CN113312758B - Health state evaluation method and device for wind generating set - Google Patents
Health state evaluation method and device for wind generating set Download PDFInfo
- Publication number
- CN113312758B CN113312758B CN202110518023.1A CN202110518023A CN113312758B CN 113312758 B CN113312758 B CN 113312758B CN 202110518023 A CN202110518023 A CN 202110518023A CN 113312758 B CN113312758 B CN 113312758B
- Authority
- CN
- China
- Prior art keywords
- temperature
- data
- residual error
- health
- power
- 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
- 230000036541 health Effects 0.000 title claims abstract description 50
- 238000011156 evaluation Methods 0.000 title claims description 20
- 238000000034 method Methods 0.000 claims abstract description 49
- 230000003862 health status Effects 0.000 claims abstract description 27
- 239000000498 cooling water Substances 0.000 claims description 8
- 238000004804 winding Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 description 19
- 238000010998 test method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Wind Motors (AREA)
Abstract
The application provides a health state assessment method and device of a wind generating set, wherein the method comprises the following steps: the method comprises the steps of acquiring SCADA data of a wind generating set, which are acquired by an SCADA system, wherein the SCADA data comprise a plurality of data sets, and each data set comprises power data and temperature data of the wind generating set at the same moment; dividing a plurality of data sets into different power intervals based on the power data, each power interval including at least one data set; determining a temperature residual error corresponding to each temperature data in each power interval based on the temperature data of each power interval; intercepting temperature residual errors of each power interval based on a preset sliding window to obtain a plurality of residual error sections; determining a Bayesian factor for each residual segment; based on the bayesian factor of each residual segment, the health status of the wind generating set is evaluated. The method and the device can reduce the influence of uncertainty in temperature data, improve the identification precision and reduce the false alarm rate.
Description
Technical Field
The application relates to the field of wind generating sets, in particular to a health state assessment method and device of a wind generating set.
Background
In the operation process of an actual wind generating set, a large amount of uncertainty exists, such as sensor abnormality, external environment interference and the like, the uncertainty can cause fluctuation of data, when the temperature data has large fluctuation, an individual temperature point can be caused to exceed a threshold value, false alarm occurs, and the false alarm rate is increased.
Disclosure of Invention
The application provides a health state assessment method and device for a wind generating set.
Specifically, the application is realized by the following technical scheme:
in a first aspect of embodiments of the present application, a method for evaluating a health status of a wind turbine generator set is provided, the method including:
the method comprises the steps of acquiring SCADA data of a wind generating set acquired by an SCADA system, wherein the SCADA data comprises a plurality of data sets, and each data set comprises power data and temperature data of the wind generating set at the same moment;
dividing the plurality of data sets into different power intervals based on the power data, each power interval including at least one of the data sets;
determining a temperature residual error corresponding to each temperature data in each power interval based on the temperature data of each power interval;
intercepting temperature residual errors of each power interval based on a preset sliding window to obtain a plurality of residual error sections;
determining a Bayesian factor for each residual segment;
based on the bayesian factor of each residual segment, the health status of the wind generating set is evaluated.
Optionally, the estimating the health status of the wind generating set based on the bayesian factor of each residual segment includes:
comparing the Bayesian factor of the current residual error section with a preset factor threshold, and judging that the wind generating set is in a health state at the moment corresponding to the current residual error section if the Bayesian factor of the current residual error section is larger than or equal to the preset factor threshold;
if the Bayesian factor of the current residual error section is smaller than the preset factor threshold, judging that the wind generating set fails at the moment corresponding to the current residual error section.
Optionally, the estimating the health status of the wind generating set based on the bayesian factor of each residual segment includes:
determining a corresponding confidence level based on the Bayesian factor of each residual segment;
and evaluating the health state of the wind generating set based on each confidence level or each confidence level and a corresponding Bayesian factor.
Optionally, the estimating the health status of the wind generating set based on each confidence level, or each confidence level and the corresponding bayesian factor includes:
comparing the confidence coefficient of the current residual error section with a preset confidence coefficient threshold value, and judging that the wind generating set is in a health state at the moment corresponding to the current residual error section if the confidence coefficient of the current residual error section is larger than or equal to the preset confidence coefficient threshold value; if the confidence coefficient of the current residual error section is smaller than the preset confidence coefficient threshold value, judging that the wind generating set fails at the moment corresponding to the current residual error section; or,
comparing the confidence coefficient of the current residual error section with a preset confidence coefficient threshold value and comparing the Bayesian factor of the current residual error section with a preset factor threshold value, and judging that the wind generating set is in a health state at the moment corresponding to the current residual error section if the confidence coefficient of the current residual error section is larger than or equal to the preset confidence coefficient threshold value and the Bayesian factor of the current residual error section is larger than or equal to the preset factor threshold value; if the confidence coefficient of the current residual error section is smaller than the preset confidence coefficient threshold value and/or the Bayesian factor of the current residual error section is smaller than the preset factor threshold value, judging that the wind generating set fails at the moment corresponding to the current residual error section.
Optionally, the determining the bayesian factor of each residual segment includes:
calculating a first mean value and a first standard deviation of temperature residuals in each residual section;
a Bayesian factor for each residual segment is determined based on the first mean and the first standard deviation for the residual segment.
Optionally, the width and/or the movement step size of the sliding window are fixed.
Optionally, the width and/or the movement step size of the sliding window may be set.
Optionally, the determining, based on the temperature data of each power interval, a temperature residual corresponding to each temperature data in each power interval includes:
determining a second mean and a second standard deviation of the temperature data in each power interval based on the temperature data in the power interval;
and determining a temperature residual error corresponding to each temperature data in each power interval based on a second average value of the temperature data in the power interval and the second standard deviation.
Optionally, the determining, based on the second average value of the temperature data in each power interval and the second standard deviation, a temperature residual corresponding to each temperature data in the power interval includes:
determining a maximum temperature threshold and a minimum temperature threshold of each power interval based on a second average value of temperature data in the power interval, the second standard deviation and a preset coefficient;
setting a temperature residual of temperature data which is greater than or equal to a minimum temperature threshold value and less than or equal to a maximum temperature threshold value in the temperature data of each power interval to 0;
setting a temperature residual of temperature data smaller than a minimum temperature threshold value in the temperature data of each power interval as a difference value between the corresponding temperature data and the minimum temperature threshold value;
and setting the temperature residual error of the temperature data which is larger than the maximum temperature threshold value in the temperature data of each power interval as the difference value between the corresponding temperature data and the maximum temperature threshold value.
Optionally, the preset coefficient is greater than or equal to 2 and less than or equal to 5.
Optionally, the temperature data includes one of a main bearing temperature, a gearbox drive end bearing temperature, a gearbox non-drive end bearing temperature, a gearbox oil temperature, a gearbox cooling water temperature, a gearbox scavenge temperature, a generator winding temperature, a generator drive end bearing temperature, a generator non-drive end bearing temperature, an engine cooling water temperature, a frequency converter reactance temperature, a frequency converter capacitance temperature, and a frequency converter power switch device temperature of the wind generating set.
Optionally, after the estimating the health status of the wind generating set based on the bayesian factor of each residual segment, the method further includes:
and outputting an evaluation result, wherein the evaluation result is used for indicating the health state of the wind generating set.
Optionally, when the evaluation result indicates that the wind generating set fails, the evaluation result further includes time information of the failure of the wind generating set.
In a second aspect of embodiments of the present application, a health status assessment device of a wind turbine generator set is provided, including one or more processors, configured to implement the health status assessment method according to any one of the first aspect.
In a third aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements the health status assessment method according to any one of the first aspects.
According to the technical scheme provided by the embodiment of the application, the plurality of data sets of SCADA data are divided into different power intervals based on the power data, then the temperature residual error corresponding to each temperature data in each power interval is determined, then the temperature residual error of each power interval is intercepted based on the sliding window to obtain a plurality of residual error sections, and each residual error section is evaluated based on the Bayesian hypothesis test method, so that the influence of uncertainty in the temperature data is reduced, the identification precision is improved, and the false alarm rate is reduced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic diagram showing the results of the current split power segment temperature thresholding method;
FIG. 2 is a flow chart illustrating a method for assessing health of a wind turbine generator set according to an exemplary embodiment of the present application;
FIG. 3 is a flowchart illustrating a process for estimating health of a wind turbine based on Bayesian factors for each residual segment according to an exemplary embodiment of the present application;
FIG. 4 is a schematic diagram showing the results of a Bayesian hypothesis test method for evaluating the health status of a wind turbine generator set according to an exemplary embodiment of the present application;
FIG. 5 is a system block diagram of a health assessment device of a wind turbine shown in an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
The following describes a method and a device for evaluating the health status of a wind turbine generator set according to the present application in detail with reference to the accompanying drawings. The features of the examples and embodiments described below may be combined with each other without conflict.
The temperature threshold value method of the power division section is a method which is commonly used for the winding temperature faults of the wind generating set at present, specifically takes SCADA operation data of the wind generating set as input, takes active power of the wind generating set as a section division basis, adopts a bin method to realize the division of temperature data, realizes the determination of the temperature threshold value in each section through the statistics of the temperature data of each section, and mainly comprises the following steps:
step one, extracting active power and temperature data of a wind generating set from a SCADA system of the wind generating set;
step two: dividing the temperature data into a plurality of intervals by using the bin method by taking the active power of the wind generating set as an interval dividing basis;
step three: the mean value mu and the variance sigma of the temperature data in each section are calculated, and the determined sections [ mu-3 sigma, mu+3 sigma ] are used as the threshold values of the temperature data in each section.
Step four: when the temperature data exceeds the threshold value of the section, the monitored unit component is indicated to be abnormal.
The biggest problem of the current power-segment temperature threshold method is that the false alarm rate is high, as shown in fig. 1, the abscissa is time, and the ordinate is temperature data.
For this, the method divides a plurality of data groups of SCADA data into different power intervals based on the power data, then determines the temperature residual error corresponding to each temperature data in each power interval, intercepts the temperature residual error of each power interval based on the sliding window to obtain a plurality of residual error sections, and evaluates each residual error section based on the Bayesian hypothesis test method, thereby reducing the influence of uncertainty in the temperature data, improving the recognition precision and reducing the false alarm rate.
FIG. 2 is a flow chart illustrating a method for assessing health of a wind turbine generator set according to an exemplary embodiment of the present application; the health state evaluation method execution body of the wind generating set in the embodiment of the application may include a wind generator, and may also be other devices with data processing capability, such as a computer.
Referring to fig. 2, the method for evaluating the health status of the wind turbine generator set according to the embodiment of the present application may include the following steps S21 to S26.
In step S21, SCADA data of the wind turbine generator set collected by the SCADA system is obtained, where the SCADA data includes a plurality of data sets, and each data set includes power data and temperature data of the wind turbine generator set at the same time.
It is understood that the SCADA data may include monitoring data of temperature, wind speed, power, etc. All the data acquired by the SCADA system at the same moment can be divided into the same data group. The SCADA system is a data acquisition monitoring system (Supervisory Control And Data Acquisition), can monitor and control a field wind generating set to realize various functions such as data acquisition, equipment control, measurement, parameter adjustment, various signal alarms and the like, and displays the functions to a user in proper forms such as sound, graphics, images and the like, so that the effect of sensing various parameter states of equipment in real time is finally achieved.
Wherein the power data may include active power or rated power, but is not limited thereto.
The temperature data may include one of a main bearing temperature, a gearbox drive-end bearing temperature, a gearbox non-drive-end bearing temperature, a gearbox oil temperature, a gearbox cooling water temperature, a gearbox scavenge temperature, a generator winding temperature, a generator drive-end bearing temperature, a generator non-drive-end bearing temperature, an engine cooling water temperature, a frequency converter reactance temperature, a frequency converter capacitance temperature, a frequency converter power switching device (e.g., IGBT or other) temperature of the wind turbine generator set, thereby monitoring the respective set component.
In step S22, the plurality of data sets are divided into different power intervals based on the power data, each power interval including at least one data set.
It should be appreciated that in the embodiments of the present application, the power of the multiple power intervals is continuous and different.
For example, the active power of the wind turbine generator is divided into m sections according to the average size from 0 to rated powerTo indicate i=1, 2, …, m; dividing temperature data into power intervals according to the temperature data of each sampling time corresponding to active power of the wind turbine generator system>Thereby dividing the temperature data into m sections. Power interval->The temperature data in (1) includes->Wherein j=1, 2, …, n, n is the power interval +.>Is a function of the temperature data.
The embodiment can divide the active power interval or the rated power interval on average, so that a plurality of data sets are divided into different power intervals according to different power data sizes.
In step S23, a temperature residual corresponding to each temperature data in each power section is determined based on the temperature data of each power section.
One implementation of step S23 may include the steps of:
(1) Determining a second mean and a second standard deviation of the temperature data in each power interval based on the temperature data in that power interval;
by calculating the power intervals one by one with the above embodimentSecond mean value of temperature data +.>And a second standard deviation->Wherein->The calculation formula of (2) is as follows:
（1）；
the calculation formula of (2) is as follows:
（2）。
the results obtained by the calculation of the above formulas (1) and (2) may be directly used as the second mean value and the second standard deviation, or the results obtained by the calculation of the above formulas (1) and (2) may be corrected, and the corrected results may be used as the second mean value and the second standard deviation.
(2) And determining a temperature residual corresponding to each temperature data in each power interval based on the second average value and the second standard deviation of the temperature data in the power interval.
Specifically, the maximum temperature threshold and the minimum temperature threshold of each power interval are determined based on the second average value, the second standard deviation and the preset coefficient of the temperature data in the power interval, wherein the preset coefficient is greater than or equal to 2 and less than or equal to 5, such as 2, 3, 4 or 5, and the preset coefficient is 3 for exampleIs +.>The minimum temperature threshold is->。
For temperature data greater than or equal to the minimum temperature threshold and less than or equal to the maximum temperature threshold in the temperature data of each power interval, optionally, a temperature residual of temperature data greater than or equal to the minimum temperature threshold and less than or equal to the maximum temperature threshold in the temperature data of each power interval is set to a first residual value, such as a residual value of 0 or near 0, e.g., for power intervalsThe power interval is +.>Is located [ ] in the temperature data of (2)>，/>]The temperature residual of the temperature data in is set to 0.
For temperature data less than the minimum temperature threshold in the temperature data of each power interval, optionally, a temperature residual of the temperature data less than the minimum temperature threshold in the temperature data of each power interval is set to a difference value of the corresponding temperature data and the minimum temperature threshold, for example,for power intervalsPower interval->Is less than +.>The temperature residual of the temperature data of (2) is set to correspond to the temperature data and +.>Is the difference of the corresponding temperature data minusThe obtained difference.
For temperature data greater than the maximum temperature threshold in the temperature data of each power interval, optionally, the temperature residual of the temperature data greater than the maximum temperature threshold in the temperature data of each power interval is set to the difference between the corresponding temperature data and the maximum temperature threshold, e.g., for the power intervalPower interval->Is greater than +.>The temperature residual of the temperature data of (2) is set to correspond to the temperature data and +.>Is the difference of the corresponding temperature data minusThe obtained difference.
It should be understood that the above-described arrangement of the temperature residuals may be combined, and by way of example, the temperature residuals of the temperature data greater than or equal to the minimum temperature threshold and less than or equal to the maximum temperature threshold in the temperature data of each power section are set to 0, the temperature residuals of the temperature data less than the minimum temperature threshold in the temperature data of each power section are set to the difference value of the corresponding temperature data and the minimum temperature threshold, and the temperature residuals of the temperature data greater than the maximum temperature threshold in the temperature data of each power section are set to the difference value of the corresponding temperature data and the maximum temperature threshold.
In step S24, the temperature residual error of each power interval is intercepted based on a preset sliding window, and a plurality of residual error sections are obtained.
In step S24, a plurality of residual segments are obtained for each power segment.
In some embodiments, the width of the sliding window and/or the movement step size is fixed, e.g., the width L of the sliding window is 72 and the movement step size S is 6.
In some embodiments, the width and/or movement step size of the sliding window may be set, for example, by a user setting the width and/or movement step size of the sliding window via an interface.
Exemplary, the power interval is obtained by step S2Temperature residual of->Cutting out the temperature residual error by using a sliding window with the width L, wherein the moving step length of the sliding window is S, and finally, the +.>Residual section with length L>Wherein t=1, 2, …, L, k=1, 2, …, +.>N is the temperature residual in the ith power interval +.>Is a number of (3).
And (3) intercepting by using a sliding window of L=72 and S=6 to obtain 831 residual segments in total, and providing data for subsequent Bayesian factor calculation.
In step S25, a bayesian factor for each residual segment is determined.
Specifically, step S25 may include the following steps:
(1) Calculating a first mean and a first standard deviation of temperature residuals in each residual segment;
exemplary, power intervalsFirst mean +.>The calculation formula of (2) is as follows:
（3）；
standard deviation ofThe calculation formula of (2) is as follows:
（4）。
the results obtained by the calculation of the above formulas (3) and (4) may be directly used as the first mean value and the first standard deviation, or the results obtained by the calculation of the above formulas (3) and (4) may be corrected, and the corrected results may be used as the first mean value and the first standard deviation.
(2) A Bayesian factor for each residual segment is determined based on the first mean and the first standard deviation for the residual segment.
Wherein, when the first standard deviationWhen the power is not 0, the power interval is +.>Bayesian factors of the kth residual segment in (a)The calculation formula is as follows:
（5）；
when the first standard deviationWhen the power interval is not 0, the result obtained by calculation in the above formula (5) can be used as the power intervalThe Bayes factor of the kth residual section in (2) can also be used for correcting the result obtained by the calculation of the formula (5), and the corrected result is taken as the power section +.>Bayesian factors of the kth residual segment in (a).
When the first standard deviationWhen 0, the power interval is +.>Bayes factor of the kth residual segment in->The calculation formula is as follows:
（6）；
when the first standard deviationWhen 0, the result obtained by calculation of the above formula (6) can be used as the power interval +.>The Bayes factor of the kth residual section in (2) can also be used for correcting the result obtained by the calculation of the formula (6), and the corrected result is taken as the power section +.>Bayesian factors of the kth residual segment in (a).
In step S26, the health status of the wind park is evaluated based on the bayesian factor of each residual segment.
The health status of the wind turbine generator system may be evaluated based on the bayesian factors of each residual segment alone, the confidence level of each residual segment may be determined based on the bayesian factors of each residual segment, and the health status of the wind turbine generator system may be evaluated based on the confidence level.
For example, in some embodiments, the evaluation of the health status of the wind turbine generator set based only on the bayesian factor of each residual segment may specifically include the steps of: comparing the Bayesian factor of the current residual error section with a preset factor threshold value, and judging that the wind generating set is in a health state at the moment corresponding to the current residual error section if the Bayesian factor of the current residual error section is larger than or equal to the preset factor threshold value; if the Bayesian factor of the current residual error section is smaller than the preset factor threshold, judging that the wind generating set fails at the moment corresponding to the current residual error section.
The magnitude of the preset factor threshold can be set according to the need, in this embodiment, the preset factor threshold corresponds to a preset confidence threshold, and when the confidence of the current residual error section is greater than or equal to the preset confidence threshold, it indicates that the wind turbine generator is in a healthy state at the moment corresponding to the current residual error section; and when the confidence coefficient of the current residual error section is smaller than a preset confidence coefficient threshold value, indicating that the wind generating set fails at the moment corresponding to the current residual error section.
The magnitude of the preset confidence threshold may be set as desired, in the embodiment of the present application, the preset confidence threshold is greater than or equal to 50% and less than or equal to 80%, such as 50%, 60%, 70% or 80%, etc.
In still other embodiments, referring to FIG. 3, based on the Bayesian factor for each residual segment, assessing the health of a wind turbine generator set may include the steps of:
step S31, determining corresponding confidence degrees based on Bayesian factors of each residual error section;
exemplary, power intervalsConfidence of kth residual segment in +.>The calculation formula is as follows:
（7）。
the result obtained by calculation using the above formula (7) can be used as a power intervalThe confidence of the kth residual section in (2) can also be modified by the result obtained by the calculation of the formula (7), and the modified result is taken as the power section +.>Confidence of the kth residual segment in (c).
And step S32, evaluating the health state of the wind generating set based on each confidence level or each confidence level and the corresponding Bayesian factor.
Optionally, comparing the confidence coefficient of the current residual error section with a preset confidence coefficient threshold value, and if the confidence coefficient of the current residual error section is greater than or equal to the preset confidence coefficient threshold value, judging that the wind generating set is in a health state at the moment corresponding to the current residual error section; if the confidence coefficient of the current residual error section is smaller than the preset confidence coefficient threshold value, judging that the wind generating set fails at the moment corresponding to the current residual error section. For example, when the confidence of the current residual error section is less than 50%, the health probability of the wind generating set at the moment corresponding to the current residual error section is considered to be less than 50%, and the wind generating set fails.
Optionally, comparing the confidence coefficient of the current residual error section with a preset confidence coefficient threshold value and comparing the Bayesian factor of the current residual error section with a preset factor threshold value, and if the confidence coefficient of the current residual error section is greater than or equal to the preset confidence coefficient threshold value and the Bayesian factor of the current residual error section is greater than or equal to the preset factor threshold value, judging that the wind turbine generator system is in a health state at the moment corresponding to the current residual error section; if the confidence coefficient of the current residual error section is smaller than a preset confidence coefficient threshold value and/or the Bayesian factor of the current residual error section is smaller than a preset factor threshold value, judging that the wind generating set fails at the moment corresponding to the current residual error section.
Compared with the current power-segment temperature threshold method which is concerned about whether a single data point exceeds the limit, the Bayesian hypothesis test method evaluates the health state of the wind generating set according to the integral distribution of temperature data in a period of time, can effectively eliminate false alarms caused by individual abnormal points, and reduces false alarm rate.
Optionally, after evaluating the health status of the wind generating set based on the bayesian factor of each residual segment, further comprising: and outputting an evaluation result, wherein the evaluation result is used for indicating the health state of the wind generating set, and a user can obtain the health state of the wind generating set through the evaluation result. Optionally, when the evaluation result indicates that the wind generating set fails, the evaluation result further includes time information of the failure of the wind generating set.
It should be noted that, when the temperature data includes multiple types, for example, the temperature data includes a main bearing temperature, a gearbox driving end bearing temperature, a gearbox non-driving end bearing temperature, a gearbox oil temperature, a gearbox cooling water temperature, a gearbox oil return temperature, a generator winding temperature, a generator driving end bearing temperature, a generator non-driving end bearing temperature, an engine cooling water temperature, a frequency converter reactance temperature, a frequency converter capacitance temperature and a frequency converter power switch device temperature, the operations of the steps S22 to S26 are required to be performed on each type of temperature data, so as to achieve the purpose of monitoring the corresponding types of unit components.
In a possible embodiment, a wind generating set with a rated power of 4MW needs to monitor whether a front bearing of a gear box (namely, temperature data comprise the temperature of the front bearing of the gear box) is in fault, active power of the wind generating set is used as a basis for dividing a section, the active power of the wind generating set is divided into 5 sections from 0-4MW from small to large on average, and the divided sections are shown in table 1.
TABLE 1 active Power section division for certain 4MW wind generating set
Then dividing the temperature of the front bearing of the gear box into power intervals based on the active power of the wind generating set at each sampling moment(i=1, 2, …), i.e. the gearbox front bearing temperature is divided into 5 power intervals.
On the basis of the power interval division, the temperature of the front bearing of the gear box is in the power intervalThe maximum temperature threshold value and the minimum temperature threshold value in the temperature sensor are determined. FIG. 1 shows the power interval->The temperature of the front bearing of the gear box in the gear box is 5000, and the second average value +.>And a second standard deviation->The method comprises the following steps: />. The temperature of the front bearing of the gearbox is within the power range +.>The threshold value range is [ -20.86 ]>，55.62/>]If the health state of the wind generating set is evaluated based on the current power-division temperature threshold method, as shown in fig. 1, it can be found that, besides the actual faults occurring in 11 months and 11 days in 2017, a large number of false alarms occur in the normal operation stage due to uncertainty in data, and the false alarm rate is too high.
Adopting a Bayesian hypothesis test method to evaluate the health state of the wind generating set, and regarding the power intervalThe temperature of the front bearing of the gear box in the gear box is [ -20.86 ]>，55.62/>]The temperature residual error corresponding to the temperature of the front bearing of the gear box in the range is 0 and is less than-20.86 +.>The temperature residual error corresponding to the temperature of the front bearing of the gear box is obtained by subtracting-20.86 from the temperature of the front bearing of the gear boxThe difference obtained is greater than 55.62->The temperature residual error corresponding to the temperature of the front bearing of the gear box is obtained by subtracting 55.62 +.>The obtained difference.
Then, for the power intervalInner gear box front axleThe temperature residual difference of the bearing temperature is intercepted by using a sliding window with L=72 and a step length S=6, 831 residual error sections are obtained in total, and data are provided for the subsequent confidence calculation.
As shown in fig. 4 (the abscissa is time information, and the ordinate is confidence), the confidence is always greater than 80% in the normal operation stage, which indicates that the bearing before the gearbox normally operates, the actual fault period of the bearing before the gearbox is 2017, 11 months and 11 days, the confidence of the bearing before the gearbox suddenly drops to 17.71% and is lower than 50%, which indicates that the bearing before the gearbox is abnormal, the bayesian hypothesis test method can evaluate the health state of the wind turbine generator set to accurately alarm, and compared with the traditional power division temperature threshold method, the bayesian hypothesis test method evaluates the health state of the wind turbine generator set to be difficult to generate false alarm in the healthy operation period, so that the false alarm rate is lower.
Referring to fig. 5, an embodiment of the present application further provides a health status assessment device of a wind generating set, including one or more processors, configured to implement the health status assessment method of any one of the first aspects.
Embodiments of the health status assessment device may be applied to a wind turbine. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. Taking software implementation as an example, the device in a logic sense is formed by reading corresponding computer program instructions in a nonvolatile memory into a memory through a processor of a wind generating set where the device is located for operation. In terms of hardware, as shown in fig. 5, a hardware structure diagram of a wind turbine generator set where the health status evaluation device of the present application is located is shown, and in addition to the processor, the internal bus, the memory, the network interface, and the nonvolatile memory shown in fig. 5, the wind turbine generator set where the device is located in the embodiment generally may further include other hardware according to the actual function of the wind turbine generator, which is not described herein again.
The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The embodiment of the application also provides a health state evaluation device of a wind generating set, which comprises:
the data acquisition module is used for acquiring SCADA data of the wind turbine generator set acquired by the SCADA system, wherein the SCADA data comprises a plurality of data sets, and each data set comprises power data and temperature data of the wind turbine generator set at the same moment;
a section dividing module, configured to divide the plurality of data sets into different power sections based on the power data, where each power section includes at least one of the data sets;
the residual determination module is used for determining a temperature residual corresponding to each temperature data in each power interval based on the temperature data of each power interval;
the residual intercepting module is used for intercepting the temperature residual of each power interval based on a preset sliding window to obtain a plurality of residual sections;
and the evaluation module is used for determining the Bayesian factor of each residual error section and evaluating the health state of the wind generating set based on the Bayesian factor of each residual error section.
The present embodiment also provides a computer-readable storage medium having stored thereon a program for implementing the health status assessment method according to any of the above embodiments when executed by a processor.
The computer readable storage medium may be an internal storage unit of the wind turbine generator system according to any of the preceding embodiments, such as a hard disk or a memory. The computer readable storage medium may also be an external storage device of the wind turbine generator, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), etc. provided on the device. Further, the computer readable storage medium may also include both an internal storage unit and an external storage device of the wind turbine generator system. The computer readable storage medium is used for storing the computer program and other programs and data required by the wind turbine generator system, and also for temporarily storing data that has been output or is to be output.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (15)
1. A method of assessing the health of a wind turbine generator system, the method comprising:
the method comprises the steps of acquiring SCADA data of a wind generating set acquired by an SCADA system, wherein the SCADA data comprises a plurality of data sets, and each data set comprises power data and temperature data of the wind generating set at the same moment;
dividing the plurality of data sets into different power intervals based on the power data, each power interval including at least one of the data sets;
determining a temperature residual error corresponding to each temperature data in each power interval based on the temperature data of each power interval; wherein, based on the temperature data of each power interval, determining the temperature residual corresponding to each temperature data in each power interval includes: setting a temperature residual of temperature data which is greater than or equal to a minimum temperature threshold value and less than or equal to a maximum temperature threshold value in the temperature data of each power interval as a first residual value; setting the temperature residual error of the temperature data smaller than the minimum temperature threshold value in the temperature data of each power interval as the difference value between the corresponding temperature data and the minimum temperature threshold value; setting the temperature residual error of the temperature data which is larger than the maximum temperature threshold value in the temperature data of each power interval as the difference value between the corresponding temperature data and the maximum temperature threshold value;
intercepting temperature residual errors of each power interval based on a preset sliding window to obtain a plurality of residual error sections;
determining a Bayesian factor for each residual segment;
based on the bayesian factor of each residual segment, the health status of the wind generating set is evaluated.
2. The method for assessing the health of a wind turbine generator system according to claim 1, wherein the assessing the health of the wind turbine generator system based on bayesian factors for each residual segment comprises:
comparing the Bayesian factor of the current residual error section with a preset factor threshold, and judging that the wind generating set is in a health state at the moment corresponding to the current residual error section if the Bayesian factor of the current residual error section is larger than or equal to the preset factor threshold;
if the Bayesian factor of the current residual error section is smaller than the preset factor threshold, judging that the wind generating set fails at the moment corresponding to the current residual error section.
3. The method for assessing the health of a wind turbine generator system according to claim 1, wherein the assessing the health of the wind turbine generator system based on bayesian factors for each residual segment comprises:
determining a corresponding confidence level based on the Bayesian factor of each residual segment;
and evaluating the health state of the wind generating set based on each confidence level or each confidence level and a corresponding Bayesian factor.
4. A method of assessing the health of a wind turbine generator system according to claim 3, wherein the assessing the health of the wind turbine generator system based on each confidence level, or each confidence level and a corresponding bayesian factor, comprises:
comparing the confidence coefficient of the current residual error section with a preset confidence coefficient threshold value, and judging that the wind generating set is in a health state at the moment corresponding to the current residual error section if the confidence coefficient of the current residual error section is larger than or equal to the preset confidence coefficient threshold value; if the confidence coefficient of the current residual error section is smaller than the preset confidence coefficient threshold value, judging that the wind generating set fails at the moment corresponding to the current residual error section; or,
comparing the confidence coefficient of the current residual error section with a preset confidence coefficient threshold value and comparing the Bayesian factor of the current residual error section with a preset factor threshold value, and judging that the wind generating set is in a health state at the moment corresponding to the current residual error section if the confidence coefficient of the current residual error section is larger than or equal to the preset confidence coefficient threshold value and the Bayesian factor of the current residual error section is larger than or equal to the preset factor threshold value; if the confidence coefficient of the current residual error section is smaller than the preset confidence coefficient threshold value and/or the Bayesian factor of the current residual error section is smaller than the preset factor threshold value, judging that the wind generating set fails at the moment corresponding to the current residual error section.
5. The method for assessing the health of a wind park according to claim 1, wherein said determining the bayesian factor of each residual segment comprises:
calculating a first mean value and a first standard deviation of temperature residuals in each residual section;
a Bayesian factor for each residual segment is determined based on the first mean and the first standard deviation for the residual segment.
6. The method for assessing the health of a wind turbine generator system according to claim 1, wherein the width and/or the movement step size of the sliding window is fixed.
7. The method for assessing the health of a wind turbine generator system according to claim 1, wherein the width and/or the movement step size of the sliding window is settable.
8. The method for evaluating the health status of a wind turbine according to claim 1, wherein determining a temperature residual corresponding to each temperature data in each power section based on the temperature data of each power section comprises:
determining a second mean and a second standard deviation of the temperature data in each power interval based on the temperature data in the power interval;
and determining a temperature residual error corresponding to each temperature data in each power interval based on a second average value of the temperature data in the power interval and the second standard deviation.
9. The method for evaluating the health status of a wind turbine according to claim 8, wherein determining the temperature residual corresponding to each temperature data in each power interval based on the second average value and the second standard deviation of the temperature data in the power interval comprises:
and determining a maximum temperature threshold value and a minimum temperature threshold value of each power interval based on a second average value of temperature data in the power interval, the second standard deviation and a preset coefficient.
10. The method for assessing the health of a wind turbine generator system according to claim 9, wherein the predetermined factor is greater than or equal to 2 and less than or equal to 5.
11. The method of claim 1, wherein the temperature data comprises one of a main bearing temperature, a gearbox drive end bearing temperature, a gearbox non-drive end bearing temperature, a gearbox oil temperature, a gearbox cooling water temperature, a gearbox scavenge oil temperature, a generator winding temperature, a generator drive end bearing temperature, a generator non-drive end bearing temperature, an engine cooling water temperature, a frequency converter reactance temperature, a frequency converter capacitance temperature, and a frequency converter power switching device temperature of the wind turbine generator set.
12. The method for evaluating the health of a wind turbine according to claim 1, wherein after evaluating the health of the wind turbine based on the bayesian factor of each residual segment, further comprising:
and outputting an evaluation result, wherein the evaluation result is used for indicating the health state of the wind generating set.
13. The method of claim 12, wherein when the evaluation result indicates that the wind turbine has failed, the evaluation result further includes time information of the failure of the wind turbine.
14. A health assessment device for a wind power generator set, comprising one or more processors configured to implement the health assessment method of any one of claims 1-13.
15. A computer-readable storage medium, characterized in that a program is stored thereon, which, when executed by a processor, implements the health status assessment method of any of claims 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518023.1A CN113312758B (en) | 2021-05-12 | 2021-05-12 | Health state evaluation method and device for wind generating set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518023.1A CN113312758B (en) | 2021-05-12 | 2021-05-12 | Health state evaluation method and device for wind generating set |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113312758A CN113312758A (en) | 2021-08-27 |
| CN113312758B true CN113312758B (en) | 2023-07-25 |
Family
ID=77373116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110518023.1A Active CN113312758B (en) | 2021-05-12 | 2021-05-12 | Health state evaluation method and device for wind generating set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113312758B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114219290A (en) * | 2021-12-15 | 2022-03-22 | 哈电风能有限公司 | Wind power plant health scheduling method, system, terminal device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109458308A (en) * | 2018-12-28 | 2019-03-12 | 中国大唐集团新能源科学技术研究院有限公司 | Blower fan main shaft overheating warning method |
| CN110991666A (en) * | 2019-11-25 | 2020-04-10 | 远景智能国际私人投资有限公司 | Fault detection method, model training method, device, equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2928833A1 (en) * | 2013-11-04 | 2015-05-07 | Nextnav, Llc | Determining calibrated measurements of pressure for different sensors |
| CN104131950B (en) * | 2014-07-24 | 2017-02-01 | 重庆大学 | Partitioning determination method for threshold value of temperature characteristic quantity of wind generating set |
| CN108763048B (en) * | 2018-06-05 | 2021-01-19 | 西安交通大学 | Hard disk fault early warning and reliability evaluation method based on particle filtering |
| CN110703025A (en) * | 2019-10-18 | 2020-01-17 | 重庆大学 | Method for identifying abnormal health state of IGBT power module of wind power converter |
-
2021
- 2021-05-12 CN CN202110518023.1A patent/CN113312758B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109458308A (en) * | 2018-12-28 | 2019-03-12 | 中国大唐集团新能源科学技术研究院有限公司 | Blower fan main shaft overheating warning method |
| CN110991666A (en) * | 2019-11-25 | 2020-04-10 | 远景智能国际私人投资有限公司 | Fault detection method, model training method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113312758A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190101103A1 (en) | