CN115169195A - Wind turbine composite material blade global strain reconstruction method and system - Google Patents
Wind turbine composite material blade global strain reconstruction method and system Download PDFInfo
- Publication number
- CN115169195A CN115169195A CN202210884650.1A CN202210884650A CN115169195A CN 115169195 A CN115169195 A CN 115169195A CN 202210884650 A CN202210884650 A CN 202210884650A CN 115169195 A CN115169195 A CN 115169195A
- Authority
- CN
- China
- Prior art keywords
- blade
- strain
- wind turbine
- finite element
- composite material
- 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
Links
Images
Classifications
-
- 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- 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
- 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
-
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/26—Composites
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a method and a system for reconstructing the global strain of a composite material blade of a wind turbine. The method comprises the following steps: step S1, step S2, step S3, step S4, step S5, and step S6. The invention also relates to a system for reconstructing the global strain of the composite material blade of the wind turbine. The method and the system provided by the invention can realize the reconstruction and visualization of the overall strain of the composite material blade of the wind turbine and provide an efficient and feasible solution for monitoring the overall strain of the blade in real time.
Description
Technical Field
The invention belongs to the technical field of wind power, and relates to a strain reconstruction method and a strain reconstruction system, in particular to a wind turbine composite material blade global strain reconstruction method and a wind turbine composite material blade global strain reconstruction system.
Background
The blade is a key component for a wind turbine to obtain wind energy. The flexible blade of the large wind turbine is elastically deformed under the action of inertia force, centrifugal force and pneumatic load, and even causes blade damage under the action of multi-factor coupling. Under the actual running state of the wind turbine, the strain of the blade is monitored globally in real time, the specific position and size of the early damage of the blade are observed in an all-around mode, and the method has important significance for guaranteeing the safety of a wind power system.
In the existing wind turbine blade monitoring, an acceleration sensor, a resistance strain sensor and the like are usually arranged at the position of a blade root, so that the global strain state of the blade cannot be obtained; if set up the electric sensor in blade middle part and sharp portion position, bring cost increase and potential safety hazard problem.
How to globally monitor and visualize the blade strain in the actual operation state of the wind turbine is a problem to be solved urgently at present.
Disclosure of Invention
The invention aims to provide a method and a system for reconstructing the global strain of a composite material blade of a wind turbine, so that the global real-time monitoring and visualization of the strain of the blade can be realized in the actual running state of the wind turbine.
In order to achieve the aim, the invention provides a wind turbine composite material blade global strain reconstruction method, which comprises the following steps:
establishing a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine;
determining u blade root strain test positions, wherein u is an integer larger than 2;
establishing a blade load inversion model;
the method for establishing the blade load inversion model comprises the following steps:
setting n working condition parameter combinations, wherein n is an integer greater than 2, the working condition parameters comprise wind speed, wind speed direction and turbulence intensity, dividing the blade into m phyllines based on the phylline momentum theory, and obtaining the lift L of the jth phylline under the ith working condition parameter combination ij Resistance D ij Moment M ij ,i=1,2,…n,j=1,2,…m;
Applying said lift L in said blade finite element model ij Resistance D ij Moment M ij And obtaining the strain epsilon of the q blade root strain test position under the i working condition parameter combination iq Q =1,2 and … u, and obtaining a blade global strain data set E under the n working condition parameter combinations;
with said lift force L ij Resistance D ij Moment M ij And the strain ε iq Establishing a load inversion training sample data set T;
based on the load inversion training sample data set T, with the strain epsilon iq As input, with said lift force L ij Resistance D ij Moment M ij As output, obtaining a blade load inversion model based on a radial basis function neural network with output feedback;
carrying out strain dynamic test on the composite material blade of the actual wind turbine to obtain a strain time series spectrum of the root strain test positions of the u blades, and obtaining an equivalent load time series spectrum of the composite material blade of the actual wind turbine based on the blade load inversion model;
establishing a blade load-strain field reduced order prediction model;
and taking the equivalent load time sequence spectrum of the composite material blade of the actual wind turbine as input, and obtaining a blade global strain cloud chart according to the blade load-strain field reduced order prediction model.
The step of establishing the blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine comprises the following steps:
determining initial layering parameters of the finite element blade according to the size, load, material, process level and installation mode of the composite material blade of the actual wind turbine, and establishing an initial blade finite element model;
acquiring the structural characteristic parameters of the composite material blade of the actual wind turbine through the initial blade finite element model; the actual wind turbine composite material blade structure characteristic parameters comprise rigidity distribution characteristics, quality characteristics and modal parameters;
selecting the initial layering parameters of the finite element blade as optimization design variables, taking the structural characteristic parameters of the finite element blade and the structural characteristic parameters of the actual wind turbine composite material blade as optimization targets, and solving to obtain the optimized layering parameters of the finite element blade by combining an optimization algorithm;
and adjusting and modifying the initial blade finite element model according to the optimized layering parameters of the finite element blade to obtain an optimized blade finite element model, checking the optimized blade finite element model, and obtaining a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine.
The step of establishing the blade load-strain field reduced order prediction model comprises the following steps:
compiling the data of the blade global strain data set E into a column matrix, and combining the column matrix and the column matrix according to a time sequence to obtain a strain snapshot matrix A;
carrying out modal decomposition on the strain snapshot matrix A by adopting an intrinsic orthogonal decomposition method to obtain a strain snapshot matrix B of a dominant mode;
obtaining an equivalent load time sequence spectrum of the n working condition parameter combinations according to the blade load inversion model;
constructing a training database Z by taking the equivalent load time sequence spectrum of the n working condition parameter combinations as input and the strain snapshot matrix B as output;
and constructing a blade load-strain field reduced order prediction model based on the training database Z by adopting a radial basis function neural network.
The invention also provides a wind turbine composite material blade global strain reconstruction system, which comprises:
a module M1: the method comprises the steps of establishing a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine;
a module M2: the method comprises the steps of determining u blade root strain test positions, wherein u is an integer larger than 2;
a module M3: the method is used for establishing a blade load inversion model;
the module M3 comprises the following modules:
module M31: the method is used for setting n working condition parameter combinations, wherein n is an integer larger than 2, the working condition parameters comprise wind speed, wind speed direction and turbulence intensity, the blade is divided into m phyllines based on the phylline momentum theory, m is an integer larger than 2, and the lift L of the jth phylline under the ith working condition parameter combination is obtained ij Resistance D ij Moment M ij ,i=1,2,…n,j=1,2,…m;
The module M32: for applying said lift force L in said blade finite element model ij Resistance D ij Moment M ij Obtaining the strain epsilon of the qth blade root strain test position under the combination of the ith working condition parameters iq Q =1,2 and … u, and obtaining a blade global strain data set E under the n working condition parameter combinations;
module M33: for applying said lifting force L ij Resistance D ij Moment M ij And the strain ε iq Establishing a load inversion training sample data set T;
a module M34: for inverting a training sample data set T based on said load with said strain ε iq As input, with said lift force L ij Resistance D ij Moment M ij As output, obtaining a blade load inversion model based on a radial basis function neural network with output feedback;
a module M4: the system is used for carrying out strain dynamic test on the composite material blade of the actual wind turbine to obtain a strain time series spectrum of the root strain test positions of the u blades, and obtaining an equivalent load time series spectrum of the composite material blade of the actual wind turbine based on the blade load inversion model;
a module M5: the method is used for establishing a blade load-strain field reduced order prediction model;
a module M6: and obtaining a blade global strain cloud picture by taking the equivalent load time sequence spectrum of the composite material blade of the actual wind turbine as input according to the blade load-strain field reduced order prediction model.
The module M1 comprises the following modules:
a module M11: the method comprises the steps of determining initial layering parameters of the finite element blade according to the size, load, material, process level and installation mode of the composite material blade of the actual wind turbine, and establishing an initial blade finite element model;
a module M12: the method comprises the steps of obtaining structural characteristic parameters of the composite material blade of the actual wind turbine through the initial blade finite element model; the actual wind turbine composite material blade structure characteristic parameters comprise rigidity distribution characteristics, quality characteristics and modal parameters;
a module M13: the method comprises the steps of selecting initial layering parameters of the finite element blade as optimization design variables, taking the structural characteristic parameters of the finite element blade and the structural characteristic parameters of the actual wind turbine composite material blade as optimization targets, and solving to obtain optimized layering parameters of the finite element blade by combining an optimization algorithm;
a module M14: and the initial blade finite element model is adjusted and modified according to the optimized layering parameters of the finite element blade to obtain an optimized blade finite element model, and the optimized blade finite element model is checked to obtain a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine.
The module M5 comprises the following modules:
the module M51: the system comprises a leaf global strain data set E, a strain snapshot matrix A and a data processing module, wherein the leaf global strain data set E is used for compiling data of the leaf global strain data set E into a column matrix and combining the column matrix according to a time sequence to obtain the strain snapshot matrix A;
the module M52: the strain snapshot matrix A is subjected to modal decomposition by adopting an intrinsic orthogonal decomposition method to obtain a strain snapshot matrix B of a dominant mode;
module M53: obtaining an equivalent load time sequence spectrum of the n working condition parameter combinations according to the blade load inversion model;
module M54: the training database Z is constructed by taking the equivalent load time sequence spectrum of the n working condition parameter combinations as input and the strain snapshot matrix B as output;
module M55: and the method is used for constructing a blade load-strain field reduced order prediction model based on the training database Z by adopting a radial basis function neural network.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the method for establishing the finite element model of the blade is combined with an optimization algorithm, so that the consistency of the finite element model of the blade and the structural characteristic parameters of the actual composite material blade can be ensured, and the accuracy of the numerical simulation of the global stress field is improved.
The strain testing position is positioned at the root part of the blade, so that the problems of cost and safety caused by arranging a plurality of electric sensors at the middle part and the tip part of the blade are solved.
According to the method for establishing the blade load inversion model, the radial basis function neural network based on output feedback is adopted, the multi-working condition sample data set is fully utilized, and the strain time sequence spectrum of the blade strain test position is combined, so that the equivalent load time sequence spectrum of the composite material blade of the actual wind turbine can be efficiently and accurately obtained.
The method for establishing the load-strain field reduced order prediction model provided by the invention adopts an intrinsic orthogonal decomposition method, greatly improves the calculation efficiency of a neural network model, and provides an efficient and feasible solution for reconstructing and visualizing the overall strain of the composite material blade of the wind turbine.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of an embodiment of a method and system for reconstructing global strain of a composite blade of a wind turbine according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for reconstructing the global strain of a composite material blade of a wind turbine.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The embodiment of the invention relates to a method for reconstructing the global strain of a composite material blade of a wind turbine, which comprises the following steps:
step S1: establishing a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine;
step S2: determining u blade root strain test positions, wherein u is an integer larger than 2;
and step S3: establishing a blade load inversion model;
the method for establishing the blade load inversion model comprises the following steps of S31-S34:
step S31: setting n working condition parameter combinations, wherein n is an integer greater than 2, the working condition parameters comprise wind speed, wind speed direction and turbulence intensity, dividing the blade into m phyllines based on the phylline momentum theory, and obtaining the lift L of the jth phylline under the ith working condition parameter combination ij Resistance D ij Moment M ij ,i=1,2,…n,j=1,2,…m;
Step S32: applying said lift L in said blade finite element model ij Resistance D ij Moment M ij And obtaining the strain epsilon of the q blade root strain test position under the i working condition parameter combination iq Q =1,2 and … u, and obtaining a blade global strain data set E under the n working condition parameter combinations;
step S33: with the lift force L ij Resistance D ij Moment M ij And the strain ε iq Establishing a load inversion training sample data set T;
step S34: based on the load inversion training sample data set T, with the strain epsilon iq As input, with said lift force L ij Resistance D ij Moment M ij As output, obtaining a blade load inversion model based on a radial basis function neural network with output feedback;
and step S4: performing dynamic strain test on the actual wind turbine composite material blade to obtain a strain time sequence spectrum of the u blade root strain test positions, and obtaining an equivalent load time sequence spectrum of the actual wind turbine composite material blade based on the blade load inversion model;
step S5: establishing a blade load-strain field reduced order prediction model;
step S6: and taking the equivalent load time sequence spectrum of the composite material blade of the actual wind turbine as input, and obtaining a blade global strain cloud chart according to the blade load-strain field reduced order prediction model.
The step of establishing the blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine comprises the following steps:
step S11: determining initial layering parameters of the finite element blade according to the size, load, material, process level and installation mode of the composite material blade of the actual wind turbine, and establishing an initial blade finite element model;
step S12: acquiring the structural characteristic parameters of the composite material blade of the actual wind turbine through the initial blade finite element model; the actual wind turbine composite material blade structure characteristic parameters comprise rigidity distribution characteristics, quality characteristics and modal parameters;
step S13: selecting the initial layering parameters of the finite element blade as optimization design variables, taking the structural characteristic parameters of the finite element blade and the structural characteristic parameters of the composite material blade of the actual wind turbine as optimization targets, and solving to obtain the optimized layering parameters of the finite element blade by combining an optimization algorithm;
step S14: and adjusting and modifying the initial blade finite element model according to the optimized layering parameters of the finite element blade to obtain an optimized blade finite element model, checking the optimized blade finite element model, and obtaining a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine. The step of establishing the blade load-strain field reduced order prediction model comprises the following steps:
step S51: compiling the data of the blade global strain data set E into a column matrix, and combining the column matrix and the column matrix according to a time sequence to obtain a strain snapshot matrix A;
step S52: performing modal decomposition on the strain snapshot matrix A by adopting an intrinsic orthogonal decomposition method to obtain a dominant modal strain snapshot matrix B;
step S53: obtaining an equivalent load time sequence spectrum of the n working condition parameter combinations according to the blade load inversion model;
step S54: constructing a training database Z by taking the equivalent load time sequence spectrum of the n working condition parameter combinations as input and the strain snapshot matrix B as output;
step S55: and constructing a blade load-strain field reduced order prediction model based on the training database Z by adopting a radial basis function neural network.
Based on the same inventive concept, the embodiment of the invention also provides a wind turbine composite material blade global strain reconstruction system, and as the principle of solving the problems of the devices is similar to a wind turbine composite material blade global strain reconstruction method, the implementation of the devices can refer to the implementation of the method, and repeated parts are not described again.
The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments but rather by the equivalents thereof as may occur to those skilled in the art upon consideration of the present inventive concept.
Claims (6)
1. A wind turbine composite material blade global strain reconstruction method is characterized by comprising the following steps:
step S1: establishing a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine;
step S2: determining u blade root strain test positions, wherein u is an integer larger than 2;
and step S3: establishing a blade load inversion model;
the establishment of the blade load inversion model comprises the following steps S31-S34:
step S31: setting n working condition parameter combinations, wherein n is an integer greater than 2, the working condition parameters comprise wind speed, wind speed direction and turbulence intensity, dividing the blade into m phyllines based on the phylline momentum theory, and obtaining the lift L of the jth phylline under the ith working condition parameter combination ij Resistance D ij Moment M ij ,i=1,2,…n,j=1,2,…m;
Step S32: applying said lift L in said blade finite element model ij Resistance D ij Moment M ij And obtaining the strain epsilon of the q blade root strain test position under the i working condition parameter combination iq Q =1,2 and … u, and obtaining a blade global strain data set E under the n working condition parameter combinations;
step S33: with the lift force L ij Resistance D ij Moment M ij And the strain ε iq Establishing a load inversion training sample data set T;
step S34: based on the load inversion training sample data set T, with the strain epsilon iq As input, with said lift force L ij Resistance D ij Moment M ij As output, obtaining a blade load inversion model based on a radial basis function neural network with output feedback;
and step S4: carrying out strain dynamic test on the composite material blade of the actual wind turbine to obtain a strain time series spectrum of the root strain test positions of the u blades, and obtaining an equivalent load time series spectrum of the composite material blade of the actual wind turbine based on the blade load inversion model;
step S5: establishing a blade load-strain field reduced order prediction model;
step S6: and taking the equivalent load time sequence spectrum of the composite material blade of the actual wind turbine as input, and obtaining a blade global strain cloud chart according to the blade load-strain field reduced order prediction model.
2. The wind turbine composite blade global strain reconstruction method as claimed in claim 1, wherein the step of establishing a blade finite element model consistent with the actual wind turbine composite blade structural characteristic parameters comprises:
step S11: determining initial layering parameters of the finite element blade according to the size, load, material, process level and installation mode of the composite material blade of the actual wind turbine, and establishing an initial blade finite element model;
step S12: acquiring the structural characteristic parameters of the composite material blade of the actual wind turbine through the initial blade finite element model; the actual wind turbine composite material blade structure characteristic parameters comprise rigidity distribution characteristics, quality characteristics and modal parameters;
step S13: selecting the initial layering parameters of the finite element blade as optimization design variables, taking the structural characteristic parameters of the finite element blade and the structural characteristic parameters of the composite material blade of the actual wind turbine as optimization targets, and solving to obtain the optimized layering parameters of the finite element blade by combining an optimization algorithm;
step S14: and adjusting and modifying the initial blade finite element model according to the optimized layering parameters of the finite element blade to obtain an optimized blade finite element model, checking the optimized blade finite element model, and obtaining a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine.
3. The method for reconstructing the global strain of the composite blade of the wind turbine as claimed in claim 1, wherein the step of establishing the reduced order prediction model of the blade load-strain field comprises:
step S51: compiling the data of the blade global strain data set E into a column matrix, and combining the column matrix and the column matrix according to a time sequence to obtain a strain snapshot matrix A;
step S52: carrying out modal decomposition on the strain snapshot matrix A by adopting an intrinsic orthogonal decomposition method to obtain a strain snapshot matrix B of a dominant mode;
step S53: obtaining an equivalent load time sequence spectrum of the n working condition parameter combinations according to the blade load inversion model;
step S54: constructing a training database Z by taking the equivalent load time sequence spectrum of the n working condition parameter combinations as input and the strain snapshot matrix B as output;
step S55: and constructing a blade load-strain field reduced order prediction model based on the training database Z by adopting a radial basis function neural network.
4. A wind turbine composite blade global strain reconstruction system is characterized by comprising the following modules:
a module M1: the method comprises the steps of establishing a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine;
a module M2: the method comprises the steps of determining u blade root strain test positions, wherein u is an integer larger than 2;
a module M3: the method is used for establishing a blade load inversion model;
the module M3 comprises the following modules:
module M31: the method is used for setting n working condition parameter combinations, wherein n is an integer larger than 2, the working condition parameters comprise wind speed, wind speed direction and turbulence intensity, the blade is divided into m phyllodes based on the phyllode momentum theory, m is an integer larger than 2, and the lift force L of the jth phyllode under the ith working condition parameter combination is obtained ij Resistance D ij Moment M ij ,i=1,2,…n,j=1,2,…m;
The module M32: for applying said lift force L in said blade finite element model ij Resistance D ij Moment M ij Obtaining the strain epsilon of the qth blade root strain test position under the combination of the ith working condition parameters iq Q =1,2, … u, and obtaining a blade global strain data set E under the n working condition parameter combinations;
module M33: for applying said lifting force L ij Resistance D ij Moment M ij And the strain ε iq Establishing a load inversion training sample data set T;
a module M34: for inverting a training sample data set T based on said load with said strain ε iq As input, with said lift force L ij Resistance D ij Moment M ij As output, obtaining a blade load inversion model based on a radial basis function neural network with output feedback;
a module M4: the system is used for carrying out strain dynamic test on the composite material blade of the actual wind turbine to obtain a strain time series spectrum of the root strain test positions of the u blades, and obtaining an equivalent load time series spectrum of the composite material blade of the actual wind turbine based on the blade load inversion model;
a module M5: the method is used for establishing a blade load-strain field reduced order prediction model;
a module M6: and obtaining a blade global strain cloud picture by taking the equivalent load time sequence spectrum of the composite material blade of the actual wind turbine as input according to the blade load-strain field reduced order prediction model.
5. The wind turbine composite blade global strain reconstruction system as claimed in claim 4, wherein said modules M1 comprise the following modules:
a module M11: the method comprises the steps of determining initial layering parameters of the finite element blade according to the size, load, material, process level and installation mode of the composite material blade of the actual wind turbine, and establishing an initial blade finite element model;
a module M12: the method comprises the steps of obtaining structural characteristic parameters of the composite material blade of the actual wind turbine through the initial blade finite element model; the actual wind turbine composite material blade structure characteristic parameters comprise rigidity distribution characteristics, quality characteristics and modal parameters;
a module M13: the method comprises the steps of selecting initial layering parameters of the finite element blade as optimization design variables, taking the structural characteristic parameters of the finite element blade and the structural characteristic parameters of the actual wind turbine composite material blade as optimization targets, and solving to obtain optimized layering parameters of the finite element blade by combining an optimization algorithm;
a module M14: and the initial blade finite element model is adjusted and modified according to the optimized layering parameters of the finite element blade to obtain an optimized blade finite element model, and the optimized blade finite element model is checked to obtain a blade finite element model consistent with the structural characteristic parameters of the composite material blade of the actual wind turbine.
6. The wind turbine composite blade global strain reconstruction system as claimed in claim 4, wherein said modules M5 comprise the following modules:
the module M51: the system comprises a leaf global strain data set E, a strain snapshot matrix A and a data processing module, wherein the leaf global strain data set E is used for compiling data of the leaf global strain data set E into a column matrix and combining the column matrix according to a time sequence to obtain the strain snapshot matrix A;
the module M52: the strain snapshot matrix A is subjected to modal decomposition by adopting an intrinsic orthogonal decomposition method to obtain a dominant modal strain snapshot matrix B;
module M53: obtaining an equivalent load time sequence spectrum of the n working condition parameter combinations according to the blade load inversion model;
module M54: the training database Z is constructed by taking the equivalent load time sequence spectrum of the n working condition parameter combinations as input and the strain snapshot matrix B as output;
module M55: and the method is used for constructing a blade load-strain field reduced order prediction model based on the training database Z by adopting a radial basis function neural network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210884650.1A CN115169195A (en) | 2022-07-26 | 2022-07-26 | Wind turbine composite material blade global strain reconstruction method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210884650.1A CN115169195A (en) | 2022-07-26 | 2022-07-26 | Wind turbine composite material blade global strain reconstruction method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115169195A true CN115169195A (en) | 2022-10-11 |
Family
ID=83496368
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210884650.1A Pending CN115169195A (en) | 2022-07-26 | 2022-07-26 | Wind turbine composite material blade global strain reconstruction method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115169195A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116227045A (en) * | 2022-11-23 | 2023-06-06 | 北京瑞风协同科技股份有限公司 | Local stress strain field construction method and system for structural test piece |
-
2022
- 2022-07-26 CN CN202210884650.1A patent/CN115169195A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116227045A (en) * | 2022-11-23 | 2023-06-06 | 北京瑞风协同科技股份有限公司 | Local stress strain field construction method and system for structural test piece |
CN116227045B (en) * | 2022-11-23 | 2023-10-20 | 北京瑞风协同科技股份有限公司 | Local stress strain field construction method and system for structural test piece |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107346357B (en) | Offshore wind turbine fatigue analysis system based on integral coupling model | |
EP3237873B1 (en) | Fatigue testing | |
WO2019165753A1 (en) | Load prediction method and apparatus for wind power generator set | |
JP4995134B2 (en) | Wind turbine monitoring device, method and program | |
WO2011024304A1 (en) | Device and method for monitoring wind turbine, and program | |
Malik et al. | Application of probabilistic neural network in fault diagnosis of wind turbine using FAST, TurbSim and Simulink | |
Tcherniak | Rotor anisotropy as a blade damage indicator for wind turbine structural health monitoring systems | |
CN107036808B (en) | Gearbox of wind turbine combined failure diagnostic method based on support vector machines probability Estimation | |
Malik et al. | Proximal support vector machine (PSVM) based imbalance fault diagnosis of wind turbine using generator current signals | |
CN115169195A (en) | Wind turbine composite material blade global strain reconstruction method and system | |
CN105065212A (en) | Checking method and system of wind generation sets of wind power plant | |
CN114154731A (en) | Wind power ultra-short-term power prediction method and system based on deep learning | |
CN111878322B (en) | Wind power generator device | |
CN113374652A (en) | Method for evaluating service life of wind generating set | |
Junior et al. | Unbalance evaluation of a scaled wind turbine under different rotational regimes via detrended fluctuation analysis of vibration signals combined with pattern recognition techniques | |
KR101413565B1 (en) | Apparatus for Performance Test of Pitch Controller for Wind Turbines and Method thereof | |
Vera-Tudela et al. | On the selection of input variables for a wind turbine load monitoring system | |
CN116306139A (en) | Intelligent monitoring method and system for service life of wind turbine blade | |
CN112131753A (en) | Method, system and device for evaluating fatigue life of fan and readable medium | |
CN115659844B (en) | Simulation method and device based on wind power plant dynamic model and computer equipment | |
CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network | |
Li et al. | Fault diagnosis of wind turbine blades based on fuzzy theory | |
Schröder et al. | Damage localization at wind turbine support structures using sequential quadratic programming for model updating | |
CN111878323B (en) | Wind generating set fault early warning method based on frequency spectrum autocorrelation function | |
CN113987870A (en) | State evaluation method for main transmission system of wind turbine generator and terminal equipment |
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 |