CN112696324B - Wind power generator group data processing method, device and system - Google Patents
Wind power generator group data processing method, device and system Download PDFInfo
- Publication number
- CN112696324B CN112696324B CN201911004441.8A CN201911004441A CN112696324B CN 112696324 B CN112696324 B CN 112696324B CN 201911004441 A CN201911004441 A CN 201911004441A CN 112696324 B CN112696324 B CN 112696324B
- Authority
- CN
- China
- Prior art keywords
- data
- wind
- power
- identifying
- wind speed
- 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
- 238000003672 processing method Methods 0.000 title abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims description 23
- 230000005611 electricity Effects 0.000 claims description 17
- 238000010248 power generation Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000011157 data evaluation Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000000630 rising effect Effects 0.000 claims description 3
- 230000008014 freezing Effects 0.000 description 13
- 238000007710 freezing Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 11
- 238000010257 thawing Methods 0.000 description 6
- 230000015654 memory Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000001174 ascending effect Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002459 sustained effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- 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
Abstract
The disclosure provides a wind driven generator group data processing method, device and system. The method comprises the following steps: acquiring wind power generator group data in a preset time period; identifying power limit data and shutdown data from the wind generating set data; identifying frozen data based on the shutdown data; and identifying wind turbine anomaly data from wind turbine generator set data other than the power limit data and the shutdown data.
Description
Technical Field
The present disclosure relates to the field of wind power generation technologies, and more particularly, to a method, an apparatus, and a system for processing data of a wind turbine generator system.
Background
In the wind power project operation process of the wind power industry, related operation data of a wind generating set in a wind power plant need to be analyzed, so that the operation condition of the wind generating set in the wind power plant is judged, and the analysis of wind generating set data needs to be established on the basis of wind generating set data classification.
However, the data format of the wind generating set is not uniform, and some wind generating set data may be artificially recorded with an identifier of a data type such as shutdown, power limit, etc., but the recording process may have delay and error, thereby causing an error when the wind generating set data is classified by using the identifier data. In addition, the types of the wind power generation group data are more, and the data have a coupling relation, so that inaccurate classification is easily caused. Therefore, a set of unified wind turbine generator group data processing method needs to be designed for wind turbine generator group data to identify the wind turbine generator group data.
Disclosure of Invention
Exemplary embodiments of the present disclosure provide a wind turbine group data processing method, apparatus, and system thereof, which solve at least the above technical problems and other technical problems not mentioned above, and provide the following advantageous effects.
An aspect of the present disclosure is to provide a wind turbine group data processing method, which may include: acquiring wind power generator group data in a preset time period; identifying power limiting data and shutdown data from the wind generating set data; identifying frozen data based on the shutdown data; and identifying wind turbine anomaly data from wind turbine generator set data other than the power limit data and the shutdown data.
Identifying the power limit data prior to identifying the shutdown data from the wind turbine group data.
The step of identifying the frozen data may comprise identifying the frozen data from the wind turbine generator set data based on time, temperature and the outage data.
The step of identifying the frozen data from the outage data may comprise: providing a sliding window having a first width; identifying shutdown data having a temperature continuously below 0 degrees within the sliding window as first frozen data; and identifying as second frozen data all wind park data having a time interval between the first frozen data being smaller than a first threshold.
The method may further comprise: combining the second freeze data with all shutdown data that is temporally continuous before and after the second freeze data, respectively, into third freeze data; identifying wind generating set data with gradually descending power in wind generating set data before the third frozen data as the frozen data; and identifying wind generating set data in which the power in the wind generating set data after the third frozen data shows a gradually rising trend as the frozen data.
The fan abnormal data comprises wind speed identification error data and sub-health data.
The step of identifying the wind speed identification error data may include: calculating a total kinetic energy of the wind per unit time based on the air density, the impeller radius, and the wind speed; and identifying wind power generation group data with power higher than a preset value at corresponding wind speed in the wind power generation group data except the electricity limiting data and the shutdown data as the wind speed identification error data.
The step of identifying the sub-health data may comprise: dividing the wind power generation set data except the power limiting data, the shutdown data and the wind speed identification error data into first data and second data by comparing the wind speed with a rated wind speed; identifying the sub-health data from the first data according to an anomaly identification algorithm; and identifying wind turbine group data in the second data, which has a power at a corresponding wind speed less than a preset proportion of a rated power, as the sub-health data.
Identifying the sub-health data from the first data according to an anomaly identification algorithm may include: carrying out sectional processing on the first data according to the wind speed; calculating the mean value mu and the standard deviation 3sigma of the power in each wind speed section; and identifying wind turbine generator set data in the first data having power less than mu-3 sigma as sub-health data.
Another aspect of the present disclosure is to provide a wind turbine group data processing apparatus, which may include: the data acquisition module is used for acquiring wind driven generator group data in a preset time period; and a data identification module to: identifying power limit data and shutdown data from the wind generating set data, identifying frozen data based on the shutdown data, and identifying wind turbine anomaly data from wind generating set data other than the power limit data and the shutdown data.
A data identification module identifies the power limit data prior to identifying the shutdown data from the wind turbine group data.
A data identification module may identify the frozen data from the wind turbine generator set data based on time, temperature, and the outage data.
The data identification module may provide a sliding window having a first width; identifying shutdown data with a temperature continuously below 0 degrees within the sliding window as first frozen data; identifying all wind generating set data with the time interval between the first frozen data smaller than a first threshold value as second frozen data; combining the second freeze data with all shutdown data that is temporally continuous before and after the second freeze data, respectively, into third freeze data; identifying wind generating set data with gradually descending power in wind generating set data before the third frozen data as the frozen data; and identifying wind generating set data with gradually rising trend of power in the wind generating set data after the third frozen data as the frozen data.
The data identification module may calculate a total kinetic energy of the wind per unit time based on the air density, the impeller radius, and the wind speed; and identifying wind power generation group data with power higher than a preset value at a corresponding wind speed in the wind power generation group data except the electricity limiting data and the shutdown data as the wind speed identification error data.
The data identification module can divide the wind generating set data except the electricity limiting data, the shutdown data and the wind speed identification error data into first data and second data by comparing the wind speed in the wind generating set with a rated wind speed; identifying the sub-health data from the first data according to an anomaly identification algorithm; and identifying the wind generator group data with the power at the corresponding wind speed less than the preset proportion of the rated power in the second data as the sub-health data.
The data identification module can perform segmented processing on the first data according to the wind speed; calculating the mean value mu and the standard deviation 3sigma of the power in each wind speed section; wind turbine generator set data in the first data having a power less than μ -3 σ is identified as sub-health data.
Another aspect of the invention provides a wind farm data processing system, the wind farm comprising at least one wind generating set, the system may comprise: a data reading module for reading data relating to the at least one wind turbine generator set; a data identification module to: identifying electricity limiting data and shutdown data from the data, identifying frozen data based on the shutdown data, and identifying fan anomaly data from the data other than the electricity limiting data and the shutdown data; and the data evaluation module is used for evaluating the overall operation condition of the at least one wind generating set according to the classification result of the data and outputting the evaluation result of the at least one wind generating set.
The system may further include: the fault analysis module is used for analyzing the operation fault condition of the at least one wind generating set according to the evaluation result and outputting the operation fault of the at least one wind generating set; the data checking module is used for comparing the operation performance of the at least one wind generating set with the preset performance according to the evaluation result and outputting a comparison result; and the data summarizing module is used for summarizing the information indexes of the whole wind power plant where the at least one wind generating set is located and outputting a summarizing result.
Another aspect of the present invention is to provide a computer-readable storage medium storing a program, which may include instructions for executing the wind turbine group data processing method described above.
An aspect of the present invention provides a computer comprising a readable medium storing a computer program and a processor, the processor executing the instructions of the wind turbine data processing method described above when executing the computer program.
The method and the device can automatically identify the data of the wind generating set only by utilizing at least the time, the wind speed, the power and the temperature in the data of the wind generating set, can identify various types of data of the wind generating set at one time, ensure the accuracy of original data, reduce the error of manual identification and effectively solve the problem that different classification algorithms need to be designed aiming at different data of the wind generating set.
Drawings
These and/or other aspects and advantages of the present disclosure will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a wind turbine group data processing method according to an exemplary embodiment of the present disclosure;
FIG. 2 is a flow chart of a wind turbine group data processing method according to another exemplary embodiment of the present disclosure;
FIG. 3 shows a profile of identified power limiting data versus normal operating data;
FIG. 4 shows a profile of identified shutdown data versus normal operating data;
FIG. 5 shows a distribution plot of identified wind speed identification error data versus normal operating data;
FIG. 6 shows a distribution plot of identified sub-health data versus normal operating data;
FIG. 7 shows a distribution plot of identified frozen data versus normal operating data;
FIG. 8 is a block diagram of a wind turbine group data processing apparatus according to an exemplary embodiment of the present disclosure;
FIG. 9 is a block diagram of a wind turbine group data processing system according to an exemplary embodiment of the present disclosure.
Detailed Description
The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of the embodiments of the disclosure as defined by the claims and their equivalents. Various specific details are included to aid understanding, but these are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.
In the present disclosure, terms including ordinal numbers such as "first", "second", etc., may be used to describe various elements, but these elements should not be construed as being limited to only these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and vice-versa, without departing from the scope of the present disclosure.
Hereinafter, according to various embodiments of the present disclosure, methods and apparatuses of the present disclosure will be described with reference to the accompanying drawings.
Fig. 1 is a flowchart of a wind turbine group data processing method according to an exemplary embodiment of the present disclosure. In the method, the wind generating set data can be automatically identified according to the characteristics of fields (such as wind speed, temperature, power and other data) existing in the wind generating set data, and the category corresponding to each wind generating set data is identified, so that subsequent data analysis and corresponding early warning can be facilitated.
Referring to fig. 1, in step S101, wind turbine group data for a predetermined period of time is acquired. The wind generating set data can be real-time data collected by a monitoring and data collection system (such as a SCADA system) or historical data stored locally. For example, the wind turbine data of a certain period of time may be directly obtained from the SCADA system, or the wind turbine data of a certain period of time may be imported from other devices.
