CN110826904B - Data processing method and device for fan, processing equipment and readable storage medium - Google Patents
Data processing method and device for fan, processing equipment and readable storage medium Download PDFInfo
- Publication number
- CN110826904B CN110826904B CN201911065104.XA CN201911065104A CN110826904B CN 110826904 B CN110826904 B CN 110826904B CN 201911065104 A CN201911065104 A CN 201911065104A CN 110826904 B CN110826904 B CN 110826904B
- Authority
- CN
- China
- Prior art keywords
- data
- distance
- probability density
- joint probability
- matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 28
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 116
- 238000012544 monitoring process Methods 0.000 claims abstract description 55
- 238000001914 filtration Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 8
- 238000010248 power generation Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002650 habitual effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Water Supply & Treatment (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a data processing method, a data processing device, processing equipment and a readable storage medium of a fan, and relates to the technical field of wind power generation. The method comprises the following steps: establishing a data matrix according to a plurality of groups of monitoring data of the fan; wherein, every data point in the data matrix includes a set of monitoring data, and the monitoring data includes: a wind speed and a power of the fan at the wind speed; determining the distance between every two data points in the data matrix; determining a joint probability density for each data point in the data matrix with respect to wind speed and power; and performing data point filtering according to the distance and the joint probability density. The distances between the data points corresponding to each group of monitoring data and other data points and the joint probability density of each data point are obtained through calculation based on the wind speed and the power of the fan, the data points are filtered without filtering through a manually set threshold, the accuracy of data filtering is improved, and therefore the accuracy of evaluating the fan based on a power curve obtained by the filtered data points is improved.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a data processing method, a data processing device, data processing equipment and a readable storage medium of a fan.
Background
With the continuous development of wind power generation technology, the output performance and the running state of a wind power generator set (called a fan for short) can be evaluated according to the power curve of the wind power generator set.
In the related art, in order to improve the evaluation accuracy, a filtering threshold value may be set according to design parameters (such as rated power) of the wind turbine generator system, each point corresponding to each group of monitoring data in the monitoring data of the fan is filtered according to the threshold value, the monitoring data after filtering abnormal points is obtained to generate a power curve of the fan, and then the output performance and the operating state of the fan are evaluated according to the power curve of the fan.
However, in the process of filtering the monitoring data of the fan, the filtered monitoring data is inaccurate due to the influence of the artificially set threshold, so that the evaluation of the fan is influenced.
Disclosure of Invention
The present invention provides a data processing method, device, processing apparatus and readable storage medium for a blower fan, so as to solve the problem of inaccurate evaluation of the blower fan.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, an embodiment of the present invention provides a data processing method for a wind turbine, where the method includes:
establishing a data matrix according to a plurality of groups of monitoring data of the fan; wherein each data point in the data matrix comprises a set of the monitoring data, the monitoring data comprising: a wind speed and a power of the fan at the wind speed;
determining a distance between every two data points in the data matrix;
determining a joint probability density for each data point in the data matrix with respect to wind speed and power;
and filtering data points according to the distance and the joint probability density.
Optionally, the filtering the data points according to the distance and the joint probability density includes:
determining a distance corresponding to each joint probability density according to the distance between every two data points in the data matrix and the joint probability density of each data point in the data matrix about the wind speed and the power; the distance corresponding to the maximum joint probability density is the maximum distance, and the distances corresponding to other joint probability densities are the minimum distances;
establishing a data set comprising a plurality of sets of data, wherein each set of data comprises: a joint probability density and a distance corresponding to said joint probability density;
determining data points in the data set, wherein the joint probability density is smaller than or equal to a preset density, and the distance is larger than or equal to a preset distance, and taking the data points as abnormal data points;
filtering the outlier data points in the data set.
Optionally, the determining, according to a distance between every two data points in the data matrix and a joint probability density of each data point in the data matrix with respect to wind speed and power, a distance corresponding to each joint probability density includes:
establishing a distance matrix according to the distance between every two data points in the data matrix, wherein each data in the distance matrix is the distance between two data points;
establishing a density matrix according to the combined probability density of each data point about the wind speed and the power, wherein each data in the density matrix is the combined probability density of the data points about the wind speed and the power within a preset distance range by taking the data point as a center;
and determining the distance corresponding to each joint probability density according to the distance matrix and the density matrix.
Optionally, the method further includes:
and generating a power curve of the fan according to the data points after filtering, wherein the power curve is used for representing the corresponding relation between the wind speed and the power of the fan.
Optionally, the generating a power curve of the fan according to the data points after filtering includes:
selecting the data point with the maximum product of the joint probability density and the distance from the filtered data points as a clustering center;
classifying data points with the distance from the clustering center within a preset range into the class of the clustering center;
and generating a power curve of the fan according to the clustered data points.
In a second aspect, an embodiment of the present invention further provides a data processing apparatus for a wind turbine, where the apparatus includes:
the establishing module is used for establishing a data matrix according to a plurality of groups of monitoring data of the fan; wherein each data point in the data matrix comprises a set of the monitoring data, the monitoring data comprising: a wind speed and a power of the fan at the wind speed;
a distance determination module for determining a distance between every two data points in the data matrix;
a density determination module for determining a joint probability density of each data point in the data matrix with respect to wind speed and power;
and the filtering module is used for filtering the data points according to the distance and the joint probability density.
Optionally, the filtering module is further configured to determine a distance corresponding to each joint probability density according to a distance between every two data points in the data matrix and the joint probability density of each data point in the data matrix with respect to wind speed and power; the distance corresponding to the maximum joint probability density is the maximum distance, and the distances corresponding to other joint probability densities are the minimum distances; establishing a data set comprising a plurality of sets of data, wherein each set of data comprises: a joint probability density and a distance corresponding to said joint probability density; determining data points in the data set, wherein the joint probability density is smaller than or equal to a preset density, and the distance is larger than or equal to a preset distance, and taking the data points as abnormal data points; filtering the outlier data points in the data set.
Optionally, the filtering module is further configured to establish a distance matrix according to a distance between every two data points in the data matrix, where each data in the distance matrix is a distance between two data points; establishing a density matrix according to the combined probability density of each data point about the wind speed and the power, wherein each data in the density matrix is the combined probability density of the data points about the wind speed and the power within a preset distance range by taking the data point as a center; and determining the distance corresponding to each joint probability density according to the distance matrix and the density matrix.
Optionally, the apparatus further comprises:
and the generating module is used for generating a power curve of the fan according to the data points after filtering, and the power curve is used for representing the corresponding relation between the wind speed and the power of the fan.
Optionally, the generating module is further configured to select, from the filtered data points, a data point with a largest product of the joint probability density and the distance as a cluster center; classifying data points with the distance from the clustering center within a preset range into the class of the clustering center; and generating a power curve of the fan according to the clustered data points.
In a third aspect, an embodiment of the present invention further provides a processing device, including: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when the processing device is operated, the processor and the storage medium communicate with each other through the bus, and the processor executes the machine-readable instructions to execute the steps of the data processing method of the wind turbine according to any one of the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the data processing method for a wind turbine according to any one of the first aspects.
The invention has the beneficial effects that:
according to the method and the device for monitoring the wind speed and the power of the wind turbine, a data matrix is established according to multiple groups of monitoring data of the wind speed and the power of the wind turbine, the distance between every two data points in the data matrix is determined, then the joint probability density of each data point in the data matrix about the wind speed and the power is determined, and finally data point filtering is carried out according to the distance and the joint probability density. The distances between the data points corresponding to each group of monitoring data and other data points and the joint probability density of each data point are obtained through calculation based on the wind speed and the power of the fan, the data points are filtered without filtering through a manually set threshold, the accuracy of data filtering is improved, and therefore the accuracy of evaluating the fan based on a power curve obtained by the filtered data points is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a data processing method of a wind turbine according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a data processing method of a wind turbine according to another embodiment of the present invention;
fig. 3 is a schematic diagram of a data processing apparatus of a wind turbine according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a data processing apparatus of a wind turbine according to another embodiment of the present invention;
fig. 5 is a schematic structural diagram of a processing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
Before the application is filed, the related technical scheme is as follows: firstly, determining a filtering threshold value according to design parameters of the wind generating set, then filtering each scattered point in a power curve according to the filtering threshold value, and finally evaluating the fan according to the filtered curve. However, the filtering threshold is set artificially according to the design parameters of the fan, so that the filtering is inaccurate, and the evaluation of the fan is inaccurate.
In order to solve the above technical problem, an embodiment of the present invention provides a data processing method for a fan. The core improvement point is as follows: and according to the monitoring data of the wind turbine including wind speed and power, determining the distance between each data point and the joint probability density of each data point about the wind speed and the power, screening and determining abnormal data points in the monitoring data according to the distance and the joint probability density, and filtering the abnormal data points.
The technical solution provided by the present invention is explained below by a plurality of possible implementation manners.
Fig. 1 is a schematic flow chart of a Data processing method of a blower according to an embodiment of the present invention, where the Data processing method may be executed by a server, the server may be a server in an SCADA (Supervisory Control And Data Acquisition, Data Acquisition And monitoring Control) system, such as a Data Acquisition server or a Data monitoring server, And the server may also be another type of server in another system, as shown in fig. 1, And the method may include:
In order to improve the accuracy of evaluating the fan, the monitoring data of the fan may be filtered first to screen out abnormal data points in multiple sets of monitoring data, the monitoring data of the fan may be obtained first, and a data matrix may be established according to the multiple sets of monitoring data, so that in subsequent steps, the monitoring data may be screened according to the data matrix.
Each set of monitoring data of the fan may include a wind speed and a power corresponding to the wind speed, where the wind speed is a wind speed in a scene where the fan is located, and the power corresponding to the wind speed is a power output by the fan at the wind speed.
In an optional embodiment, multiple sets of monitoring data of the fan within a preset time period may be acquired, the wind speed and the power are respectively used as a row vector and a column vector according to the acquired multiple sets of monitoring data, a data matrix including the multiple sets of monitoring data is established, and each set of monitoring data is filled to a position corresponding to the wind speed and the power in the data matrix and is used as a data point corresponding to each wind speed and power.
For example, multiple sets of monitoring data recorded by the SCADA system may be acquired, and a data matrix D ═ v, P may be established from the multiple sets of monitoring data, where v is wind speed and P is power.
After the data matrix is obtained, the data points in the data matrix may be further processed to obtain a distance between any two data points in the data matrix, so that in a subsequent step, abnormal data points may be filtered according to the calculated distance.
In an alternative embodiment, for any one data point, other data points in the data matrix may be traversed, and a preset distance algorithm is used according to the wind speed and power of the data point and the wind speed and power of other data points, so as to calculate the distance between the data point and other data points, and further, the distance between every two data points may be calculated.
It should be noted that, in practical applications, the distance between any two data points may be a euclidean distance, or may be another distance used to represent a difference between two data points, which is not limited in the embodiment of the present application.
After the data matrix is obtained, the joint probability density of each data point can be calculated based on the wind speed and the power, so that the density degree of each data point can be determined according to the joint probability density, and abnormal data points can be screened in a subsequent step by combining the joint probability density.
Wherein, the joint probability density is used for indicating the density degree of the data point in the preset area. For example, if the joint probability density of a certain data point is greater, it means that there are more other data points distributed around the data point; if the joint probability density of a certain data point is smaller, it means that there are fewer other data points distributed around the data point.
In an optional embodiment, for each data point, the data point may be used as a center of a circle, a preset distance is used as a radius, each data point in the circular area is obtained, and then calculation is performed according to a preset joint probability density algorithm to obtain a joint probability density of the data point with respect to wind speed and power.
The preset distance may be set according to the wind speed and power of the data point, or may be set according to an empirical value, which is not limited in the embodiment of the present application.
It should be noted that, in the embodiment of the present application, only the step 102 is executed first and then the step 103 is executed, but in practical applications, the step 103 may be executed first and then the step 102 is executed, or the step 102 and the step 103 may be executed simultaneously, and the order of executing the step 102 and the step 103 is not limited in the embodiment of the present application.
In addition, in the process of calculating the joint probability density, a gaussian kernel function may be used for calculation, and also other joint probability density functions may be used for calculation, which is not limited in the embodiment of the present application.
And 104, filtering data points according to the distance and the joint probability density.
After the distance between each data and other data points and the joint probability density of each data point are calculated, abnormal data points in each data point can be determined based on the distance and the joint probability density, and the abnormal data points in each data point are screened to complete the filtering of the data points.
In an alternative embodiment, for each data point, a joint probability density of the data point may be obtained, and if the joint probability density of the data point is greater than a preset density threshold, it indicates that there are more other data points distributed around the data point, and the data point may be determined to be a non-abnormal data point.
However, if the joint probability density of the data point is less than or equal to the preset density threshold, it is determined that there are fewer other data points distributed around the data point, distances between the data point and the other data points may be obtained again, and it is determined whether the minimum distance among the obtained distances is greater than the preset distance threshold, if so, it is determined that there are fewer other data points distributed around the data point, and the data point may be an abnormal data point, the data point may be filtered, so that after each data point is analyzed and determined, it is determined whether each data point is an abnormal data point, and finally, each determined abnormal data point is filtered.
In summary, according to the data processing method of the wind turbine provided by the embodiment of the application, a data matrix is established according to multiple groups of monitoring data of the wind speed and the power of the wind turbine, the distance between every two data points in the data matrix is determined, the joint probability density of each data point in the data matrix about the wind speed and the power is determined, and finally, data point filtering is performed according to the distance and the joint probability density. The distances between the data points corresponding to each group of monitoring data and other data points and the joint probability density of each data point are obtained through calculation based on the wind speed and the power of the fan, the data points are filtered without filtering through a manually set threshold, the accuracy of data filtering is improved, and therefore the accuracy of evaluating the fan based on a power curve obtained by the filtered data points is improved.
Fig. 2 is a schematic flow chart of a data processing method of a wind turbine according to another embodiment of the present invention, and as shown in fig. 2, the method may include:
And step 204, filtering data points according to the distance and the joint probability density.
After the distance and the joint probability density are determined, abnormal data points in each data point can be determined based on the distance and the joint probability density so as to filter each abnormal data point, and in the subsequent step, a power curve of the fan is generated according to the filtered data points.
In determining the outlier data point, the distance and the joint probability density need to be further processed, and optionally, step 204 as shown above can be implemented by at least the following steps:
and step 204a, determining the distance corresponding to each joint probability density according to the distance between every two data points in the data matrix and the joint probability density of each data point in the data matrix about the wind speed and the power.
The distance corresponding to the maximum joint probability density is the maximum distance, and the distances corresponding to other joint probability densities are the minimum distances.
Because each data point has a distance with other data points, in order to reduce the operation amount and improve the efficiency of screening abnormal data points, the distance which can embody the characteristics of the data point can be selected from a plurality of distances of the data point by combining the joint probability density of each data point, and the distance is used as the distance corresponding to the joint probability density of the data point.
Further, the distances meeting different conditions can be selected as the distances corresponding to the joint probability density according to the parameter values of the joint probability density of the data points.
Optionally, a distance matrix may be established according to a distance between every two data points in the data matrix, where each data in the distance matrix is a distance between two data points; establishing a density matrix according to the joint probability density of each data point about the wind speed and the power, wherein each data in the density matrix is the joint probability density of the data point about the wind speed and the power, which takes the data point as the center, and is within a preset distance range; and determining the distance corresponding to each joint probability density according to the distance matrix and the density matrix.
For example, a distance matrix D ═ D is established based on the calculated distance between each data point and other data points ij ]Wherein d is ij Which is used to represent the distance between the ith data point and the jth data point, i and j are positive integers.
Similarly, a density matrix ρ ═ ρ may be established based on the joint probability density of each data point i ]，ρ i The combined probability density of the ith data point is represented, and the combined probability density of the habitual wind speed and the habitual wind power of the ith data point in the preset distance (dc) range is represented.
Correspondingly, in the process of determining the distance corresponding to each joint probability density according to the distance matrix and the density matrix, for each data point, the joint probability density of the data point may be compared with the joint probability densities of other data points to determine whether the joint probability density of the data point is the maximum joint probability density.
If the joint probability density of the data point is the maximum joint probability density, the distance (d) with the largest parameter value can be selected from the distances between the data point and each of the other data points max ) As the distance corresponding to the joint probability density.
If the joint probability density of the data point is not the maximum joint probability density, the data point is used as a circle center, a preset distance is used as a radius, a plurality of data points are selected in the circular area, and the distance (mind) with the minimum parameter value is selected from the distances between the plurality of data points and the data point ij ) The distance corresponding to the joint probability density is obtained by selecting the distance with the smallest distance from the centers of the circles from the distances between the plurality of data points and the centers of the circles as the distance corresponding to the joint probability density.
And ρ i Less than rho j That is, the joint probability density of the ith data point is smaller than the joint probability density of the jth data point, and the distance between the ith data point and the jth data point is the minimum distance in the circular region corresponding to the preset distance, the distance between the ith data point and the jth data point can be taken as the distance corresponding to the joint probability density of the ith data point.
And step 204b, establishing a data set comprising multiple groups of data.
Wherein each set of data may include: a joint probability density and a distance corresponding to the joint probability density.
After determining the distance corresponding to the joint probability density for each data point, a data set including the data point may be established based on the joint probability density and the corresponding distance for each data point, so that in a subsequent step, an outlier data point may be determined based on the joint probability density and the corresponding distance for each data point in the data set.
For example, the data set M may include a joint probability density (ρ) corresponding to each data point and a distance (δ), ρ, corresponding to the joint probability density i Represents the joint probability density, δ, of the ith data point i And (3) representing the distance corresponding to the joint probability density of the ith data point.
And 204c, determining data points in the data set, wherein the joint probability density is smaller than or equal to the preset density, and the distance is larger than or equal to the preset distance, and taking the data points as abnormal data points.
For each data point in the data set, whether the joint probability density of the data point is less than or equal to a preset density can be judged, if the joint probability density of the data point is greater than the preset density, it is indicated that other data points around the data point are more, and the probability that the data point belongs to an abnormal data point is smaller; however, if the joint probability density of the data point is less than or equal to the predetermined density, it indicates that there are fewer other data points around the data point, and the probability that the data point belongs to an abnormal data point is higher, and the determination may be further performed according to the distance corresponding to the joint probability density.
If the distance corresponding to the joint probability density of the data point is greater than or equal to the preset distance, it is indicated that the minimum distance between the data point and other data points is also greater than or equal to the preset distance, and the distances between the data point and other data points are far, the data point may be an abnormal data point, and the data point may be taken as an abnormal data point.
And step 204d, filtering abnormal data points in the data set.
After the abnormal data points are determined, each abnormal data point can be filtered out from the plurality of data points, so that in the subsequent step, a more accurate power curve of the fan can be generated according to each filtered data point.
It should be noted that, in practical applications, after the step 204c is executed to determine the abnormal data point, the step 204d is executed to filter the abnormal data point immediately, and the steps 204c and 204d are executed in a circulating manner until each data point is judged to be completed; step 204d may also be performed after step 204c is performed to determine all abnormal data points in each data point, so as to filter out each abnormal data point.
Optionally, the method may further include:
and step 205, generating a power curve of the fan according to the data points after filtering.
The power curve is used for representing the corresponding relation between the wind speed and the power of the fan.
After the filtered data points are obtained, a power curve of the fan can be generated according to the filtered data points, so that the performance and the running state of the fan can be evaluated according to the generated accurate power curve.
In the process of generating the power curve, the cluster center in the power curve can be determined, and then each data point is arranged near the cluster center according to the cluster center, so that the power curve of the fan is generated.
Optionally, the data point with the maximum product of the joint probability density and the distance may be selected from the filtered data points as a cluster center, the data points with the distance from the cluster center within a preset range are classified into the class in which the cluster center is located, and then the power curve of the fan is generated according to the clustered data points.
In an optional embodiment, for each data point, a product between the joint probability density of the data point and the corresponding distance may be obtained, so as to obtain a product corresponding to each data point, and the data point corresponding to the product with the largest parameter value is taken as a cluster center, and then according to the wind speed and power corresponding to each data point, each data point is arranged near the cluster center, and finally, a power curve is generated according to the arranged data points.
In summary, according to the data processing method of the wind turbine provided by the embodiment of the application, a data matrix is established according to multiple groups of monitoring data of the wind speed and the power of the wind turbine, the distance between every two data points in the data matrix is determined, the joint probability density of each data point in the data matrix about the wind speed and the power is determined, and finally, data point filtering is performed according to the distance and the joint probability density. The distances between the data points corresponding to each group of monitoring data and other data points and the joint probability density of each data point are obtained through calculation based on the wind speed and the power of the fan, the data points are filtered without filtering through a manually set threshold, the accuracy of data filtering is improved, and therefore the accuracy of evaluating the fan based on a power curve obtained by the filtered data points is improved.
Fig. 3 is a schematic diagram of a data processing device of a wind turbine according to an embodiment of the present invention, and as shown in fig. 3, the data processing device specifically includes:
the establishing module 301 is configured to establish a data matrix according to multiple sets of monitoring data of the fan; wherein each data point in the data matrix comprises a set of the monitoring data, and the monitoring data comprises: a wind speed and a power of the fan at the wind speed;
a distance determining module 302 for determining a distance between every two data points in the data matrix;
a density determination module 303 for determining a joint probability density of each data point in the data matrix with respect to wind speed and power;
and a filtering module 304 for performing data point filtering according to the distance and the joint probability density.
Optionally, the filtering module 304 is further configured to determine a distance corresponding to each joint probability density according to a distance between every two data points in the data matrix and the joint probability density of each data point in the data matrix with respect to wind speed and power; the distance corresponding to the maximum joint probability density is the maximum distance, and the distances corresponding to other joint probability densities are the minimum distances; establishing a data set comprising a plurality of sets of data, wherein each set of data comprises: a joint probability density and a distance corresponding to the joint probability density; determining data points in the data set, wherein the joint probability density is less than or equal to a preset density, and the distance is greater than or equal to a preset distance, and taking the data points as abnormal data points; the outlier data point in the data set is filtered.
Optionally, the filtering module 304 is further configured to establish a distance matrix according to a distance between every two data points in the data matrix, where each data in the distance matrix is a distance between two data points; establishing a density matrix according to the combined probability density of each data point about the wind speed and the power, wherein each data in the density matrix is the combined probability density of the data points about the wind speed and the power within a preset distance range by taking the data point as a center; and determining the distance corresponding to each joint probability density according to the distance matrix and the density matrix.
Optionally, referring to fig. 4, the apparatus further includes:
and a generating module 305, configured to generate a power curve of the fan according to the filtered data points, where the power curve is used to represent a corresponding relationship between a wind speed and a power of the fan.
Optionally, the generating module 305 is further configured to select, from the filtered data points, a data point with a largest product of the joint probability density and the distance as a cluster center; classifying the data points with the distance from the cluster center within a preset range into the class of the cluster center; and generating a power curve of the fan according to the clustered data points.
To sum up, the data processing device for a wind turbine, provided by the embodiment of the present application, establishes a data matrix according to multiple groups of monitoring data of the wind speed and power of the wind turbine, determines a distance between every two data points in the data matrix, determines a joint probability density of each data point in the data matrix with respect to the wind speed and the power, and finally performs data point filtering according to the distance and the joint probability density. The distances between the data points corresponding to each group of monitoring data and other data points and the joint probability density of each data point are obtained through calculation based on the wind speed and the power of the fan, the data points are filtered without filtering through a manually set threshold, the accuracy of data filtering is improved, and therefore the accuracy of evaluating the fan based on a power curve obtained by the filtered data points is improved.
The above-mentioned apparatus is used for executing the method provided by the foregoing embodiment, and the implementation principle and technical effect are similar, which are not described herein again.
These above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Fig. 5 is a schematic structural diagram of a processing device according to an embodiment of the present invention, where the processing device may be a server, and the server may be a device having a data processing function of a fan.
The processing apparatus includes: a processor 501, a storage medium 502, and a bus 503.
The storage medium 502 stores machine-readable instructions executable by the processor 501, and when the processing device is running, the processor 501 communicates with the storage medium 502 via the bus 503, and the processor 501 executes the machine-readable instructions to perform the above-mentioned method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
Optionally, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, performs the above-mentioned method embodiments.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall cover the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A data processing method of a fan is characterized by comprising the following steps:
establishing a data matrix according to a plurality of groups of monitoring data of the fan; wherein each data point in the data matrix comprises a set of the monitoring data, the monitoring data comprising: a wind speed and a power of the fan at the wind speed;
determining a distance between every two data points in the data matrix;
determining a joint probability density for each data point in the data matrix with respect to wind speed and power;
filtering data points according to the distance and the joint probability density;
said filtering data points according to said distance and said joint probability density, comprising:
determining a distance corresponding to each joint probability density according to the distance between every two data points in the data matrix and the joint probability density of each data point in the data matrix about the wind speed and the power; the distance corresponding to the maximum joint probability density is the maximum distance, and the distances corresponding to other joint probability densities are the minimum distances;
establishing a data set comprising a plurality of sets of data, wherein each set of data comprises: a joint probability density and a distance corresponding to said joint probability density;
determining data points in the data set, wherein the joint probability density is smaller than or equal to a preset density, and the distance is larger than or equal to a preset distance, and taking the data points as abnormal data points;
filtering the outlier data points in the data set.
2. The method of claim 1, wherein determining the distance corresponding to each joint probability density based on the distance between each two data points in the data matrix and the joint probability density of each data point in the data matrix with respect to wind speed and power comprises:
establishing a distance matrix according to the distance between every two data points in the data matrix, wherein each data in the distance matrix is the distance between two data points;
establishing a density matrix according to the combined probability density of each data point about the wind speed and the power, wherein each data in the density matrix is the combined probability density of the data points about the wind speed and the power within a preset distance range by taking the data point as a center;
and determining the distance corresponding to each joint probability density according to the distance matrix and the density matrix.
3. The method of claim 1, further comprising:
and generating a power curve of the fan according to the data points after filtering, wherein the power curve is used for representing the corresponding relation between the wind speed and the power of the fan.
4. The method of claim 3, wherein generating the power curve for the wind turbine from the filtered data points comprises:
selecting a data point with the maximum product of the joint probability density and the corresponding distance from the filtered data points as a clustering center; the corresponding distance is the distance corresponding to the joint probability density;
classifying data points with the distance from the clustering center within a preset range into the class of the clustering center;
and generating a power curve of the fan according to the clustered data points.
5. A data processing apparatus for a wind turbine, the apparatus comprising:
the establishing module is used for establishing a data matrix according to a plurality of groups of monitoring data of the fan; wherein each data point in the data matrix comprises a set of the monitoring data, the monitoring data comprising: a wind speed and a power of the fan at the wind speed;
the distance determining module is used for determining the distance between every two data points in the data matrix;
a density determination module for determining a joint probability density of each data point in the data matrix with respect to wind speed and power;
the filtering module is used for filtering data points according to the distance and the joint probability density;
the filtering module is further used for determining a distance corresponding to each joint probability density according to the distance between every two data points in the data matrix and the joint probability density of each data point in the data matrix with respect to wind speed and power; the distance corresponding to the maximum joint probability density is the maximum distance, and the distances corresponding to other joint probability densities are the minimum distances; establishing a data set comprising a plurality of sets of data, wherein each set of data comprises: a joint probability density and a distance corresponding to said joint probability density; determining data points in the data set, wherein the joint probability density is smaller than or equal to a preset density, and the distance is larger than or equal to a preset distance, and taking the data points as abnormal data points; filtering the outlier data points in the data set.
6. The apparatus of claim 5, wherein the filtering module is further configured to establish a distance matrix according to a distance between every two data points in the data matrix, and each data in the distance matrix is a distance between two data points; establishing a density matrix according to the combined probability density of each data point about the wind speed and the power, wherein each data in the density matrix is the combined probability density of the data points about the wind speed and the power within a preset distance range by taking the data point as a center; and determining the distance corresponding to each joint probability density according to the distance matrix and the density matrix.
7. The apparatus of claim 5, further comprising:
and the generating module is used for generating a power curve of the fan according to the data points after filtering, and the power curve is used for representing the corresponding relation between the wind speed and the power of the fan.
8. The apparatus according to claim 7, wherein the generating module is further configured to select a data point with a largest product of the joint probability density and the corresponding distance from the filtered data points as a cluster center; the corresponding distance is the distance corresponding to the joint probability density; classifying data points with the distance from the clustering center within a preset range into the class where the clustering center is located; and generating a power curve of the fan according to the clustered data points.
9. A processing device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the processing device is running, the processor executing the machine-readable instructions to perform the steps of the data processing method of the wind turbine according to any one of claims 1 to 4.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when being executed by a processor, performs the steps of the data processing method of a wind turbine according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911065104.XA CN110826904B (en) | 2019-11-01 | 2019-11-01 | Data processing method and device for fan, processing equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911065104.XA CN110826904B (en) | 2019-11-01 | 2019-11-01 | Data processing method and device for fan, processing equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110826904A CN110826904A (en) | 2020-02-21 |
| CN110826904B true CN110826904B (en) | 2022-08-02 |
Family
ID=69552639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911065104.XA Active CN110826904B (en) | 2019-11-01 | 2019-11-01 | Data processing method and device for fan, processing equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110826904B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304898B (en) * | 2023-05-15 | 2023-08-01 | 北京信息科技大学 | Sensor data intelligent storage system based on machine learning |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013054088A1 (en) * | 2011-10-10 | 2013-04-18 | Isis Innovation Limited | Improvements in localisation estimation |
| CN105930933B (en) * | 2016-04-26 | 2019-05-31 | 华北电力科学研究院有限责任公司 | Wind power plant theoretical power curve determines method and device |
| CN107103175B (en) * | 2017-02-03 | 2019-11-12 | 华北电力科学研究院有限责任公司 | A kind of wind power generating set disorder data recognition method and device |
| CN107122475A (en) * | 2017-05-02 | 2017-09-01 | 杭州泰指尚科技有限公司 | Big data abnormal point detecting method and its system |
| CN109783486B (en) * | 2019-01-17 | 2020-11-24 | 华北电力大学 | Data cleaning method and device and server |
-
2019
- 2019-11-01 CN CN201911065104.XA patent/CN110826904B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110826904A (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111626360B (en) | Method, apparatus, device and storage medium for detecting boiler fault type | |
| CN108809734B (en) | Network alarm root analysis method, system, storage medium and computer equipment | |
| CN111881617A (en) | Data processing method, and performance evaluation method and system of wind generating set | |
| CN106897945A (en) | The clustering method and equipment of wind power generating set | |
| EP4053757A1 (en) | Degradation suppression program, degradation suppression method, and information processing device | |
| EP4050527A1 (en) | Estimation program, estimation method, information processing device, relearning program, and relearning method | |
| CN110532613A (en) | Ship power system operation mode recognition method and device | |
| CN110826904B (en) | Data processing method and device for fan, processing equipment and readable storage medium | |
| CN117495891B (en) | Point cloud edge detection method and device and electronic equipment | |
| CN117092525B (en) | Training method and device for battery thermal runaway early warning model and electronic equipment | |
| CN116365519B (en) | Power load prediction method, system, storage medium and equipment | |
| CN112398226A (en) | Power supply system electricity stealing prevention method, system, terminal and storage medium | |
| CN114116853B (en) | Data security analysis method and device based on time sequence association analysis | |
| CN117134318A (en) | Photovoltaic power generation power prediction method, device, medium and equipment | |
| CN114676781A (en) | Vehicle fault diagnosis and prediction method, device and equipment and vehicle | |
| CN110826899B (en) | Performance evaluation method, device, equipment and storage medium of wind generating set | |
| CN116107859B (en) | Container fault prediction method and device, electronic equipment and storage medium | |
| CN111291464A (en) | Dynamic equivalence method and device for power system | |
| CN111698700B (en) | Method and device for judging working state of cell | |
| CN113055339B (en) | Process data processing method and device, storage medium and computer equipment | |
| CN117541832B (en) | Abnormality detection method, abnormality detection system, electronic device, and storage medium | |
| CN118394988B (en) | BIM technology-based assembly type building data optimal storage method and system | |
| CN117197036B (en) | Image detection method and device | |
| CN115953724B (en) | User data analysis and management method, device, equipment and storage medium | |
| CN118604640B (en) | Battery evaluation method, device, electronic equipment, storage medium and program product |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 102206 31 Industrial Park, North Qing Road, Beijing, Changping District Applicant after: Sany Heavy Energy Co.,Ltd. Address before: 102206 31 Industrial Park, North Qing Road, Beijing, Changping District Applicant before: SANY HEAVY ENERGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |