CN116881662A - Method for predicting icing disaster of rotating wind power blade - Google Patents
Method for predicting icing disaster of rotating wind power blade Download PDFInfo
- Publication number
- CN116881662A CN116881662A CN202310924821.3A CN202310924821A CN116881662A CN 116881662 A CN116881662 A CN 116881662A CN 202310924821 A CN202310924821 A CN 202310924821A CN 116881662 A CN116881662 A CN 116881662A
- Authority
- CN
- China
- Prior art keywords
- icing
- wind power
- power blade
- blade
- disaster
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 239000011248 coating agent Substances 0.000 claims description 29
- 238000000576 coating method Methods 0.000 claims description 29
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 23
- 238000012544 monitoring process Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000001133 acceleration Effects 0.000 claims description 12
- 239000003595 mist Substances 0.000 claims description 10
- 239000007921 spray Substances 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 6
- 238000010248 power generation Methods 0.000 description 5
- 230000005611 electricity Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a method for predicting icing disasters of a rotating wind power blade, which simulates an actual running environment through a rotating wind power blade icing vibration test platform; collecting vibration signals of the rotating wind power blade in different icing states and icing influence factor data; preprocessing the collected vibration signals in different icing states to obtain and collect vibration characteristic data in different icing states as sample data; constructing a wind power blade state prediction model based on the sample data and the icing influence factor data; and obtaining the icing state of the wind power blade according to the output result; and constructing a wind power blade icing disaster prediction model based on a gray theory according to the icing state of the wind power blade, and obtaining the position and moment of the icing disaster in the next time sequence of different positions of the wind power blade according to the output prediction result and the set icing disaster value. The icing state of the rotating wind power blade can be accurately predicted in real time, and the disaster occurrence time can be accurately predicted.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a method for predicting icing disasters of a rotating wind power blade.
Background
At present, as the global ecological environment is increasingly worsened, development and utilization of renewable energy sources have become a focus. Wind energy is the fastest-growing clean energy in renewable energy sources, has market prospects of large-scale development and commercialization, in recent years, the capacity of a wind generating set in China is rapidly increased, the scale of a wind power generating station is continuously enlarged, the application scene of the wind generating set is continuously widened, wind energy in China is mainly concentrated in the three north (northeast, northwest and North China) regions with cold climate and the southeast coastal regions with higher humidity, and meanwhile, the safe and stable operation of the wind generating set faces new challenges. Particularly when the wind power generation unit enters severe cold winter, the mountain wind power generation unit is subjected to environmental influences such as high altitude, low temperature and high humidity, the wind power generation unit is subjected to adverse effects of icing, particularly, the blade is in icing condition, the load and the power characteristics of the blade are changed, the safe and stable operation of the wind power generation unit is seriously influenced, and the blade is possibly broken and the tower tube is collapsed in serious conditions. The icing position, the icing thickness and the catastrophe moment of the blade are timely and accurately predicted, so that timely and effective operation and maintenance measures are conveniently taken for the wind turbine, and the method has important significance for improving the safety reliability and the economy of the operation of a wind farm.
However, in the prior art, a great deal of researches are carried out on icing of wind power equipment blades by numerical simulation, experimental analysis and other methods, and analysis is mainly carried out by taking a single blade in a static state as a research object. The method for predicting the icing state and the disaster occurrence time of the rotating wind power equipment blade has less research on the aspects of predicting the icing state and the icing disaster occurrence time of the rotating wind power equipment blade, and has not been developed.
Therefore, how to accurately predict the icing state and disaster occurrence time of the rotating wind power blade in real time is a problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides a method for predicting icing disasters of a rotating wind power blade, which can accurately predict icing states and disaster occurrence moments of the rotating wind power blade in real time.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a method for predicting icing disasters of a rotating wind power blade comprises the following steps:
simulating the actual running environment of the rotating wind power blade through the icing vibration test platform of the rotating wind power blade;
collecting vibration signals of the rotating wind power blade in different icing states and icing influence factor data;
preprocessing the vibration signals in different icing states to obtain vibration characteristic data in different icing states; collecting all of the vibration characteristic data as sample data;
constructing a wind power blade state prediction model based on the sample data and the icing influence factor data; obtaining the icing state of the wind power blade according to the output prediction result;
and constructing a wind power blade icing disaster prediction model based on a gray theory according to the icing state of the wind power blade, and obtaining the position and time of the icing disaster in the next time sequence of different positions of the wind power blade according to the prediction result output by the wind power blade icing disaster prediction model and the set icing disaster value.
Further, the ice coating state includes: ice coating thickness and ice coating position; the icing influencing factors at least comprise: temperature, humidity, wind speed and run time.
Further, through the rotatory wind-powered electricity generation blade icing vibration test platform, simulate rotatory wind-powered electricity generation blade actual operation environment specifically includes:
the water in the water tank is conveyed to the high-pressure spray head through the high-pressure water pump, the high-pressure spray head outputs water mist, the output water mist is blown to the wind turbine blade through the axial flow fan, and the water mist covered on the wind turbine blade is frozen to simulate a natural icing state, so that the actual running environment of the rotating wind turbine blade is restored.
Further, the collecting vibration signals of the rotating wind power blade in different icing states specifically comprises:
collecting vibration signals of the rotating wind power blade in different icing states in real time by adopting a plurality of triaxial acceleration sensors; the plurality of tri-axial acceleration sensors are arranged at different locations on the wind power blade with the aerodynamic center near the leading edge of the blade.
Further, the preprocessing of the vibration signal specifically includes:
the missing values of the collected vibration signals are processed by adopting a mean value interpolation method, and the collected vibration signals are filtered by adopting a Kalman method to filter noise signals.
Further, the building of the wind power blade state prediction model specifically includes:
obtaining time series original data of one period through experiments, wherein the original data comprises: blade icing thickness of different monitoring points and 4 icing influence factor sample data sequences;
the collected blade icing thicknesses of the different monitoring points and the 4 icing influence factor sample data sequences are accumulated once and generated and recorded as Wherein m is the number of monitoring points arranged on the wind power blade, n is the number of factors affecting the thickness of the icing, and +.>To monitor the original sequence of the jth factor affecting the icing thickness at the ith measuring point on the rotating wind blade in time, for +.>Adding to generate 1-AGO once to obtain +.>
For a pair ofGenerating the immediate mean value to obtain->Wherein (1)>Is->Next to the mean sequence, k=1, 2, …, l;
establishing a differential equation:wherein (1)>Is the gray derivative; a is the development coefficient, < >>To drive items, b ij Is a driving coefficient;
for parameter columnsAnd (5) carrying out least square estimation to obtain: />Wherein Y is a data vector, "> The method comprises the steps of monitoring ice coating thickness raw data of an ith measuring point on a wind power equipment blade in time; b is a data matrix, ">Parameter column->The element in (2) is the reaction of each influencing factor to the influence magnitude of the main factor; solving to obtain a development coefficient a and a driving coefficient b ij ；
The thickness prediction model of the ice coating measuring point of the ith rotating wind power equipment blade is as follows:
from the formulaSolving to obtain a predicted value +.f of the icing thickness of the ith measuring point on the rotating wind power equipment blade in the monitoring time>
Further, the wind power blade icing disaster prediction model has the following prediction process:
setting an ice coating thickness upper limit abnormal value, namely an ice coating disaster value xi, for an ice coating thickness prediction data sequence on an ith measuring point of a blade of the rotary wind power equipment;
obtaining an icing disaster sequence X based on the icing disaster value xi iξ ：
X iξ ＝{x i [q(1)],x i [q(2)],...,x i [q(l)]}＝{x i [q(k)]≥ξ,k＝1 , 2.. I }, wherein q (k) is a disaster time sequence number and i is an acquisition time sequence originalThe number of cycles of the data;
obtaining a wind power blade icing disaster date sequence on the ith measuring point based on the icing disaster sequenceBased on->Obtaining a 1-AGO sequence of icing disaster date of wind power bladeWherein q i (l) Is the disaster time serial number of the ith measuring point of the first period,the value after 1-AGO is carried out for the disaster time sequence number of the ith measuring point in the first period, i=1, 2, …, m, and m is the number of monitoring points arranged on the wind power blade;
and calculating the icing disaster date 1-AGO sequence of the wind power blade to obtain the moment when the icing thickness value of the wind power blade reaches the upper limit of the abnormal value, and obtaining the position where the icing thickness value reaches the upper limit of the abnormal value according to the value of i.
Compared with the prior art, the invention discloses the method for predicting the icing disaster of the rotating wind power blade, which has the following beneficial effects:
1. according to the invention, based on the collected vibration signals, not only can the icing thickness of different positions of the wind power blade be accurately predicted, but also the moment of icing disaster can be accurately predicted, so that a worker can conveniently and timely and effectively operate and maintain the wind power blade, and the service life of the wind power blade is prolonged;
2. the invention can provide theoretical basis for anti-icing and deicing of wind power equipment blades, provides basic data for running and maintenance of rotating wind power blades at different icing positions and icing thicknesses, and has important significance for improving running reliability of wind power equipment, reducing power loss of wind power equipment and reducing running accidents of wind power equipment.
3. The method has the advantages of simple calculation process, high calculation efficiency, no higher calculation performance requirement on hardware equipment and higher popularization value;
4. the required sensor types and the number of measuring points are small, the realization cost is low, and the blade cannot be damaged newly.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the method provided by the invention.
FIG. 2 is a schematic diagram of a test process of the icing vibration test platform of the rotary wind power blade; wherein: the device comprises a water tank 1, a high-pressure water pump 2, an axial flow fan 3, a high-pressure spray head 4, wind power blades 5, a collecting ring 6, a triaxial acceleration sensor 7, a computer 8, a case and a data acquisition card 9.
FIG. 3 is a diagram showing a three-axis acceleration sensor measuring point arrangement provided by the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
With reference to fig. 1, the embodiment of the invention discloses a method for predicting icing disasters of a rotating wind power blade, which comprises the following steps:
simulating the actual running environment of the rotating wind power blade through the icing vibration test platform of the rotating wind power blade;
collecting vibration signals of the rotating wind power blade in different icing states and icing influence factor data;
preprocessing vibration signals in different icing states to obtain vibration characteristic data in different icing states; collecting all vibration characteristic data as sample data;
constructing a wind power blade state prediction model based on the sample data and the icing influence factor data; obtaining the icing state of the wind power blade according to the output prediction result;
and constructing a wind power blade icing disaster prediction model based on a gray theory according to the icing state of the wind power blade, and obtaining the position and moment of the icing disaster in the next time sequence of different positions of the wind power blade according to the prediction result output by the wind power blade icing disaster prediction model.
Preferably, the icing state includes: ice coating thickness and ice coating position; the icing influencing factors at least comprise: temperature, humidity, wind speed and run time.
Preferably, in combination with fig. 2, the rotary wind power blade icing vibration test platform includes: the device comprises a water tank 1, a high-pressure water pump 2, an axial flow fan 3, a high-pressure spray head 4, wind power blades 5, a collecting ring 6, a triaxial acceleration sensor 7, a computer 8 and a case and data acquisition card 9;
through rotatory wind-powered electricity generation blade icing vibration test platform, simulate rotatory wind-powered electricity generation blade actual operation environment specifically includes: the water in the water tank 1 is conveyed to the high-pressure spray head 4 through the high-pressure water pump 2, the high-pressure spray head 4 outputs water mist, the output water mist is blown to the wind turbine blade 5 through the axial fan 3, and the water mist covered on the wind turbine blade 5 is frozen to simulate a natural icing state, so that the actual running environment of the rotating wind turbine blade is restored. The actual running environment of the rotating wind power blade is restored, so that the collected data are more real, and the prediction result is more accurate and reliable.
Preferably, the water mist output can be adjusted through the high-pressure spray head 4, so that the humidity of the test environment can be adjusted;
preferably, the method for collecting vibration signals of the rotating wind power blade in different icing states specifically comprises the following steps:
collecting vibration signals of the rotating wind power blade in different icing states in real time by adopting a plurality of triaxial acceleration sensors; a plurality of triaxial acceleration sensors are arranged at different positions on the wind power blade with aerodynamic center near the blade leading edge.
Preferably, in connection with fig. 3, the plurality of triaxial acceleration sensor measurement points are specifically arranged as follows: the wind power blade has the extension of R, 4 triaxial acceleration sensors are sequentially arranged from the tip to the root of the wind power blade, corresponding measuring points 1 to 4 are numbered, and the distances between the measuring points 1 to 4 and the root are respectively 0.85R,0.55R,0.35R and 0.2R.
Preferably, the fan blade vibration signal acquisition device further comprises a collecting ring 6 arranged at the center of the fan blade rotating shaft and used for being connected with a plurality of triaxial acceleration sensors so as to ensure stable transmission of the acquired rotating blade vibration signals.
Preferably, the vibration signal is preprocessed, specifically including:
the data acquisition and preprocessing are completed through the case and the data acquisition card 9; the pretreatment comprises the following steps: the missing values of the collected vibration signals are processed by adopting a mean value interpolation method, and the collected vibration signals are filtered by adopting a Kalman method to filter noise signals.
Preferably, the chassis and the data acquisition card 9 specifically include: an NI-9230 data acquisition card and a CDAQ-9171 chassis, wherein the CDAQ-9171 chassis is used for controlling timing, synchronization and data transmission between the I/O module and the computer 8.
Preferably, the temperature and humidity data are measured and collected by a high-precision hygrothermograph; wind speed data may be collected by AM-4201 hand-held digital anemometer measurements; the run-time data is collected by a stopwatch.
Preferably, the wind power blade state prediction model is constructed, and specifically comprises the following steps:
obtaining time sequence original data of one period through experiments, wherein the original data comprises: blade icing thickness of different monitoring points and 4 icing influence factor sample data sequences;
the collected blade icing thickness of different monitoring points and 4 icing influence factor sample data sequences are accumulated once and generated and recorded as Wherein m is the number of monitoring points arranged on the wind power blade, n is the number of factors affecting the thickness of the icing, and +.>To monitor the original sequence of the jth factor affecting the icing thickness at the ith measuring point on the rotating wind blade in time, for +.>Adding to generate 1-AGO once to obtain +.>
For a pair ofGenerating the immediate mean value to obtain->Wherein (1)>Is->Next to the mean sequence, k=1, 2, …, l;
establishing a differential equation:wherein (1)>Is the gray derivative; a is the development coefficient, < >>To drive items, b ij To drive outDynamic coefficients;
for parameter columnsAnd (5) carrying out least square estimation to obtain: />Wherein Y is a data vector, "> In order to monitor the ice coating thickness original data of the ith measuring point on the wind power equipment blade in time, T is a transposed matrix mark; b is a matrix of data which is to be displayed,parameter column->The element in (2) is the reaction of each influencing factor to the influence magnitude of the main factor; solving to obtain a development coefficient a and a driving coefficient b ij ；
The icing influence factors are taken as input, the acquired vibration characteristic data of different positions of the rotary wind power blade are taken as intermediate quantity, the icing thickness of the rotary wind power blade is taken as output, a model of the icing thickness GM (1, N) of the rotary wind power blade is constructed, and the thickness prediction model of the icing measuring point of the ith rotary wind power equipment blade is as follows:
from the formulaSolving to obtain a predicted value +.f of the icing thickness of the ith measuring point on the rotating wind power equipment blade in the monitoring time>
Preferably, the method further comprises a prediction model reliability test, and specifically comprises the following steps:
taking the average percentage error (MMAPE) and the root mean square error (RRMSE) as reliability evaluation indexes of a prediction model, wherein the smaller the two reference index values are, the smaller the actual prediction value error is, and the specific formula is as follows:
wherein M is MAPE R is the average absolute percentage error RMSE Is the root mean square error, l is the number of samples,for the actual value of the ice coating thickness, < >>And outputting a predicted value of the ice coating thickness for the prediction model.
Preferably, the wind power blade icing disaster prediction model comprises the following prediction processes:
setting an ice coating thickness upper limit abnormal value, namely an ice coating disaster value xi, for an ice coating thickness prediction data sequence on an ith measuring point of a blade of the rotary wind power equipment;
obtaining an icing disaster sequence X based on the icing disaster value xi iξ ：
X iξ ＝{x i [q(1)],x i [q(2)],...,x i [q(l)]}＝{x i [q(k)]More than or equal to ζ, k=1, 2.. Degree.l., where q (k) is a disaster time sequence number, and l is a cycle number for acquiring time-series original data;
obtaining a wind power blade icing disaster date sequence on an ith measuring point based on the icing disaster sequence Based on->Obtaining a wind power blade icing disaster date 1-AGO sequence-> Wherein q i (l) Disaster time sequence number for ith measuring point of the first period,/for the first period>The value after 1-AGO is carried out for the disaster time sequence number of the ith measuring point in the first period, i=1, 2, …, m, and m is the number of monitoring points arranged on the wind power blade;
and calculating a 1-AGO sequence of the icing disaster date of the wind power blade to obtain the moment when the icing thickness value of the wind power blade reaches the upper limit of the abnormal value, and obtaining the position where the icing thickness value reaches the upper limit of the abnormal value according to the value of i.
And analyzing the time of occurrence of the abnormal value of the icing state in a certain time sequence, and searching the regularity of occurrence of the abnormal value of the icing thickness of different measuring points of the wind power blade under different environmental conditions. And the moment when abnormal values appear in the icing thickness of the wind power blade at different measuring points in the next time sequence is predicted, and the specific position of the icing disaster is obtained according to the icing disaster prediction results of the different measuring points.
According to the invention, the actual running environment is simulated by rotating the wind power blade icing vibration test platform; collecting vibration signals of the rotating wind power blade in different icing states and icing influence factor data; preprocessing the collected vibration signals in different icing states to obtain and collect vibration characteristic data in different icing states as sample data; constructing a wind power blade state prediction model based on the sample data and the icing influence factor data; and obtaining the icing state of the wind power blade according to the output result; and constructing a wind power blade icing disaster prediction model based on a gray theory according to the icing state of the wind power blade, and obtaining the position and moment of the icing disaster in the next time sequence of different positions of the wind power blade according to the output prediction result and the set icing disaster value. Has the following beneficial effects:
1. according to the invention, based on the collected vibration signals, not only can the icing thickness of different positions of the wind power blade be accurately predicted, but also the moment of icing disaster can be accurately predicted, so that a worker can conveniently and timely and effectively operate and maintain the wind power blade, and the service life of the wind power blade is prolonged;
2. the invention can provide theoretical basis for anti-icing and deicing of wind power equipment blades, provides basic data for running and maintenance of rotating wind power blades at different icing positions and icing thicknesses, and has important significance for improving running reliability of wind power equipment, reducing power loss of wind power equipment and reducing running accidents of wind power equipment.
3. The method has the advantages of simple calculation process, high calculation efficiency, no higher calculation performance requirement on hardware equipment and higher popularization value;
4. the required sensor types and the number of measuring points are small, the realization cost is low, and the blade cannot be damaged newly.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. The method for predicting the icing disaster of the rotating wind power blade is characterized by comprising the following steps of:
simulating the actual running environment of the rotating wind power blade through the icing vibration test platform of the rotating wind power blade;
collecting vibration signals of the rotating wind power blade in different icing states and icing influence factor data;
preprocessing the vibration signals in different icing states to obtain vibration characteristic data in different icing states; taking all the vibration characteristic data as sample data;
constructing a wind power blade state prediction model based on the sample data and the icing influence factor data; obtaining the icing state of the wind power blade according to the output prediction result;
and constructing a wind power blade icing disaster prediction model based on a gray theory according to the icing state of the wind power blade, and obtaining the position and moment of the icing disaster in the next time sequence of different positions of the wind power blade according to the prediction result output by the wind power blade icing disaster prediction model and the set icing disaster value.
2. The method for predicting ice coating disaster of a rotating wind power blade according to claim 1, wherein the ice coating state comprises: ice coating thickness and ice coating position; the icing influencing factors at least comprise: temperature, humidity, wind speed and run time.
3. The method for predicting the icing disaster of the rotating wind power blade according to claim 1, wherein the method for simulating the actual running environment of the rotating wind power blade by the icing vibration test platform of the rotating wind power blade specifically comprises the following steps:
the water in the water tank is conveyed to the high-pressure spray head through the high-pressure water pump, the high-pressure spray head outputs water mist, the output water mist is blown to the wind turbine blade through the axial flow fan, and the water mist covered on the wind turbine blade is frozen to simulate a natural icing state, so that the actual running environment of the rotating wind turbine blade is restored.
4. The method for predicting ice coating disasters of a rotating wind power blade according to claim 1, wherein the collecting vibration signals of the rotating wind power blade in different ice coating states specifically comprises:
collecting vibration signals of the rotating wind power blade in different icing states in real time by adopting a plurality of triaxial acceleration sensors; the plurality of tri-axial acceleration sensors are arranged at different locations on the wind power blade with the aerodynamic center near the leading edge of the blade.
5. The method for predicting ice coating disasters of a rotating wind power blade according to claim 1, wherein the preprocessing of the vibration signal specifically comprises:
the missing values of the collected vibration signals are processed by adopting a mean value interpolation method, and the collected vibration signals are filtered by adopting a Kalman method to filter noise signals.
6. The method for predicting ice coating disasters of a rotating wind power blade according to claim 2, wherein the constructing a wind power blade state prediction model specifically comprises:
obtaining time series original data of one period through experiments, wherein the original data comprises: blade icing thickness of different monitoring points and 4 icing influence factor sample data sequences;
the collected blade icing thicknesses of the different monitoring points and the 4 icing influence factor sample data sequences are accumulated once and generated and recorded as Wherein m is the number of monitoring points arranged on the wind power blade, n is the number of factors affecting the thickness of the icing, and +.>To monitor the original sequence of the jth factor affecting the icing thickness at the ith measuring point on the rotating wind blade in time, for +.>Adding to generate 1-AGO once to obtain +.>
For a pair ofGenerating the immediate mean value to obtain->Wherein (1)>Is->Next to the mean sequence, k=1, 2, …, l;
establishing a differential equation:wherein (1)>Is the gray derivative; a is the coefficient of development and,to drive items, b ij Is a driving coefficient;
for parameter columnsAnd (5) carrying out least square estimation to obtain: />Wherein Y is a data vector, "> The method comprises the steps of monitoring ice coating thickness raw data of an ith measuring point on a wind power equipment blade in time; b is a data matrix, ">Parameter column->The element in (2) is the reaction of each influencing factor to the influence magnitude of the main factor; solving to obtain a development coefficient a and a driving coefficient b ij ；
The thickness prediction model of the ice coating measuring point of the ith rotating wind power equipment blade is as follows:
from the formulaSolving to obtain a predicted value +.f of the icing thickness of the ith measuring point on the rotating wind power equipment blade in the monitoring time>
7. The method for predicting the icing disaster of the rotating wind power blade according to claim 1, wherein the wind power blade icing disaster prediction model is characterized in that the prediction process is as follows:
setting an ice coating thickness upper limit abnormal value, namely an ice coating disaster value xi, for an ice coating thickness prediction data sequence on an ith measuring point of a blade of the rotary wind power equipment;
obtaining an icing disaster sequence X based on the icing disaster value xi iξ ：
X iξ ＝{x i [q(1)],x i [q(2)],...,x i [q(l)]}＝{x i [q(k)]More than or equal to ζ, k=1, 2.. Degree.l., where q (k) is a disaster time sequence number, and l is a cycle number for acquiring time-series original data;
obtaining a wind power blade icing disaster date sequence on the ith measuring point based on the icing disaster sequenceBased on->Obtaining a 1-AGO sequence of icing disaster date of wind power bladeWherein q i (l) The disaster time sequence number of the ith measuring point of the ith period is the disaster time sequence number of the ith measuring point of the ith period,the value after 1-AGO is carried out for the disaster time sequence number of the ith measuring point in the first period, i=1, 2, …, m, and m is the number of monitoring points arranged on the wind power blade;
and calculating the icing disaster date 1-AGO sequence of the wind power blade to obtain the moment when the icing thickness value of the wind power blade reaches the upper limit of the abnormal value, and obtaining the position where the icing thickness value reaches the upper limit of the abnormal value according to the value of i.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310924821.3A CN116881662A (en) | 2023-07-26 | 2023-07-26 | Method for predicting icing disaster of rotating wind power blade |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310924821.3A CN116881662A (en) | 2023-07-26 | 2023-07-26 | Method for predicting icing disaster of rotating wind power blade |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116881662A true CN116881662A (en) | 2023-10-13 |
Family
ID=88258533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310924821.3A Pending CN116881662A (en) | 2023-07-26 | 2023-07-26 | Method for predicting icing disaster of rotating wind power blade |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116881662A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117759487A (en) * | 2023-11-20 | 2024-03-26 | 国家电投集团湖北电力有限公司风电分公司 | Blade icing-preventing performance detection method and system based on hanging piece test |
-
2023
- 2023-07-26 CN CN202310924821.3A patent/CN116881662A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117759487A (en) * | 2023-11-20 | 2024-03-26 | 国家电投集团湖北电力有限公司风电分公司 | Blade icing-preventing performance detection method and system based on hanging piece test |
| CN117759487B (en) * | 2023-11-20 | 2024-05-24 | 国家电投集团湖北电力有限公司风电分公司 | Blade icing-preventing performance detection method and system based on hanging piece test |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101706508B1 (en) | Data Analysis System of Mechanical Load Measurement Data for Wind Turbine | |
| CN106779208B (en) | Wind power ultra-short-term power prediction method based on virtual anemometer tower technology | |
| CN116881662A (en) | Method for predicting icing disaster of rotating wind power blade | |
| CN110080921B (en) | Online monitoring and evaluating method and system for main water inlet valve of pumped storage power station | |
| CN104122086A (en) | Kriging model based wind turbine gearbox fault diagnosis method | |
| CN114692669A (en) | Forecasting method and application of three-dimensional space attitude of offshore wind turbine | |
| CN105758602A (en) | Truss girder bridge section buffeting force synchronous measurement method | |
| Wang et al. | EEMD-based videogrammetry and vibration analysis method for rotating wind power blades | |
| CN113357099B (en) | Fatigue diagnosis and detection method for fan tower drum based on acceleration sensor | |
| CN102298072B (en) | High precision wind measuring device with micro-differential pressure type and method thereof | |
| CN110987396A (en) | Intelligent fault diagnosis and service life prediction method for coal mining machine rocker arm | |
| CN104008284A (en) | Correcting method for anemometer tower in numerical weather prediction | |
| CN105138845B (en) | The method for obtaining wind-driven generator air speed value | |
| CN109798226B (en) | Wind turbine generator tower load prediction method and system | |
| CN103217507A (en) | Wireless intelligent carbon sequestration monitoring system | |
| CN113344252A (en) | Wind power prediction method based on virtual meteorological technology | |
| CN106225916B (en) | The quantitative of fixed offshore platform security reliability, online detection method | |
| CN203275384U (en) | Wireless intelligent carbon sink monitoring system | |
| WO2018073688A1 (en) | Determining loads on a wind turbine | |
| CN116256016A (en) | Whole process health monitoring system of building structure system | |
| CN109100102B (en) | Fan modal analysis method, device, terminal and computer readable storage medium based on strain continuous monitoring | |
| CN110942218B (en) | Method, device and system for calculating online electric quantity of wind power plant | |
| CN202041228U (en) | Building group energy consumption monitoring device based on thermotechnical parameter field monitoring | |
| CN111325440A (en) | Method and device for estimating wind speed of free flow of wind measuring tower of wind power plant | |
| CN111561907A (en) | Tower drum uneven settlement monitoring method based on plane dip angle measurement |
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 |