LU501554B1 - Evaluation method of compliance of wind turbine operation power curve - Google Patents

Evaluation method of compliance of wind turbine operation power curve Download PDF

Info

Publication number
LU501554B1
LU501554B1 LU501554A LU501554A LU501554B1 LU 501554 B1 LU501554 B1 LU 501554B1 LU 501554 A LU501554 A LU 501554A LU 501554 A LU501554 A LU 501554A LU 501554 B1 LU501554 B1 LU 501554B1
Authority
LU
Luxembourg
Prior art keywords
power curve
wind turbine
data
operation power
micro
Prior art date
Application number
LU501554A
Other languages
German (de)
Inventor
Yuan Li
Zengjin Xu
Qiujuan Huang
Original Assignee
Univ Shenyang Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Univ Shenyang Technology filed Critical Univ Shenyang Technology
Priority to LU501554A priority Critical patent/LU501554B1/en
Application granted granted Critical
Publication of LU501554B1 publication Critical patent/LU501554B1/en

Links

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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/06—Wind turbines or wind farms

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Sustainable Development (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Sustainable Energy (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Wind Motors (AREA)

Abstract

The evaluation method of compliance of wind turbine operation power curve is as follows: step 1: establishing a standard power curve function according to the wind speed and power data table of the model of wind turbine to be evaluated; step 2, cleaning the historical operation second-level wind speed and power data of the wind turbine model to be evaluated, and establishing an operation power curve function; and step 3: calculating the coincidence coefficient between the standard power curve function model in step 1 and the operation power curve function model in step 2. The main structure of the whole power curve is divided into four regions: wind turbine start-up stage, the constant power coefficient stage, the constant power stage and the constant speed stage.

Description

DESCRIPTION LUS01554
EVALUATION METHOD OF COMPLIANCE OF WIND TURBINE OPERATION POWER CURVE
TECHNICAL FIELD The content of the invention relates to a method for evaluating the compliance degree of the operation power curve of wind turbines, which can realize the preliminary design evaluation of the whole wind turbines and can be used for the performance evaluation of wind power systems.
BACKGROUND Good power generation performance of wind turbines is the decisive factor to ensure the production operation management and development strategic planning of wind power enterprises. The power curve is an important index to describe the operation performance of wind turbines. However, due to the influence of temperature, air pressure, blade pollution and the characteristics of the turbines themselves, the power curves formed by different wind fields, different turbines and different times are different. Therefore, analyzing the difference between the actual operation power curve and the standard power curve, and knowing the factors that affect the power characteristics of wind turbines, is conducive to mastering the operating state of wind turbines and making preliminary work for fault diagnosis. There is no report yet.
SUMMARY Purpose of the invention: The invention provides an evaluation method of compliance of wind turbine operation power curve, aiming at solving the problem that the difference between actual operation power curve and standard power curve can not be better analyzed in the past.
Technical proposal: The evaluation method of compliance of wind turbine operation power curve is characterized in that: the method comprises the following steps: step 1, establishing a standard power curve function according to the wind speed and power data table of the wind turbine to be evaluated; step 2, cleaning the historical operation second-level wind speed and power data of the wind turbine to be evaluated, and establishing an operation power curve function;
and step 3: calculating the coincidence coefficient of the standard power curve function 901554 model in step 1 and the operation power curve function model in step 2, and getting the final evaluation result.
The least square method is used to establish the mathematical model of standard power curve in step 1 and the mathematical model of power curve to be evaluated in step 2.
The cleaning processing in step 2 includes the historical data standardization processing method and the data cleaning processing method.
The historical data standardization processing method is as follows: convert and return to the reference air density; the gas constant R is 287.05//(kg - K), the measured mean absolute temperature in 10 min is T1omin, the measured mean air pressure in 10 min is B1omin> the measured mean wind speed in 10 min is Viomin, and the standard air density is pp, and then the converted wind speed V, is as follows: The data cleaning method is as follows: divide the power and standardized wind speed data into segments with a wind speed interval of 0.5 m/s, and use a data cleaning algorithm based on Spark optimized K-means clustering algorithm to form multiple micro-clusters; the data brief structure of micro-clusters is defined as: C = [N, Ls, Ss, Cs, Bg, p, p1], wherein N is the number of data points contained in the micro-cluster and Lg is the linear sum of data element attributes, S, is the sum of squares of data elements, C, is the cubic sum of data elements, B, is the fourth power sum of data elements, p is the initial position of micro-cluster generation, and p, is the last update position of micro-cluster; with the change of position, the number N of micro-clusters is increasing, which requires regular maintenance, that is, firstly, calculate the distance D between every two micro-clusters according to formula (2), and if D is less than the set threshold, combine it according to formula (3), otherwise, eliminate the data as follows: po [ee _ F2 oo N,N2 Ni Np NN» C, + Cy = [Ny + Np, Lg, + Lp, Ss1 + Ss2, Cs1 + Cs, Bs1 + Bs2] 3);
in which ©, and ©, are two micro-clusters; x;, x; are the ith and jth data values in two micro-clusters, respectively; Vi and N, are the number of data points contained in two micro-clusters, Ls1 and Ly, are the linear sum of data element attributes in two micro-clusters, Sa and 5, are the sum of squares of data elements in two micro-clusters, Ca and Cy, are the cubic sum of data elements in two micro-clusters, and Ps and By, are the fourth power sum of data elements in two micro-clusters; according to the distance D between micro-clusters and the set threshold, data cleaning can be realized; the set threshold generally selects u + 30, where u is the mean value and o is the standard deviation.
