CN114135449B - Wind turbine generator blade fault early warning method - Google Patents
Wind turbine generator blade fault early warning method Download PDFInfo
- Publication number
- CN114135449B CN114135449B CN202111496602.7A CN202111496602A CN114135449B CN 114135449 B CN114135449 B CN 114135449B CN 202111496602 A CN202111496602 A CN 202111496602A CN 114135449 B CN114135449 B CN 114135449B
- Authority
- CN
- China
- Prior art keywords
- wind speed
- score
- speed
- coordinate value
- obtaining
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000007621 cluster analysis Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 206010061619 Deformity Diseases 0.000 description 1
- 235000012571 Ficus glomerata Nutrition 0.000 description 1
- 244000153665 Ficus glomerata Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Wind Motors (AREA)
Abstract
The embodiment of the invention provides a wind turbine generator blade fault early warning method, and relates to the field of wind turbine generators. The method aims at solving the problem that damage and faults in the blades of the wind turbine generator are difficult to evaluate. The method comprises the steps of obtaining a first score representing the running condition of wind speed-power, a second score representing the running condition of wind speed-hub rotating speed and a third score representing the running condition of wind speed-tip speed ratio according to a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios; obtaining a fourth score representing the running condition of the axial second-level vibration data according to the plurality of groups of axial second-level vibration data; and determining the state of the wind turbine blade according to the first score, the second score, the third score and the fourth score. And obtaining a first score, a second score, a third score and a fourth score according to the wind speed-power, the wind speed-hub rotating speed, the wind speed-tip speed ratio and the axial second vibration data, and determining the state of the wind turbine generator blade according to the scores, so that the evaluation difficulty is reduced.
Description
Technical Field
The invention relates to the field of wind turbine generators, in particular to a wind turbine generator blade fault early warning method.
Background
Wind energy is a clean renewable energy source, and the wind power generation industry in recent years develops rapidly. However, damage to large parts of the wind turbine generator system caused by various reasons such as environmental disfigurement of the wind farm causes great obstruction to the wind power industry, and especially shutdown replacement caused by cracking of blades is avoided. Therefore, the control of the running state of the blades of the wind turbine is urgent. In the related art, the problem that the dominant fault of the wind turbine generator blade is difficult to evaluate exists.
Disclosure of Invention
The invention aims at providing a wind turbine generator blade fault early warning method, which can be used for example.
Embodiments of the invention may be implemented as follows:
the embodiment of the invention provides a wind turbine generator blade fault early warning method, which comprises the following steps:
acquiring a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios in a first preset time period;
acquiring multiple groups of axial second-level vibration data in a second preset time period;
obtaining a first score representing the running condition of the wind speed-power, a second score representing the running condition of the wind speed-hub rotating speed and a third score representing the running condition of the wind speed-tip speed ratio according to a plurality of groups of the wind speed-power, a plurality of groups of the wind speed-hub rotating speeds and a plurality of groups of the wind speed-tip speed ratios;
obtaining a fourth score representing the running condition of the axial second-level vibration data according to a plurality of groups of the axial second-level vibration data;
and determining the state of the wind turbine blade according to the first score, the second score, the third score and the fourth score.
In addition, the wind turbine generator blade fault early warning method provided by the embodiment of the invention can also have the following additional technical characteristics:
optionally, the step of obtaining a first score representing the wind speed-power operation condition, a second score representing the wind speed-hub rotation speed operation condition, and a third score representing the wind speed-tip speed ratio operation condition according to the plurality of groups of wind speed-power, the plurality of groups of wind speed-hub rotation speeds, and the plurality of groups of wind speed-tip speed ratios includes:
obtaining a maximum wind speed-power coordinate value and a minimum wind speed-power coordinate value of each wind speed section according to a plurality of groups of wind speed-power, obtaining a first intermediate score representing the running condition of each wind speed section according to the maximum wind speed-power coordinate value and the minimum wind speed-power coordinate value, and obtaining the first score according to a plurality of first intermediate scores;
obtaining a maximum coordinate value of the wind speed-hub rotating speed and a minimum coordinate value of the wind speed-hub rotating speed of each wind speed section according to a plurality of groups of wind speed-hub rotating speeds, obtaining a second intermediate score representing the running condition of each wind speed section according to the maximum coordinate value of the wind speed-hub rotating speed and the minimum coordinate value of the wind speed-hub rotating speed, and obtaining the second score according to a plurality of second intermediate scores;
obtaining a maximum wind speed-tip speed ratio coordinate value and a minimum wind speed-tip speed ratio coordinate value of each wind speed section according to a plurality of groups of wind speed-tip speed ratios, obtaining a third intermediate score representing the running condition of each wind speed section according to the maximum wind speed-tip speed ratio coordinate value and the minimum wind speed-tip speed ratio coordinate value, and obtaining the third score according to a plurality of third intermediate scores.
Optionally, the step of obtaining a maximum wind speed-power coordinate value and a minimum wind speed-power coordinate value of each wind speed segment according to a plurality of groups of the wind speed-power, obtaining a first intermediate score representing the running condition of each wind speed segment according to the maximum wind speed-power coordinate value and the minimum wind speed-power coordinate value, and obtaining the first score according to a plurality of the first intermediate scores includes:
the maximum coordinate value of the wind speed and the power isThe minimum coordinate value of wind speed and power is +.>；
The first intermediate score is，/>；
The first score is，/>；
And so on to obtain the second score T 2 And the third score T 3 。
Optionally, the step of obtaining a maximum wind speed-power coordinate value and a minimum wind speed-power coordinate value of each wind speed segment according to multiple groups of the wind speed-power, obtaining a first intermediate score representing the running condition of each wind speed segment according to the maximum wind speed-power coordinate value and the minimum wind speed-power coordinate value, and obtaining the first score according to multiple first intermediate scores further includes:
according to a cluster analysis method, processing a plurality of groups of wind speed-power to obtain the maximum coordinate value of the wind speed-power of each wind speed section as followsThe minimum coordinate value of wind speed and power is +.>。
Optionally, the step of acquiring multiple sets of axial second-level vibration data in a second preset period of time includes:
obtaining a time point corresponding to a data point with the maximum deviation degree according to a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios;
the time point is t1, and the second preset time period is t1-h to t1+h.
Optionally, the step of obtaining the time point corresponding to the data point with the greatest deviation degree according to the plurality of groups of wind speed-power, the plurality of groups of wind speed-hub rotating speeds and the plurality of groups of wind speed-tip speed ratios includes:
according to a cluster analysis method, processing a plurality of groups of wind speed-power to obtain first data with the maximum wind speed-power deviation degree;
according to a cluster analysis method, processing a plurality of groups of wind speed-hub rotating speeds to obtain second data with the maximum wind speed-hub rotating speed deviation degree;
according to a cluster analysis method, processing a plurality of groups of wind speed-tip speed ratios to obtain third data with the maximum wind speed-tip speed ratio deviation degree;
and obtaining the data point with the maximum deviation degree according to the first data, the second data and the third data.
Optionally, the step of obtaining a fourth score representing the running condition of the axial second-order vibration data according to multiple groups of the axial second-order vibration data comprises the following steps:
processing a plurality of groups of axial second-level vibration data according to a Fourier series transformation algorithm to obtain a maximum coordinate value of a y axis;
and obtaining the fourth score according to the maximum coordinate value of the y axis.
Optionally, the step of obtaining the fourth score according to the maximum coordinate value of the y-axis includes:
the maximum coordinate value of the Y axis is Y, and when Y is more than or equal to 2, the fourth score T 4 =1; when Y < 2, the fourth score T 4 =0。
Optionally, the step of determining the state of the wind turbine blade according to the first score, the second score, the third score and the fourth score includes:
according to the first score of T 1 The second score T 2 The third score T 3 Said fourth score T 4 Yielding an overall score of t=t 1 +T 2 +T 3 +T 4 ；
And determining the state of the wind turbine blade according to the overall score T.
Optionally, the step of determining the state of the wind turbine blade according to the overall score T includes:
。
the wind turbine blade fault early warning method provided by the embodiment of the invention has the beneficial effects that:
the wind turbine generator blade fault early warning method comprises the steps of obtaining a first score for representing the running condition of wind speed-power, a second score for representing the running condition of wind speed-hub rotating speed and a third score for representing the running condition of wind speed-tip speed ratio according to a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios; obtaining a fourth score representing the running condition of the axial second-level vibration data according to the plurality of groups of axial second-level vibration data; and determining the state of the wind turbine blade according to the first score, the second score, the third score and the fourth score.
The first score, the second score, the third score and the fourth score are obtained according to the wind speed-power, the wind speed-hub rotating speed, the wind speed-tip speed ratio and the axial second vibration data, then the state of the wind turbine generator blade is determined according to the scores, the scores are accurate, the state of the blade can be intuitively determined, and the evaluation difficulty is reduced. The problem of dominant faults of the wind turbine generator blades can be quickly pre-warned, and particularly, the fault pre-warning of large components according to the short-term historical operation data of the wind turbine generator is realized aiming at judging dominant faults on the surfaces of the wind turbine generator blades and large cracks in the wind turbine generator blades. The method has important help in the aspect of monitoring the performance of the wind turbine generator.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart diagram of a wind turbine blade fault early warning method provided by an embodiment of the invention;
FIG. 2 is a block flow diagram of step S2 in a wind turbine blade failure early warning method provided by an embodiment of the invention;
FIG. 3 is a block flow diagram of step S3 in a wind turbine blade failure early warning method provided by an embodiment of the invention;
FIG. 4 is a block flow diagram of step S4 in a wind turbine blade failure early warning method according to an embodiment of the present invention;
fig. 5 is a flowchart of step S5 in the wind turbine generator blade fault early warning method according to the embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be noted that, if the terms "upper", "lower", "inner", "outer", and the like indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, or the azimuth or the positional relationship in which the inventive product is conventionally put in use, it is merely for convenience of describing the present invention and simplifying the description, and it is not indicated or implied that the apparatus or element referred to must have a specific azimuth, be configured and operated in a specific azimuth, and thus it should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, if any, are used merely for distinguishing between descriptions and not for indicating or implying a relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
The method for early warning of the failure of the wind turbine blade according to the present embodiment is described in detail below with reference to fig. 1 to 5.
Referring to fig. 1, an embodiment of the present invention provides a wind turbine generator blade fault early warning method, including:
step S1, acquiring a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios in a first preset time period;
s2, acquiring multiple groups of axial second-level vibration data in a second preset time period;
step S3, obtaining a first score representing the running condition of the wind speed-power, a second score representing the running condition of the wind speed-hub rotating speed and a third score representing the running condition of the wind speed-tip speed ratio according to a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios;
step S4, obtaining a fourth score representing the running condition of the axial second-level vibration data according to a plurality of groups of axial second-level vibration data;
and S5, determining the state of the wind turbine generator blade according to the first score, the second score, the third score and the fourth score.
In step S1, the first preset time period may be one month, two months, or three months. For example, taking a 2MW wind turbine as a research object, collecting the wind speed-power, wind speed-hub rotating speed and wind speed-tip speed of the wind turbine for one month, preprocessing the data, and screening out the data when the wind turbine is in the following conditions: 1. a wind turbine generator set power limit state; 2. abnormal state of wind turbine generator; 3. and data outside the rated wind speed of the wind turbine generator. For example, data having an ambient temperature below 5 ℃ is deleted.
In the embodiment, the first score, the second score, the third score and the fourth score are obtained according to the wind speed-power, the wind speed-hub rotating speed, the wind speed-tip speed ratio and the axial second vibration data, then the state of the wind turbine generator blade is determined according to the scores, the scores are accurate, the state of the blade can be intuitively determined, and the evaluation difficulty is reduced.
Referring to fig. 3, in the present embodiment, step S3 includes:
step S31, obtaining a maximum wind speed-power coordinate value and a minimum wind speed-power coordinate value of each wind speed section according to a plurality of groups of wind speed-power, obtaining a first intermediate score representing the running condition of each wind speed section according to the maximum wind speed-power coordinate value and the minimum wind speed-power coordinate value, and obtaining a first score according to the plurality of first intermediate scores.
And S32, obtaining a maximum coordinate value of the wind speed-hub rotating speed and a minimum coordinate value of the wind speed-hub rotating speed of each wind speed section according to a plurality of groups of wind speed-hub rotating speeds, obtaining a second intermediate score representing the running condition of each wind speed section according to the maximum coordinate value of the wind speed-hub rotating speed and the minimum coordinate value of the wind speed-hub rotating speed, and obtaining the second score according to the plurality of second intermediate scores.
Step S33, obtaining a maximum wind speed-tip speed ratio coordinate value and a minimum wind speed-tip speed ratio coordinate value of each wind speed section according to a plurality of groups of wind speed-tip speed ratios, obtaining a third intermediate score representing the running condition of each wind speed section according to the maximum wind speed-tip speed ratio coordinate value and the minimum wind speed-tip speed ratio coordinate value, and obtaining a third score according to the plurality of third intermediate scores.
The wind speed-power, wind speed-hub rotation speed and wind speed-tip speed ratio are processed in the same way. In this embodiment, the wind speed interval is set to 0.5 m/s.
In this embodiment, step S31 includes:
step S311, taking wind speed-power as an example, the maximum coordinate value of wind speed-power isThe minimum coordinate value of wind speed and power is +.>；
A first intermediate score of，/>；
A first score of，/>。
Wind speed-power, wind speed-hub rotational speed, windThe scoring criteria for the three categories of speed-tip speed ratios are the same. Taking wind speed-power as an example, a wind speed interval is divided intoWherein->Assume that the cluster center coordinate of a certain wind speed interval has an upper and lower value of +.>Andthe wind speed section is scored +.>The method comprises the steps of carrying out a first treatment on the surface of the Total score of->。
And so on, the step S321 includes bringing the maximum coordinate value of the wind speed-hub rotation speed and the minimum coordinate value of the wind speed-hub rotation speed into the calculation T 1 In the formula of (1), a second score T is obtained 2 。
Step S331 includes bringing the maximum coordinate value of the wind speed-tip speed ratio and the minimum coordinate value of the wind speed-tip speed ratio into the above-mentioned T 1 In the formula of (1), a third score T is obtained 3 。
In this embodiment, step S31 further includes:
step S312, processing multiple groups of wind speed-power according to the cluster analysis method to obtain the maximum coordinate value of wind speed-power of each wind speed section asThe minimum coordinate value of wind speed and power is +.>。
The K-Means clustering algorithm model is as follows:
the idea of the K-Means algorithm is to divide a specified sample set into K categories, called K cluster trees. So that the sample sets of the class are closely connected together and as far as possible from sample data outside the sample set.
Assuming that the sample set isThe output cluster class is divided into +.>Square error->To determine the K value:
wherein the method comprises the steps ofIs->Is a centroid of (c).
After determining the number of clusters of the sample set, assume that the data points in the same cluster areThe distance between the sample and the cluster core is:
the effectiveness of the clustering result is measured by adopting the contour coefficient. Presuming a sampleThe average distance to other sample points within the cluster is +.>The method comprises the steps of carrying out a first treatment on the surface of the Sample->The average distance to other sample points in other clusters is +.>Will->Defined as sample->Inter-cluster dissimilarity of (a):
profile coefficient：
From the above equation, the contour coefficient is an important parameter for evaluating the number of clusters, so as to evaluate the rationality of the number of clusters, and determine the accuracy of the clustering algorithm. In the embodiment, the hub coefficient is close to 1 at the interval of 0.5 m/s, and the effect is optimal.
Similarly, step S32 further includes:
and S322, processing a plurality of groups of wind speed-hub rotating speeds according to a cluster analysis method to obtain a maximum coordinate value of the wind speed-hub rotating speed and a minimum coordinate value of the wind speed-hub rotating speed of each wind speed section.
Similarly, step S33 further includes:
and S332, processing a plurality of groups of wind speed-tip speed ratios according to a cluster analysis method to obtain a maximum coordinate value of the wind speed-tip speed ratio and a minimum coordinate value of the wind speed-tip speed ratio of each wind speed section.
Referring to fig. 2, in the present embodiment, step S2 includes:
step S21, obtaining a time point corresponding to a data point with the maximum deviation degree according to a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios;
in step S22, the time point is t1, and the second preset time period is t1-h to t1+h.
After the time t1 is obtained, the time t1 is taken as a time center point to move back and forth for a time period h, a second preset time period is obtained, and then axial second-level vibration data in the second preset time period are called.
Referring to fig. 2, in the present embodiment, step S21 includes:
step S211, processing a plurality of groups of wind speed-power according to a cluster analysis method to obtain first data with the maximum wind speed-power deviation degree;
step S212, processing a plurality of groups of wind speed-hub rotating speeds according to a cluster analysis method to obtain second data with the maximum wind speed-hub rotating speed deviation degree;
step S213, processing a plurality of groups of wind speed-tip speed ratios according to a cluster analysis method to obtain third data with the maximum wind speed-tip speed ratio deviation degree;
in step S214, the data point with the greatest deviation degree is obtained according to the first data, the second data and the third data.
Referring to fig. 4, in the present embodiment, step S4 includes:
s41, processing a plurality of groups of axial second-level vibration data according to a Fourier series transformation algorithm to obtain a maximum coordinate value of a y axis;
and S42, obtaining a fourth score according to the maximum coordinate value of the y axis.
Referring to fig. 4, in the present embodiment, step S42 includes:
step S421, the maximum coordinate value of the Y-axis is Y, and when Y is more than or equal to 2, the fourth score T 4 =1; when Y < 2, then the fourth score T 4 =0。
Referring to fig. 5, in the present embodiment, step S5 includes:
referring to FIG. 5, step S51, a score T is determined according to the first score 1 Second score T 2 Third score T 3 Fourth score T 4 Yielding an overall score of t=t 1 +T 2 +T 3 +T 4 ；
Referring to FIG. 5, step S52, the state of the wind turbine blade is determined based on the overall score T.
In this embodiment, step S52 includes:
in step S521, a step of,。
finally, example verification can be performed as follows.
30 wind turbines of a certain wind power plant in the south of China are taken as research objects, the wind turbines of the wind power plant are composed of three types of 2MW, 2.5MW and 3.2MW, and three wind turbines have blade failure phenomena of different degrees. The data segment is randomly extracted as 1 month, 3 months and 5 months.
Firstly, preprocessing data, and screening out operation data in abnormal conditions; and secondly, respectively acquiring wind speed-power, wind speed-hub rotating speed, wind speed-tip speed ratio and axial second-level vibration data of the wind turbine generator. And three wind motor groups are judged as follows according to the scoring standard of the wind turbine blade faults through cluster analysis: blade failure.
The experimental results show that: the wind power plant has three wind motor group blade faults, and the judging accuracy is 100%; one 3.2MW wind turbine realizes early warning of the fault of the pre-judging blade.
According to the wind turbine generator blade fault early warning method provided by the embodiment, the working principle of the wind turbine generator blade fault early warning method is as follows:
firstly, preprocessing data, and screening out abnormal operation data of a wind turbine generator; secondly, classifying the hub rotation speed-hub torque, wind speed-power, wind speed-hub rotation speed, wind speed-tip speed ratio and vibration data by using cluster analysis, and calculating cluster center interval distances of all interval sections respectively; and finally, judging the dominant fault possibility of the wind turbine blade according to the dominant fault judging rule of the wind turbine blade. The feasibility of the dominant fault early warning method of the wind turbine generator blade based on cluster analysis is verified through the example, and early warning can be performed in advance especially for damage inside the wind turbine generator blade. Has important significance in the aspect of early warning of faults of large components of the wind turbine generator.
The wind turbine generator blade fault early warning method provided by the embodiment has at least the following advantages:
according to the wind speed-power, the wind speed-hub rotating speed, the wind speed-tip speed ratio and the axial second vibration data, a first score, a second score, a third score and a fourth score are obtained, then the state of the wind turbine blade is determined according to the scores, the problem of dominant faults of the wind turbine blade can be quickly pre-warned, and particularly, the problem of fault pre-warning of large parts according to the short-term historical running data of the wind turbine is realized aiming at judging dominant faults on the surface and large cracks inside the wind turbine blade.
The method for early warning the faults of the wind turbine generator blades based on cluster analysis is provided, the feasibility of the method for early warning the faults of the wind turbine generator blades based on cluster analysis is verified through examples, and early warning can be performed in advance especially for damage inside the wind turbine generator blades. Has important significance in the aspect of early warning of faults of large components of the wind turbine generator.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present invention should be included in the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. The wind turbine generator blade fault early warning method is characterized by comprising the following steps of:
acquiring a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios in a first preset time period;
acquiring multiple groups of axial second-level vibration data in a second preset time period;
obtaining a maximum wind speed-power coordinate value and a minimum wind speed-power coordinate value of each wind speed section according to a plurality of groups of wind speed-power, obtaining a first intermediate score representing the running condition of each wind speed section according to the maximum wind speed-power coordinate value and the minimum wind speed-power coordinate value, and obtaining a first score according to a plurality of first intermediate scores;
obtaining a maximum coordinate value of the wind speed-hub rotating speed and a minimum coordinate value of the wind speed-hub rotating speed of each wind speed section according to a plurality of groups of wind speed-hub rotating speeds, obtaining a second intermediate score representing the running condition of each wind speed section according to the maximum coordinate value of the wind speed-hub rotating speed and the minimum coordinate value of the wind speed-hub rotating speed, and obtaining a second score according to a plurality of second intermediate scores;
obtaining a maximum wind speed-tip speed ratio coordinate value and a minimum wind speed-tip speed ratio coordinate value of each wind speed section according to a plurality of groups of wind speed-tip speed ratios, obtaining a third intermediate score representing the running condition of each wind speed section according to the maximum wind speed-tip speed ratio coordinate value and the minimum wind speed-tip speed ratio coordinate value, and obtaining a third score according to a plurality of third intermediate scores;
obtaining a fourth score representing the running condition of the axial second-level vibration data according to a plurality of groups of the axial second-level vibration data;
and determining the state of the wind turbine blade according to the first score, the second score, the third score and the fourth score.
2. The wind turbine blade failure early warning method according to claim 1, wherein the step of obtaining a wind speed-power maximum coordinate value and a wind speed-power minimum coordinate value of each wind speed segment according to a plurality of sets of the wind speed-power, obtaining a first intermediate score representing an operation condition of each wind speed segment according to the wind speed-power maximum coordinate value and the wind speed-power minimum coordinate value, and obtaining the first score according to a plurality of the first intermediate scores comprises:
the maximum coordinate value of the wind speed and the power isThe minimum coordinate value of wind speed and power is +.>；
The first intermediate score is according to formula 1，/>，/>A first intermediate score that is a single wind speed segment;
the first score is according to formula 2，/>N is the number of wind speed segments, +.>N first intermediate scores +.>Sum of (A)/(B)>Is the first intermediate score +.>The obtained score;
and analogically, obtaining a maximum coordinate value of the wind speed-hub rotating speed and a minimum coordinate value of the wind speed-hub rotating speed of each wind speed section according to a plurality of groups of wind speed-hub rotating speeds, obtaining a second intermediate score representing the running condition of each wind speed section according to the maximum coordinate value of the wind speed-hub rotating speed and the minimum coordinate value of the wind speed-hub rotating speed, and obtaining the second score according to a plurality of second intermediate scores, wherein the steps comprise:
substituting the maximum coordinate values of the wind speed and the hub rotating speed of the wind speed sections and the minimum coordinate values of the wind speed and the hub rotating speed into the formula 1 respectively to obtain a plurality of second intermediate scores T 2i， Scoring a plurality of second intermediate scores T 2i Substituting the formula 2 to obtain a second score T 2 ；
Obtaining a maximum wind speed-tip speed ratio coordinate value and a minimum wind speed-tip speed ratio coordinate value of each wind speed section according to a plurality of groups of wind speed-tip speed ratios, obtaining a third intermediate score representing the running condition of each wind speed section according to the maximum wind speed-tip speed ratio coordinate value and the minimum wind speed-tip speed ratio coordinate value, and obtaining the third score according to a plurality of third intermediate scores, wherein the step of obtaining the third score comprises the following steps:
substituting the maximum coordinate values of the wind speed-tip speed ratio and the minimum coordinate values of the wind speed-tip speed ratio of a plurality of wind speed sections into the formula 1 to obtain a plurality of third intermediate scores T 3i A plurality of third intermediate scores T 3i Substituting the formula 2 to obtain a third score T 3 。
3. The wind turbine blade failure pre-warning method according to claim 2, wherein,
the step of obtaining a wind speed-power maximum coordinate value and a wind speed-power minimum coordinate value of each wind speed section according to a plurality of groups of wind speed-power, obtaining a first intermediate score representing the running condition of each wind speed section according to the wind speed-power maximum coordinate value and the wind speed-power minimum coordinate value, and obtaining the first score according to a plurality of the first intermediate scores further comprises:
according to a cluster analysis method, processing a plurality of groups of wind speed-power to obtain the maximum coordinate value of the wind speed-power of each wind speed section as followsThe minimum coordinate value of wind speed and power is +.>。
4. The wind turbine blade failure warning method according to any one of claims 1 to 3, wherein the step of acquiring a plurality of sets of axial second-level vibration data within a second preset time period includes:
obtaining a time point corresponding to a data point with the maximum deviation degree according to a plurality of groups of wind speed-power, a plurality of groups of wind speed-hub rotating speeds and a plurality of groups of wind speed-tip speed ratios;
the time point is t1, the second preset time period is t1-h to t1+h, and h is a time period.
5. The wind turbine blade failure pre-warning method according to claim 4, wherein the step of obtaining the time point corresponding to the data point with the greatest deviation degree according to the plurality of groups of wind speed-power, the plurality of groups of wind speed-hub rotating speeds and the plurality of groups of wind speed-tip speed ratios comprises:
according to a cluster analysis method, processing a plurality of groups of wind speed-power to obtain first data with the maximum wind speed-power deviation degree;
according to a cluster analysis method, processing a plurality of groups of wind speed-hub rotating speeds to obtain second data with the maximum wind speed-hub rotating speed deviation degree;
according to a cluster analysis method, processing a plurality of groups of wind speed-tip speed ratios to obtain third data with the maximum wind speed-tip speed ratio deviation degree;
and obtaining the data point with the maximum deviation degree according to the first data, the second data and the third data.
6. The wind turbine blade failure warning method according to any one of claims 1 to 3, wherein the step of obtaining a fourth score representing the running condition of the axial second-order vibration data according to the plurality of sets of the axial second-order vibration data comprises:
processing a plurality of groups of axial second-level vibration data according to a Fourier series transformation algorithm to obtain a maximum coordinate value of a y axis;
and obtaining the fourth score according to the maximum coordinate value of the y axis.
7. The wind turbine blade failure warning method of claim 6, wherein,
the step of obtaining the fourth score according to the maximum coordinate value of the y axis comprises the following steps:
the maximum coordinate value of the Y axis is Y, and when Y is more than or equal to 2, the fourth score T 4 =1; when Y < 2, the fourth score T 4 =0。
8. A wind turbine blade failure warning method according to any one of claims 1 to 3, wherein the step of determining the state of the wind turbine blade based on the first score, the second score, the third score and the fourth score comprises:
according to the first score of T 1 The second score T 2 The third score T 3 Said fourth score T 4 Yielding an overall score of t=t 1 +T 2 +T 3 +T 4 ；
And determining the state of the wind turbine blade according to the overall score T.
9. The wind turbine blade failure warning method according to claim 8, wherein the step of determining the state of the wind turbine blade according to the overall score T includes:
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111496602.7A CN114135449B (en) | 2021-12-09 | 2021-12-09 | Wind turbine generator blade fault early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111496602.7A CN114135449B (en) | 2021-12-09 | 2021-12-09 | Wind turbine generator blade fault early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114135449A CN114135449A (en) | 2022-03-04 |
| CN114135449B true CN114135449B (en) | 2024-03-26 |
Family
ID=80385108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111496602.7A Active CN114135449B (en) | 2021-12-09 | 2021-12-09 | Wind turbine generator blade fault early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114135449B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105065212A (en) * | 2015-08-13 | 2015-11-18 | 南车株洲电力机车研究所有限公司 | Checking method and system of wind generation sets of wind power plant |
| JP2019027860A (en) * | 2017-07-27 | 2019-02-21 | 日本精工株式会社 | System and method for performing abnormality diagnosis on rotary machine facility |
| CN110005580A (en) * | 2019-05-06 | 2019-07-12 | 保定绿动风电设备科技有限公司 | A kind of running of wind generating set state monitoring method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DK2757252T3 (en) * | 2013-01-17 | 2018-03-26 | Ge Renewable Tech | Procedure for operating a wind turbine |
| JP2018059450A (en) * | 2016-10-06 | 2018-04-12 | 株式会社日立製作所 | Wind power generation device and control method of wind power generation device |
-
2021
- 2021-12-09 CN CN202111496602.7A patent/CN114135449B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105065212A (en) * | 2015-08-13 | 2015-11-18 | 南车株洲电力机车研究所有限公司 | Checking method and system of wind generation sets of wind power plant |
| JP2019027860A (en) * | 2017-07-27 | 2019-02-21 | 日本精工株式会社 | System and method for performing abnormality diagnosis on rotary machine facility |
| CN110005580A (en) * | 2019-05-06 | 2019-07-12 | 保定绿动风电设备科技有限公司 | A kind of running of wind generating set state monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114135449A (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106682814B (en) | Wind turbine generator fault intelligent diagnosis method based on fault knowledge base | |
| US8141416B2 (en) | Systems and methods for identifying wind turbine performance inefficiency | |
| CN112304613B (en) | Wind turbine generator bearing early warning method based on feature fusion | |
| CN108932580A (en) | Wind turbines pitch variable bearings wear monitoring and method for early warning based on data modeling | |
| CN108072524B (en) | Wind turbine generator gearbox bearing fault early warning method | |
| CN111878320B (en) | Monitoring method and system of wind generating set and computer readable storage medium | |
| CN107728059B (en) | Pitch system state evaluation method | |
| CN108304350B (en) | Fan index prediction and fault early warning method based on big data set neighbor strategy | |
| CN111209934A (en) | Fan fault prediction and alarm method and system | |
| Peng et al. | Research on fault diagnosis of wind power generator blade based on SC-SMOTE and kNN | |
| CN114135449B (en) | Wind turbine generator blade fault early warning method | |
| CN116771610A (en) | Method for adjusting fault evaluation value of variable pitch system of wind turbine | |
| CN114295367B (en) | Wind turbine generator system gear box working condition on-line monitoring method | |
| KR102226971B1 (en) | Method for fault diagnosis based on multiple variables and apparatus using the method | |
| CN112211794B (en) | Cabin temperature abnormity early warning method, device, equipment and medium of wind turbine generator | |
| CN116557230A (en) | Wind power plant unit power abnormality online assessment method and system | |
| Pang et al. | Multi kernel fusion convolutional neural network for wind turbine fault diagnosis | |
| Han et al. | Characteristic curve fitting method of wind speed and wind turbine output based on abnormal data cleaning | |
| CN114169681A (en) | Wind turbine generator power curve data preprocessing method considering space-time outlier detection | |
| CN113946977A (en) | Application method for early warning of fan variable pitch fault based on decision tree algorithm | |
| Zhang et al. | An unsupervised anomaly detection approach based on industrial big data | |
| WO2021122194A1 (en) | Method and an apparatus for computer-implemented monitoring of a wind turbine | |
| CN111159885B (en) | Fan parameter discrete rate anomaly analysis method based on curve fitting | |
| CN116502543B (en) | Wind turbine generator set wind deviation recognition method and device, electronic equipment and storage medium | |
| CN113095693B (en) | Wind power bearing health state assessment method based on temperature characteristic quantity |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |