CN114876731A - Method, system, equipment and medium for checking wind turbine generator in inefficient operation of wind farm - Google Patents
Method, system, equipment and medium for checking wind turbine generator in inefficient operation of wind farm Download PDFInfo
- Publication number
- CN114876731A CN114876731A CN202210542166.0A CN202210542166A CN114876731A CN 114876731 A CN114876731 A CN 114876731A CN 202210542166 A CN202210542166 A CN 202210542166A CN 114876731 A CN114876731 A CN 114876731A
- Authority
- CN
- China
- Prior art keywords
- wind turbine
- wind
- turbine generator
- low
- data
- 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 53
- 239000013598 vector Substances 0.000 claims abstract description 35
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000003064 k means clustering Methods 0.000 claims description 8
- 238000010248 power generation Methods 0.000 claims description 8
- 238000013024 troubleshooting Methods 0.000 claims description 8
- 238000007621 cluster analysis Methods 0.000 claims description 7
- 238000007619 statistical method Methods 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 5
- 230000005611 electricity Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 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
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
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
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
- F03D7/048—Automatic control; Regulation by means of an electrical or electronic controller controlling wind farms
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/80—Diagnostics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- 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 invention provides a method, a system, computer equipment and a medium for checking wind turbines in inefficient operation of a wind farm, which are characterized in that after cycle statistical data of SCADA operation data of all wind turbines in the wind farm are obtained, geographical plane coordinates of all the wind turbines are added to obtain operation data of the wind turbines to be analyzed, then necessary variables and essential variables except generated energy in the operation data of the wind turbines to be analyzed are extracted to obtain corresponding multidimensional characteristic vectors in a combined manner, clustering analysis is respectively carried out on the multidimensional characteristic vectors of all the wind turbines in each statistical cycle to obtain corresponding clusters, then inefficient identification tags are added to the wind turbines in each cluster, the sum of the inefficient identification tags of all the wind turbines in all the statistical cycles is counted as an inefficient decision value, the technical scheme for identifying the wind turbines in inefficient operation is adopted, a plurality of environments and control factors are comprehensively considered, the wind turbine generator set with low-efficiency operation is efficiently and accurately identified, and therefore stable operation of the wind power plant is effectively guaranteed.
Description
Technical Field
The invention relates to the technical field of new energy wind power, in particular to a method and a system for checking wind turbine generators in inefficient operation of a wind power plant, computer equipment and a storage medium.
Background
Under the background of vigorously developing new energy, along with the increase of the scale of a wind power plant, the number of wind power generation sets is increased, and the operation data volume generated by the wind power generation sets is also increased in an explosive manner. However, among all the operating wind turbines in the wind power plant, the wind turbines of the same model can cause the problem of reduction of the power generation efficiency due to blade pollution, sub-health of mechanical equipment or certain defects of the equipment, and the like, and further affect the normal operation of the whole wind power plant, so for a wind power operator, it is very important to rapidly and accurately identify the low-efficiency operating wind turbines in the wind power plant through data and improve the power generation performance of the low-efficiency operating wind turbines.
Because the local environment of each operating wind turbine of the wind power plant is different, such as different environmental factors including wind speed, terrain, wind direction, wind shear, turbulence, temperature, humidity and the like, and because the factors such as power limitation, field group control and the like cause control differences, and the factors can cause different operating conditions of each wind turbine, the power generation efficiency of the corresponding wind turbine is determined to be inaccurate simply through the power curve of each wind turbine, and meanwhile, the environment differences and the control differences bring difficulty for accurately identifying the wind turbine operating in low efficiency.
The existing technical method for identifying the wind turbine generator with low-efficiency operation mainly comprises the following steps: calculating a power curve of a single wind turbine generator by adopting the single or few wind turbine generator operation data variables obtained by screening, and identifying the wind turbine generator with low-efficiency operation through transverse comparison; or screening normal grid-connected operation data of the units through the grid-connected data and the electricity limiting data, calculating the average wind speed and the generated energy of each unit, and judging the unit with low generated energy to be an inefficient operation unit when the standardized wind speed is equal to the wind speed. However, in the case of a large amount of data application scenarios, the existing conventional method is not only low in processing efficiency, but also does not fully consider the difference between the local environment and the active control of each operating wind turbine in the case of a complex wind farm environment, so that the identified inefficient operating wind turbine is unreliable.
Therefore, it is desirable to provide a checking method capable of comprehensively considering a plurality of environmental factors and control factor variables and accurately identifying the wind turbine operating inefficiently.
Disclosure of Invention
The invention aims to provide a method for checking wind turbine generators operating in a low-efficiency mode in a wind power plant.
In order to achieve the above object, it is necessary to provide a method, a system, a computer device and a storage medium for checking wind turbines in inefficient operation of wind farms.
In a first aspect, an embodiment of the present invention provides a method for checking a wind turbine generator in inefficient operation of a wind farm, where the method includes the following steps:
acquiring SCADA operation data and geographical plane coordinates of all wind turbines in a wind power plant; the SCADA operation data are wind turbine generator operation data collected according to preset frequency and preset duration;
respectively calculating period statistical data corresponding to SCADA (supervisory control and data acquisition) operation data of each wind turbine generator according to a preset statistical period;
adding the geographical plane coordinates of each wind turbine generator to corresponding period statistical data to obtain wind turbine generator operation data to be analyzed;
extracting necessary variables and essential variables except the generated energy in the operation data of the wind turbine generator to be analyzed, and combining the necessary variables and the essential variables to obtain corresponding multi-dimensional characteristic vectors;
respectively carrying out clustering analysis on the multi-dimensional characteristic vectors of all the wind turbine generators in each statistical period to obtain corresponding clustering clusters, and adding inefficient identification labels to the wind turbine generators in each clustering cluster;
and counting the sum of the low-efficiency identification labels of each wind turbine generator in all counting periods to obtain a corresponding low-efficiency judgment value, and identifying the wind turbine generator which operates in low efficiency according to the low-efficiency judgment value.
Further, the period statistical data comprise the maximum value, the minimum value, the average value and the standard deviation of each SCADA running data in each statistical period.
Further, the step of extracting the essential variables and the essential variables except the power generation amount in the wind turbine generator operation data to be analyzed comprises the following steps:
screening out variables directly related to the generated energy in the operation data of the wind turbine generator to be analyzed, and taking the variables as necessary variables; the optional variables comprise cabin wind speed, cabin wind direction, pitch angle, generator rotating speed, generator torque, electricity limiting signals, fault signals and grid-connected signals;
and respectively calculating the Pearson correlation coefficient of other variables except the necessary variable in the operation data of the wind turbine generator to be analyzed and the generated energy, and screening to obtain the necessary variable according to the Pearson correlation coefficient.
Further, the step of screening necessary variables according to the pearson correlation coefficient includes:
and calculating the absolute value of each Pearson correlation coefficient, and selecting a variable with the absolute value larger than a preset threshold value as a necessary variable.
Further, the step of performing cluster analysis on the multidimensional feature vectors of all the wind turbines in each statistical period to obtain corresponding cluster includes:
according to the geographic plane coordinates of each wind turbine generator, determining the clustering number in advance;
and according to the clustering number, respectively carrying out clustering analysis on the multi-dimensional characteristic vectors of all the wind turbines in each statistical period through a K-means clustering algorithm.
Further, the step of adding the low-efficiency identification tag to the wind turbine generator in each cluster includes:
counting the total period number of the period statistical data and the number of the wind generating sets in each cluster, and generating a numerical label number sequence corresponding to each cluster according to the total period number and the number of the wind generating sets in each cluster; the numerical label number sequence is a first item of 0, the last item is the ratio of the number of the wind generating sets in the cluster to the total number of the periods, and the item number is an arithmetic number sequence corresponding to the number of the wind generating sets in the cluster;
and the wind turbine generators in each cluster are arranged in a descending order according to the corresponding generated energy, and low-efficiency identification labels are smoothly and sequentially added from top to bottom according to the first item to the last item of the corresponding numerical label number sequence.
Further, the step of identifying the wind turbine generator set operating inefficiently according to the inefficiency determining value includes:
and arranging the low-efficiency judgment values of the wind generation sets in a descending order, selecting the low-efficiency judgment values in a preset proportion from top to bottom, and judging the corresponding wind generation sets as the low-efficiency operation wind generation sets.
In a second aspect, an embodiment of the present invention provides a system for checking a wind turbine in inefficient operation of a wind farm, where the system includes:
the data acquisition module is used for acquiring SCADA operation data and geographical plane coordinates of all wind turbines in the wind power plant; the SCADA operation data are wind turbine generator operation data acquired according to preset frequency and preset duration;
the statistical analysis module is used for respectively calculating period statistical data corresponding to the SCADA operating data of each wind turbine generator according to a preset statistical period;
the position adding module is used for adding the geographical plane coordinates of each wind turbine generator to the corresponding period statistical data to obtain the wind turbine generator operation data to be analyzed;
the variable extraction module is used for extracting necessary variables and necessary variables except the generated energy in the operation data of the wind turbine generator to be analyzed, and combining the necessary variables and the necessary variables to obtain corresponding multi-dimensional feature vectors;
the clustering analysis module is used for respectively clustering analysis on the multi-dimensional characteristic vectors of all the wind turbine generators in each statistical period to obtain corresponding clustering clusters and adding low-efficiency identification labels to the wind turbine generators in each clustering cluster;
and the low-efficiency identification module is used for counting the sum of low-efficiency identification labels of each wind turbine generator in all counting periods to obtain a corresponding low-efficiency judgment value, and identifying the wind turbine generator which operates in low efficiency according to the low-efficiency judgment value.
In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method when executing the computer program.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the above method.
The application provides a method, a system, computer equipment and a storage medium for checking wind turbines in inefficient operation of a wind farm, by which the method, after preset duration SCADA operation data and geographical plane coordinates of all the wind turbines in the wind farm are obtained, cycle statistical data corresponding to the SCADA operation data of each wind turbine are respectively calculated according to a preset statistical cycle, the geographical plane coordinates of each wind turbine are added to the corresponding cycle statistical data to obtain the operation data of the wind turbine to be analyzed, optional variables and necessary variables except generated energy in the operation data of the wind turbine to be analyzed are extracted to obtain corresponding multidimensional characteristic vectors through combination, the multidimensional characteristic vectors of all the wind turbines in each statistical cycle are respectively analyzed to obtain corresponding clusters, and after inefficient identification labels are added to the wind turbines in each cluster, and counting the sum of the low-efficiency identification labels of each wind turbine generator in all counting periods to obtain a corresponding low-efficiency judgment value, and identifying the low-efficiency operation wind turbine generator according to the low-efficiency identification value. Compared with the prior art, the method for checking the wind turbine generator set operated inefficiently in the wind farm has the advantages of single required data source, simplicity and suitability for a big data application scene, low implementation cost, solving of the problem of low data processing efficiency in the identification process of the inefficiently operated wind turbine generator set, further improvement of the accuracy of identifying the inefficiently operated wind turbine generator set by comprehensively considering a plurality of environment and control factors, and reliable and effective guarantee for stable operation of the wind farm.
Drawings
FIG. 1 is a schematic view of an application scenario of a method for checking a wind turbine generator in inefficient operation of a wind farm in an embodiment of the invention;
FIG. 2 is a schematic flow chart of a method for checking wind turbines in the inefficient operation of a wind farm in the embodiment of the invention;
FIG. 3 is a schematic structural diagram of a wind turbine troubleshooting system for inefficient operation of a wind farm in an embodiment of the invention;
fig. 4 is an internal structural diagram of a computer device in the embodiment of the present invention.
Detailed Description
In order to make the purpose, technical solution and advantages of the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments, and it is obvious that the embodiments described below are part of the embodiments of the present invention, and are used for illustrating the present invention only, but not for limiting the scope of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The method for checking the wind turbine generator in the inefficient operation of the wind farm provided by the invention can be applied to the terminal or the server shown in the figure 1. The terminal can be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server can be implemented by an independent server or a server cluster formed by a plurality of servers. The invention relates to a generator set inefficiency identification method which is developed on the basis of SCADA (supervisory Control And Data acquisition) operation Data such as wind turbine generator Control, operation And surrounding environment Data acquired by an SCADA (supervisory Control And Data acquisition) system. The SCADA system generally records that sampling points are hundreds, corresponding frequencies are selected in different times of 1s or several seconds, for example, a server can acquire operation data of each wind turbine generator in a wind power plant acquired by the SCADA system with preset duration according to preset frequencies according to requirements, and low-efficiency identification and investigation are performed on the wind turbine generators in any wind power plant according to the method of the invention by combining geographic position information of each wind turbine generator, and the results obtained by the investigation are used for other subsequent researches of the server or transmitted to a terminal for receiving and using by a terminal user; the following embodiments will describe the wind turbine inspection method for wind farm inefficient operation according to the present invention in detail.
In one embodiment, as shown in fig. 2, there is provided a method for checking wind turbines in inefficient operation of a wind farm, comprising the following steps:
s11, obtaining SCADA operation data and geographical plane coordinates of all wind turbines in the wind power plant; the SCADA operation data are wind turbine generator operation data collected according to preset frequency and preset duration; the wind turbine generator operation data is data collected by an original SCADA system comprising a plurality of data such as wind turbine generator control, operation and surrounding environment data, and is subsequently processed and screened according to needs to obtain related data which is beneficial to troubleshooting and analysis of the low-efficiency wind turbine generator; it should be noted that the preset frequency and the preset duration of the wind turbine generator operation data acquisition can be selected according to actual requirements, for example, operation data with an annual or monthly acquisition frequency f of 1Hz is obtained, and no specific limitation is made here;
s12, respectively calculating period statistical data corresponding to the SCADA operation data of each wind turbine generator according to a preset statistical period; the period statistical data comprise the maximum value, the minimum value, the average value and the standard deviation of each SCADA operation data in each statistical period; the method comprises the steps that a preset statistical period can be reasonably selected according to actual application requirements and the preset frequency and the preset time of obtained SCADA operation data, if the preset time is 1 month, the preset frequency is 1Hz, and the preset statistical period is 10min (minutes), the SCADA operation data of each wind turbine generator set in 1 month are divided into a plurality of periods according to 10 minutes, statistical analysis is conducted on the data in each 10 minutes by adopting the existing mathematical statistical method, and the maximum value, the minimum value, the average value and the standard deviation of each variable in the SCADA operation data in each 10 minutes are obtained and used for subsequent analysis; it should be noted that the period statistical data includes the maximum value, the minimum value, the average value and the standard deviation of each SCADA operation data in the corresponding period, and also includes the serial number of each wind turbine generator and the start time point of the corresponding statistical period, so that the cluster analysis and use of each generator set operation data are facilitated;
s13, adding the geographical plane coordinates of each wind turbine generator to corresponding period statistical data to obtain wind turbine generator operation data to be analyzed; the geographical plane coordinates can be understood as position information of the wind turbine generators, each wind turbine generator set is correspondingly provided with two values of an abscissa and an ordinate, and the values are added into the obtained periodic statistical data, so that each periodic statistical data of each wind turbine generator contains corresponding geographical position information, and the corresponding clustering number can be conveniently determined during subsequent clustering analysis;
s14, extracting essential variables and essential variables except the generated energy in the wind turbine generator operation data to be analyzed, and combining the essential variables and the essential variables to obtain corresponding multi-dimensional feature vectors; wherein, the multidimensional characteristic vector can be understood as a row vector which simultaneously comprises a necessary variable and a necessary variable; specifically, the step of extracting the indispensable variables and the necessary variables except the generated energy in the wind turbine generator operation data to be analyzed includes:
screening out variables directly related to the generated energy in the operation data of the wind turbine generator to be analyzed, and taking the variables as necessary variables; the optional variables comprise cabin wind speed, cabin wind direction, pitch angle, generator rotating speed, generator torque, electricity limiting signals, fault signals and grid-connected signals;
respectively calculating Pearson correlation coefficients of other variables except for the necessary variables in the operation data of the wind turbine generator to be analyzed and the generated energy, and screening to obtain necessary variables according to the Pearson correlation coefficients; specifically, the step of screening necessary variables according to the pearson correlation coefficient includes:
calculating the absolute value of each Pearson correlation coefficient, and selecting a variable with the absolute value larger than a preset threshold value as a necessary variable; for example, if the preset threshold is 0.6, that is, if the absolute value of the correlation coefficient between a certain variable and the power generation amount calculated according to the pearson correlation coefficient formula is greater than 0.6, the variable is considered to be a necessary variable and can be used for subsequent cluster analysis.
S15, respectively carrying out clustering analysis on the multi-dimensional characteristic vectors of all the wind turbine generators in each statistical period to obtain corresponding clustering clusters, and adding inefficient identification labels to the wind turbine generators in each clustering cluster; the method comprises the steps of performing clustering analysis on multi-dimensional characteristic vectors of wind turbine generators by using a K-means clustering algorithm, wherein the clustering analysis can be realized by using any existing clustering algorithm in principle, but in order to be more suitable for the characteristics of real wind power plant data and ensure the high efficiency of the clustering analysis, the embodiment preferably performs the clustering analysis on the multi-dimensional characteristic vectors of the wind turbine generators by using the K-means clustering algorithm;
specifically, the step of performing cluster analysis on the multidimensional feature vectors of all the wind turbines in each statistical period to obtain corresponding cluster includes:
according to the geographic plane coordinates of each wind turbine generator, determining the clustering number in advance; the method is characterized in that the selection of a proper clustering number K is very critical when a K-means clustering algorithm is executed, and the conventional K value selection method comprises the following steps: (1) a simple setting method, namely directly dividing the sample quantity n by 2 and then squaring to obtain a value as a K value; (2) in the elbow method, when the selected K value is smaller than the real clustering number, the cost value is greatly reduced along with the increase of the K value; when the selected K value is greater than the true cluster number, the cost value will not change as significantly as the K value increases, and the correct K value is at this inflection point; (3) the interval statistical method comprises the steps of randomly generating random samples as many as the number of original samples in a rectangular area (a cubic area if the random samples are high-dimensional) where the samples are located according to uniform distribution, carrying out K-Means clustering on the random samples to obtain the distance Dk between sample points in one class, repeatedly collecting a plurality of data, introducing appropriate measure as an interval measure value Gapk, and obtaining the optimal clustering number corresponding to the maximum value obtained by the Gapk by adopting a Monte Carlo method; (4) the contour coefficient method is characterized in that the similarity, namely the cohesiveness, between a sample and a cluster to which the sample belongs is measured by calculating the average distance from the sample point to other samples in the same cluster and the average distance from the sample point to all samples in other clusters, so that the cluster number with high cohesiveness of all sample points is selected as the optimal cluster number; (5) the Canopy algorithm determines an initial clustering number and a clustering center point for the K-means algorithm in a mode of coarse clustering in advance; the above 5 methods can be used for selecting the cluster number, but all have the best application scenarios, so that in the practical application process, a user can select and determine the cluster number according to the existing data scale and the specific prediction scenario. In the embodiment, considering a real wind farm, because of geographical position factors, natural grouping often exists and consistency exists, preferably, the clustering number is predetermined according to geographical plane coordinates of each wind turbine, namely the geographical position far and near degree, for example, the wind turbines in a preset range are taken as one type, the clustering number is obtained under the condition of ensuring the number balance of various wind turbines, so that the clustering number is well matched with a K-means algorithm, and the workload of clustering analysis is simplified to a certain extent while the clustering accuracy is ensured;
according to the clustering number, respectively carrying out clustering analysis on the multi-dimensional characteristic vectors of all the wind turbine generators in each statistical period through a K-means clustering algorithm; after the clustering number is determined according to the method, clustering analysis can be performed on the multi-dimensional feature vectors of all the wind turbines in each statistical period according to the following steps:
1) according to the determined clustering number K, randomly selecting a multi-dimensional feature vector of the K wind turbine generators from each statistical period as an initial clustering center; assuming that 100 running wind turbines in a wind power plant and the preset clustering number K is 5, randomly selecting 5(K) data from the original data as an initial clustering center, wherein the number of each clustering sample is not less than 100/2K, namely 10 wind turbines in each class;
2) respectively calculating the distance value between each multi-dimensional feature vector and K clustering centers in each statistical period, dividing each multi-dimensional feature vector to a clustering point with the nearest distance, calculating the corresponding average value ci of all clusters as the same clustering point after the clustering is finished, and taking the average value ci as a new clustering center, wherein:
wherein N is i The number of sample data is contained in the ith cluster, and x represents the sample data;
3) repeatedly executing multiple iterations until certain requirements are met, stopping clustering, and marking the obtained clustering center as C (C1, C2, C3 …) to obtain a corresponding clustering family;
in the embodiment, the multidimensional feature vectors of the wind turbine generator in each statistical period are subjected to clustering analysis by adopting a K-means clustering algorithm, so that not only can the accuracy of a clustering result be well ensured, but also good adaptability can be ensured when the number of the wind turbine generator in a large wind farm is increased to cause the increase of the operation data amount, namely, the method disclosed by the invention has strong generalization capability;
after the clustering analysis corresponding to all the statistical periods is respectively completed through the steps, corresponding low-efficiency identification labels need to be added to the wind turbine generators in all the clustering families obtained in each statistical period; specifically, the step of adding the low-efficiency identification tag to the wind turbine generator in each cluster includes:
counting the total period number of the periodic statistical data and the number of the wind turbine sets in each cluster, and generating a numerical label number sequence corresponding to each cluster according to the total period number and the number of the wind turbine sets in each cluster; the numerical label number sequence is a first item of 0, the last item is the ratio of the number of the wind generating sets in the cluster to the total number of the periods, and the item number is an arithmetic number sequence corresponding to the number of the wind generating sets in the cluster; for example, if n groups of periodic statistical data corresponding to each wind turbine generator and the number of the wind turbine generators in a cluster of a certain cluster is m, a 0-m/n arithmetic difference sequence containing m items is generated as a numerical label sequence and used for marking each wind turbine generator in the cluster according to the following steps;
the wind turbine generators in each cluster are arranged in a descending order according to the corresponding generated energy, and low-efficiency identification labels are smoothly and sequentially added from top to bottom according to the first item to the last item of the corresponding numerical label number sequence; specifically, the assignment completion flag corresponding to the numerical value label sequence obtained in the foregoing manner can be understood as a rule that the lower the generated energy is, the larger the assignment inefficient identification label is, the larger the wind turbine generator in each cluster is.
S16, counting the sum of the low-efficiency identification labels of the wind generation sets in all counting periods to obtain corresponding low-efficiency judgment values, and identifying the wind generation sets running with low efficiency according to the low-efficiency judgment values; based on this, the preferred embodiment determines a part of the wind turbines in a preset proportion through the low-efficiency determination value as the low-efficiency operation wind turbines, and specifically, the step of identifying the low-efficiency operation wind turbines according to the low-efficiency determination value includes:
and arranging the low-efficiency judgment values of the wind generation sets in a descending order, selecting the low-efficiency judgment values in a preset proportion from top to bottom, and judging the corresponding wind generation sets as the wind generation sets operating with low efficiency.
The embodiment of the application provides a method for checking the wind generation sets in low-efficiency operation, which comprises the steps of performing statistical analysis on wind generation set operation data added with geographical plane coordinates according to a preset statistical period, extracting multi-dimensional characteristic vectors, performing cluster analysis on the multi-dimensional characteristic vectors of all the wind generation sets in each statistical period through K-means, sequencing the wind generation sets of each cluster according to generated energy, assigning an equal-difference series low-efficiency identification tag, counting the sum of the low-efficiency identification tags of the wind generation sets as a low-efficiency judgment value, and screening the wind generation sets with higher low-efficiency judgment values in preset proportion as the low-efficiency operation wind generation sets, wherein the method is single in required data source, simple, suitable for large-data application scenes, low in cost, efficient in identification process, and capable of ensuring the accuracy of identification results by comprehensively considering a plurality of environments and control factors, and further provides reliable guarantee for the stable operation of the wind power plant.
It should be noted that, although the steps in the above-described flowcharts are shown in sequence as indicated by arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise.
In one embodiment, as shown in FIG. 3, there is provided a wind farm under-efficiency wind turbine troubleshooting system, the system comprising:
the data acquisition module is used for acquiring SCADA operation data and geographical plane coordinates of all wind turbines in the wind power plant; the SCADA operation data are wind turbine generator operation data acquired according to preset frequency and preset duration;
the statistical analysis module is used for respectively calculating period statistical data corresponding to the SCADA operating data of each wind turbine generator according to a preset statistical period;
the position adding module is used for adding the geographical plane coordinates of each wind turbine generator to the corresponding period statistical data to obtain the wind turbine generator operation data to be analyzed;
the variable extraction module is used for extracting necessary variables and necessary variables except the generated energy in the operation data of the wind turbine generator to be analyzed, and combining the necessary variables and the necessary variables to obtain corresponding multi-dimensional feature vectors;
the clustering analysis module is used for respectively clustering analysis on the multi-dimensional characteristic vectors of all the wind turbine generators in each statistical period to obtain corresponding clustering clusters and adding low-efficiency identification labels to the wind turbine generators in each clustering cluster;
and the low-efficiency identification module is used for counting the sum of low-efficiency identification labels of each wind turbine generator in all counting periods to obtain a corresponding low-efficiency judgment value, and identifying the wind turbine generator which operates in low efficiency according to the low-efficiency judgment value.
For specific limitations of the wind turbine troubleshooting system for inefficient operation of the wind farm, reference may be made to the above limitations on the wind turbine troubleshooting method for inefficient operation of the wind farm, and details are not described here again. All or part of each module in the wind turbine troubleshooting system for inefficient operation of the wind power plant can be realized through software, hardware and a combination of the software and the hardware. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Fig. 4 shows an internal structure diagram of a computer device in one embodiment, and the computer device may be specifically a terminal or a server. As shown in fig. 4, the computer apparatus includes a processor, a memory, a network interface, a display, and an input device, which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a method for checking wind turbines in the inefficient operation of a wind farm. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those of ordinary skill in the art that the architecture shown in fig. 4 is merely a block diagram of a portion of architecture associated with aspects of the present application, and is not intended to limit the computing devices to which aspects of the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a similar arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the steps of the above method being performed when the computer program is executed by the processor.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned method.
To sum up, the method for checking wind turbine generators operating inefficiently in a wind farm, provided by the embodiments of the present invention, includes obtaining SCADA operating data and geographical plane coordinates of all wind turbine generators operating at a preset duration in the wind farm, calculating period statistical data corresponding to the SCADA operating data of each wind turbine generator according to a preset statistical period, adding the geographical plane coordinates of each wind turbine generator to the corresponding period statistical data to obtain wind turbine generator operating data to be analyzed, extracting optional variables and essential variables except for generated energy in the wind turbine generator operating data to be analyzed, combining the optional variables and essential variables to obtain corresponding multidimensional feature vectors, performing cluster analysis on the multidimensional feature vectors of all the wind turbine generators in each statistical period to obtain corresponding clusters, and adding inefficiently identifying labels to the wind turbine generators in each cluster, the method has the advantages that the sum of the low-efficiency identification tags of the wind generation sets in all the statistical periods is counted to obtain the corresponding low-efficiency judgment value, and the technical scheme of the low-efficiency operation wind generation sets is identified according to the low-efficiency identification tags.
The embodiments in this specification are described in a progressive manner, and all the same or similar parts of the embodiments are directly referred to each other, and each embodiment is described with emphasis on differences from other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. It should be noted that, the technical features of the embodiments may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express some preferred embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for those skilled in the art, various modifications and substitutions can be made without departing from the technical principle of the present invention, and these should be construed as the protection scope of the present application. Therefore, the protection scope of the present patent shall be subject to the protection scope of the claims.
Claims (10)
1. A method for checking wind turbine generators in inefficient operation of a wind farm is characterized by comprising the following steps:
acquiring SCADA operation data and geographical plane coordinates of all wind turbines in a wind power plant; the SCADA operation data are wind turbine generator operation data collected according to preset frequency and preset duration;
respectively calculating period statistical data corresponding to SCADA (supervisory control and data acquisition) operation data of each wind turbine generator according to a preset statistical period;
adding the geographical plane coordinates of each wind turbine generator to corresponding period statistical data to obtain wind turbine generator operation data to be analyzed;
extracting necessary variables and essential variables except the generated energy in the operation data of the wind turbine generator to be analyzed, and combining the necessary variables and the essential variables to obtain corresponding multi-dimensional characteristic vectors;
respectively carrying out clustering analysis on the multi-dimensional characteristic vectors of all the wind turbine generators in each statistical period to obtain corresponding clustering clusters, and adding inefficient identification labels to the wind turbine generators in each clustering cluster;
and counting the sum of the low-efficiency identification labels of each wind turbine generator in all counting periods to obtain a corresponding low-efficiency judgment value, and identifying the wind turbine generator which operates in low efficiency according to the low-efficiency judgment value.
2. The method for troubleshooting wind turbines for wind farm inefficient operation as recited in claim 1, wherein said period statistical data includes a maximum value, a minimum value, an average value and a standard deviation of each SCADA operation data in each statistical period.
3. The method for checking wind turbines in inefficient operation of wind farm according to claim 1, wherein said step of extracting essential variables and essential variables except for power generation amount in said wind turbine operation data to be analyzed comprises:
screening out variables directly related to the generated energy in the operation data of the wind turbine generator to be analyzed, and taking the variables as necessary variables; the optional variables comprise cabin wind speed, cabin wind direction, pitch angle, generator rotating speed, generator torque, electricity limiting signals, fault signals and grid-connected signals;
and respectively calculating the Pearson correlation coefficient of other variables except the necessary variable in the operation data of the wind turbine generator to be analyzed and the generated energy, and screening to obtain the necessary variable according to the Pearson correlation coefficient.
4. The method for checking wind turbine generators in wind farm inefficient operation according to claim 3, wherein the step of screening essential variables according to the Pearson correlation coefficient comprises:
and calculating the absolute value of each Pearson correlation coefficient, and selecting a variable with the absolute value larger than a preset threshold value as a necessary variable.
5. The method for checking wind turbine generators in inefficient operation of a wind farm according to claim 1, wherein the step of performing cluster analysis on the multidimensional feature vectors of all the wind turbine generators in each statistical period to obtain corresponding cluster comprises:
according to the geographic plane coordinates of each wind turbine generator, determining the clustering number in advance;
and according to the clustering number, respectively carrying out clustering analysis on the multi-dimensional characteristic vectors of all the wind turbine generators in each statistical period through a K-means clustering algorithm.
6. The method for checking wind turbines in a wind farm for inefficient operation according to claim 1, wherein the step of adding an inefficiency identification tag to the wind turbines in each cluster comprises:
counting the total period number of the periodic statistical data and the number of the wind turbine sets in each cluster, and generating a numerical label number sequence corresponding to each cluster according to the total period number and the number of the wind turbine sets in each cluster; the numerical label number sequence is that the first item is 0, the last item is the ratio of the number of the wind turbine generator sets in the cluster to the total number of the period, and the item number is an arithmetic number sequence corresponding to the number of the wind turbine generator sets in the cluster;
and the wind turbine generators in each cluster are arranged in a descending order according to the corresponding generated energy, and low-efficiency identification labels are smoothly and sequentially added from top to bottom according to the first item to the last item of the corresponding numerical label number sequence.
7. The method for troubleshooting wind farm inefficiently operating wind turbine generators as set forth in claim 1, wherein said step of identifying an inefficiently operating wind turbine generator based on said inefficiently determining value comprises:
and arranging the low-efficiency judgment values of the wind generation sets in a descending order, selecting the low-efficiency judgment values in a preset proportion from top to bottom, and judging the corresponding wind generation sets as the wind generation sets operating with low efficiency.
8. A wind turbine generator system for checking inefficient operation of a wind power plant is characterized by comprising the following steps:
the data acquisition module is used for acquiring SCADA operation data and geographical plane coordinates of all wind turbines in the wind power plant; the SCADA operation data are wind turbine generator operation data acquired according to preset frequency and preset duration;
the statistical analysis module is used for respectively calculating period statistical data corresponding to the SCADA operating data of each wind turbine generator according to a preset statistical period;
the position adding module is used for adding the geographical plane coordinates of each wind turbine generator to the corresponding period statistical data to obtain the wind turbine generator operation data to be analyzed;
the variable extraction module is used for extracting necessary variables and necessary variables except the generated energy in the operation data of the wind turbine generator to be analyzed, and combining the necessary variables and the necessary variables to obtain corresponding multi-dimensional feature vectors;
the clustering analysis module is used for respectively clustering analysis on the multi-dimensional characteristic vectors of all the wind turbine generators in each statistical period to obtain corresponding clustering clusters and adding low-efficiency identification labels to the wind turbine generators in each clustering cluster;
and the low-efficiency identification module is used for counting the sum of low-efficiency identification labels of each wind turbine generator in all counting periods to obtain a corresponding low-efficiency judgment value, and identifying the wind turbine generator which operates in low efficiency according to the low-efficiency judgment value.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210542166.0A CN114876731A (en) | 2022-05-17 | 2022-05-17 | Method, system, equipment and medium for checking wind turbine generator in inefficient operation of wind farm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210542166.0A CN114876731A (en) | 2022-05-17 | 2022-05-17 | Method, system, equipment and medium for checking wind turbine generator in inefficient operation of wind farm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114876731A true CN114876731A (en) | 2022-08-09 |
Family
ID=82676136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210542166.0A Pending CN114876731A (en) | 2022-05-17 | 2022-05-17 | Method, system, equipment and medium for checking wind turbine generator in inefficient operation of wind farm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114876731A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116682128A (en) * | 2023-06-02 | 2023-09-01 | 中央民族大学 | Method, device, equipment and medium for constructing and identifying data set of water book single word |
-
2022
- 2022-05-17 CN CN202210542166.0A patent/CN114876731A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116682128A (en) * | 2023-06-02 | 2023-09-01 | 中央民族大学 | Method, device, equipment and medium for constructing and identifying data set of water book single word |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112686464A (en) | Short-term wind power prediction method and device | |
| CN113505537A (en) | Building energy consumption detection method and device, computer equipment and storage medium | |
| CN113822418A (en) | Wind power plant power prediction method, system, device and storage medium | |
| Gao et al. | Spectral clustering based demand-oriented representative days selection method for power system expansion planning | |
| CN114498619A (en) | Wind power prediction method and device | |
| CN112506757A (en) | Automatic test method, system, computer device and medium thereof | |
| CN114876731A (en) | Method, system, equipment and medium for checking wind turbine generator in inefficient operation of wind farm | |
| CN116992274B (en) | Short-term wind speed prediction method and system based on improved principal component regression model | |
| CN114021425A (en) | Power system operation data modeling and feature selection method and device, electronic equipment and storage medium | |
| Bodík et al. | HiLighter: Automatically Building Robust Signatures of Performance Behavior for Small-and Large-Scale Systems. | |
| CN117234844A (en) | Cloud server abnormality management method and device, computer equipment and storage medium | |
| CN117093477A (en) | Software quality assessment method and device, computer equipment and storage medium | |
| CN116703466A (en) | System access quantity prediction method based on improved wolf algorithm and related equipment thereof | |
| CN116841808A (en) | Multi-core processor abnormality detection method and device, electronic equipment and storage medium | |
| CN116304713A (en) | Wind power plant fault scene prediction model generation method and device and computer equipment | |
| CN115905360A (en) | Abnormal data measurement identification method and device based on random construction matrix | |
| CN112256735B (en) | Power consumption monitoring method and device, computer equipment and storage medium | |
| CN115344495A (en) | Data analysis method and device for batch task test, computer equipment and medium | |
| CN113627514A (en) | Data processing method and device of knowledge graph, electronic equipment and storage medium | |
| CN114123190A (en) | Method and device for determining target region to which ammeter belongs, electronic equipment and storage medium | |
| Bi et al. | Workload and renewable energy prediction in cloud data centers with multi-scale wavelet transformation | |
| Nong | Construction and Simulation of Financial Risk Prediction Model Based on LSTM | |
| Xiao et al. | Enhanced-xgb: An online service resource demand forecasting method for colocation data centers | |
| CN115062495B (en) | Method and device for analyzing insulating property of material, electronic equipment and storage medium | |
| CN116541766B (en) | Training method of electroencephalogram data restoration model, electroencephalogram data restoration method and device |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240328 Address after: Room 407, Building 7, No. 6 Libin Road, Songshanhu Park, Dongguan City, Guangdong Province, 523808 Applicant after: CR POWER TECHNOLOGY INSTITUTE Co.,Ltd. Country or region after: China Address before: Room 606, 6th floor, Huaneng Henan building, No.40 Zhengguang North Street, Zhengzhou area (Zhengdong), 450000 Zhengzhou pilot Free Trade Zone, Henan Province Applicant before: RUNDIAN ENERGY SCIENCE AND TECHNOLOGY Co.,Ltd. Country or region before: China |