In step S102, power limiting data and shutdown data are identified from the acquired wind turbine generator set data. The power-limited data is characterized by a steady level of power over a period of time. Shutdown data is characterized by power less than a certain threshold. In the present disclosure, the power limiting data is first identified from the wind turbine generator set data, and then the shutdown data is identified from the wind turbine generator set data. Given the similarity in data characteristics between electricity-limiting data and shutdown data, identifying shutdown data as electricity-limiting data tends to occur when identifying both types of data. Thus, by identifying the power limit data first, and then identifying the shutdown data, the power limit data identifying the error may be re-identified as the power limit data. Specifically, power limit data and shutdown data may be identified from wind turbine generator set data based on power. For example, in identifying the power limiting data, a sliding window having a predetermined width is set, a standard deviation of power in the wind turbine generator set data within the sliding window is calculated, and then wind turbine generator set data having a standard deviation within the sliding window that is less than a predetermined threshold value is identified as the power limiting data. In the process of identifying the shutdown data, wind generating set data with power less than a certain threshold in the wind generating set data can be identified as shutdown data. However, the above identification methods of the power limit data and the shutdown data are only exemplary, and other methods for identifying the power limit data and the shutdown data may be used in the present disclosure, without being limited thereto.
In step S103, frozen data is identified from the wind turbine generator set data based on the shutdown data identified in step S102. The frozen data may exist only when the temperature is below 0 degrees for a period of time, and the frozen data is characterized by a continuously lower power, as is the case with the shutdown data, and therefore, it is desirable to identify the frozen data upon identifying the shutdown data.
Specifically, in the process of identifying the obtained frozen data, a sliding window with a first width is arranged, shutdown data with the temperature continuously lower than 0 ℃ in the sliding window is identified as first frozen data, and all wind generating set data with the time interval between the first frozen data smaller than a first threshold value are identified as second frozen data. In addition, the power of the wind generating set gradually decreases during freezing and gradually increases during thawing, so that the data in the process of freezing and thawing after freezing should be identified as frozen data. For example, the second frozen data is combined with all shutdown data before and after the second frozen data in time respectively to form third frozen data, wind turbine generator set data before the third frozen data and wind turbine generator set data after the third frozen data, which show a gradual descending trend, are identified as the frozen data, and wind turbine generator set data after the third frozen data and wind turbine generator set data, which show a gradual ascending trend, are identified as the frozen data. According to the method, obvious frozen data are identified by combining the originally existing temperature data and shutdown data in the wind generating set, and on the basis, the non-visible frozen data are further identified by considering the characteristic performance of the wind generating set in the freezing process, so that the integrity and the accuracy of the frozen data are ensured. According to the method, the marks about the frozen data do not need to be recorded in the wind power generator group data manually to distinguish the frozen data, so that the error of the original data in the data classification process is reduced, and the method better meets the application requirements of the post-evaluation in the wind power industry at present.
At step S104, wind turbine anomaly data is identified from the wind turbine generator set data in addition to the power limit data and the shutdown data. Here, the wind turbine anomaly data may include wind speed identification error data and sub-health data. In identifying the fan anomaly data, the classification of the fan anomaly data is realized by using the wind speed and the power existing in the wind generating set according to the definition of the fan anomaly data.
In identifying wind speed identification error data, a wind speed identification error may be identified from wind generating set data other than power limiting data and shutdown data according to wind speed and power using Betz theory. The betz theory refers to the theory regarding the maximum energy that a wind generator may convert, which indicates that a wind generator can absorb 59.3% of the wind energy at the most. In identifying sub-health data, the sub-health data may be identified based on wind speed and power from wind generating set data other than power limiting data, shutdown data, and wind speed identification error data. For example, the sub-health data is identified from the first wind turbine group data according to the abnormality recognition algorithm by dividing the wind turbine group data into the first wind turbine group data and the second wind turbine group data by comparing the wind speed in the wind turbine group data other than the electricity limit data, the stop data, and the wind speed recognition error data with the rated wind speed. The abnormal recognition means that an acceptable range is described by using a statistical analysis mode so as to distinguish abnormal data which is contrary to normal data. In the present disclosure, a 3sigma principle may be used as the anomaly identification algorithm, where the 3sigma principle means that the data is almost concentrated in the data standard deviation of plus or minus 3 times the data mean in the positive distribution. And then, the wind generating set data with the power lower than the preset proportion of the rated power at the corresponding wind speed in the second wind generating set data is marked as sub-health data.
The processing method of the wind driven generator group data can be applied to different types of wind driven generator group data, and can be used for identifying and classifying multiple types of wind driven generation data at one time, so that the traditional mode of adopting manually recorded identification data for different wind driven generator group data is changed.
Fig. 2 is a flowchart of a wind turbine group data processing method according to an exemplary embodiment of the present disclosure.
Referring to fig. 2, in step S201, wind turbine group data for a predetermined period of time is acquired. For example, the wind turbine group data may be obtained from a SCADA system, or imported from other external devices. The wind park data may include, but is not limited to, SCADA data.
At step S202, electricity limit data is identified from the wind park data based on the power field present in the wind park data. The power-limited data is characterized by a steady level of power over a period of time. When identifying the electricity limiting data from the wind park data, a sliding window having a certain width may be first set. Then, standard deviations of the power sequences in the wind turbine group data in the sliding window are calculated, and the wind turbine group data with the standard deviations smaller than a first threshold value in the sliding window are identified as electricity limiting data. For example, the width of the sliding window may be set to 2 hours, and when the sliding window slides along the time axis for acquiring the wind turbine generator group data each time, here, the time interval for each sliding of the sliding window may be set to 10 minutes, that is, the sliding window slides every 10 minutes in time sequence, then the standard deviation is solved for the power in the wind turbine generator group data included in the sliding window, the solved standard deviation is compared with a preset threshold, if the solved standard deviation is smaller than the first threshold, the wind turbine generator group data in the sliding window is identified as the power limiting data, otherwise, the wind turbine generator group data is not identified as the power limiting data, and the subsequent classification processing is performed. The first threshold may be set to 0.5, however, the first threshold is not limited thereto and may vary based on actual demand. FIG. 3 shows a plot of identified power limiting data versus normal operating data, where the horizontal axis represents wind speed and the vertical axis represents power. The above-described method is merely exemplary, and the present disclosure is not limited thereto.
In step S203, shutdown data is identified from the wind park data based on the power present in the wind park data. Shutdown data is characterized by power less than a certain threshold. The power in each of the acquired wind turbine group data may be compared to a second threshold value to identify shutdown data from the wind turbine group data. For example, the second threshold value may be set to 0.9 times the rated power value, the power value in each wind turbine group data is compared with 0.9 times the rated power value, if the power value in the wind turbine group data is less than 0.9 times the rated power value, the piece of wind turbine group data is identified as shutdown data, otherwise, the piece of wind turbine group data is not identified as shutdown data. Here, the second threshold value is not limited thereto, and may be modified by a designer according to actual circumstances. FIG. 4 shows a plot of identified shutdown data versus normal operating data, with wind speed on the horizontal axis and power on the vertical axis. The above-described method is merely exemplary, and the present disclosure is not limited thereto.
In step S204, wind speed identification error data is identified from the wind turbine generator set data, excluding the power limit data and the shutdown data, based on the wind speed and power present in the wind turbine generator set data. After identifying the electricity limiting data and the shutdown data, wind speed identification errors can be identified from the wind generating set data excluding the electricity limiting data and the shutdown data according to Betz theory. Betz theory is the theory on the maximum energy that a wind generator may convert, and Betz theory indicates that a wind generator can absorb 59.3% of wind energy at the most. For example, the total kinetic energy of the wind per unit time may be calculated according to equation (1) based on the air density, impeller radius, and wind speed:
wherein, P 0 Represents the total kinetic energy of wind per unit time, ρ is the air density, v is the wind speed, and R is the impeller radius. Here, the recorded wind speed in the wind turbine group data is used.
And after the total kinetic energy of the wind power generator group data under the wind speed is calculated, comparing the corresponding power in the wind power generator group data with the value of 0.593 of the calculated total kinetic energy according to the Betz limit, if the power in the wind power generator group data under the corresponding wind speed is greater than 0.593 of the total kinetic energy, identifying the data of the wind power generator group as wind speed identification error data, and otherwise, not identifying the data as the wind speed identification error data. FIG. 5 shows a plot of identified wind speed identification error data versus normal operating data, with wind speed on the horizontal axis and power on the vertical axis.
In step S205, sub-health data is identified from the wind turbine set data, excluding power limit data, shutdown data, and wind speed identification error data, based on the wind speed and power present in the wind turbine set data. Specifically, first, comparing the wind speed in the wind turbine group data other than the electricity limit data, the shutdown data, and the wind speed recognition error data with the rated wind speed divides the wind turbine group data into the first wind turbine group data and the second wind turbine group data because the data of the wind speed close to the maximum wind speed is less and does not conform to the positive distribution, and if the same algorithm is used for identification for all the wind turbine group data, the identified sub-health data may not be accurate. After the first wind generating set data and the second wind generating set data are identified based on the rated wind speed, sub-health data are identified from the first wind generating set data according to an abnormal recognition algorithm, and the sub-health data are identified from the second wind generating set data by comparing the power in the second wind generating set data at the corresponding wind speed with the rated power in a preset proportion.
For example, for the first wind turbine group data, the identification may be performed using the 3sigma principle of the positive distribution as the abnormality recognition algorithm. According to the 3sigma principle, 99% of the data should be included within μ ± 3 σ, where μ represents the mean of the data and σ represents the standard deviation of the data. Specifically, the first wind generating set data is firstly processed in a segmented mode according to wind speeds, corresponding power in each wind speed segment is in accordance with positive-too distribution, then the mean value mu and the standard deviation 3sigma of the power in each wind speed segment are calculated, the wind generating set data in each wind generating set data, with the power being smaller than mu-3 sigma, in the first wind generating set data is marked as sub-health data, otherwise, the wind generating set data is not marked as sub-health data, and subsequent classification processing is carried out. The above-described 3sigma principle is merely exemplary as an anomaly recognition algorithm, and the present disclosure is not limited thereto.
For the second wind power generation group data, because the data of the wind speed close to the maximum wind speed are less and do not accord with the positive distribution, the 3sigma principle is not applicable to the data, and therefore the sub-health data are identified by adopting another supplementary mode for the data of the wind speed larger than the rated wind speed. For example, for data in which the wind speed in the wind turbine data is greater than the rated wind speed, but the power at the corresponding wind speed is less than a preset proportion of the rated power, the piece of wind turbine data is identified as sub-health data. Here, the preset ratio may be set to 0.9, however, the preset ratio is not limited thereto and may be varied based on actual needs. FIG. 6 shows a plot of the identified sub-health data versus normal operating data, with wind speed on the horizontal axis and power on the vertical axis.
In step S206, it is determined whether temperature data is present in the wind park data. Because the data of the wind generating set does not necessarily have temperature data, whether the temperature is recorded in the data of the wind generating set or not needs to be judged so as to perform subsequent frozen data classification. If temperature data exists in the wind turbine generator data, the process proceeds to step S206. And if the temperature data does not exist in the wind turbine generator data, ending the flow of the method.
In step S207, frozen data is identified from the wind turbine generator set data based on the time and temperature present in the wind turbine generator set data and the identified outage data. Frozen data may exist when the temperature is below 0 degrees for a sustained period of time and is characterized by a sustained lower power, as is characteristic of shutdown data, and is therefore identified on the basis of identifying shutdown data. Specifically, a sliding window with a second width is set, shutdown data with the temperature continuously lower than 0 degree in the sliding window is marked as first freezing data, and all wind generating set data with the time interval between the first freezing data smaller than a third threshold value are marked as second freezing data. For example, the width of the sliding window for identifying the frozen data may be set to 30 minutes, and each time the sliding window slides along the time axis of the frozen data, here, the time interval of each sliding of the sliding window may be set to 10 minutes, that is, the sliding window slides every 10 minutes in chronological order, and then it is determined whether all the temperatures in the frozen data included in the sliding window are lower than 0 degree, and if all the temperatures in the frozen data included in the sliding window are lower than 0 degree, the frozen data are identified as the frozen data (i.e., the first frozen data). If the temperatures in the shutdown data contained in the sliding window are not all below 0 degrees, comparing the time interval between the shutdown data as the first freeze data with a third threshold value, and identifying all wind turbine generator set data with the time interval smaller than the third threshold value as second freeze data. For example, the third threshold may be set to 10 minutes, however, the above example is only exemplary, and the present disclosure is not limited thereto.
In addition, the power of the wind generating set gradually decreases during freezing and gradually increases during thawing, so that the data in the process of freezing and thawing after freezing should be identified as frozen data. In the present disclosure, the second frozen data is combined with all shutdown data that is temporally continuous before and after the second frozen data into third frozen data. For example, the continuous shutdown data before the second frozen data and the continuous shutdown data after the second frozen data are combined into third frozen data. And identifying wind generating set data with gradually descending power in the wind generating set data before the third frozen data as frozen data, and identifying wind generating set data with gradually ascending power in the wind generating set data after the third frozen data as frozen data.
As an example, the power in the wind turbine group data before the third frozen data is subjected to difference calculation, the data corresponding to the difference of the sign which is always negative is identified as frozen data, and the power in the wind turbine group data after the third frozen data is subjected to difference, the data corresponding to the difference of the sign which is always positive is identified as frozen data. FIG. 7 shows a plot of the identified frozen data versus normal operating data, with wind speed on the horizontal axis and power on the vertical axis.
The wind driven generator group data processing method only uses fields existing in various wind driven generator group data to automatically identify the wind driven generator group data, and avoids manually classifying the wind driven generator group data by setting a data type mark. As can be seen from the profiles of the various types of data of fig. 3-7, after the wind turbine group data passes through the algorithm of the present disclosure, each data type follows the state of the profile it should assume.
Fig. 8 is a block diagram of a wind turbine group data processing apparatus according to an exemplary embodiment of the present disclosure.
Referring to fig. 8, the wind turbine data processing apparatus 800 may include a data acquisition module 801 and a data identification module 802. Each module in the wind turbine group data processing apparatus 800 according to the present disclosure may be implemented by one or more modules, and names of the corresponding modules may vary according to types of the modules. In various embodiments, some modules of wind turbine data processing apparatus 800 may be omitted, or additional modules may be further included, for example, wind turbine data processing apparatus 800 may further include a determination module (not shown) or the like. Furthermore, modules/elements according to various embodiments of the present disclosure may be combined to form a single entity, and thus the functions of the respective modules/elements may be equivalently performed prior to the combination.
The data acquisition module 801 may acquire wind turbine group data for a predetermined period of time from a SCADA system or an external device.
The data identification module 802 may identify electricity limit data from the wind turbine set data using the time and power present in the wind turbine set data. For example, the data identification module 802 first sets a sliding window with a width of 2 hours, and sets a time interval of each sliding of the sliding window to 10 minutes, that is, the sliding window slides every 10 minutes in chronological order. And then, solving the standard deviation of the power in the wind generator group data contained in the sliding window, and identifying the wind generator group data with the standard deviation smaller than a first threshold value in the sliding window as electricity limiting data. The first threshold may be set to 0.5, however, the first threshold is not limited thereto and may vary based on actual demand.
The data identification module 802 may identify shutdown data from the wind turbine generator set data using power present in the wind turbine generator set data. For example, the data identification module 802 may compare the power in each of the acquired wind turbine group data with a second threshold value to identify shutdown data from the wind turbine group data. The second threshold may be set to 0.9 times the rated power value, although the disclosure is not limited thereto.
The data identification module 802 may identify wind speed identification error data from wind turbine generator set data other than the power limit data and the shutdown data using the wind speed and power present in the wind turbine generator set data. After identifying the power limiting data and the shutdown data, the data identification module 802 may identify a wind speed identification error from the wind generating set data excluding the power limiting data and the shutdown data according to Betz theory. For example, after calculating the total kinetic energy at the wind speed of the wind turbine group data according to equation (1), the data identification module 802 may compare the corresponding power in the wind turbine group data with a value of 0.593 of the calculated total kinetic energy according to the betz limit, and identify the piece of wind turbine group data as wind speed identification error data if the power at the corresponding wind speed in the wind turbine group data is greater than 0.593 of the total kinetic energy.
The data identification module 802 may identify sub-health data from the wind generating set data in addition to the power limit data, the shutdown data, and the wind speed identification error data using the wind speed and power present in the wind generating set data. Specifically, first, the data identification module 802 compares the wind speed in the wind turbine group data other than the electricity limit data, the shutdown data, and the wind speed recognition error data with the rated wind speed to divide the wind turbine group data into first wind turbine group data and second wind turbine group data. After identifying the first wind turbine group data and the second wind turbine group data based on the rated wind speed, the data identification module 802 may identify sub-health data from the first wind turbine group data using an anomaly identification algorithm and identify sub-health data from the second wind turbine group data by comparing power at a corresponding wind speed in the second wind turbine group data with a preset proportion of the rated power.
According to an embodiment of the present disclosure, the wind turbine group data processing apparatus 800 may further include a determination module (not shown). The determination module is used for determining whether temperature data exist in the wind generating set data. If temperature data is present in the wind turbine data, the data identification module 802 may identify frozen data from the wind turbine data using the time and temperature present in the wind turbine data and the shutdown data. First, the data identification module 802 may set a sliding window with a second width, and when the sliding window slides along a time axis of the shutdown data each time, identify shutdown data with a temperature continuously lower than 0 degree in the sliding window as first frozen data, and identify all wind turbine generator system data with a time interval between the first frozen data smaller than a third threshold as second frozen data. For example, the third threshold may be set to 10 minutes, however, the above example is only exemplary, and the present disclosure is not limited thereto.
In addition, the power of the wind generating set gradually decreases during freezing and gradually increases during thawing, so that the data in the process of freezing and thawing after freezing should be identified as frozen data. In particular, the data identification module 802 can combine the second frozen data with all shutdown data that is prior to and subsequent to the second frozen data in a temporal succession into third frozen data. For example, wind turbine generator group data that continues to be shutdown data before the piece of data of the second frozen data and wind turbine generator group data that continues to be shutdown data after the piece of data of the second frozen data are combined into third frozen data. And then, identifying wind generating set data with gradually descending power in the wind generating set data before the third frozen data as frozen data, and identifying wind generating set data with gradually ascending power in the wind generating set data after the third frozen data as frozen data.
According to the method, algorithm design is carried out according to at least four fields of time, wind speed, power and possible temperature in the wind generating set data, the wind generating set data are automatically identified and processed, the problem of classification of different types of wind generating set data can be solved, and because the four fields are automatically recorded by a wind generating set system, the accuracy of original data is guaranteed, identification data recorded manually is not used, and errors in the data classification process are reduced.
FIG. 9 is a block diagram of a wind turbine group data processing system according to an exemplary embodiment of the present disclosure.
Referring to fig. 9, a wind turbine group data processing system 900 according to the present disclosure may include a data reading module 901, a data identification module 902, a data evaluation module 903, a fault analysis module 904, a data verification module 905, and a data summarization module 906. However, the above examples are merely exemplary, each module in the wind turbine group data processing system 900 according to the present disclosure may be implemented by one or more modules, and names of the corresponding modules may vary according to types of the modules. In various embodiments, some modules in wind turbine data processing system 900 may be omitted, or additional modules may also be included, to which the present disclosure is not limited.
The data reading module 901 may read the wind turbine group data from the SCADA system or an external device. For example, the data reading module 901 may read wind turbine data, such as SCADA data, GPC data, WT data, and the like, from the wind turbine system for a period of time.
The data identification module 902 may use its own fields (such as temperature, wind speed, power, time, etc.) in the wind turbine generator data to automatically identify the wind turbine generator data as, for example, shutdown data, electricity limit data, wind turbine anomaly data, and freeze data.
As an example, data identification module 902 may identify power limit data and shutdown data from wind generating set data, identify frozen data based on the shutdown data, and identify wind turbine anomaly data from wind generating set data other than the power limit data and the shutdown data. Here, the data identification module 902 may have the same configuration and function as the data identification module 802, and a detailed description thereof will not be provided.
The data evaluation module 903 may obtain the identification result of the wind turbine group data from the data identification module 902, then evaluate the overall operation condition of the wind turbine group data according to the identification result of the wind turbine group data, and output an operation index of the wind turbine group, for example, the output operation index of the wind turbine group may include PBA, power curve, power loss amount, and the like.
When the error data is output from the data evaluation module 903, the fault analysis module 904 may analyze an operation fault situation of the wind turbine generator set according to an evaluation result (for example, information on a loss power generation amount) of the data evaluation module 903, and output an operation fault of the wind turbine generator set.
When no error data exists in the output operation index of the wind generating set, the data checking module 905 may compare the operation performance of the wind generating set with the preset performance according to the evaluation result, and output the comparison result.
The data summarization module 906 may summarize the information indicators for each wind generating set in the wind farm and output a summary result regarding the information indicators for the entire wind farm.
The processing method and the data identification module can be independently applied to classification of wind driven generator group data, can also be applied to a nested platform combined with other functional modules, and have good compatibility.
One skilled in the art will appreciate that the present disclosure includes apparatus directed to performing one or more of the operations/steps described in the present disclosure. These devices may be specially designed and manufactured for the required purposes, or they may comprise known devices in general-purpose computers. These devices have stored therein computer programs that are selectively activated or reconfigured. Such a computer program may be stored in a device (e.g., computer) readable medium, including, but not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magnetic-optical disks, ROMs (Read-Only memories), RAMs (Random Access memories), EPROMs (Erasable Programmable Read-Only memories), EEPROMs (Electrically Erasable Programmable Read-Only memories), flash memories, magnetic cards, or optical cards, or any type of media suitable for storing electronic instructions, and each coupled to a bus. That is, readable media includes any medium that stores or transmits information in a form readable by a device (e.g., a computer).
The method and the device only utilize the fields of all the wind power generation group data without adopting artificial identification data for classification, so that the method and the device are suitable for the identification of the wind power generation group data of different types, change the traditional mode of adopting artificial recorded identification data for classifying the wind power generation group data of different types, and better meet the application requirements of the current post-evaluation of the wind power industry.
While the disclosure has been shown and described with reference to exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the disclosure as defined by the appended claims and their equivalents.
Claims (10)
1. A method of wind turbine generator system data processing, the method comprising:
acquiring wind power generator group data in a preset time period;
based on the power of the wind generating set data, first identifying electricity limiting data from the wind generating set data, and then identifying shutdown data from the wind generating set data;
identifying frozen data based on the shutdown data;
identifying wind turbine anomaly data from wind turbine generator set data other than the power limit data and the shutdown data,
wherein the abnormal data of the fan comprises wind speed identification error data and sub-health data,
identifying the wind speed identification error data by: calculating a total kinetic energy of the wind per unit time based on the air density, the impeller radius, and the wind speed; identifying, as the wind speed recognition error data, wind-power generation group data in which power at a corresponding wind speed is greater than a preset value among the wind-power generation group data other than the power limit data and the shutdown data,
identifying the sub-health data by: dividing the wind power generation set data except the power limiting data, the shutdown data and the wind speed identification error data into first data and second data by comparing the wind speed with a rated wind speed; and identifying the sub-health data from the first data according to an anomaly identification algorithm; and identifying wind generator group data with power at corresponding wind speed lower than a preset proportion of rated power in the second data as the sub-health data.
2. The method of claim 1, wherein the step of identifying the frozen data comprises: identifying the frozen data from the wind generating set data based on time, temperature, and the outage data.
3. The method of claim 2, wherein the step of identifying the frozen data from the outage data comprises:
providing a sliding window having a first width;
identifying shutdown data with a temperature continuously below 0 degrees within the sliding window as first frozen data;
all wind turbine generator set data having a time interval between the first frozen data smaller than a first threshold value are identified as second frozen data.
4. The method of claim 3, wherein the method further comprises:
combining the second freeze data with all shutdown data that is temporally continuous before and after the second freeze data, respectively, into third freeze data;
identifying wind generating set data with gradually descending power in wind generating set data before the third frozen data as the frozen data;
and identifying wind generating set data with gradually rising trend of power in the wind generating set data after the third frozen data as the frozen data.
5. The method of claim 1, wherein identifying the sub-health data from the first data according to an anomaly identification algorithm comprises:
carrying out sectional processing on the first data according to the wind speed;
calculating the mean value mu and the standard deviation 3sigma of the power in each wind speed section;
wind turbine generator set data in the first data having a power less than μ -3 σ is identified as sub-health data.
6. A wind turbine generator set data processing apparatus, the apparatus comprising:
the data acquisition module is used for acquiring wind driven generator group data in a preset time period; and
a data identification module to:
based on the power of the wind park group data, first identifying electrical limit data from the wind park group data, then identifying shutdown data from the wind park group data,
based on the outage data, identifying frozen data, and
identifying wind turbine anomaly data from wind turbine generator set data other than the power limit data and the shutdown data,
the abnormal data of the fan comprise wind speed identification error data and sub-health data, and the data identification module is further used for:
calculating a total kinetic energy of the wind per unit time based on the air density, the impeller radius, and the wind speed; identifying, as the wind speed recognition error data, wind-power generation group data in which power at a corresponding wind speed is greater than a preset value among the wind-power generation group data other than the power limit data and the shutdown data,
dividing wind-power-generation-group data other than the power-limiting data, the shutdown data and the wind speed identification error data into first data and second data by comparing a wind speed with a rated wind speed; and identifying the sub-health data from the first data according to an anomaly identification algorithm; and identifying the wind generator group data with the power at the corresponding wind speed less than the preset proportion of the rated power in the second data as the sub-health data.
7. A wind farm data processing system, the wind farm comprising at least one wind generating set, the system comprising:
a data reading module for reading data about the at least one wind turbine generator set;
a data identification module to:
based on the power of the data, first identifying power limiting data from the data, then identifying shutdown data from the data,
based on the outage data, identifying frozen data, and
identifying fan anomaly data from the data other than the power limit data and the shutdown data;
a data evaluation module for evaluating the overall operation condition of the at least one wind generating set according to the classification result of the data and outputting the operation index of the at least one wind generating set,
the abnormal data of the fan comprise wind speed identification error data and sub-health data, and the data identification module is further used for:
calculating a total kinetic energy of the wind per unit time based on the air density, the impeller radius, and the wind speed; identifying data of which power at a corresponding wind speed is greater than a preset value among the data other than the power limit data and the shutdown data as the wind speed recognition error data,
dividing the data other than the power limit data, the shutdown data, and the wind speed identification error data into first data and second data by comparing a wind speed with a rated wind speed; and identifying the sub-health data from the first data according to an anomaly identification algorithm; and identifying data, in the second data, with the power at the corresponding wind speed being smaller than the preset proportion of the rated power, as the sub-health data.
8. The system of claim 7, wherein the system further comprises:
the fault analysis module is used for analyzing the operation fault condition of the at least one wind generating set according to the evaluation result and outputting the operation fault of the at least one wind generating set;
the data checking module is used for comparing the operation performance of the at least one wind generating set with the preset performance according to the evaluation result and outputting a comparison result; and
and the data summarizing module is used for summarizing the information indexes of the whole wind power plant where the at least one wind generating set is located and outputting a summarizing result.
9. A computer-readable storage medium storing a program, characterized in that the program comprises instructions for performing the method according to any one of claims 1-5.
10. A computer comprising a readable medium having a computer program stored thereon, wherein the computer program comprises instructions for performing the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911004441.8A CN112696324B (en) | 2019-10-22 | 2019-10-22 | Wind power generator group data processing method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911004441.8A CN112696324B (en) | 2019-10-22 | 2019-10-22 | Wind power generator group data processing method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112696324A CN112696324A (en) | 2021-04-23 |
| CN112696324B true CN112696324B (en) | 2022-08-23 |
Family
ID=75504524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911004441.8A Active CN112696324B (en) | 2019-10-22 | 2019-10-22 | Wind power generator group data processing method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112696324B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3138478A1 (en) * | 2022-08-01 | 2024-02-02 | Electricite De France | METHOD FOR CHARACTERIZING OPERATING STATES OF A WIND TURBINE |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102102626B (en) * | 2011-01-30 | 2012-08-29 | 华北电力大学 | Method for forecasting short-term power in wind power station |
| CN104819107B (en) * | 2015-05-13 | 2017-07-28 | 北京天源科创风电技术有限责任公司 | The diagnostic method and system of a kind of Wind turbines power curve drift extremely |
| CN107339194B (en) * | 2016-04-28 | 2019-05-07 | 北京天诚同创电气有限公司 | Optimal tip speed ratio control method, data processing method, device and system |
| CN108412710B (en) * | 2018-01-30 | 2019-08-06 | 同济大学 | A kind of Wind turbines wind power data cleaning method |
| US10997180B2 (en) * | 2018-01-31 | 2021-05-04 | Splunk Inc. | Dynamic query processor for streaming and batch queries |
| CN110224970B (en) * | 2018-03-01 | 2021-11-23 | 西门子公司 | Safety monitoring method and device for industrial control system |
-
2019
- 2019-10-22 CN CN201911004441.8A patent/CN112696324B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112696324A (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10815972B2 (en) | System and method for assessing and validating wind turbine and wind farm performance | |
| US9644612B2 (en) | Systems and methods for validating wind farm performance measurements | |
| CN117093879B (en) | Intelligent operation management method and system for data center | |
| CN106570790B (en) | Wind power plant output data restoration method considering wind speed data segmentation characteristics | |
| CN112696324B (en) | Wind power generator group data processing method, device and system | |
| CN110761958B (en) | Blade stall diagnosis method and device of wind generating set | |
| CN116775731B (en) | Sliding window-based calculation method for fault-connection trace-back electric quantity of three-phase electric energy meter | |
| CN114968999A (en) | Abnormal data cleaning method based on time sequence matching and bidirectional quartile algorithm | |
| Ferreira et al. | Predicting Ramp Events with a Stream-based HMM framework | |
| CN104680010A (en) | Method for screening steady-state operation data of turbine unit | |
| CN115898787A (en) | Method and device for dynamically identifying static yaw error of wind turbine generator | |
| CN111242411B (en) | Wind turbine generator power characteristic evaluation method and system | |
| Qiao et al. | A multivariable wind turbine power curve modeling method considering segment control differences and short-time self-dependence | |
| KR20140042290A (en) | Method and apparatus for assessing voltage sag considering wind power generation | |
| Singh | Analytical techniques of scada data to assess operational wind turbine performance | |
| CN111310959A (en) | Wind generating set damage prediction analysis method, device, equipment and storage medium | |
| CN114638312A (en) | Unsupervised learning classification algorithm for wind power | |
| Lou et al. | A data-mining approach for wind turbine power generation performance monitoring based on power curve | |
| Wang et al. | Power curve based online condition monitoring for wind turbines | |
| KR20200057942A (en) | System and method for estimating net load fluctuation reflecting renewable energy supply expansion | |
| CN116933570B (en) | Method and device for evaluating power generation capacity in wind power plant redevelopment process | |
| Liu et al. | The detection method of wind turbine operation outliers based on mutidimensional cluster | |
| CN117189509A (en) | Lightning stroke fault detection method for offshore wind turbine | |
| CN117313415A (en) | Wind power plant fan blade extension transformation site selection evaluation method, device and storage medium | |
| CN117213886A (en) | Method and system for testing operation energy efficiency ratio of refrigeration machine room system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |