Wave self-adaptive wave absorbing device and method for floating wind power and power generation equipment

Abstract

The invention belongs to the technical field of wave absorbing devices, and provides a wave self-adaptive wave absorbing device and method for floating wind power and power generation equipment, a plurality of fins are arranged around the floating wind power through driving assemblies, and each fin is provided with a wave sensing sensor assembly through a sensor mounting groove; the driving assembly and the wave sensing sensor assembly are connected with an intelligent control system, and the intelligent control system is used for adaptively adjusting the action of the fins according to the wave condition monitored by the wave sensing sensor assembly; on the basis of improving wave dissipation by arranging a fin special mechanism, wave changes can be sensed and responded in real time, the stability and the power generation efficiency of the offshore floating type wind power platform are improved, the service life of the platform is prolonged, the performance of the platform under the complex sea condition can be optimized, the reliability of the platform can be improved, and the service life of the platform is prolonged. And commercial application and sustainable development of the offshore floating type wind power technology are promoted.

Description

Technical Field

[0001] The present invention belongs to the technical field of wave dissipation devices, and particularly relates to a wave adaptive wave dissipation device, method and power generation equipment for floating wind power. Background Art

[0002] With the continuous growth of the global demand for clean energy, floating offshore wind power, as a renewable energy technology with great potential, is gradually becoming an important part of the sustainable energy system. Different from traditional fixed offshore wind power platforms, floating wind power platforms float on the sea surface and are more significantly affected by waves and the marine environment. These environmental factors pose severe challenges to the power generation efficiency, stability and safety of floating wind power devices. In particular, the frequent changes and complexity of waves make the dynamic response of floating platforms more complex.

[0003] At present, although traditional wave dissipation devices can alleviate the impact brought by waves to a certain extent, they are usually difficult to adapt to the complexity and dynamic changes of the marine environment. Especially in the application of floating platforms, they lack sufficient flexibility and adaptive ability; traditional wave dissipation technologies are often relatively simple and cannot effectively cope with the movement of the platform and the impact brought by waves under different sea conditions. Summary of the Invention

[0004] In order to solve the above problems, the present invention provides a wave adaptive wave dissipation device, method and power generation equipment for floating wind power. By setting a special fin structure, on the basis of improving wave dissipation, it can sense and respond to wave changes in real time, which is of great significance for improving the stability, power generation efficiency of offshore floating wind power platforms and extending the service life of the platforms. It can not only optimize the performance of the platform under complex sea conditions, but also improve its reliability, and promote the commercial application and sustainable development of offshore floating wind power technology. To achieve the above object, in the first aspect, the present invention provides a wave adaptive wave dissipation device for offshore floating wind power, adopting the following technical solutions:

[0005] A wave adaptive wave dissipation device for offshore floating wind power includes a plurality of fins arranged around the floating wind power through a driving component, and a wave sensing sensor assembly is installed on each fin through a sensor mounting groove;

[0006] The driving component and the wave sensing sensor assembly are connected to an intelligent control system, and the intelligent control system is used to adaptively adjust the actions of the fins according to the wave conditions monitored by the wave sensing sensor assembly.

[0007] Further, the fin is a fish fin imitation, and a plurality of protrusions are distributed on the fin.

[0008] Further, the wave perception sensor assembly includes one or several of a pressure sensor, an acceleration sensor, a speed sensor, and a direction sensor.

[0009] To achieve the above object, in a second aspect, the present invention also provides a wave adaptive wave - damping method for offshore floating wind power, adopting the following technical solutions:

[0010] A wave adaptive wave - damping method for offshore floating wind power uses the wave adaptive wave - damping device for offshore floating wind power as described in the first aspect, including: automatically adjusting the angle and swing of the fins according to the relationship between the wave state and the fin movement.

[0011] Further, according to the height, frequency, and wave speed of the sea waves, and based on the trained Q - network, the adaptive angle and speed adjustment values of the fins are obtained.

[0012] Further, if the device reduces the wave energy or impact force, a positive reward is given; otherwise, a negative reward is given.

[0013] Further, initialize a Q - network to estimate the Q - value of each state - action pair. In each step, record each state - action, reward, and the next state to form an experience sample; store the experience replay pool and randomly sample batches to train the Q - network.

[0014] Further, calculate the target of the Q - value:

[0015]

[0016] where γ is the discount factor, θ - is the parameter of the target network, is the maximum Q - value under the next state s t+1 ; update the Q - network by minimizing the mean square error between the Q - network output and the target value.

[0017] Further, after every preset number of steps, copy the parameters of the Q - network to the target network; select a random action with probability ∈ and select the action with the largest currently estimated Q - value with probability 1 - ∈; during each training process, continuously optimize the strategy through the Q - network to gradually improve the control effect of the wave - damping device; after every preset number of steps, evaluate the performance of the device and adjust the network parameters.

[0018] To achieve the above object, in a third aspect, the present invention also provides a wave adaptive wave - damping power generation device for offshore floating wind power, adopting the following technical solutions:

[0019] A wave adaptive wave - damping power generation device for offshore floating wind power uses the wave adaptive wave - damping device for offshore floating wind power as described in the first aspect.

[0020] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0021] In the present invention, a plurality of fins are arranged around a floating wind power by a driving component, and a wave sensing sensor component is installed on each fin through a sensor installation groove; the driving component and the wave sensing sensor component are connected to an intelligent control system, and the intelligent control system is configured to adaptively adjust the actions of the fins according to the wave conditions monitored by the wave sensing sensor component; by setting a special fin mechanism, on the basis of improving wave elimination, it can sense and respond to wave changes in real time, which is of great significance for improving the stability, power generation efficiency of the offshore floating wind power platform and extending the service life of the platform. It can not only optimize the performance of the platform in complex sea conditions, but also improve its reliability, and promote the commercial application and sustainable development of offshore floating wind power technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The attached drawings forming a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments and descriptions thereof of this embodiment are used to explain this embodiment and do not constitute an improper limitation to this embodiment.

[0023] Figure 1 Schematic diagram of the wave elimination device in Embodiment 1 of the present invention;

[0024] Figure 2 Schematic diagram of the fish fin-like wave elimination mechanism in Embodiment 1 of the present invention;

[0025] Figure 3 Deep Q-Network (DQN) control algorithm in Embodiment 1 of the present invention;

[0026] Figure 4 Example of wave generation and elimination in Embodiment 1 of the present invention;

[0027] Figure 5 Execution block diagram of the wave elimination device in Embodiment 1 of the present invention;

[0028] Wherein, 101, fin; 1011, protrusion; 1012, sensor installation groove; 102, driving component; 201, floating pile foundation; 202, connecting rod; 203, wind turbine; 204, anchor. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] The present invention will be further described below in conjunction with the drawings and embodiments.

[0030] It should be noted that the following detailed descriptions are all exemplary and are intended to provide further descriptions of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0031] Example 1:

[0032] As Figure 1 shown, this embodiment provides a wave adaptive wave - damping device for offshore floating wind power. By using a Deep Q - Network (DQN), it can real - time sense and respond to wave changes, adjust the posture of the fish - fin - like wave - damping mechanism, which is of great significance for improving the stability, power generation efficiency of the offshore floating wind power platform and extending the service life of the platform. It can not only optimize the performance of the platform under complex sea conditions, but also improve its reliability, promoting the commercial application and sustainable development of offshore floating wind power technology.

[0033] The wave adaptive wave - damping device in this embodiment includes a fish - fin - like wave - damping mechanism, a wave sensing sensor assembly and an intelligent control system.

[0034] As Figure 1 shown, the basic principle of the fish - fin - like wave - damping mechanism is to adjust the speed and direction of water flow by simulating the movement of fish fins, so that the energy of waves can be effectively dispersed or absorbed. The fish - fin - like wave - damping mechanism consists of multiple dynamic fins 101, which can be arranged in a circular ring around the floating wind power. It can automatically change the angle and swing, by imitating the streamline structure of water flow changed by fish fins through swinging and vibrating in water, reducing the impact force of waves. The floating wind power includes multiple floating pile foundations 201, connecting rods 202 connected to the floating pile foundations 201, a wind turbine 203, an anchor 204, etc. Specifically, the fins 101 can be installed on the floating pile foundations 201.

[0035] Optionally, the fins 101 can be made of high - strength and corrosion - resistant materials, such as carbon fiber composite materials or aluminum alloys. The surface of the fish fins of the fish - fin - like wave - damping mechanism is distributed with multiple tiny protrusions 1011, which can increase the surface roughness, so that more friction and resistance are generated when water flow passes through, thereby reducing the propagation speed and energy of waves. The fish fins should be reserved with sensor installation grooves 1012 to ensure the embedded installation of sensors. The fish - fin - like wave - damping mechanism is equipped with a driving component 102, such as a motor or other driving devices. The driving component 102 can control the angle and swing frequency of the fins 101 to adapt to different wave conditions. Optionally, the fish - fin - like wave - damping mechanism is connected by ball joints. A spherical joint is installed at the connection point between the fish fin and the floating wind turbine, and the fish fin is connected to the spherical joint through a connecting rod. In this way, the fish fin can rotate freely in multiple directions to achieve angle adjustment and swing. A small servo motor is installed at the joint of the fish fin. By controlling the rotation angle and speed of the motor, the posture of the fish fin can be precisely adjusted. The motor can be remotely controlled by the control system to adjust the angle and swing of the fish fin in real - time according to the marine environment and the operating state of the floating wind turbine. The power supply of the fish fin comes from the electricity generated by the floating wind turbine.

[0036] The wave sensing sensor assembly is used to monitor the wave changes in the ocean in real time, including parameters such as wave height, speed, period, direction, etc. The wave sensing sensor assembly is responsible for monitoring the wave conditions in the ocean in real time, providing accurate data support for the intelligent adjustment of the fish fin wave dissipation mechanism. The wave sensing sensor assembly adopts a combination of multiple sensors such as pressure sensors, acceleration sensors, speed sensors and direction sensors to improve the accuracy and reliability of monitoring. Among them, the pressure sensor is installed on the surface or near the fish fin wave dissipation device to measure the pressure change of the wave on the device. By analyzing the pressure data, parameters such as wave height and period can be inferred. The acceleration sensor is installed on the fish fin wave dissipation device to detect the acceleration change of the device under the action of the wave. The acceleration data helps to understand the intensity and direction of the wave. The direction sensor is also installed on the fish fin wave dissipation mechanism to determine the propagation direction of the wave, providing a basis for the angle adjustment of the fish fin wave dissipation device. The sensors should have the characteristics of high precision, high reliability and fast response.

[0037] The intelligent control system plays a core role in the entire fish fin wave dissipation mechanism and floating wind turbine system. It can adjust the angle and swing of the fish fin wave dissipation mechanism in real time according to the data provided by the wave sensing sensor assembly to achieve the best wave dissipation effect and protect the stable operation of the floating wind turbine. It mainly consists of a central processor, a memory, an input / output interface, and a communication module.

[0038] Optionally, the hardware part includes: Central processor: responsible for processing data from the wave sensing sensor assembly and running control algorithms. A high-performance microprocessor or digital signal processor (DSP) can be used, which has powerful computing capabilities and fast data processing speeds. The central processor needs to be able to respond to wave changes in real time, quickly calculate the optimal control strategy, and send control instructions to the drive system. Memory: used to store information such as control algorithms, wave data, and system parameters. It can include random access memory (RAM) and read-only memory (ROM), as well as external storage devices such as flash cards or hard disks. Input / output interface: connects the wave sensing sensor assembly, the drive system, and other external devices. The input interface receives data from the wave sensing sensor assembly, and the output interface sends control instructions to the drive system. The input / output interface should have good compatibility and reliability, and be able to accurately transmit data and control signals. Communication module: realizes communication with a remote monitoring center or other systems. Wireless communication technology is adopted to enable remote monitoring and management in the marine environment. The communication module should have a stable connection and high-speed data transmission capabilities.

[0039] Software part: including control algorithms: The entire device system uses Deep Q-Network (DQN) for control. Deep Q-Network (DQN) is an algorithm that combines deep learning and reinforcement learning to solve the decision-making problem of an agent in a complex environment. In the fish fin wave dissipation mechanism, DQN can automatically adjust the angle and swing of the fish fin by learning the relationship between different wave states and fish fin actions to achieve the best wave dissipation effect. The framework is as follows:

[0040] Definition of state space: Dynamic information such as the height, frequency, wave speed of the sea wave, and the current angle and speed of the fish fin wave dissipation mechanism. It can be represented as a multi-dimensional state vector s t :

[0041] s t ={h t ,f t ,v t ,θ t};

[0042] Among them, h t ,f t ,v t ,θ t is the wave height, f t is the wave frequency, v t is the speed of the device, θ t is the angle of the device, etc.

[0043] Definition of action space: The control strategy of the device can be achieved by adjusting the angle of the fish fin, movement, etc. These control methods can be discretized or continuousized and represented as an action vector:

[0044] a t ={v t ,θ t ,…};

[0045] Reward function: The reward function gives rewards according to the wave dissipation effect. If the device can effectively reduce the wave energy or impact force, a positive reward is given; otherwise, a negative reward is given.

[0046] r t =α×Cc - Ew;

[0047] Among them, Ew represents the wave energy, Cc is the cost (energy consumed) of the control device, and α is a weight factor.

[0048] First, initialize a Q-network (neural network) to estimate the Q value of each state-action pair, usually implemented through a deep neural network.

[0049] Q(s t ,at ; c) ≈ Q - Value for state - Action pair;

[0050] Among them, Value for state represents the state, that is, the environmental state where the agent is at a certain moment; Action pair represents the action, that is, the specific behavior taken by the agent in this state.

[0051] Secondly, for experience replay, in each step, record each state s t action a t , reward r t and the next state s t+1 to form an experience sample (s t , a t , r t , s t+1 ). Store it in the experience replay pool and randomly sample batches to train the Q - network to break the correlation between samples and improve the stability of training.

[0052] Update the Q - network by calculating the target of the Q - value through the Bellman Equation:

[0053]

[0054] Among them, γ is the discount factor, θ - is the parameter of the target network, is the maximum Q - value under the next state s t+1 .

[0055] Update the Q - network by minimizing the mean square error between the output of the Q - network and the target value y t :

[0056]

[0057] Use the gradient descent method to optimize the network parameter θ.

[0058] To improve the training stability, after every certain number of steps, copy the parameters of the Q - network to the target network:

[0059] θ - = θ;

[0060] Use the ε - greedy strategy to balance exploration and exploitation. That is, select a random action with probability ∈ (exploration), and select the action with the largest currently estimated Q - value with probability 1 - ∈.

[0061] During each training process, the policy is continuously optimized through the Q-network, gradually improving the control effect of the wave-dissipating device. After a certain number of steps, the performance of the device is evaluated and the network parameters are adjusted.

[0062]

[0063] Among them, random action means randomly selecting an action (uniformly and randomly selected from the action space); with probability ∈ means with probability ∈, which defines the probability of the "random action" occurring and controls the exploration frequency; arg max represents the parameter of the action a that maximizes the Q value; with probability 1 - ∈ means "with probability 1 - ∈" (complementary to the exploration probability).

[0064] Control policy: Once the training is completed, the DQN model can give the optimal control action for each given state. For example, under a certain wave condition, the model can recommend the best fin angle and motion strategy, and drive the fish-fin-like wave-dissipating mechanism for control according to the optimal action output by the DQN to respond to the changing sea waves in real time to maximize the wave-dissipating effect.

[0065]

[0066] Example 2:

[0067] This example provides a wave adaptive wave-dissipating method for offshore floating wind power, using the wave adaptive wave-dissipating device for offshore floating wind power as described in Example 1, including: automatically adjusting the angle and swing of the fins according to the relationship between the wave state and the fin actions. The specific framework of the method is as follows:

[0068] State space definition: Dynamic information such as the height, frequency, wave speed of the sea waves, and the current angle and speed of the fish-fin-like wave-dissipating mechanism. It can be represented as a multi-dimensional state vector s t :

[0069] s t = {h t , f t , v t , θ t};

[0070] Among them, h t , f t , v t , θ t are the wave height, f t is the wave frequency, v t is the speed of the device, θ t is the angle of the device, etc.

[0071] Action Space Definition: The control strategy of the device can be achieved by adjusting the angles of the fins, movements, etc. These control methods can be discretized or continuous, and represented as an action vector:

[0072] a t ={v t , θ t ,…};

[0073] Reward Function: The reward function gives rewards based on the wave dissipation effect. If the device can effectively reduce wave energy or impact force, a positive reward is given; otherwise, a negative reward is given.

[0074] r t =α×Ccontrol - Ewave;

[0075] where Ewave represents wave energy, Ccontrol is the cost (energy consumed) of the control device, and α is a weight factor.

[0076] First, initialize a Q-network (neural network) to estimate the Q-value of each state-action pair, usually implemented through a deep neural network.

[0077] Q(s t , a t ; c)≈Q–Value for state–Action pair;

[0078] Second, experience replay. At each step, record each state s t action a t , reward r t and the next state s t+1 to form an experience sample (s t , a t , r t , s t+1 ). Store the experience replay pool and randomly sample batches to train the Q-network to break the correlation between samples and improve the stability of training.

[0079] Update the Q-network, calculate the target of the Q-value through the Bellman Equation:

[0080]

[0081] where γ is the discount factor, θ - is the parameter of the target network, is the maximum Q-value under the next state s t+1 .

[0082] By minimizing the output of the Q-network and the target value y tUpdate the Q network using the mean squared error between them:

[0083]

[0084] Use the gradient descent method to optimize the network parameters θ.

[0085] To improve the training stability, after every certain number of steps, copy the parameters of the Q network to the target network:

[0086] θ - = θ;

[0087] Use the ε-greedy strategy to balance exploration and exploitation. That is, select a random action with probability ∈ (exploration), and select the action with the largest currently estimated Q value with probability 1 - ∈.

[0088] During each training process, continuously optimize the strategy through the Q network, and gradually improve the control effect of the wave-dissipating device. After every certain number of steps, evaluate the performance of the device and adjust the network parameters.

[0089]

[0090] Control strategy: Once the training is completed, the DQN model can give the optimal control action for each given state. For example, under a certain wave condition, the model can recommend the best fin angle and motion strategy, and drive the fish-fin-like wave-dissipating mechanism for control according to the optimal action output by the DQN to respond to the changing sea waves in real time to maximize the wave-dissipating effect.

[0091]

[0092] Example 3:

[0093] This embodiment provides a wave adaptive wave-dissipating power generation device for offshore floating wind power, which uses the wave adaptive wave-dissipating device for offshore floating wind power as described in Example 1.

[0094] The above are only the preferred embodiments of this embodiment and are not used to limit this embodiment. For those skilled in the art, this embodiment can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this embodiment shall be included within the protection scope of this embodiment.

Claims

1. A wave adaptive wave absorbing device for offshore floating wind power, characterized in that: It includes a plurality of fins arranged around the floating wind turbine through a driving assembly, and a wave sensing sensor assembly is installed on each fin through a sensor installation slot; The driving assembly and the wave sensing sensor assembly are connected with an intelligent control system, and the intelligent control system is used to adaptively adjust the movement of the fins according to the wave conditions monitored by the wave sensing sensor assembly.

2. The wave adaptive wave absorbing device for offshore floating wind power according to claim 1, characterized in that: The fin is an imitation fish fin, and a plurality of protrusions are distributed on the fin.

3. The wave adaptive wave absorbing device for offshore floating wind power according to claim 1, characterized in that: The wave sensing sensor assembly includes one or more of a pressure sensor, an acceleration sensor, a speed sensor and a direction sensor.

4. A wave adaptive wave absorption method for offshore floating wind power, characterized in that: The wave adaptive wave absorbing device for offshore floating wind power as claimed in any one of claims 1 to 3 comprises: automatically adjusting the angle and swing of the fin according to the relationship between the wave state and the movement of the fin.

5. The wave adaptive wave absorption method for offshore floating wind power according to claim 4, characterized in that: According to the height, frequency and wave speed of the waves, the adaptive angle and speed adjustment values ​​of the fins are obtained based on the trained Q network.

6. The wave adaptive wave absorption method for offshore floating wind power according to claim 5, characterized in that: If the device reduces wave energy or impact force, a positive reward is given; otherwise, a negative reward is given.

7. The wave adaptive wave absorption method for offshore floating wind power according to claim 6, characterized in that: Initialize a Q network to estimate the Q value of each state-action pair. At each step, record each state action, reward and next state to form an experience sample; store the experience replay pool and randomly sample batches to train the Q network.

8. The wave adaptive wave absorption method for offshore floating wind power according to claim 7, characterized in that: The goal of calculating Q value is: Where γ is the discount factor, θ - are the parameters of the target network, is the next state s t+1 The maximum Q value under ; Update the Q network by minimizing the mean square error between the Q network output and the target value.

9. The wave adaptive wave absorption method for offshore floating wind power according to claim 8, characterized in that: After each preset number of steps, the parameters of the Q network are copied to the target network; A random action is selected with probability ∈, and the action with the largest estimated Q value is selected with probability 1-∈. During each training process, the Q network optimization strategy is continuously used to gradually improve the control effect of the wave-breaking device. After each preset number of steps, the performance of the device is evaluated and the network parameters are adjusted.

10. A wave adaptive wave-absorbing power generation device for offshore floating wind power, characterized in that: A wave adaptive wave absorbing device for offshore floating wind power as described in any one of claims 1 to 3 is used.

Images