction model did not perform well under certain wind speed conditions. Through loss analysis, it was found that the model had insufficient training samples or insufficient feature extraction under these conditions. Therefore, relevant data was added, feature selection was optimized, or the network architecture was adjusted to improve the model's prediction ability under these environments. After multiple rounds of training and optimization, a highly accurate and generalizable offshore wind power equipment attitude prediction model was finally generated, which can effectively predict the equipment's attitude changes under various environmental conditions and provide accurate data support for subsequent attitude adjustment strategies.

[0049] Further, such as Figure 3 As shown, the adjustment strategy generation module 40 in the embodiment of the present application is also used to perform the following steps:

[0050] According to the structural information of the buoyancy attitude adjustment device, a posture adjustment strategy library is designed; based on the posture adjustment strategy library, the device posture prediction information is adjusted and predicted respectively to obtain multiple strategy adjustment effects; based on the multiple strategy adjustment effects, the posture adjustment strategy library is optimized to obtain the target posture adjustment strategy.

[0051] Specifically, first, the module designs an attitude adjustment strategy library based on the physical characteristics of the buoyancy attitude adjustment device, adjustable components, ballast water system capacity, and thruster performance. The strategy library stores a variety of possible adjustment schemes, such as the order and magnitude of ballast water filling and discharging, the start and stop timing and thrust size of the thruster, etc. Each scheme corresponds to the equipment attitude changes under different environmental conditions.

[0052] Next, the module matches the device posture prediction information obtained above with different adjustment schemes in the strategy library. For each adjustment strategy, the module simulates the device response under different strategies through numerical simulation and physical model simulation, and calculates multiple strategy adjustment effects. These effects include the device's posture recovery speed within a certain period of time, whether it has completely recovered to a stable state, and the energy consumption during the adjustment process.

[0053] Then, by comparing multiple adjustment effects, the execution cost, equipment response time, attitude stability index, etc. of the comprehensive evaluation strategy are evaluated through multi-objective optimization algorithms to determine the target attitude adjustment strategy that best suits the current prediction information and achieve optimal equipment attitude control.

[0054] The adjustment strategy generation module 40 designs and uses the attitude adjustment strategy library, combines the equipment's attitude prediction information, predicts and compares the effects of different adjustment strategies, and finally determines the adjustment plan that is most suitable for the current environmental conditions through optimization, thereby ensuring the stable and efficient operation of floating offshore wind power equipment under complex sea conditions.

[0055] Furthermore, the adjustment parameter generation module 50 of the embodiment of the present application is also used to perform the following steps:

[0056] The target posture adjustment strategy is used to adjust and analyze the device posture prediction information to obtain a posture adjustment strategy parameter threshold; M posture adjustment strategy parameters are randomly selected within the posture adjustment strategy parameter threshold, and the M posture adjustment strategy parameters are optimized to obtain the posture dynamic adjustment parameters.

[0057] Specifically, the module analyzes the effect and feasibility of the target strategy under different parameter settings based on the device attitude prediction information, combined with the physical characteristics of the buoyancy attitude adjustment device and environmental conditions, so as to determine the attitude adjustment strategy parameter threshold. The attitude adjustment strategy parameter threshold is the specific range of parameter adjustment, which is used to constrain the adjustment operation, such as the size of the adjustment force, the range of buoyancy adjustment, etc.

[0058] Next, M attitude adjustment strategy parameters are randomly selected from the attitude adjustment strategy parameter threshold as candidate adjustment parameters. These parameters represent different adjustment schemes that can be used by the buoyancy attitude adjustment device. The optimization algorithm is used to optimize these M attitude adjustment strategy parameters to find the optimal parameter combination, that is, the attitude dynamic adjustment parameter. Commonly used optimization algorithms include genetic algorithms and particle swarm algorithms. For example, through genetic algorithms, a buoyancy adjustment parameter that best suits the current sea conditions is found through multiple iterations. This parameter can enable the wind power equipment group to recover as quickly as possible after tilting and consume the least energy.

[0059] Furthermore, the adjustment parameter generation module 50 of the embodiment of the present application is also used to perform the following steps:

[0060] The M attitude adjustment strategy parameters are calculated according to a genetic algorithm to obtain M predicted attitude adjustment curves, wherein the M predicted attitude adjustment curves correspond one-to-one to the M attitude adjustment strategy parameters; an ideal attitude adjustment curve of the floating offshore wind power equipment group is obtained; and the M predicted attitude adjustment curves are compared with the ideal attitude adjustment curve to obtain the attitude dynamic adjustment parameters, wherein the predicted attitude adjustment curve corresponding to the attitude dynamic adjustment parameters has the greatest similarity to the ideal attitude adjustment curve.

[0061] Specifically, the module uses genetic algorithms to calculate M attitude adjustment strategy parameters. The genetic algorithm encodes, crosses, mutates and selects parameters by simulating natural selection and genetic mechanisms to gradually explore the optimal solution. This process generates M predicted attitude adjustment curves, each of which corresponds to a set of strategy parameters and describes the attitude change trend of the wind power equipment group under the execution of specific parameters.

[0062] The module obtains the ideal attitude adjustment curve of the floating offshore wind power equipment group. The ideal curve is based on the stable operation requirements and safety standard settings of the equipment, represents the optimal attitude change path under the predicted environmental conditions, and is the reference benchmark for the optimization strategy. M predicted attitude adjustment curves are compared with the ideal attitude adjustment curve, and the similarity between each predicted curve and the ideal curve is calculated using indicators such as curve fitting, mean square error or correlation coefficient to evaluate the degree of closeness between the equipment response and the ideal state under different parameter configurations. The attitude adjustment strategy parameters corresponding to the predicted attitude adjustment curve with the greatest similarity are determined as the final attitude dynamic adjustment parameters.

[0063] The adjustment parameter generation module 50 selects the best attitude dynamic adjustment parameters through parameter optimization to ensure that the wind power equipment group can adjust its attitude in a manner closest to the ideal state, thereby achieving efficient attitude adjustment of the equipment under complex sea conditions.

[0064] Furthermore, the posture adjustment execution module 60 of the embodiment of the present application is also used to execute the following steps:

[0065] The buoyancy attitude adjustment device performs multi-point attitude adjustment monitoring on the floating offshore wind power equipment group based on the attitude dynamic adjustment parameters to obtain attitude adjustment feedback parameters; if the attitude adjustment feedback parameters do not achieve the preset attitude adjustment effect, the parameter fine-tuning rules are analyzed and obtained; based on the parameter fine-tuning rules, the attitude dynamic adjustment parameters are fine-tuned and optimized to obtain attitude optimization adjustment parameters.

[0066] Specifically, the buoyancy attitude adjustment device starts to adjust the attitude of the device according to the attitude dynamic adjustment parameters calculated previously. For example, by adjusting the buoyancy device, the buoyancy of the device in a certain direction is increased, so that the device can gradually recover from the tilted state to the normal level. During the adjustment process, the sensor monitoring group is used to perform multi-point attitude adjustment monitoring at different positions of the device, for example, to monitor the inclination and stability of the device at different heights or angles. A set of attitude adjustment feedback parameters are obtained through attitude adjustment monitoring. These parameters can reflect the actual effect of the adjustment. The attitude adjustment feedback parameters are compared with the preset attitude adjustment effects to determine whether the attitude adjustment has achieved the expected effect. Among them, the preset attitude adjustment effect is the set adjustment target, usually the device is restored to a certain angle range and remains stable. For example, the target of the device tilt angle is less than 1 degree.

[0067] If the feedback parameters show that the adjustment effect is not up to standard, the module will further analyze the reasons for not meeting the standard and obtain the parameter fine-tuning rules, where the parameter fine-tuning rules are preset adjustment guidelines used to determine how to optimize based on the current parameters. Based on the obtained parameter fine-tuning rules, the module further optimizes the adjustment parameters on the basis of the existing adjustment parameters to obtain the posture optimization adjustment parameters. For example, if it is found that the current buoyancy increase is insufficient, the buoyancy parameters can be adjusted according to the fine-tuning rules to increase the buoyancy. If the previous buoyancy adjustment parameter is 20N, the module will fine-tune it to 21N or 22N based on the feedback to ensure that the device posture is more stable.

[0068] Through fine-tuning and optimization, the module can obtain the final posture optimization adjustment parameters to achieve the preset adjustment effect and ensure the accuracy and effectiveness of the equipment posture adjustment.

[0069] In summary, the floating attitude adjustment optimization system for a floating offshore wind power equipment group provided in the embodiment of the present application has the following technical effects:

[0070] The sensor monitoring module 10 installs a sensor monitoring group on the floating offshore wind power equipment group, and obtains the equipment operation attitude parameter set and the marine environment data set in real time through the sensor monitoring group, providing an accurate real-time data basis for the subsequent attitude adjustment analysis. The data transmission module 20 wirelessly transmits the equipment operation attitude parameter set and the marine environment data set to the central control unit through the Internet of Things module, realizing the instant transmission of data and ensuring the real-time and accuracy of the data source of the central control unit. The equipment attitude prediction module 30 analyzes and processes the equipment operation attitude parameter set and the marine environment data set through the central control unit calling the offshore risk equipment attitude prediction model, predicts future attitude changes, generates equipment attitude prediction information, and provides a basis for the generation of attitude adjustment strategy. The adjustment strategy generation module 40 obtains the buoyancy attitude adjustment device of the floating offshore wind power equipment group, obtains the target attitude adjustment strategy based on the equipment attitude prediction information and the structural information of the buoyancy attitude adjustment device, and ensures the scientificity and effectiveness of the adjustment measures. The adjustment parameter generation module 50 uses the target attitude adjustment strategy to adjust and analyze the equipment attitude prediction information, and provides specific attitude dynamic adjustment parameters for the attitude adjustment execution module 60 to achieve precise attitude control. The attitude adjustment execution module 60 performs multi-point attitude adjustment and dynamic feedback optimization on the floating offshore wind power equipment group based on the attitude dynamic adjustment parameters through the buoyancy attitude adjustment device to ensure that the equipment maintains the best attitude in the marine environment.

[0071] In general, the embodiment of the present application integrates multiple modules such as sensor monitoring, data transmission, equipment attitude prediction, adjustment strategy generation, adjustment parameter generation and attitude adjustment execution, monitors the marine environment and equipment operating status in real time, quickly transmits data to the central control unit, uses the prediction model to analyze data and generate accurate attitude adjustment strategies, and combines dynamic feedback optimization to achieve dynamic and intelligent adjustment of the attitude of the floating offshore wind power equipment group. The system significantly improves the adaptability of the floating offshore wind power equipment group to the frequently changing marine environment, enables the floating offshore wind power equipment group to always maintain the best attitude under various marine environmental conditions, effectively reduces the risk of equipment failure, thereby improving the operating stability and power generation efficiency of the wind power equipment group, extending the service life of the equipment group, and further promoting the sustainable development of offshore wind power.

[0072] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A floating attitude adjustment optimization system for a floating offshore wind power equipment group, characterized in that: The system comprises: A sensor monitoring module, wherein the sensor monitoring module is used to install a sensor monitoring group on a floating offshore wind power equipment group, and obtain a device operation attitude parameter set and a marine environment data set through the sensor monitoring group in real time; A data transmission module, the data transmission module is used to wirelessly transmit the device operation attitude parameter set and the marine environment data set to a central control unit through an Internet of Things module; An equipment posture prediction module, wherein the equipment posture prediction module is used by the central control unit to call the offshore risk equipment posture prediction model to analyze and process the equipment operation posture parameter set and the marine environment data set to generate equipment posture prediction information; An adjustment strategy generation module, the adjustment strategy generation module is used to obtain the buoyancy attitude adjustment device of the floating offshore wind power equipment group, and obtain a target attitude adjustment strategy based on the equipment attitude prediction information and the construction information of the buoyancy attitude adjustment device; An adjustment parameter generation module, wherein the adjustment parameter generation module is used to adjust and analyze the device posture prediction information using the target posture adjustment strategy to obtain posture dynamic adjustment parameters; The attitude adjustment execution module is used for the buoyancy attitude adjustment device to perform multi-point attitude adjustment and dynamic feedback optimization on the floating offshore wind power equipment group based on the attitude dynamic adjustment parameters.

2. The floating attitude adjustment optimization system for a floating offshore wind power equipment group according to claim 1, characterized in that: The data transmission module is also used to perform the following steps: Performing sea condition analysis on the marine environment data set through the Internet of Things module to obtain data transmission sea condition information; Performing a data transmission impact assessment on the data transmission sea condition information to obtain a data transmission impact coefficient; Acquire a wireless transmission link set according to the Internet of Things module, match the wireless transmission link set based on the data transmission influence coefficient, and obtain a target transmission link; The target transmission link is used to wirelessly transmit the equipment operation attitude parameter set and the ocean environment data set to the central control unit.

3. The floating attitude adjustment optimization system for a floating offshore wind power equipment group according to claim 1, characterized in that: The device posture prediction module is also used to perform the following steps: The floating offshore wind power equipment posture database is acquired through data mining technology; Marking the posture data in the floating offshore wind power equipment posture database, and using the marked floating offshore wind power equipment posture database as model training sample information; Performing deep network model training and verification optimization based on the model training sample information to generate an offshore wind power equipment posture prediction model; The offshore wind power equipment posture prediction model is stored in the central control unit.

4. The floating attitude adjustment optimization system for a floating offshore wind power equipment group according to claim 3, characterized in that: The device posture prediction module is also used to perform the following steps: Performing deep network model training based on the model training sample information to obtain an initial device posture prediction model; Performing performance verification on the initial device posture prediction model to obtain model performance verification feedback data; Performing loss analysis on the model performance verification feedback data to obtain predicted loss data; The performance of the initial equipment posture prediction model is optimized based on the predicted loss data to generate the offshore wind power equipment posture prediction model.

5. The floating attitude adjustment optimization system for a floating offshore wind power equipment group according to claim 1, characterized in that: The adjustment strategy generation module is also used to perform the following steps: Designing an attitude adjustment strategy library according to the structural information of the buoyancy attitude adjustment device; Based on the posture adjustment strategy library, the device posture prediction information is adjusted and predicted respectively to obtain multiple strategy adjustment effects; Based on the multiple strategy adjustment effects, the posture adjustment strategy library is optimized to obtain the target posture adjustment strategy.

6. The floating attitude adjustment optimization system for a floating offshore wind power equipment group according to claim 1, characterized in that: The adjustment parameter generation module is also used to perform the following steps: Adopting the target posture adjustment strategy to adjust and analyze the device posture prediction information to obtain a posture adjustment strategy parameter threshold; M posture adjustment strategy parameters are randomly selected within the posture adjustment strategy parameter threshold, and the M posture adjustment strategy parameters are optimized to obtain the posture dynamic adjustment parameters.

7. The floating attitude adjustment optimization system for a floating offshore wind power equipment group according to claim 6, characterized in that: The adjustment parameter generation module is also used to perform the following steps: Calculating the M posture adjustment strategy parameters according to a genetic algorithm to obtain M predicted posture adjustment curves, wherein the M predicted posture adjustment curves correspond one to one to the M posture adjustment strategy parameters; Obtaining an ideal attitude adjustment curve for the floating offshore wind power equipment group; The M predicted posture adjustment curves are compared with the ideal posture adjustment curve to obtain the posture dynamic adjustment parameter, wherein the predicted posture adjustment curve corresponding to the posture dynamic adjustment parameter has the greatest similarity with the ideal posture adjustment curve.

8. The floating attitude adjustment optimization system for a floating offshore wind power equipment group according to claim 1, characterized in that: The posture adjustment execution module is also used to execute the following steps: The buoyancy attitude adjustment device performs multi-point attitude adjustment monitoring on the floating offshore wind power equipment group based on the attitude dynamic adjustment parameters to obtain attitude adjustment feedback parameters; If the posture adjustment feedback parameters do not achieve the preset posture adjustment effect, analyzing and obtaining parameter fine-tuning rules; The posture dynamic adjustment parameters are fine-tuned and optimized based on the parameter fine-tuning rules to obtain posture optimization adjustment parameters.

Images