The calculation method of coincidence coefficient in step 3 is as follows: at the same wind speed, the two power sequences corresponding to the standard power curve function a and the operation power curve function b are x, and x,, respectively; the calculation formula of the cross-correlation coefficient R,, of the power series of the two curves a and b is formula (4), and the formula for deviation coefficient dap is formula (5); the calculation process of coincidence coefficient based on correlation analysis is as follows: Rap = = Eh=1 xa OU xp (7) (4) dap = 5 XX 11xa C1) — x, (0) (5) wherein N is the number of data, and x,(n) is the power value corresponding to the nth data in the a curve power sequence, and xp(n is the power value corresponding to the nth data in the b curve power sequence; if the number of wind turbines is M and the number of wind turbines is i, the coincidence coefficient Con is expressed as formula (6): Con; = Rap, / GEL, Rap) + dap,/ 241 day) (6); in which, Rab: is the cross-correlation coefficient between the operation power curve and the standard power curve of No.i wind turbine, and the deviation coefficient between the operation power curve and the standard power curve of No. wind turbine.
After calculating the coincidence coefficient, rank and evaluate the coincidence coefficients 901554 of several wind turbines.
The ranking adopts the overall operation power curve coincidence coefficient ranking and the partition operation power curve coincidence coefficient ranking, either or both; the overall operation power curve coincidence coefficient ranking is to rank the coincidence coefficient of the overall operation power curve of each wind turbine when there are multiple wind turbines; the partition operation power curve coincidence coefficient ranking, that is, when there are multiple wind turbines, divide the operation power curve of each wind turbine into regions, and then rank the operation power curve coincidence coefficient of the corresponding region of each wind turbine.
There are two ways to divide regions, either one or both: according to the wind speed and power data of the wind turbine model to be evaluated provided by the manufacturer, the operation power curve is divided into three parts: the wind speed curve of the cut-in section, the wind speed curve of the full-blown section and the wind speed curve of the cut-out section; according to the classification of wind turbine operation state, the operation power curve is divided into wind turbine start-up zone curve, constant power coefficient zone curve, constant power zone curve and constant speed zone curve. (Explanation: when calculating the sub-regional conformity, divide the standard power curve into corresponding regions, calculate the conformity between the corresponding regions of the operation power curve and the corresponding regions of the standard power curve, and then rank the calculation results) The system includes a standard power curve function construction module, an operation power curve function construction module and a coincidence coefficient calculation module; the standard power curve function construction module establishes a standard power curve function according to the wind speed and power data table of the wind turbine model to be evaluated; the operation power curve function construction module cleans the historical operation second-level data of the wind turbine model to be evaluated, and establishes the operation power curve function;
and the coincidence coefficient calculation module calculates the coincidence coefficient of 901554 the standard power curve function model constructed in the standard power curve function construction module and the operation power curve function model constructed by the operation power curve function construction module, and obtains the final evaluation result.
Advantages: The invention provides an evaluation method of compliance of wind turbine operation power curve, which divides the main structure of the whole power curve into four regions: wind turbine start-up stage, constant power coefficient stage, constant power stage and constant speed stage; on the premise of clarifying the relationship among the various regions of the wind turbine, the design evaluation methods of the above regions are put forward respectively, and the design and calculation flow chart of the whole wind turbine is designed at the same time, so that the preliminary evaluation design of the wind turbine is realized, which provides the basis for the subsequent numerical simulation and experimental verification.
BRIEF DESCRIPTION OF THE FIGURES FIG. 1: Standard power characteristic curve FIG. 2: Data cleaning algorithm framework based on Spark optimized K-means clustering algorithm FIG. 3: Flow chart of coincidence coefficient calculation based on correlation analysis FIG. 4: Flow chart of calculation of power curve coincidence coefficient of wind turbine FIG. 5: Ranking of 33 units of a specified model in a wind field
DESCRIPTION OF THE INVENTION The power curve can directly reflect the operation state of wind turbine. The power curve can be roughly divided into three parts according to the cut-in wind speed, full-blown wind speed and cut-out wind speed in the wind speed and power data to be evaluated of a certain wind turbine model provided by the manufacturer. According to the division of wind turbine operation state, the power curve is mainly composed of four sub-regions of wind turbine start-up region, constant power coefficient region, constant power region and constant speed region, as shown in FIG. 1. The curve shapes of different regions are influenced by the corresponding main control components. Therefore, partition and overall calculation should be carried out for the compliance degree of the power curve.
1) Standardized calculation method of historical data 17901556 The design and calculation of the power curve in the invention is mainly the calculation of wind speed-power. In the drawing of the power curve, because the operating environment of the wind turbine is changeable, in order to ensure that the whole power curve in the operating state can be directly compared and analyzed with the standard power curve provided by the manufacturer, it is necessary to carry out standardized calculation on the wind speed in the data.
According to the generating power formula of wind turbine, the main parameter affecting the power curve is air density. Therefore, it is necessary to convert and return to the reference air density. According to GBT 18451.2-2003, if the wind turbine is under automatic power control, the gas constant R is 287.05//(kg - K), the measured mean absolute temperature in 10 min is T10min; the measured mean air pressure in 10 min is B1omin, the measured mean wind speed in min is Viomin, and the standard air density is po, and then the converted wind speed V, is as follows: 2) Data cleaning calculation method Wind speed and power are the main research subjects in power curve drawing, and the quantity and quality of wind speed-power data reflect the performance and stability of wind turbine. Therefore, the invention adopts Spark technology to optimize data distribution, and applies K-means clustering algorithm to clean data.
The power and standardized wind speed data are divided into segments with a wind speed interval of 0.5 m/s, and each data segment is formed into multiple micro-clusters by K-means. The data brief structure of micro-clusters is defined as: C = [N, Lg, Ss, Cs, Bs, p, p1], wherein N is the number of data points contained in the micro-cluster and Lg is the linear sum of data element attributes, Sg is the sum of squares of data elements, Cs is the cubic sum of data elements, B, is the fourth power sum of data elements, p is the initial position of micro-cluster generation, and p, is the last update position of micro-cluster. With the change of position, the number N of micro-clusters is increasing, which requires regular maintenance, that is, firstly, calculate the distance D between every two micro-clusters according to formula (2), and if D is less than the set threshold, combine it according to formula (3), otherwise, eliminate the data.
The framework of data cleaning algorithm based on Spark optimized K-means clustering. 901554 algorithm is shown in FIG. 2. po [ee _ FEE oo N; N» N, N2 — N,N, C, + Cy = [Ny + Np, Lg, + Lp, Ss1 + Ss2, Cs1 + Cs, Bs1 + Bs2] (3) In which ©, and ©, are two micro-clusters; Ni and NV, are the number of data points contained in two micro-clusters, Ly, and La are the linear sum of data element attributes in two micro-clusters, S,1 and 5, are the sum of squares of data elements in two micro-clusters, Ca and Care the cubic sum of data elements in two micro-clusters, and B and By, are the fourth power sum of data elements in two micro-clusters.
According to the distance D between micro-clusters and the set threshold, data cleaning can be realized. The set threshold generally selects u + 30, where u is the mean value and 0 is the standard deviation. Finally, the scattered points of the power curve are analyzed by using the cleaned wind speed-power data.
3) Drawing of power curve According to the wind speed and power data to be evaluated of a certain wind turbine model provided by the manufacturer, see Table 1.
Table 1: standard power curve table of wind turbine Wind speed | Power (kW) | Wind speed | Power (kW) | Wind speed | Power (kW) (m/s) (m/s) (m/s) 00 Joo [85 | 7390 1500.0 05 Joo |90 [8860 1500.0 Joo Jos [1027.0 1500.0 15s Joo {100 [1187.0 1500.0 Joo ]105 [13260 1500.0 Joo |110 [14350 1500.0
1478.0 1500.0
1500.0 1500.0
1500.0 1500.0
1500.0 1500.0
126.0 1500.0 1500.0
181.0 1500.0 1500.0 60 EX 1500.0 1500.0
315.0 1500.0 1500.0
402.0 1500.0 1500.0
502.0 1500.0 1500.0 80 |620.0 1500.0 1500.0 It can be seen from the table that the cut-in wind speed set by the manufacturer is 3 m/s, and when the wind speed reaches 12 m/s, it enters the full-blown, and the cut-out wind speed is 25 m/s. When the wind speed interval is from 3 m/s to 12 m/s, the corresponding growth trend of wind speed is nonlinear. The least square method can be used to establish mathematical model 1 of power curve and draw standard power curve, as shown in FIG. 1. Based on the historical data, the least square method can be used to establish the mathematical model 2, hereinafter referred to as the operation power curve. Other methods can be used to draw the power curve, but this patent requires that the power curve can be expressed by function, so the least square method is used to construct the power curve.
4) Calculation method of compliance degree Correlation analysis is the basic method to compare the similarity between two functions. Its basic idea is to estimate the power offset by using two correlation functions. Compared with other algorithms, cross-correlation matching algorithm is simple to implement, low in computational complexity and strong in robustness, so it is applied to many occasions.
According to the partition of the power curve, the calculation of the compliance degree of the 901554 power curve of the wind turbine is divided into four sub-calculation and analysis regions. According to the method, the cross-correlation unbiased estimation is applied to calculate the compliance degree of the power curve and the standard curve of the unit, and the performance ranking of the unit is completed.
At the same wind speed, the two power sequences corresponding to the standard power curve function and the operation power curve function are x, and x,, respectively; the calculation formula of the cross-correlation coefficient R,, of the power series of the two curves a and b 1s formula (4), and the formula for deviation coefficient dap 1s formula (5). The calculation process of coincidence coefficient based on correlation analysis is as follows: the calculation process of coincidence coefficient based on correlation analysis is shown in FIG. 3.
Rap = = Eh=1 xa OU xp (7) (4) dap = 5 XX 11xa C1) — x, (0) (5) Wherein N is the number of data, and x(n) is the power value corresponding to the nth data.
If the number of wind turbines is M and the number of wind turbines is i, the coincidence coefficient Con is expressed as formula (6).
Con; = Rap, / GEL, Rap) + dap,/ 241 day) (6) In which, Rap, is the cross-correlation coefficient between the operation power curve and the standard power curve of No.i wind turbine, and the deviation coefficient between the operation power curve and the standard power curve of No.1 wind turbine.
The coincidence coefficient between the power curves of several units of the same type and the standard power curves can be ranked by the way of partition first and then integration (partition with wind speed as reference). The partition ranking reflects the status of each component, and the overall ranking reflects the compliance of the whole machine, which is more suitable for judging whether it is up to standard. Zoning and the whole complement each other, which can more accurately evaluate the compliance with the standard. Partition and integration complement each other, which can more accurately evaluate the compliance degree of the standard. The flow chart for calculating the overall coincidence coefficient of the power curve of 901554 a single wind turbine is shown in FIG. 4.
5) Ranking According to the calculated values of coincidence degree, many wind turbines are ranked for easy understanding and analysis, and the values of coincidence coefficient are standardized, all of which belong to the interval (0,1). Taking the wind turbine number as the representative, the ranking situation is presented in the form of line chart. The larger the coincidence coefficient, the higher the rank of the unit. Take 33 wind turbines of a specified type in a wind field as an example, and rank them as a whole, as shown in FIG. 5.
The evaluation system of compliance of wind turbine operation power curve is characterized by comprising a standard power curve function construction module, an operation power curve function construction module and a coincidence coefficient calculation module; the standard power curve function construction module establishes a standard power curve function according to the wind speed and power data table of the wind turbine model to be evaluated; the operation power curve function construction module cleans the historical operation second-level data of the wind turbine model to be evaluated, and establishes the operation power curve function; the coincidence coefficient calculation module calculates the coincidence coefficient of the standard power curve function model constructed in the standard power curve function construction module and the operation power curve function model constructed by the operation power curve function construction module, and obtains the final evaluation result.
Embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, this application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) having computer usable program codes embodied therein.
The application is described with reference to flow charts and/or block diagrams of methods, 901554 devices (systems), and computer program products according to embodiments of the application. It should be understood that each flow and/or block in the flow charts and/or block diagrams, as well as combinations of flows and/or blocks in the flow charts and/or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing equipment to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are used to generate a device that realizes the functions specified in one process or multiple processes in the flow chart and/or one block or multiple blocks in the block diagram.
These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific way, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The instruction device implements the functions specified in one process or multiple processes in the flow chart and/or one block or multiple blocks in the block diagram.
These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to generate computer-implemented processing, so that the instructions executed on the computer or other programmable equipment provide steps for realizing the functions specified in one process or multiple processes in the flow chart and/or one block or multiple blocks in the block diagram.

Claims (10)

CLAIMS LU501554
1. An evaluation method of compliance of wind turbine operation power curve, which 1s characterized by: the method comprises the following steps: step 1, establishing a standard power curve function according to the wind speed and power data table of the wind turbine to be evaluated: step 2, cleaning the historical operation second-level wind speed and power data of the wind turbine to be evaluated, and establishing an operation power curve function; and step 3: calculating the coincidence coefficient of the standard power curve function model in step 1 and the operation power curve function model in step 2, and getting the final evaluation result.
2. The evaluation method of compliance of wind turbine operation power curve according to claim 1, which is characterized in that the least square method is used to establish the mathematical model of standard power curve in step 1 and the mathematical model of power curve to be evaluated in step 2.
3. The evaluation method of compliance of wind turbine operation power curve according to claim 1, which is characterized in that the cleaning treatment in step 2 includes historical data standardization treatment method and data cleaning treatment method.
4. The evaluation method of compliance of wind turbine operation power curve according to claim 3, which 1s characterized in that: historical data standardization processing method is as follows: convert and return to the reference air density; the gas constant R is 287.05//(kg - K), the measured mean absolute temperature in 10 min is T1omin, the measured mean air pressure in 10 min is B1omin> the measured mean wind speed in 10 min is Viomin, and the standard air density is pp, and then the converted wind speed V, is as follows:
5. The evaluation method of compliance of wind turbine operation power curve according to claim 4, which 1s characterized in that: the data cleaning method 1s as follows:
divide the power and standardized wind speed data into segments with a wind speed” 901554 interval of 0.5 m/s, and use a data cleaning algorithm based on Spark optimized K-means clustering algorithm to form multiple micro-clusters; the data brief structure of micro-clusters is defined as: C = [N, Ls, Ss, Cs, Bg, p, p1], wherein N is the number of data points contained in the micro-cluster and Lg is the linear sum of data element attributes, S, is the sum of squares of data elements, C, is the cubic sum of data elements, B, is the fourth power sum of data elements, p is the initial position of micro-cluster generation, and p, is the last update position of micro-cluster; with the change of position, the number N of micro-clusters is increasing, which requires regular maintenance, that is, firstly, calculate the distance D between every two micro-clusters according to formula (2), and if D is less than the set threshold, combine it according to formula (3), otherwise, eliminate the data as follows: po [ee _ F2 oo N,N2 Ni Np NN» C, + Cy = [Ny + Np, Lg, + Lp, Ss1 + Ss2, Cs1 + Cs, Bs1 + Bs2] 3); in which ©, and ©, are two micro-clusters; x;, x; are the ith and jth data values in two micro-clusters, respectively; Vi and N, are the number of data points contained in two micro-clusters, Ls1 and Ly, are the linear sum of data element attributes in two micro-clusters, Sa and 5, are the sum of squares of data elements in two micro-clusters, Ca and Cy, are the cubic sum of data elements in two micro-clusters, and Ps and By, are the fourth power sum of data elements in two micro-clusters; according to the distance D between micro-clusters and the set threshold, data cleaning can be realized; the set threshold generally selects u + 30, where u is the mean value and o is the standard deviation.
6. The evaluation method of compliance of wind turbine operation power curve according to any one of claims 1 to 5, which is characterized in that: the calculation method of coincidence coefficient in step 3 is as follows: at the same wind speed, the two power sequences corresponding to the standard power curve function a and the operation power curve function b are x, and x,, respectively; the calculation formula of the cross-correlation coefficient R,, of the power series of the wo. 201554 curves a and b is formula (4), and the formula for deviation coefficient dap is formula (5); the calculation process of coincidence coefficient based on correlation analysis is as follows: Rap = = Eh=1 xa OU xp (7) (4) dap = 5 XX 11xa C1) — x, (0) (5) wherein N is the number of data, and x,(n) is the power value corresponding to the nth data in the a curve power sequence, and x,(n is the power value corresponding to the nth data in the b curve power sequence; if the number of wind turbines is M and the number of wind turbines is i, the coincidence coefficient Con is expressed as formula (6): Con; = Rap, / GEL, Rap) + dap,/ 241 day) (6); in which, Rab: is the cross-correlation coefficient between the operation power curve and the standard power curve of No.i wind turbine, and the deviation coefficient between the operation power curve and the standard power curve of No. wind turbine.
7. The evaluation method of compliance of wind turbine operation power curve according to claim 6, which is characterized in that: after calculating the coincidence coefficient, rank and evaluate the coincidence coefficients of several wind turbines.
8. The evaluation method of compliance of wind turbine operation power curve according to claim 7, which is characterized in that the ranking evaluation adopts the overall operation power curve coincidence coefficient ranking and the partition operation power curve coincidence coefficient ranking, either or both; the overall operation power curve coincidence coefficient ranking is to rank the coincidence coefficient of the overall operation power curve of each wind turbine when there are multiple wind turbines; the partition operation power curve coincidence coefficient ranking, that is, when there are multiple wind turbines, divide the operation power curve of each wind turbine into regions, and then rank the operation power curve coincidence coefficient of the corresponding region of each wind turbine.
9. The evaluation method of compliance of wind turbine operation power curve according 201554 to claim 8, which is characterized in that there are the following two ways of region division, either one or both: according to the wind speed and power data of the wind turbine model to be evaluated provided by the manufacturer, the operation power curve is divided into three parts: the wind speed curve of the cut-in section, the wind speed curve of the full-blown section and the wind speed curve of the cut-out section; according to the classification of wind turbine operation state, the operation power curve is divided into wind turbine start-up zone curve, constant power coefficient zone curve, constant power zone curve and constant speed zone curve.
10. An evaluation system of compliance of wind turbine operation power curve, which is characterized in that the system comprises a standard power curve function construction module, an operation power curve function construction module and a coincidence coefficient calculation module; the standard power curve function construction module establishes a standard power curve function according to the wind speed and power data table of the wind turbine model to be evaluated; the operation power curve function construction module cleans the historical operation second-level data of the wind turbine model to be evaluated, and establishes the operation power curve function; and the coincidence coefficient calculation module calculates the coincidence coefficient of the standard power curve function model constructed in the standard power curve function construction module and the operation power curve function model constructed by the operation power curve function construction module, and obtains the final evaluation result.
LU501554A 2022-02-28 2022-02-28 Evaluation method of compliance of wind turbine operation power curve LU501554B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
LU501554A LU501554B1 (en) 2022-02-28 2022-02-28 Evaluation method of compliance of wind turbine operation power curve

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
LU501554A LU501554B1 (en) 2022-02-28 2022-02-28 Evaluation method of compliance of wind turbine operation power curve

Publications (1)

Publication Number Publication Date
LU501554B1 true LU501554B1 (en) 2022-08-29

Family

ID=83060488

Family Applications (1)

Application Number Title Priority Date Filing Date
LU501554A LU501554B1 (en) 2022-02-28 2022-02-28 Evaluation method of compliance of wind turbine operation power curve

Country Status (1)

Country Link
LU (1) LU501554B1 (en)

Similar Documents

Publication Publication Date Title
CN110083896B (en) Standard reaching conformity degree evaluation method for wind turbine generator operating power curve
CN104808587B (en) A kind of mobility statistical method based on machining apparatus running status
CN110659693B (en) K-nearest neighbor classification-based power distribution network rapid topology identification method, system and medium
CN104750973B (en) Unit load (standard) steady state condition clustering algorithm based on data smoothness function
CN110263998B (en) Double-layer correction method for multisource numerical weather forecast set
CN110442911B (en) High-dimensional complex system uncertainty analysis method based on statistical machine learning
CN109508895A (en) Control performance assessment device, method and the storage medium of tobacco cutting equipment
CN110309949A (en) A kind of region electric energy substitution Potential Prediction method and system
CN112651576A (en) Long-term wind power prediction method and device
CN115587433A (en) State condition based unit consumption difference analysis optimization method and system
LU501554B1 (en) Evaluation method of compliance of wind turbine operation power curve
CN108519760A (en) A kind of Primary Processing stable state recognition methods based on detection of change-point theory
CN104182511A (en) Cluster-feature-weighted fuzzy compact scattering and clustering method
Kamisan et al. Forecasting Wind Speed Data by Using a Combination of ARIMA Model with Single Exponential Smoothing.
CN109840536A (en) A kind of power grid power supply reliability horizontal clustering method and system
CN116500296A (en) Intelligent enhanced flow measurement method and system for ecological base flow monitoring and application of intelligent enhanced flow measurement method and system
CN114662333B (en) Smart power grids line loss detecting system based on thing networking
CN114970766A (en) Power station unit operation parameter reference value obtaining method based on linear fitting
CN113595152B (en) Power grid AGC instruction optimal allocation method and system based on thermal power generating unit speed regulation envelope curve
CN114840591A (en) Method and device for determining sectional switch power data
Bo et al. Research of Typical Line Loss Rate in Transformer District Based on Data-Driven Method
CN111445132B (en) Data processing method, data processing system and computer storage medium
CN105447598A (en) Error correction model based load prediction apparatus and method in power system
CN112308340A (en) Power data processing method and device
CN108595753B (en) Method and device for optimizing electromagnetic transient recovery characteristic curve of fan

Legal Events

Date Code Title Description
FG Patent granted

Effective date: 20220829