CN117846894A - Data processing method, early warning device, equipment and medium of wind turbine generator - Google Patents
Data processing method, early warning device, equipment and medium of wind turbine generator Download PDFInfo
- Publication number
- CN117846894A CN117846894A CN202410044735.8A CN202410044735A CN117846894A CN 117846894 A CN117846894 A CN 117846894A CN 202410044735 A CN202410044735 A CN 202410044735A CN 117846894 A CN117846894 A CN 117846894A
- Authority
- CN
- China
- Prior art keywords
- data
- operation parameter
- wind turbine
- target
- parameter 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
- 238000003672 processing method Methods 0.000 title claims abstract description 17
- 238000004140 cleaning Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims description 69
- 238000000034 method Methods 0.000 claims description 68
- 230000002159 abnormal effect Effects 0.000 claims description 54
- 238000001514 detection method Methods 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 22
- 238000006073 displacement reaction Methods 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000010219 correlation analysis Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 abstract description 16
- 238000007781 pre-processing Methods 0.000 abstract description 4
- 230000007613 environmental effect Effects 0.000 description 15
- 238000011161 development Methods 0.000 description 8
- 238000012423 maintenance Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000013450 outlier detection Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- 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
- F03D7/043—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic
- F03D7/045—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic with model-based controls
-
- 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
- F03D7/043—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic
- F03D7/046—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic with learning or adaptive control, e.g. self-tuning, fuzzy logic or neural network
-
- 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
- F03D80/00—Details, components or accessories not provided for in groups F03D1/00 - F03D17/00
-
- 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)
- Mechanical Engineering (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a data processing method, an early warning device, equipment and a medium for a wind turbine, wherein the data processing method for the wind turbine comprises the following steps: acquiring initial operation parameter data and target environment data of a wind turbine generator; performing data cleaning on the initial operation parameter data and the target environment data through an edge server arranged at the wind turbine generator; carrying out correlation on the initial operation parameter data after data cleaning and the target environment data after data cleaning to obtain target operation parameter data corresponding to the target environment data from the initial operation parameter data; and outputting the target operation parameter data to the outside. By preprocessing the operation parameter data at the edge server, the quality of the operation parameter data is improved, and meanwhile, the transmission quantity of the data can be reduced, so that the transmission efficiency of the data is improved.
Description
Technical Field
The invention relates to the field of data processing, in particular to a data processing method, an early warning method, a device, equipment and a medium of a wind turbine generator.
Background
The wind driven generator is a novel energy device for converting wind energy into electric energy. Along with the rapid increase of the number of wind driven generators, the management cost is increased, so that the three-dimensional visualized management platform of the fan is built by utilizing a digital twin technology to carry out lean management on the fan.
The digital twin system is an analog system based on a digital technology, and can combine digital information of a physical entity with virtual information in a visual management platform to form an analog system capable of truly simulating the physical entity. Digital twinning systems are typically composed of three parts: digital model, data acquisition and analysis, and applications. The digital model and the data acquisition and analysis are key components in the digital twin system; the digital model is used for simulating physical systems, processes and behaviors in the real world, the precision and the accuracy of the digital model are very important, and the reliability and the practicability of the digital twin system are directly affected; data acquisition and analysis is used to collect data in the real world through sensors and data acquisition devices and compare and analyze it with digital models to better simulate physical systems and processes in the real world and to help users better understand and predict behaviors and events in the real world.
However, the digital twin system related to the wind driven generator at present cannot predict the potential risk of the wind driven generator, and because the current wind power site is remote, a large amount of data is directly collected at the wind power site and transmitted to the cloud, so that the transmitted data is large in amount and low in efficiency; further resulting in lower precision and accuracy of the digital model in the digital twin system for the wind turbine, resulting in high operational and maintenance costs for the associated equipment.
Disclosure of Invention
The invention aims to solve the technical problems that a digital twin system of a wind power generator cannot predict potential risks of the wind power generator and has large data transmission quantity in the prior art, and provides a data processing method, an early warning device, equipment and a medium of the wind power generator.
The invention solves the technical problems by the following technical scheme:
according to a first aspect of the present invention, there is provided a data processing method of a wind turbine, the data processing method comprising:
acquiring initial operation parameter data and target environment data of a wind turbine generator;
performing data cleaning on the initial operation parameter data and the target environment data through an edge server arranged at the wind turbine generator;
Performing correlation analysis on the initial operation parameter data after data cleaning and the target environment data after data cleaning to obtain target operation parameter data corresponding to the target environment data from the initial operation parameter data; and outputting the target operation parameter data to the outside.
Preferably, the specific steps of data cleaning include:
acquiring the initial operation parameter data and/or the target environment data, and judging whether missing data exists in the initial operation parameter data and/or the target environment data;
if so, interpolation processing is carried out on the initial operation parameter data and/or the target environment data so as to fill the missing data.
Preferably, before said determining whether there is missing data in the initial operating parameter data and/or the target environment data, the method further comprises:
acquiring the initial operation parameter data and/or the target environment data, and judging whether the initial operation parameter data and/or the target environment data comprise shutdown data or not;
if so, deleting the shutdown data;
and/or the number of the groups of groups,
before the step of judging whether missing data exists in the initial operation parameter data and/or the target environment data, the method further comprises the following steps:
Acquiring the initial operation parameter data and/or the target environment data, and judging whether the acquisition frequency of the initial operation parameter data and/or the target environment data is greater than a first preset value or not;
if yes, downsampling is conducted on the initial operation parameter data and/or the target environment data until the acquired frequency reaches a preset frequency.
Preferably, the interpolation is implemented by a K nearest neighbor algorithm.
Preferably, the step of data cleansing further comprises:
acquiring the initial operation parameter data and/or the target environment data, respectively detecting whether abnormal data exists in the initial operation parameter data and/or the target environment data through a plurality of abnormal value detection methods, and performing group decision judgment based on corresponding detection results of the plurality of abnormal value detection methods to judge whether abnormal data exists in the operation parameter data;
if so, the abnormal data is deleted.
Preferably, the initial operation parameter data includes at least one of rotational speed data, yaw angle data, and output power data;
the target environment data are wind speed data;
the correlation analysis is achieved by the pearson correlation coefficient method.
According to a second aspect of the present invention, there is provided a data processing apparatus of a wind turbine, where the data processing apparatus is configured to implement the data processing method of a wind turbine according to the first aspect of the present invention; the data processing apparatus includes:
the data acquisition module is used for acquiring initial operation parameter data and target environment data of the wind turbine generator;
the data processing module comprises an edge server; the data processing module is used for cleaning the initial operation parameter data and the target environment data through an edge server arranged at the wind turbine generator; the data processing module is also used for carrying out correlation analysis on the initial operation parameter data after data cleaning and the target environment data after data cleaning so as to obtain target operation parameter data corresponding to the target environment data from the initial operation parameter data;
and the data output module is used for outputting the target operation parameter data to the outside.
According to a third aspect of the present invention, there is provided an early warning method for a wind turbine generator, the early warning method comprising:
acquiring target operation parameter data of a current wind turbine generator;
Inputting the target operation parameter data into a first model to obtain target environment data corresponding to the target operation parameter data; the first model is obtained based on first historical data training; the first historical data comprises historical operation parameter data and historical environment data corresponding to the historical operation parameter data;
inputting the target environment data into a second model to obtain target physical data corresponding to the target environment data; wherein the second model is trained based on second historical data; the second historical data comprises historical environment data and historical physical data corresponding to the historical environment data;
and carrying out early warning on the specific running state of the wind turbine generator based on the physical data.
Preferably, the physical data includes: target stress data and/or target displacement data;
the early warning of the wind turbine generator based on the target physical data specifically comprises the following steps:
determining whether the target stress data is greater than a first threshold,
if yes, early warning is carried out on the wind turbine generator;
and/or the number of the groups of groups,
judging whether the target displacement data is larger than a second threshold value or not;
if yes, early warning is carried out on the wind turbine generator.
Preferably, the operation parameter data includes: at least one of rotational speed data, yaw angle data, and output power data;
the first historical data are operation parameter data which are preprocessed by an edge server arranged on the wind turbine generator.
Preferably, the early warning method further includes:
acquiring piezoelectric data of the tower top of the wind turbine generator;
inputting the piezoelectric data into a pre-trained third model to obtain target piezoelectric data of a related time sequence;
judging whether the target piezoelectric data is larger than a third threshold value or not;
if yes, early warning is carried out on the wind turbine generator.
According to a fourth aspect of the present invention, there is provided an early warning device for a wind turbine, where the early warning device is configured to implement the early warning method for a wind turbine according to the third aspect of the present invention; the early warning device comprises:
the operation data acquisition module is used for acquiring target operation parameter data of the current wind turbine generator;
a first processing module, the first processing module comprising a first model; the first processing module is used for inputting the target operation parameter data into a first model for processing to obtain target environment data corresponding to the target operation parameter; the first model is obtained based on first historical data training; the first historical data comprises historical operation parameter data and historical environment data corresponding to the historical operation parameter data;
A second processing module, the second processing module comprising a second model; the second processing module is used for inputting the target environment data into a second model for processing to obtain target physical data corresponding to the target environment data; wherein the second model is trained based on second historical data; the second historical data comprises historical environment data and historical physical data corresponding to the historical environment data;
and the early warning module is used for carrying out early warning on the specific running state of the wind turbine generator based on the target physical data.
According to a fifth aspect of the present invention, there is provided a wind power system comprising: the data processing device of the wind turbine generator set, the early warning device of the wind turbine generator set and the cloud storage device are described in the second aspect of the invention;
the data processing device is used for transmitting target operation parameter data to the cloud storage device;
the cloud storage device is used for storing the target operation parameter data;
the early warning device is used for acquiring the target operation parameter data from the cloud storage device and realizing early warning of the wind turbine generator based on the target operation parameter data.
According to a sixth aspect of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and running on the processor, where the processor implements the data processing method of the wind turbine according to the first aspect of the present invention or implements the early warning method of the wind turbine according to the third aspect of the present invention when executing the computer program.
According to a seventh aspect of the present invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for processing data of a wind turbine according to the first aspect of the present invention, or implements the method for early warning of a wind turbine according to the third aspect of the present invention.
The invention has the positive progress effects that:
according to the data processing method of the wind turbine generator, the operation parameter data is preprocessed at the edge server, so that the quality of the operation parameter data is improved, the transmission quantity of the data is reduced, and the transmission efficiency of the data is improved; according to the early warning method of the wind turbine generator, the state and the performance of the wind turbine generator can be monitored by obtaining the corresponding target physical data, possible faults or problems can be identified early, corresponding repair and maintenance measures can be taken by finding the potential faults in advance, and the downtime and the production loss of related equipment are avoided or reduced.
Drawings
FIG. 1 is a flow chart of a data processing method of a wind turbine in embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of a flow chart of data cleaning in embodiment 1 of the present invention;
FIG. 3 is a schematic structural diagram of a data processing device of a wind turbine generator in embodiment 2 of the present invention;
FIG. 4 is a flow chart of a method for early warning of a wind turbine in embodiment 3 of the present invention;
FIG. 5 is a schematic diagram of the implementation of the pre-warning method in embodiment 3 of the present invention;
FIG. 6 is a schematic structural diagram of a warning device of a wind turbine generator in embodiment 4 of the present invention;
FIG. 7 is a schematic diagram of a wind power system according to embodiment 5 of the present invention;
fig. 8 is a schematic structural diagram of an electronic device in embodiment 6 of the present invention.
Detailed Description
The invention is further illustrated by means of the following examples, which are not intended to limit the scope of the invention.
Example 1
As shown in fig. 1, in one embodiment of the present invention, a data processing method of a wind turbine is provided, where the data processing method includes.
S11: and acquiring initial operation parameter data and target environment data of the wind turbine generator.
In a specific embodiment of the present invention, the initial operation parameter data includes at least one of rotational speed data, yaw angle data, and output power data; the target environment data is wind speed data.
The method for acquiring the initial operation parameter data and the target environment data of the wind turbine generator set may be:
and simultaneously acquiring a set of initial operation parameter data and a set of target environment data in the time t 1.
S12: and cleaning the initial operation parameter data and the target environment data through an edge server arranged at the wind turbine generator.
S13: and performing correlation analysis on the initial operation parameter data after data cleaning and the target environment data after data cleaning to obtain target operation parameter data corresponding to the target environment data from the initial operation parameter data.
S14: and outputting the target operation parameter data to the outside.
In one specific embodiment of the present invention, the specific steps of data cleaning include: acquiring the initial operation parameter data and/or the target environment data, and judging whether missing data exists in the initial operation parameter data and/or the target environment data; if so, interpolation processing is carried out on the initial operation parameter data and/or the target environment data so as to fill the missing data.
In particular, in a specific embodiment of the invention, the interpolation is implemented by a K nearest neighbor algorithm (K-Nearest Neighbors, KNN).
In a specific implementation manner, the specific steps for implementing the interpolation processing through the K nearest neighbor algorithm include:
and acquiring a complete data set, wherein the complete data set comprises a plurality of data to be cleaned, and the data to be cleaned is the initial operation parameter data and/or the target environment data. A 6*6 data set, index row 2 and column 3 have missing data, and the missing data is removed, namely the complete data set.
When data are collected through a sensor, a singlechip and the like, the collected data are stored in the complete data set according to categories (such as wind speed, yaw angle, rotating speed and the like) as rows and time sequences as columns. The position point information of the missing data is obtained through Python, and a plurality of position point information in the complete data set is obtained; wherein the row information and the column information of any data form position point information of corresponding data.
Calculating a plurality of first distances based on a preset formula; wherein the first distance is characterized as the Euclidean distance of the missing data to each data in the complete dataset.
Wherein, the preset formula is:
wherein d i For Euclidean distance from missing data to other data in the complete data set, i is position point information of the ith data in the complete data set; x is X 1 To miss position point information of data, X i Is location point information for other data within the complete data set.
And selecting a first number of the initial operation parameter data and/or the target environment data from the complete data set according to preset conditions and a plurality of the first distances.
In a specific embodiment, the distance d is based on Euclidean distance i And (3) the size is increased, and the first k initial operation parameter data and/or the target environment data are screened out in an ascending order.
And determining the weighting value corresponding to each initial operation parameter data and/or the target environment data according to the Euclidean distance corresponding to the first k initial operation parameter data and/or the target environment data.
The formula for calculating the weighting value corresponding to each data is as follows:
wherein w is j Is the weighted value of the j-th data, d j The euclidean distance for the j-th data.
And multiplying the weighting values respectively corresponding to the first k initial operation parameter data and/or the target environment data with the position point information respectively to obtain first intermediate data of each initial operation parameter data and/or the target environment data.
Superposing the first k pieces of initial operation parameter data and/or first intermediate data corresponding to the target environment data to obtain filling data; and padding the real data according to the padding data.
Wherein, the calculation formula of the filling data is:
wherein F is filling data, w j Is the weighted value of the j-th data, x j Is the position point information of the j-th data.
In a preferred embodiment of the present invention, before said determining whether there is missing data in said initial operating parameter data and/or said target environment data, further comprises: acquiring the initial operation parameter data and/or the target environment data, and judging whether the initial operation parameter data and/or the target environment data comprise shutdown data or not; and if so, deleting the shutdown data.
In another preferred embodiment of the present invention, before said determining whether there is missing data in said initial operating parameter data and/or said target environment data, further comprises: acquiring the initial operation parameter data and/or the target environment data, and judging whether the acquisition frequency of acquiring the initial operation parameter data and/or the target environment data is greater than a first preset value or not; if yes, downsampling is conducted on the initial operation parameter data and/or the target environment data until the acquired frequency reaches a preset frequency.
The initial operation parameter data and/or the target environment data collected in the embodiment of the present invention are time-series data, specifically, the initial operation parameter data and/or the target environment data are collected in a preset step length, so that downsampling refers to adjusting (reducing) the step length for collecting the initial operation parameter data and/or the target environment data, so as to improve the calculation efficiency of the data.
Furthermore, in a preferred implementation manner of the embodiment of the present invention, the upper limit of the time interval of downsampling is 1 hour, that is, in the embodiment of the present invention, the minimum value of the preset frequency is 1/3600= 0.00027778HZ.
In one embodiment of the present invention, the step of data cleansing further comprises: acquiring the initial operation parameter data and/or the target environment data, respectively detecting whether abnormal data exists in the initial operation parameter data and/or the target environment data through a plurality of abnormal value detection methods, and performing group decision based on the corresponding detection results of the plurality of abnormal value detection methods so as to judge whether abnormal data exists in the initial operation parameter data and/or the target environment data; if so, the abnormal data is deleted.
The abnormal value detection method comprises at least one of the following steps: local anomaly factor (LOF), cluster-based local anomaly factor (CBLOF), K Nearest Neighbor (KNN), average KNN (AKNN), feature Bagging (FB), histogram-based outlier detection (HBOS), angle-based outlier detector (ABOD), minimum Covariance Determinant (MCD).
In a specific embodiment of the present invention, the above-mentioned abnormal value detection method is selected to detect whether the initial operation parameter data and/or the target environment data are abnormal data, respectively; realizing group decision according to the detection result; if eight abnormal value detection methods are used to detect whether the initial operation parameter data and/or the target environment data have abnormal data, at this time, when the abnormal value detection methods exceeding a preset number (such as five) determine that a certain data is abnormal data, the data is determined to be abnormal data.
In a specific embodiment of the present invention, if more than half of the outlier detection methods detect that the initial operating parameter data and/or the target environment data have abnormal data, the data is determined to be abnormal data by group decision.
In other specific embodiments of the present invention, whether abnormal data exists may be detected by an abnormal value detection method; the presence or absence of abnormal data may be detected by at least two abnormal value detection methods, and the same data may be used as abnormal data for the abnormal data detected by each abnormal value detection method, or the data detected by each abnormal value detection method may be used as abnormal data.
Of course, the present invention is not limited to the method for detecting abnormal data, and other methods for detecting abnormal data are within the scope of the present invention.
By cleaning the operation parameter data, the quality of the operation parameter data is improved, and meanwhile, the transmission quantity of the data can be reduced, so that the transmission efficiency of the data is improved; furthermore, missing or abnormal operation parameter data in the wind turbine generator can be removed, so that the accuracy of the operation parameter data is improved; and through the cleaning of the operation parameter data, the cleaned operation parameter data has higher reliability and usability, thereby improving the reliability of the operation parameter data.
In the embodiment of the invention, the abnormal data at least comprises an infinite value, a missing value and an outlier, and when the abnormal data is cleaned, the abnormal data in the initial operation parameter data and/or the target environment data is detected first, so that the abnormal data is processed to clean the data.
In a specific implementation manner in the embodiment of the invention, the detection of the abnormal data is realized by utilizing the isolated deep forest algorithm, and compared with the normal data, the abnormal data in the isolated forest algorithm has the characteristics of small data quantity, large difference of characteristic values and the like, so that the abnormal data is easier to isolate, and the abnormal data is obtained.
In another specific implementation manner in the embodiment of the present invention, detection of abnormal data may be further implemented based on a statistical and machine learning manner, for example, based on two statistical methods including 3-sigma and box graph, and a detection method including multiple machine learning such as independent forest, DBScan cluster, etc., identification of abnormal data is implemented according to different machine learning manners, and evaluation and statistics of abnormal data is implemented based on a statistical method, so as to obtain abnormal data in the operation parameter data.
In one implementation manner of the embodiment of the present invention, when the abnormal data is a missing value, a multi-method data missing value filling algorithm, such as a multi-interpolation missing value method based on a random forest method, may be obtained based on the principles of various missing data filling methods, so as to realize filling of the missing value.
The working principle of data cleaning on operation parameter data in the embodiment of the present invention is specifically described below with reference to fig. 2:
as shown in fig. 2, when data cleaning starts, step S21 is first entered to read the original data, that is, the operation parameter data and/or the environment data of the wind turbine are obtained by the sensor located at the wind turbine end, and the original data is read by the Arduino development board (an open source electronic platform development board). Step S22 is then carried out to judge whether the sampling frequency of the acquired operation parameter data and/or the environment data is too high; if the sampling frequency is the normal sampling frequency, step S24 is directly performed to determine whether the operation parameter data includes shutdown data; if the sampling frequency is too high, step S23 is performed to downsample the operation environment parameter data and/or the environment data until the acquisition frequency reaches a preset frequency, and step S24 is performed.
If it is determined in step S24 that the operation parameter data and/or the environmental data do not include the shutdown data, the process proceeds to step S26 to detect whether the operation parameter data and/or the environmental data have abnormal values by using the group decision method, and if it is determined in step S24 that the operation parameter data and/or the environmental data include the shutdown data, the process proceeds to step S25 to delete the shutdown data, and the process proceeds to step S26.
If it is determined in step S26 that no abnormal value exists, the process proceeds directly to step S28 to determine whether a missing value exists in the operation parameter data and/or the environmental data; if it is determined in step S26 that an abnormal value exists, the routine proceeds to step S27, where the abnormal value is deleted, and proceeds to step S28.
If it is determined in step S28 that the operation parameter data and/or the environment data do not have a missing value, directly proceeding to step S210 to perform data normalization on the operation parameter data and/or the environment data; if it is determined in step S28 that there is a missing value in the operation parameter data and/or the environment data, the process proceeds to step S29, where the missing value is filled in, and the process proceeds to step S210.
The method for carrying out data standardization on the operation parameter data and/or the environment data at least comprises a mean value removing and variance normalizing method; the data filling algorithm used for filling the missing values is a multiple interpolation method based on random forests.
After the operation parameter data and/or the environmental data are standardized, step S211 is further performed, that is, the operation parameter data are denoised by a bayesian wavelet packet denoising method, so as to enhance the usability of the data.
This ends the data cleansing of the operating parameter data and/or the environment data.
The operation parameter data in the embodiment of the invention at least comprises: rotational speed data and yaw angle data; the environmental parameter data in the embodiment of the invention at least comprises: wind speed data and wind direction data; the operation parameter data and the environment parameter data can be collected by a data collecting device positioned at the wind turbine generator. Such as wind speed data collected by a wind speed sensor positioned at the wind turbine, rotational speed data collected by a gyroscope positioned at the wind turbine, yaw angle data collected by an angle sensor positioned at the wind turbine, wind direction data collected by a pose sensor positioned at the wind turbine, etc.
The edge server in the embodiment of the invention can be an embedded development board, further can be an Arduino (open source electronic platform) development board, the collection of the operation parameter data and the environment parameter data is realized through the Arduino development board, and the data analysis of the collected data is realized through a development program on the Arduino development board so as to perform preprocessing, improve the quality of the operation parameter data, reduce the transmission quantity of the data and further improve the transmission efficiency of the data.
In the embodiment of the invention, the initial operation parameter data comprises at least one of rotating speed data, yaw angle data and output power data; the target environment data are wind speed data; therefore, in the embodiment of the invention, the correlation analysis is realized by a pearson correlation coefficient method.
When the initial operation parameter data and the target environment data of the wind turbine are obtained, the method comprises the following steps: simultaneously acquiring a group of initial operation parameter data and a group of target environment data in t1 time; at this time, a set of data with strong correlation between the initial operation parameter and the target environmental data is determined by the pearson correlation coefficient method. According to the embodiment of the invention, the data group with the strongest correlation with the target environment data in the initial operation parameters is determined to be wind speed data and output power data by a Pearson correlation coefficient method.
Through correlation analysis of the operation parameter data and the environment data, the relation between the operation parameter data and the environment data, such as causal relation, is determined, so that the most relevant data can be selected for training a model required by the follow-up; namely, through correlation analysis, the prediction performance and accuracy of the model required by the follow-up can be improved.
Example 2
As shown in fig. 3, in an embodiment of the present invention, a data processing device of a wind turbine is provided, where the data processing device is used to implement a data processing method of a wind turbine described in embodiment 1 of the present invention; the data processing apparatus includes:
the data acquisition module 101 acquires initial operation parameter data and target environment data of the wind turbine generator.
A data processing module 102, the data processing module comprising an edge server; the data processing module is used for cleaning the initial operation parameter data and the target environment data through an edge server arranged at the wind turbine generator; and the data processing module 102 is further configured to perform correlation analysis on the initial operation parameter data after data cleaning and the target environment data after data cleaning, so as to obtain target operation parameter data corresponding to the target environment data from the initial operation parameter data. And a data output module 103, configured to output the target operation parameter data to the outside.
The data processing device of the wind turbine provided by the invention can preprocess the operation parameter data at the edge server, improve the quality of the operation parameter data, reduce the transmission quantity of the data and further improve the transmission efficiency of the data.
Example 3
As shown in fig. 4, in an embodiment of the present invention, there is provided an early warning method for a wind turbine generator, where the early warning method includes:
s41: and acquiring target operation parameter data of the current wind turbine generator.
S42: and inputting the target operation parameter data into a first model to obtain target environment data corresponding to the target operation parameter data.
The first model is obtained based on first historical data training; the first historical data includes historical operating parameter data and historical environment data corresponding to the historical operating parameter data.
S43: and inputting the target environment data into a second model to obtain target physical data corresponding to the target environment data.
Wherein the second model is trained based on second historical data; the second historical data includes historical environmental data and historical physical data corresponding to the historical environmental data.
S44: and carrying out early warning on the specific running state of the wind turbine generator based on the target physical data.
In the embodiment of the invention, the target physical data at a certain future time point is determined through the first model and the second model, so that the early warning of the specific running state of the wind turbine generator at the certain future time point is realized, wherein the specific running state is that the fan breaks down.
The physical data includes: target stress data and/or target displacement data.
In a specific embodiment of the present invention, the early warning of the wind turbine generator based on the target stress data and the target displacement data specifically includes: and judging whether the target stress data is larger than a first threshold value, and if so, carrying out early warning on the wind turbine generator.
In another specific embodiment of the present invention, the early warning of the wind turbine generator based on the target stress data and the target displacement data may further include: judging whether the target displacement data is larger than a second threshold value or not; if yes, early warning is carried out on the wind turbine generator.
The operation parameter data in the embodiment of the invention at least comprises: at least one of rotational speed data, yaw angle data, and output power data; the environmental data in the embodiment of the invention at least comprises: at least one of stress data and displacement data.
The first model in the embodiment of the invention is obtained based on first historical data training; the first historical data comprises historical operation parameter data and historical environment data corresponding to the historical operation parameter data, wherein the first historical data is operation parameter data which is preprocessed by an edge server arranged on the wind turbine generator.
The second model in the embodiment of the invention is obtained based on second historical data training; the second historical data comprises historical environment data and historical physical data corresponding to the historical environment data; the second model is generated, for example, by stress data and displacement data training.
In addition, in the embodiment of the present invention, the early warning method further includes:
acquiring piezoelectric data of the tower top of the wind turbine generator; inputting the piezoelectric data into a pre-trained third model to obtain target piezoelectric data of a related time sequence; judging whether the target piezoelectric data is larger than a third threshold value or not; if yes, early warning is carried out on the wind turbine generator. The prediction of future points in time by piezoelectric data is achieved by adding a time dimension to the piezoelectric data.
According to the early warning method of the wind turbine generator provided by the embodiment of the invention, the state and the performance of the wind turbine generator are monitored by obtaining the target stress data and the target displacement data corresponding to the target wind speed data, possible faults or problems can be identified early, and corresponding maintenance measures can be taken by discovering potential faults in advance, so that the downtime and the production loss of related equipment are avoided or reduced.
As shown in fig. 5, the following specifically illustrates the working principle of implementing the early warning method in the embodiment of the present invention:
in a specific embodiment, the early warning method provided by the invention uses an intelligent early warning platform. The early warning platform mainly comprises four parts of model processing, data acquisition, a server side and an intelligent operation and maintenance platform. When early warning is realized, a finite element model corresponding to a fan tower barrel is required to be established firstly, then, the stress and displacement values of 20 nodes under different wind speeds are acquired, and the acquired node stress values and displacement values are analyzed, so that the tower bottom displacement values are kept to be zero due to fixed constraint, under the condition that the wind direction is unchanged, the stress and the strain of the windward and leeward boundary nodes of the tower top are kept relatively constant under the condition that the wind direction is unchanged, and the stress and the strain are increased along with the approach of the wind speed to a rated value, and of course, it can be understood that the number of the acquired nodes is not unique, namely the number of the acquired nodes is not limited in the embodiment of the invention.
Simultaneously taking wind speed data and stress and displacement values of the nodes as input and output of a training decision tree algorithm respectively; after performing a principal component analysis (Principal Component Analysis, PCA) degradation and normalization technology on the operation parameter data, inputting the processed data into a single-step prediction model of a Long Short-Term Memory (LSTM), and taking the result data of 10 minutes as the input of an integrated regression decision tree algorithm to obtain the prediction condition of a specific node, thereby realizing early warning of the wind turbine generator through an intelligent early warning platform. Example 4
As shown in fig. 6, in the embodiment of the present invention, an early warning device of a wind turbine is provided, where the early warning device is used to implement the early warning method of the wind turbine described in embodiment 3; the early warning device comprises:
an operation data acquisition module 201, configured to acquire target operation parameter data of a current wind turbine generator;
the first processing module 202, where the first processing module 202 includes a first model, and the first processing module 202 is configured to input the target operating parameter data into the first model for processing, to obtain target environmental data corresponding to the target operating parameter data; the first model is obtained based on first historical data training; the first historical data includes historical operating parameter data and historical environment data corresponding to the historical operating parameter data.
The second processing module 203, where the second processing module 203 includes a second model, and the second processing module 203 is configured to input the target environmental data into the second model to obtain target physical data corresponding to the target environmental data; wherein the second model is trained based on second historical data; the second historical data includes historical environmental data and historical physical data corresponding to the historical environmental data.
And the early warning module 204 is used for carrying out early warning on the running state of the wind turbine generator based on the target physical data.
According to the early warning device of the wind turbine generator, the state and the performance of the wind turbine generator can be monitored by obtaining the target stress data and the target displacement data corresponding to the target wind speed data, possible faults or problems can be identified early, corresponding maintenance measures can be taken by finding the potential faults in advance, and the downtime and the production loss of related equipment are avoided or reduced.
Example 5
As shown in fig. 7, in an embodiment of the present invention, there is provided a wind power system, including: the data processing device 301 of the wind turbine generator set as described in embodiment 2, the early warning device 302 of the wind turbine generator set as described in embodiment 4, and the cloud storage device 303.
Wherein the data processing device 301 is configured to transmit target operation parameter data to the cloud storage device 303; the cloud storage 303 is configured to store the target operation parameter data; the early warning device 302 is configured to obtain the target operation parameter data from the cloud storage device 303, and implement early warning on the wind turbine generator based on the target operation parameter data.
The wind power system provided by the invention can preprocess the operation parameter data at the edge server, and can reduce the transmission quantity of the data while improving the quality of the operation parameter data, thereby improving the transmission efficiency of the data; moreover, the wind power system provided by the invention can also realize the acquisition of the target stress data and the target displacement data corresponding to the target wind speed data, monitor the state and the performance of the wind turbine generator, and recognize possible faults or problems as soon as possible.
In a specific implementation manner, after the cloud server is started, a firewall management interface is entered, and external port numbers required by running an EMQ X server and a Web server are added to application type rules. Thereby realizing the connection of the data processing device 301, the early warning device 302 and the cloud storage device 303.
In the embodiment, the data processing device of the wind turbine generator and the early warning device of the wind turbine generator are integrated in the wind power system, so that the wind power system can preprocess the operation parameter data at the edge server, improve the quality of the operation parameter data, reduce the transmission quantity of the data and further improve the transmission efficiency of the data; and moreover, the state and the performance of the wind turbine generator can be monitored by acquiring target stress data and target displacement data corresponding to target wind speed data, possible faults or problems can be identified early, and corresponding repair and maintenance measures can be taken by discovering potential faults in advance, so that the downtime and the production loss of related equipment are avoided or reduced.
The working principle of the electro-mechanical system in the embodiment of the invention is specifically described as follows:
the layout of the wind power system in the embodiment of the invention is as follows: the method comprises the steps of adopting a websocket (a network transmission protocol) two-way communication protocol, dynamically rendering running pictures of a wind turbine generator in real time based on a Solidworks (a three-dimensional design software) three-dimensional graphic engine, and thus constructing a visual platform. The data acquisition device at the fan resistor is a wind speed sensor or an angle sensor, and the embedded development board (namely an Arduino development board) is responsible for acquisition of sensor data, data preprocessing, data packaging, subscription and release of data information to the cloud storage device. The data display end is a visual supervision platform based on a Web browser and is used for receiving data in the cloud storage device and displaying the data on a fan digital twin platform.
The wind power system provided by the invention can complete the communication of basic functions and the whole flow, designs the overall framework of the wind power system, synthesizes the mechanism and the data method, and focuses on building a database from a wind turbine to a sensor to a cloud server in the wind power system and dynamically presenting data at a webpage end. By processing and organizing the data information, the problems of real-time data communication, data mapping and visual presentation between the wind driven generator and the wind power system are solved. Through an algorithm, the data correlation presentation is realized by processing the uploaded data, preprocessing is performed on the data, the data quality is improved, and a foundation is laid for the subsequent research on the aspects of wind turbine generator state detection, fault diagnosis, early warning and the like, the operation and maintenance of the digital twin wind turbine generator is realized, and the operation and maintenance cost is saved.
Example 6
Fig. 8 is a schematic structural diagram of an electronic device according to embodiment 4 of the present invention. The electronic device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the methods of the above embodiments when executing the program. The electronic device 30 shown in fig. 8 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 8, the electronic device 30 may be in the form of a general purpose computing device, which may be a server device, for example. Components of electronic device 30 may include, but are not limited to: the at least one processor 31, the at least one memory 32, a bus 33 connecting the different system components, including the memory 32 and the processor 31.
The bus 33 includes a data bus, an address bus, and a control bus.
Memory 32 may include volatile memory such as Random Access Memory (RAM) 321 and/or cache memory 322, and may further include Read Only Memory (ROM) 323.
Memory 32 may also include a program/utility 325 having a set (at least one) of program modules 324, such program modules 324 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The processor 31 executes various functional applications and data processing, such as the method in the above-described embodiments of the present invention, by running a computer program stored in the memory 32.
The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). Such communication may be through an input/output (I/O) interface 35. Also, model-generating device 30 may also communicate with one or more networks, such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet, via network adapter 36. As shown in fig. 8, network adapter 36 communicates with the other modules of model-generating device 30 via bus 33. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in connection with the model-generating device 30, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, data backup storage systems, and the like.
It should be noted that although several units/modules or sub-units/modules of an electronic device are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more units/modules described above may be embodied in one unit/module in accordance with embodiments of the present invention. Conversely, the features and functions of one unit/module described above may be further divided into ones that are embodied by a plurality of units/modules.
Example 7
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method in the above embodiments.
More specifically, among others, readable storage media may be employed including, but not limited to: portable disk, hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation manner, the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps of the method as in the above-described embodiments, when the program product is run on the terminal device.
Wherein the program code for carrying out the invention may be written in any combination of one or more programming languages, the program code may be executed entirely on the user device, partially on the user device, as a stand-alone software package, partially on the user device, partially on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the invention, but such changes and modifications fall within the scope of the invention.
Claims (15)
1. The data processing method of the wind turbine generator is characterized by comprising the following steps of:
acquiring initial operation parameter data and target environment data of a wind turbine generator;
performing data cleaning on the initial operation parameter data and the target environment data through an edge server arranged at the wind turbine generator;
performing correlation analysis on the initial operation parameter data after data cleaning and the target environment data after data cleaning to obtain target operation parameter data corresponding to the target environment data from the initial operation parameter data;
and outputting the target operation parameter data to the outside.
2. The method for processing data of a wind turbine according to claim 1, wherein the specific step of data cleaning comprises:
acquiring the initial operation parameter data and/or the target environment data, and judging whether missing data exists in the initial operation parameter data and/or the target environment data;
if so, interpolation processing is carried out on the initial operation parameter data and/or the target environment data so as to fill the missing data.
3. The method for processing data of a wind turbine according to claim 2, further comprising, before said determining whether missing data exists in the initial operating parameter data and/or the target environment data:
Acquiring the initial operation parameter data and/or the target environment data, and judging whether the initial operation parameter data and/or the target environment data comprise shutdown data or not;
if so, deleting the shutdown data;
and/or the number of the groups of groups,
before the step of judging whether missing data exists in the initial operation parameter data and/or the target environment data, the method further comprises the following steps:
acquiring the initial operation parameter data and/or the target environment data, and judging whether the acquisition frequency of the initial operation parameter data and/or the target environment data is greater than a first preset value or not;
if yes, downsampling is conducted on the initial operation parameter data and/or the target environment data until the acquired frequency reaches a preset frequency.
4. The method for processing data of a wind turbine according to claim 2, wherein the interpolation is implemented by a K nearest neighbor algorithm.
5. The method for processing data of a wind turbine according to claim 1, wherein the step of cleaning the data further comprises:
the initial operation parameter data and/or the target environment data are obtained by:
the abnormal value detection methods are used for respectively detecting whether abnormal data exists in the initial operation parameter data and/or the target environment data, and group decision is carried out based on the corresponding detection results of the abnormal value detection methods so as to judge whether the initial operation parameter data and/or the target environment data exist abnormal data or not;
If so, the abnormal data is deleted.
6. The method for processing data of a wind turbine according to claim 1, wherein the initial operation parameter data includes at least one of rotational speed data, yaw angle data, and output power data;
the target environment data are wind speed data;
the correlation analysis is achieved by the pearson correlation coefficient method.
7. A data processing device of a wind turbine, characterized in that the data processing device is configured to implement a data processing method of a wind turbine according to any one of claims 1-6; the data processing apparatus includes:
the data acquisition module is used for acquiring initial operation parameter data and target environment data of the wind turbine generator;
the data processing module comprises an edge server; the data processing module is used for cleaning the initial operation parameter data and the target environment data through an edge server arranged at the wind turbine generator; the data processing module is also used for carrying out correlation analysis on the initial operation parameter data after data cleaning and the target environment data after data cleaning so as to obtain target operation parameter data corresponding to the target environment data from the initial operation parameter data;
And the data output module is used for outputting the target operation parameter data to the outside.
8. The early warning method of the wind turbine generator is characterized by comprising the following steps of:
acquiring target operation parameter data of a current wind turbine generator;
inputting the target operation parameter data into a first model to obtain target environment data corresponding to the target operation parameter; the first model is obtained based on first historical data training; the first historical data comprises historical operation parameter data and historical environment data corresponding to the historical operation parameter data;
inputting the target environment data into a second model to obtain target physical data corresponding to the target environment data; wherein the second model is trained based on second historical data; the second historical data comprises historical environment data and historical physical data corresponding to the historical environment data;
and carrying out early warning on the specific running state of the wind turbine generator based on the target physical data.
9. The method for early warning of a wind turbine generator according to claim 8, wherein the target physical data comprises: target stress data and/or target displacement data;
The early warning of the wind turbine generator based on the target physical data specifically comprises the following steps:
determining whether the target stress data is greater than a first threshold,
if yes, early warning is carried out on the wind turbine generator;
and/or the number of the groups of groups,
judging whether the target displacement data is larger than a second threshold value or not;
if yes, early warning is carried out on the wind turbine generator.
10. The method for early warning of a wind turbine generator according to claim 8, wherein the target operation parameter data includes: at least one of rotational speed data, yaw angle data, and output power data;
the first historical data are operation parameter data which are preprocessed by an edge server arranged on the wind turbine generator.
11. The method for early warning of a wind turbine generator according to claim 8, further comprising:
acquiring piezoelectric data of the tower top of the wind turbine generator;
inputting the piezoelectric data into a pre-trained third model to obtain target piezoelectric data of a related time sequence;
judging whether the target piezoelectric data is larger than a third threshold value or not;
if yes, early warning is carried out on the wind turbine generator.
12. An early warning device of a wind turbine generator, wherein the early warning device is used for realizing the early warning method of the wind turbine generator according to any one of claims 8-11; the early warning device comprises:
The operation data acquisition module is used for acquiring target operation parameter data of the current wind turbine generator;
a first processing module, the first processing module comprising a first model; the first processing module is used for inputting the target operation parameter data into a first model for processing to obtain target environment data corresponding to the target operation parameter; the first model is obtained based on first historical data training; the first historical data comprises historical operation parameter data and historical environment data corresponding to the historical operation parameter data;
a second processing module, the second processing module comprising a second model; the second processing module is used for inputting the target environment data into a second model for processing to obtain target physical data corresponding to the target environment data; wherein the second model is trained based on second historical data; the second historical data comprises historical environment data and historical physical data corresponding to the historical environment data;
and the early warning module is used for carrying out early warning on the specific running state of the wind turbine generator based on the target physical data.
13. A wind power system, the wind power system comprising: a data processing device of a wind turbine as claimed in claim 7, an early warning device of a wind turbine as claimed in claim 12, and a cloud storage device;
The data processing device is used for transmitting target operation parameter data to the cloud storage device;
the cloud storage device is used for storing the target operation parameter data;
the early warning device is used for acquiring the target operation parameter data from the cloud storage device and realizing early warning of the wind turbine generator based on the target operation parameter data.
14. An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, characterized in that the processor, when executing the computer program, implements the method for data processing of a wind turbine according to any of claims 1-6 or implements the method for early warning of a wind turbine according to any of claims 8-11.
15. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements a method for data processing of a wind turbine according to any one of claims 1-6, or implements a method for early warning of a wind turbine according to any one of claims 8-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410044735.8A CN117846894A (en) | 2024-01-11 | 2024-01-11 | Data processing method, early warning device, equipment and medium of wind turbine generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410044735.8A CN117846894A (en) | 2024-01-11 | 2024-01-11 | Data processing method, early warning device, equipment and medium of wind turbine generator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117846894A true CN117846894A (en) | 2024-04-09 |
Family
ID=90547871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410044735.8A Pending CN117846894A (en) | 2024-01-11 | 2024-01-11 | Data processing method, early warning device, equipment and medium of wind turbine generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117846894A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118094486A (en) * | 2024-04-26 | 2024-05-28 | 湖南慧明谦数字能源技术有限公司 | Full scene time sequence decomposition-based photovoltaic power generation power prediction method and system |
| CN119163569A (en) * | 2024-11-25 | 2024-12-20 | 中况检测技术（上海）有限公司 | A fault monitoring system and method for fan status |
-
2024
- 2024-01-11 CN CN202410044735.8A patent/CN117846894A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118094486A (en) * | 2024-04-26 | 2024-05-28 | 湖南慧明谦数字能源技术有限公司 | Full scene time sequence decomposition-based photovoltaic power generation power prediction method and system |
| CN119163569A (en) * | 2024-11-25 | 2024-12-20 | 中况检测技术（上海）有限公司 | A fault monitoring system and method for fan status |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Han et al. | An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems | |
| CN117846894A (en) | Data processing method, early warning device, equipment and medium of wind turbine generator | |
| CN106682814B (en) | Wind turbine generator fault intelligent diagnosis method based on fault knowledge base | |
| CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
| CN118939988B (en) | A mechanical equipment fault diagnosis method and system using correlation analysis | |
| CN115329986A (en) | Wind turbine generator anomaly detection and positioning method based on interpretable graph neural network | |
| CN117972547B (en) | Fault early warning method, device and medium for key components of wind turbine generator | |
| CN119312205B (en) | Intelligent fire-fighting equipment fault identification method and system | |
| CN117410961A (en) | Wind power prediction method, device, equipment and storage medium | |
| CN118300082B (en) | A power fault early warning method and system based on AI big model | |
| CN118293969A (en) | Wind generating set drive chain fault on-line measuring system based on AI intelligence | |
| CN116484168A (en) | Fault prediction method, device and electronic equipment of ship multi-level fusion model | |
| Cao et al. | Condition monitoring of wind turbine based on a novel spatio-temporal feature aggregation network integrated with adaptive threshold interval | |
| Ashkarkalaei et al. | Optimum feature selection for the supervised damage classification of an operating wind turbine blade | |
| CN119272138A (en) | A Fault Diagnosis Method for Underwater Vector Thruster | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN118998004A (en) | Intelligent detection supervision system and detection method for wind power generation equipment | |
| CN118966784A (en) | Methods, systems, equipment, media and products for predicting geological risks in tunnel construction | |
| CN116662920A (en) | Method, system, equipment and medium for identifying abnormal data of drilling and blasting construction equipment | |
| CN118760835B (en) | A method for monitoring the health status of electric fluid machinery | |
| CN116821800B (en) | Structure state classification method and related equipment based on semi-supervised generation countermeasure network | |
| CN118861944B (en) | A system construction method combining Internet of Things and virtual reality technology | |
| CN119442161B (en) | Selective state space model and apparatus for rolling bearing residual life prediction | |
| CN119128656A (en) | A method, system, device and medium for diagnosing oil pump motor fault | |
| CN116429240A (en) | Rotating equipment vibration signal prediction system based on deep Boltzmann machine |
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 |