CN116890967A - Combined floating wind power platform and intelligent power generation efficiency optimization method thereof - Google Patents

Combined floating wind power platform and intelligent power generation efficiency optimization method thereof Download PDF

Info

Publication number
CN116890967A
CN116890967A CN202310786749.2A CN202310786749A CN116890967A CN 116890967 A CN116890967 A CN 116890967A CN 202310786749 A CN202310786749 A CN 202310786749A CN 116890967 A CN116890967 A CN 116890967A
Authority
CN
China
Prior art keywords
power generation
generation efficiency
fan
platform
axis fan
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310786749.2A
Other languages
Chinese (zh)
Inventor
张建华
张艺巍
孙科
刘志成
郭军
唐朝
陈悦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Harbin Engineering University
Original Assignee
Harbin Engineering University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Harbin Engineering University filed Critical Harbin Engineering University
Priority to CN202310786749.2A priority Critical patent/CN116890967A/en
Publication of CN116890967A publication Critical patent/CN116890967A/en
Pending legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
    • B63B35/44—Floating buildings, stores, drilling platforms, or workshops, e.g. carrying water-oil separating devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B21/00—Tying-up; Shifting, towing, or pushing equipment; Anchoring
    • B63B21/50—Anchoring arrangements or methods for special vessels, e.g. for floating drilling platforms or dredgers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B21/00—Tying-up; Shifting, towing, or pushing equipment; Anchoring
    • B63B21/50—Anchoring arrangements or methods for special vessels, e.g. for floating drilling platforms or dredgers
    • B63B2021/505—Methods for installation or mooring of floating offshore platforms on site
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
    • B63B35/44—Floating buildings, stores, drilling platforms, or workshops, e.g. carrying water-oil separating devices
    • B63B2035/4433—Floating structures carrying electric power plants
    • B63B2035/4453—Floating structures carrying electric power plants for converting solar energy into electric energy
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
    • B63B35/44—Floating buildings, stores, drilling platforms, or workshops, e.g. carrying water-oil separating devices
    • B63B2035/4433—Floating structures carrying electric power plants
    • B63B2035/446—Floating structures carrying electric power plants for converting wind energy into electric energy
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/06—Wind turbines or wind farms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/70—Wind energy
    • Y02E10/72—Wind turbines with rotation axis in wind direction

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Architecture (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Combustion & Propulsion (AREA)
  • Structural Engineering (AREA)
  • Mechanical Engineering (AREA)
  • Civil Engineering (AREA)
  • Chemical & Material Sciences (AREA)
  • Ocean & Marine Engineering (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Fluid Mechanics (AREA)
  • Algebra (AREA)
  • Computational Mathematics (AREA)
  • Wind Motors (AREA)

Abstract

The application provides a combined floating wind power platform and an intelligent power generation efficiency optimization method thereof, wherein the combined floating wind power platform is provided with six groups of buoyancy cabins, the six groups of buoyancy cabins are distributed in a regular hexagon, the buoyancy cabins are connected by trusses, the upper part of each buoyancy cabin is provided with a round platform component and a tower barrel installation base, a tower barrel is installed on the tower barrel installation base, and two groups of horizontal shaft fans and four groups of vertical shaft fans are symmetrically installed on the six groups of tower barrels; the lower part of the buoyancy cabin is provided with a supporting rod and a mooring rope, a heave plate is arranged below the supporting rod, a ballast cabin is arranged below the heave plate, and the mooring rope is connected with a gravity anchor; the combined floating wind power platform is symmetrically distributed in a regular hexagon, is uniformly stressed and stable in structure, and can be used for cooperatively controlling each fan through an intelligent matching optimization method, so that wind energy of different heights and angles can be efficiently obtained, and the efficiency and the productivity of a single floating platform are improved.

Description

Combined floating wind power platform and intelligent power generation efficiency optimization method thereof
Technical Field
The application relates to the technical field of offshore wind power, in particular to a combined floating wind power platform and an intelligent power generation efficiency optimization method thereof.
Background
In wind power development technology, wind turbines mainly comprise two major types of horizontal shafts and vertical shafts, wherein the horizontal shaft wind power utilization efficiency is relatively high, and the wind turbines are most widely applied in the wind power field, but the horizontal shaft wind turbines are arranged at the top of a supporting structure and have eccentric action on a basic platform, so that the whole structural system is light in weight and poor in stability. The horizontal axis fan needs to be continuously turned to keep vertical to the wind direction to obtain energy, and the blade tips of the blades in the engineering are generally far away from the water surface, so that the wind energy utilization rate near the water surface is low. For the vertical axis wind turbine, the transmission system is arranged at the bottom, so that the influence on the wind turbine tower is avoided, the incoming wind in the 360-degree direction can be accepted, a windward adjusting system is not needed, but the vertical axis wind turbine is difficult to be high in engineering due to the limitation of a supporting structure, and therefore, the wind energy utilization rate at the high position of the water surface is low. According to the development requirements of wind power, the applicant provides a combined floating wind power platform and an intelligent optimization method for generating efficiency of the combined floating wind power platform, wherein the combined floating wind power platform is in regular hexagon symmetrical distribution, is uniform in stress and stable in structure, can fully acquire wind energy of different heights and angles, improves the efficiency and productivity of a single floating platform, and provides an intelligent matching optimization method for adjusting the interference of blades of a single device, optimally deploying a plurality of fan platforms and guaranteeing minimum wake effects.
Disclosure of Invention
In order to solve the technical problems, the application provides a combined floating wind power platform and an intelligent power generation efficiency optimizing method thereof, wherein six groups of buoyancy cabins are distributed in a regular hexagon, the buoyancy cabins are connected by adopting trusses, a round platform component and a tower barrel installation base are arranged at the upper part of the buoyancy cabins, a tower barrel is installed on the tower barrel installation base, and two groups of horizontal shaft fans and four groups of vertical shaft fans are symmetrically installed on the six groups of tower barrels; a supporting rod and a mooring rope are arranged at the lower part of the buoyancy cabin, a heave plate is arranged below the supporting rod, a ballast cabin is arranged below the heave plate, and the mooring rope is connected with a gravity anchor; the combined floating wind power platform is arranged at sea, the buoyancy cabin is positioned at sea level, the buoyancy cabin is connected with the gravity anchor through the mooring rope, the gravity anchor is fixed in sea water, the combined floating wind power platform which is symmetrically distributed in a regular hexagon is uniformly stressed, the structure is stable, wind energy with different heights and angles can be fully obtained, and the efficiency and the productivity of a single floating platform are greatly improved.
In order to achieve the above purpose, the technical scheme adopted by the application is as follows:
the utility model provides a combination formula floating wind-powered electricity generation platform, including horizontal axis fan, long tower section of thick bamboo, short tower section of thick bamboo, vertical axis fan, tower section of thick bamboo installation base, round platform component, buoyancy cabin, truss, vertical support pole, diagonal bracing piece, heave plate, ballast tank, mooring rope and gravity anchor, its characterized in that: the combined floating wind power platform is provided with six groups of buoyancy cabins, the six groups of buoyancy cabins are distributed in a regular hexagon, the buoyancy cabins are connected through trusses, the upper part of each buoyancy cabin is provided with a round platform component, the round platform component is provided with a tower barrel installation base, the six groups of tower barrel installation bases are symmetrically provided with two groups of long tower barrels and four groups of short tower barrels, the long tower barrels are provided with horizontal shaft fans, and the short tower barrels are provided with vertical shaft fans; the bottom of the buoyancy cabin is provided with a vertical supporting rod, an inclined supporting rod and a mooring rope, heave plates are arranged below the vertical supporting rod and the inclined supporting rod, the lower ends of the heave plates are connected with a ballast cabin, and the lower ends of the mooring rope are connected with a gravity anchor.
Further, the combined floating wind power platform is provided with two groups of horizontal axis fans and four groups of vertical axis fans, and the two groups of horizontal axis fans and the four groups of vertical axis fans are symmetrically arranged on the upper parts of the six groups of buoyancy cabins.
Further, the combined floating wind power platform is provided with a horizontal axis fan and a vertical axis fan, the horizontal axis fan and the vertical axis fan are arranged in a staggered manner on a plane and a vertical plane, and the blade tips of the horizontal axis fan blades are 3-5 meters higher than the blade tips of the vertical axis fan blades at the lowest rotating position.
Furthermore, the tower barrel installation base and the round platform component are modularized prefabricated members.
Further, the cross section of the truss is round or square.
Further, the cross sections of the vertical support rods and the inclined support rods are round.
The application provides an intelligent power generation efficiency optimization method based on a convolutional neural network for a combined floating wind power platform, which comprises the following steps:
1) Grid deployment of a fan platform;
initializing deployment by adopting a gridding deployment mode to ensure that a large enough area on the sea surface can be covered, and finding a place with larger sea surface wind energy;
2) Measuring parameters;
measuring parameters on the sea surface by utilizing high-precision sensors on each fan platform, wherein the parameters comprise characteristics closely related to wind energy at each place on the sea surface, such as sea surface wind speed, sea surface wind direction, turbulence degree, air temperature and humidity;
3) Training a convolutional neural network;
the sea surface wind speed and the wind direction are obvious characteristics, namely the wind speed and the wind direction are required to be subjected to network specific optimization to increase the expression capacity of the wind speed and the wind direction, a multilayer accumulated convolution mode is adopted to enhance the expression capacity of the wind speed and the wind direction, and a filling formula is utilized to fill two units in the gap;
4) Evaluation of efficacy;
wind energy evaluation is carried out on the predicted power generation efficiency according to a power generation efficiency evaluation formula so as to find a region with better power generation efficiency;
5) Performing field interpolation processing;
carrying out Newton polynomial interpolation on the whole field to obtain the overall power generation efficiency condition of the sea surface where the fan platform is positioned after initial deployment;
6) Matching individual power generation efficiency;
when the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are smaller at the highest point of prediction, the fan blade rotating speed can be used for unlimited operation, when the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan at the highest point of prediction are both larger, the horizontal axis fan blade and the vertical axis fan blade of the device can be used in an allowable operation range, but when the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are extremely unbalanced, the adjustment is needed according to a vertical axis fan blade adjustment formula or a horizontal axis fan blade adjustment formula so as to maximize the energy collection of the whole system;
7) SVM bisects wake effects;
adopting an SVM (support vector machine) classification algorithm to extract a wind speed value, a wind direction, a turbulence degree, an air temperature, a wind energy value and a distance value between each wind turbine at the position with the highest power generation efficiency so as to predict whether the wake effect of the wake effect when all devices are arranged to the position with the maximum power generation efficiency is higher than a set threshold value;
8) Optimizing deployment;
arranging all devices to a place with maximum power generation efficiency at the minimum distance, predicting the wake effect at the moment by using an SVM algorithm, and when the predicted wake effect is smaller than a set pavilion value, maximizing the power generation efficiency, and if the predicted wake effect value is higher than a threshold value, amplifying the distance and re-predicting until the wake effect is still below the threshold value when the power generation efficiency is maximized, so that the power generation efficiency is maximized and the wake effect is lower;
as a further improvement of the application, the filling formula in the step 3) of the intelligent power generation efficiency optimization method based on the convolutional neural network is expressed as:
wherein the filling formula is expressed as:
k＝1，2，3，...，n
0≤α≤2
0≤β≤2
wherein S is k Newly filling each layer with a wind speed related characteristic value, wherein alpha is a super parameter, k represents that the current filling value is positioned in a k-th convolution layer, n represents that n layers of convolution layers are shared, and W s The first layer initial input value d after the sea surface wind speed is normalized is represented k Filling relevant characteristic values of wind directions into each layer, wherein beta is super parameter, W d The first layer initial input value of the sea surface wind direction after normalization processing is represented.
As a further improvement of the present application, the power generation efficiency evaluation formula in step 4) of the power generation efficiency intelligent optimization method based on the convolutional neural network is expressed as:
in step 3), the prediction of the power generation efficiency of each platform is completed, wherein the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan of each point are included, and the efficiency evaluation is required to be performed to find a region with better power generation efficiency, and the power generation efficiency evaluation formula is as follows:
wherein P is an estimated value of power generation efficiency, y 1 The power generation efficiency of the horizontal axis fan at the place is y 2 The power generation efficiency of the vertical axis fan at the place is obtained.
As a further improvement of the present application, the vertical axis fan blade adjustment formula in step 6) of the convolutional neural network-based power generation efficiency intelligent optimization method is expressed as:
wherein the vertical axis fan blade adjustment formula is as follows:
y 1 -y 2 ＞y 2
wherein V is 2 In order to adjust the rotating speed of the rear vertical axis fan blade when the power generation efficiency of the horizontal axis fan is far greater than that of the vertical axis fan, v 2 In the direction of y for the fan blade on the vertical axis 2 The rotation speed of the vertical axis fan under the power generation efficiency. y is 1 ，y 2 The power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are respectively.
The horizontal axis fan blade adjustment formula in the step 6) is expressed as:
the horizontal axis fan blade adjustment formula is as follows:
y 2 -y 1 ＞y 1
wherein V is 1 In order to adjust the rotating speed of the blades of the rear horizontal axis fan when the generating efficiency of the vertical axis fan is far greater than that of the horizontal axis fan, v 1 In the direction of y for the fan blade on the horizontal axis 1 The rotating speed of the horizontal shaft fan under the power generation efficiency. y is 1 ，y 2 Respectively the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan
The application provides a combined floating wind power platform and an intelligent power generation efficiency optimizing method thereof, wherein six groups of buoyancy cabins are arranged and distributed in a regular hexagon, the buoyancy cabins are connected by adopting trusses, a round platform component and a tower barrel installation base are arranged at the upper part of the buoyancy cabins, the tower barrel is installed on the tower barrel installation base, and two groups of horizontal shaft fans and four groups of vertical shaft fans are symmetrically installed on the six groups of tower barrels; a supporting rod and a mooring rope are arranged at the lower part of the buoyancy cabin, a heave plate is arranged below the supporting rod, a ballast cabin is arranged below the heave plate, and the mooring rope is connected with a gravity anchor; the combined floating wind power platform is arranged at sea, half of the buoyancy cabin is positioned below sea level, half of the buoyancy cabin is positioned on sea level, the buoyancy cabin is fixed in sea water by connecting a gravity anchor through a mooring rope, the combined floating wind power platform with regular hexagonally and symmetrically distributed is uniformly stressed, the structure is stable, and the advantages are that:
1. the combined floating wind power platform provided by the patent can fully acquire wind energy with different heights and different angles, and greatly improves the efficiency and the productivity of a single floating platform;
2. the combined floating wind power platform provided by the patent adopts six groups of buoyancy cabins, the six groups of buoyancy cabins are symmetrically distributed in a regular hexagon, the stress is uniform, and the vertical axis fan can not only improve the unit wind energy utilization rate, but also improve the stability of the platform structure;
3. the combined floating wind power platform is convenient and simple to install, flexible to construct and install, capable of being directly transported to a fixed position in open sea for installation after land assembly, and capable of completing installation by being connected with a mooring rope and a gravity anchor after being towed to a construction site through floating of the whole machine by utilizing the self-floating characteristic of the combined floating wind power platform, so that the use of large hoisting machinery in the offshore construction process is reduced, and the construction cost is reduced;
4. the utility model provides a generating efficiency intelligent optimization method based on convolutional neural network is suitable for a novel offshore wind turbine generating platform, can cooperatively control the efficiency of horizontal axis and vertical axis wind turbine generator, can improve the wind energy utilization rate in unit space, improves generating efficiency, reduce cost to guarantee that the structure is more stable.
5. The power generation efficiency intelligent optimization method based on the convolutional neural network predicts the power generation efficiency of each single fan platform by using the convolutional neural network, performs power generation efficiency matching optimization of the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan, can improve the power generation efficiency of the single fan platform, and ensures the normal operation of equipment.
6. The patent provides an intelligent power generation efficiency optimization method based on a convolutional neural network, which uses an SVM algorithm to evaluate and predict the wake effect of a fan platform group, so that the power generation efficiency of the fan platform group is maximized, and the wake effect is ensured to be within a threshold value.
Drawings
FIG. 1 is a schematic diagram of the overall structure of the present application;
FIG. 2 is a schematic top view of the present application;
FIG. 3 is a flow chart of a method for intelligently optimizing power generation efficiency based on a convolutional neural network;
FIG. 4 is a schematic deployment diagram of fan platform meshing for an intelligent power generation efficiency optimization method based on a convolutional neural network;
fig. 5 is a schematic diagram of a power generation efficiency prediction convolutional neural network architecture based on a convolutional neural network intelligent power generation efficiency optimization method.
Marked in the figure as: 1. a horizontal axis fan; 2. a long tower; 3. a short tower; 4. a vertical axis fan; 5. a tower barrel mounting base; 6. a circular truncated cone member; 7. a buoyancy chamber; 8. truss; 9. sea level; 10. a vertical support bar; 11. a diagonal support bar; 12. a heave plate; 13. a ballast tank; 14. mooring a wire rope; 15. gravity anchors.
Detailed Description
The application is described in further detail below with reference to the attached drawings and detailed description:
as shown in fig. 1-2: the combined floating wind power platform and the intelligent power generation efficiency optimizing method thereof are shown, and comprise a horizontal shaft fan 1, a long tower barrel 2, a short tower barrel 3, a vertical shaft fan 4, a tower barrel installation base 5, a round platform member 6, a buoyancy cabin 7, a truss 8, a vertical support rod 10, a diagonal support rod 11, a heave plate 12, a ballast tank 13, a mooring rope 14 and a gravity anchor 15; as shown in fig. 1-2, the combined floating wind power platform is provided with six groups of buoyancy tanks 7, the buoyancy tanks 7 are made of special steel materials by welding, the combined floating wind power platform has stronger seawater corrosion resistance, protective paint is painted on the outer parts of the buoyancy tanks 7, the six groups of buoyancy tanks 7 are distributed in a regular hexagon, the buoyancy tanks 7 are connected by trusses 8, the cross section of each truss 8 is round or rectangular, the diameter is 3 meters-5 meters, the wall thickness is 4.5 centimeters-8 centimeters, the trusses 8 are made of special steel materials identical to the buoyancy tanks 7, the trusses 8 are gathered together in the center after the six groups of buoyancy tanks 7 are connected, a round platform member 6 is arranged at the upper part of the buoyancy tanks 7, a tower barrel installation base 5 is arranged on the round platform member 6, the tower barrel installation base 5 and the round platform member 6 are modularized prefabricated members, the six groups of tower barrel installation bases 5 can be installed in a modularized mode, two groups of long tower barrels 2 and four groups of short tower barrels 3 are symmetrically installed, a horizontal shaft fan 1 is installed on the short tower barrel 3, a vertical shaft fan 4 is installed on the short tower barrel 3, the horizontal shaft fan 1 and the wind power fan 1 and the vertical shaft fan 4 are arranged on the vertical shaft 4 in a staggered mode, and the vertical shaft has different wind power to the same level as the wind power platform, and the wind power 1 has different wind power efficiency and can be fully improved in the vertical shaft and has different wind power level and vertical wind power with the same level; the bottom of the buoyancy chamber 7 is provided with a vertical supporting rod 10, a diagonal supporting rod 11 and a mooring rope 14, the cross sections of the vertical supporting rod 10 and the diagonal supporting rod 11 are circular, the diameter is 1 m-1.5 m, the wall thickness is 1.5 cm-3 cm, the vertical supporting rod is made of special steel materials similar to the buoyancy chamber 7, a heave plate 12 is arranged below the vertical supporting rod 10 and the diagonal supporting rod 11, a ballast tank 13 is connected below the heave plate 12, the gravity center of the whole floating platform can be lowered by the ballast tank 13, the stability of the platform is improved, the lower end of the mooring rope 14 is connected with a gravity anchor 15, and the mooring rope 14 and the gravity anchor 15 can enable the combined floating wind-power platform to be fixed on a seabed, so that the displacement cannot be excessively large under the action of wind waves; after the installation of the combined floating wind power platform is completed, half of the buoyancy cabin 7 is positioned below the sea level 9, and the other half of the buoyancy cabin is positioned on the sea level 9, so that the combined floating wind power platform has good wind wave resistance, the buoyancy cabin 7 and the truss 8 are integrally and symmetrically distributed in a regular hexagon, is uniformly stressed, has a stable structure, can fully acquire wind energy with different heights and angles, is convenient and simple to install, is flexible to construct and install, can be directly transported to a fixed position in open sea for installation after land assembly, can also utilize the self-floating characteristic of the combined floating wind power platform, is connected with a gravity anchor 15 through a mooring cable 14 after being towed to a construction site in a floating way of the whole machine, reduces the use of large hoisting machinery in the offshore construction process, and reduces the construction cost.
Fig. 3 is a flowchart of a power generation efficiency intelligent optimization method based on a convolutional neural network.
Step S1: and (5) grid deployment of the fan platform.
Fig. 4 is a schematic diagram showing the deployment of the fan platform meshing of the intelligent power generation efficiency optimization method based on the convolutional neural network.
For the application of the application, the fan platform needs to be deployed initially in priority. The application adopts a gridding deployment mode to perform initialization deployment so as to ensure that a large enough area on the sea surface can be covered and a place with larger sea surface wind energy can be found.
Step S2: and (5) measuring parameters.
In step S1, the initial grid deployment of the fan platform is completed. In this step, the parameters on the sea surface of the wind turbine are measured by using high-precision sensors on each fan platform, wherein the high-precision sensors include characteristics of sea surface wind speed, sea surface wind direction, turbulence degree, air temperature and humidity which are closely related to the power generation efficiency of each place on the sea surface.
Step S3, convolutional neural network training
Fig. 5 is a schematic diagram of a power generation efficiency prediction convolutional neural network architecture of the power generation efficiency intelligent optimization method based on the convolutional neural network.
In step S2, characteristic parameters closely related to sea surface wind energy are obtained, which need to be processed for convolution analysis of a subsequent network. And firstly, carrying out normalization processing on all the features, and keeping the dimension uniform.
For the network layer, in the application, the sea surface wind speed and the wind direction are significant characteristics, namely, the wind speed and the wind direction are required to be subjected to network specific optimization so as to increase the expression capacity of the network specific optimization. The application proposes to use a multi-layer accumulated convolution method to enhance the expression capability.
The initial input parameters are the sea wind speed, the sea wind direction, the turbulence degree, the air temperature and the humidity.
Where Conv1 is convolved with dimension 3*1, where the step size is 1, filling in one bit 0 value in each of the two measurements. The use of this convolution ensures that the input and output remain consistent during the first convolution. In the subsequent convolutions, i.e., conv2, conv3, …, 3*1 convolutions were also employed, with a step size of 1, but no padding was performed so that the output layer was two units less than the input layer. In addition, in the network structure, in order to accelerate the operation speed and the accuracy, a ReLU activation function is adopted. And filling the two vacant units by adopting characteristic values of factors related to the sea wind speed and the sea wind direction.
Wherein the filling formula is expressed as:
k＝1，2，3，…，n
0≤α≤2 (4)
0≤β≤2 (5)
wherein s is k And newly adding a wind speed related characteristic value for each layer, wherein alpha is a super parameter, and k represents that the current filling value is in a k-th convolution layer. n represents a total of n convolutional layers. W (W) s The first layer initial input value of the sea surface wind speed after normalization processing is represented. d, d k Filling wind direction related characteristic value, beta is super parameter, W d The first layer initial input value of the sea surface wind direction after normalization processing is represented.
After the network is built, training and evaluating the algorithm model, wherein the evaluation standard is the mean square error evaluation standard. When the accuracy of the training set and the test set is higher, the training can be completed.
Step S4: efficacy evaluation.
As shown in fig. 4, in step S3, the prediction of the power generation efficiency of each platform is completed, where the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan at each point are included, and the following power generation efficiency evaluation needs to be performed to find a region with better power generation efficiency, where the power generation efficiency evaluation formula is as follows:
wherein P is an estimated value of power generation efficiency, y 1 The power generation efficiency of the horizontal axis fan at the place is y 2 The power generation efficiency of the vertical axis fan at the place is obtained.
And obtaining the power generation efficiency evaluation value of each node after initial deployment through the formula.
Step S5: and (5) field interpolation processing.
In S4, the evaluation of the power generation efficiency of each site is completed, and in this step, newton polynomial interpolation is performed on the entire field, as shown in fig. 4, where the interpolated data object is the data on each line. The target value is the power generation efficiency evaluation value of the rest points on the data line. By the method, the overall power generation efficiency condition of the sea surface where the fan platform is positioned after the initialization and deployment can be obtained.
Step S6: individual power generation efficiency matching
In step S6, the field interpolation processing is completed, that is, the sea surface power generation efficiency covered by the whole fan platform is known. The power generation efficiency of the predicted highest value is used as follows. The application adopts a novel fan blade platform, and the novel fan blade platform comprises a vertical shaft fan blade and a horizontal shaft fan blade, wherein the vertical blade, the horizontal transverse shaft blade and the vertical shaft blade have different working characteristics and efficiency curves, and the novel fan blade platform is in the same platform. In a certain wind speed range, the power generation efficiency of the horizontal axis blade can be higher; while in other wind speed ranges, vertical axis blades may be more efficient. When the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are smaller at the highest predicted point, the fan blade can operate without limitation. When the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan at the highest point are predicted to be larger, the horizontal axis fan blade and the vertical axis fan blade of the device are enabled to be in the allowed operation range. However, when the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are extremely unbalanced, adjustment is needed so as to maximize the energy collection of the whole system. For example, when the wind direction is predominantly horizontal, vertical axis blades are typically more efficient at capturing wind energy, while horizontal axis blades may be relatively inefficient at capturing. In this case, the rotation of the horizontal axis fan blade can be reduced by controlling the rotation speed or the power output of the horizontal axis fan blade, thereby realizing the adjustment of the power generation efficiency.
Wherein the vertical axis fan blade adjustment formula is as follows:
y 1 -y 2 ＞y 2 (8)
wherein V is 2 In order to adjust the rotating speed of the rear vertical axis fan blade when the power generation efficiency of the horizontal axis fan is far greater than that of the vertical axis fan, v 2 In the direction of y for the fan blade on the vertical axis 2 The rotation speed of the vertical axis fan under the power generation efficiency. y is 1 ，y 2 The power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are respectively.
The horizontal axis fan blade adjustment formula is as follows:
y 2 -y 1 ＞y 1 (10)
wherein V is 1 To adjust the blades of the rear horizontal axis fan when the power generation efficiency of the vertical axis fan is far greater than that of the horizontal axis fanRotational speed, v 1 In the direction of y for the fan blade on the horizontal axis 1 The rotating speed of the horizontal shaft fan under the power generation efficiency. y is 1 ，y 2 The power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are respectively. Through the formula, when the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are greatly different, the rotating speed of the device with lower power generation efficiency is limited, and more wind energy is ensured to be effectively utilized by the fan blades with high power generation efficiency.
S7: SVM classifies wake effects.
In steps S5 and S6, prediction of the sea surface maximum power generation efficiency point and the running state when the blade is at the maximum power generation efficiency are completed. The plurality of wind turbine clusters is generally optimized as follows. It is first necessary to consider the wake effects of multiple clusters of wind turbines. The application adopts SVM classification algorithm to extract the wind speed value, wind direction, turbulence degree, air temperature, wind energy value and interval value between each wind machine at the position of highest power generation efficiency. To predict whether the wake effect of arranging all the devices to the power generation efficiency maximization site is higher than a set threshold.
The SVM algorithm training process comprises data label processing and normalization. The kernel function of the SVM algorithm is selected as a polynomial kernel function. Finally, the SVM classification accuracy reaches 0.95.
S8: optimizing deployment.
And S7, training of the SVM-capable two-class wake effect algorithm is completed, and in the step, all the fan clusters are deployed. Firstly, arranging all devices to the place with the maximum power generation efficiency at the minimum distance, predicting the wake effect at the moment by using an SVM algorithm, and when the predicted wake effect is smaller than a set pavilion value, performing according to the maximum power generation efficiency. And if the predicted wake effect value is above the threshold, the pitch is enlarged and the prediction is resumed. Until the power generation efficiency is maximized, the wake effect is still below the threshold value, and the efficiency is maximized and the wake effect is lower.
The above description is only of the preferred embodiment of the present application, and is not intended to limit the present application in any other way, but is intended to cover any modifications or equivalent variations according to the technical spirit of the present application, which fall within the scope of the present application as defined by the appended claims.

Claims (10)

1. The utility model provides a combination formula floating wind-powered electricity generation platform, including horizontal axis fan (1), long tower section of thick bamboo (2), short tower section of thick bamboo (3), vertical axis fan (4), tower section of thick bamboo installation base (5), round platform component (6), buoyancy cabin (7), truss (8), vertical bracing piece (10), diagonal bracing piece (11), heave plate (12), ballast tank (13), mooring cable (14) and gravity anchor (15), its characterized in that: the combined floating wind power platform is provided with six groups of buoyancy cabins (7), the six groups of buoyancy cabins (7) are distributed in a regular hexagon, the buoyancy cabins (7) are connected by adopting trusses (8), the upper part of each buoyancy cabin (7) is provided with a round table component (6), the round table component (6) is provided with a tower barrel installation base (5), two groups of long tower barrels (2) and four groups of short tower barrels (3) are symmetrically installed on the six groups of tower barrel installation bases (5), a horizontal shaft fan (1) is installed on the long tower barrels (2), and a vertical shaft fan (4) is installed on the short tower barrels (3); the buoyancy tank is characterized in that a vertical supporting rod (10), a diagonal supporting rod (11) and a mooring rope (14) are arranged at the bottom of the buoyancy tank (7), a heave plate (12) is arranged below the vertical supporting rod (10) and the diagonal supporting rod (11), a ballast tank (13) is connected below the heave plate (12), and the lower end of the mooring rope (14) is connected with a gravity anchor (15).
2. The combined floating wind power platform of claim 1, wherein: the combined floating wind power platform is provided with two groups of horizontal axis fans (1) and four groups of vertical axis fans (4), wherein the two groups of vertical axis fans (4) are symmetrically arranged on the upper parts of six groups of buoyancy cabins (7).
3. The combined floating wind power platform of claim 2, wherein: the combined floating wind power platform is provided with a horizontal axis fan (1) and a vertical axis fan (4), the horizontal axis fan (1) and the vertical axis fan (4) are arranged in a staggered manner on a plane and a vertical plane, and the blade tips of the blades of the horizontal axis fan (1) are 3-5 meters higher than the blade tips of the blades of the vertical axis fan (4) at the lowest rotating position.
4. The combined floating wind power platform of claim 1, wherein: the tower barrel installation base (5) and the round platform component (6) are modularized prefabricated members.
5. The combined floating wind power platform of claim 1, wherein: the cross section of the truss (8) is round or square.
6. The combined floating wind power platform of claim 1, wherein: the cross sections of the vertical supporting rods (10) and the inclined supporting rods (11) are round.
7. The intelligent power generation efficiency optimization method based on the convolutional neural network of the combined floating wind power platform according to any one of claims 1 to 6, which is characterized by comprising the following steps:
1) Grid deployment of a fan platform;
initializing deployment by adopting a gridding deployment mode to ensure that a large enough area on the sea surface can be covered, and finding a place with larger sea surface wind energy;
2) Measuring parameters;
measuring parameters on the sea surface by utilizing high-precision sensors on each fan platform, wherein the parameters comprise characteristics closely related to wind energy at each place on the sea surface, such as sea surface wind speed, sea surface wind direction, turbulence degree, air temperature and humidity;
3) Training a convolutional neural network;
the sea surface wind speed and the wind direction are obvious characteristics, namely the wind speed and the wind direction are required to be subjected to network specific optimization to increase the expression capacity of the wind speed and the wind direction, a multilayer accumulated convolution mode is adopted to enhance the expression capacity of the wind speed and the wind direction, and a filling formula is utilized to fill two units in the gap;
4) Evaluation of efficacy;
evaluating the predicted power generation efficiency according to a power generation efficiency evaluation formula to find a region with better power generation efficiency;
5) Performing field interpolation processing;
carrying out Newton polynomial interpolation on the whole field to obtain the overall power generation efficiency condition of the sea surface where the fan platform is positioned after initial deployment;
6) Matching individual power generation efficiency;
when the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are smaller at the highest point of prediction, the fan blade rotating speed can be used for unlimited operation, when the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan at the highest point of prediction are both larger, the horizontal axis fan blade and the vertical axis fan blade of the device can be used in an allowable operation range, but when the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are extremely unbalanced, the adjustment is needed according to a vertical axis fan blade adjustment formula or a horizontal axis fan blade adjustment formula so as to maximize the energy collection of the whole system;
7) SVM bisects wake effects;
adopting an SVM (support vector machine) classification algorithm to extract a wind speed value, a wind direction, a turbulence degree, an air temperature, a wind energy value and a distance value between each wind turbine at the position with the highest power generation efficiency so as to predict whether the wake effect of the wake effect when all devices are arranged to the position with the maximum power generation efficiency is higher than a set threshold value;
8) Optimizing deployment;
and arranging all devices to a place with maximum power generation efficiency at the minimum distance, predicting the wake effect at the moment by using an SVM algorithm, and when the predicted wake effect is smaller than a set pavilion value, maximizing the power generation efficiency, and if the predicted wake effect value is higher than a threshold value, amplifying the distance and re-predicting until the wake effect is still below the threshold value when the power generation efficiency is maximized, so that the power generation efficiency is maximized and the wake effect is lower.
8. The intelligent power generation efficiency optimization method based on the convolutional neural network according to claim 7, wherein the method comprises the following steps of:
the filling formula in the step 3) is expressed as follows:
wherein the filling formula is expressed as:
k＝1，2，3，...，n
0≤α≤2
0≤β≤2
wherein s is k Newly filling each layer with a wind speed related characteristic value, wherein alpha is a super parameter, k represents that the current filling value is positioned in a k-th convolution layer, n represents that n layers of convolution layers are shared, and W s The first layer initial input value d after the sea surface wind speed is normalized is represented k Filling relevant characteristic values of wind directions into each layer, wherein beta is super parameter, W d The first layer initial input value of the sea surface wind direction after normalization processing is represented.
9. The intelligent power generation efficiency optimization method based on the convolutional neural network according to claim 7, wherein the method comprises the following steps of:
the power generation efficiency evaluation formula in the step 4) is expressed as follows:
in step 3), the prediction of the power generation efficiency of each platform is completed, wherein the power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan of each point are included, and the efficiency evaluation is required to be performed to find a region with better power generation efficiency, and the power generation efficiency evaluation formula is as follows:
wherein P is an estimated value of power generation efficiency, y 1 The power generation efficiency of the horizontal axis fan at the place is y 2 The power generation efficiency of the vertical axis fan at the place is obtained.
10. The intelligent power generation efficiency optimization method based on the convolutional neural network according to claim 7, wherein the method comprises the following steps of:
the vertical axis fan blade adjustment formula in the step 6) is expressed as:
wherein the vertical axis fan blade adjustment formula is as follows:
y 1 -y 2 ＞y 2
wherein V is 2 In order to adjust the rotating speed of the rear vertical axis fan blade when the power generation efficiency of the horizontal axis fan is far greater than that of the vertical axis fan, v 2 In the direction of y for the fan blade on the vertical axis 2 The rotation speed of the vertical axis fan under the power generation efficiency. y is 1 ，y 2 The power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are respectively;
the horizontal axis fan blade adjustment formula in the step 6) is expressed as:
the horizontal axis fan blade adjustment formula is as follows:
y 2 -y 1 ＞y 1
wherein V is 1 In order to adjust the rotating speed of the blades of the rear horizontal axis fan when the generating efficiency of the vertical axis fan is far greater than that of the horizontal axis fan, v 1 In the direction of y for the fan blade on the horizontal axis 1 The rotating speed of the horizontal shaft fan under the power generation efficiency. y is 1 ，y 2 The power generation efficiency of the horizontal axis fan and the power generation efficiency of the vertical axis fan are respectively.
CN202310786749.2A 2023-06-30 2023-06-30 Combined floating wind power platform and intelligent power generation efficiency optimization method thereof Pending CN116890967A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310786749.2A CN116890967A (en) 2023-06-30 2023-06-30 Combined floating wind power platform and intelligent power generation efficiency optimization method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310786749.2A CN116890967A (en) 2023-06-30 2023-06-30 Combined floating wind power platform and intelligent power generation efficiency optimization method thereof

Publications (1)

Publication Number Publication Date
CN116890967A true CN116890967A (en) 2023-10-17

Family

ID=88310187

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310786749.2A Pending CN116890967A (en) 2023-06-30 2023-06-30 Combined floating wind power platform and intelligent power generation efficiency optimization method thereof

Country Status (1)

Country Link
CN (1) CN116890967A (en)

Similar Documents

Publication Publication Date Title
Claus et al. Key issues in the design of floating photovoltaic structures for the marine environment
Leimeister et al. Critical review of floating support structures for offshore wind farm deployment
Sun et al. The current state of offshore wind energy technology development
Edwards et al. Evolution of floating offshore wind platforms: A review of at-sea devices
Tong Fundamentals of wind energy
EP2604501B1 (en) System of anchoring and mooring of floating wind turbine towers and corresponding methods for towing and erecting thereof
US6755608B2 (en) Wind turbine enhancement apparatus, method and system
US20070138797A1 (en) Wind energy harnessing apparatuses, systems, methods, and improvements
JP2007518912A (en) Power generation assembly
Pantaleo et al. Feasibility study of off-shore wind farms: an application to Puglia region
US20100278630A1 (en) Power generation assemblies, and apparatus for use therewith
US20120091727A1 (en) Apparatus for generating electricity from wind power
CN110015384A (en) A kind of semi-submersible type offshore wind farm and cultivation fishing ground platform compages
Nakamura et al. Floating axis wind and water turbine for high utilization of sea surface area: Design of sub-megawatt prototype turbine
CN110118155A (en) A kind of the marine power generation platform and electricity-generating method of stormy waves complementation
CN110356521A (en) A kind of semisubmersible-type floatation type blower fan structure of floating drum flexible connection
CN116890967A (en) Combined floating wind power platform and intelligent power generation efficiency optimization method thereof
Achard et al. Floating vertical axis wind turbine—OWLWIND project
NO347179B1 (en) A mooring system for a plurality of floating units
CN218198744U (en) Floating type photovoltaic platform on sea
US9726141B2 (en) Wave energy absorption unit
Dymarski Design of jack-up platform for 6 MW wind turbine: Parametric analysis based dimensioning of platform legs
CN212487988U (en) Integrated development device of single-pile type offshore wind turbine and vertical shifting aquaculture net cage
Estefen et al. Wave energy hyperbaric converter: Small scale models, prototype and control strategies
Zheng et al. A Novel Floating Wind-Solar-Aquaculture Concept: Fully Coupled Analysis and Technical Feasibility Study

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination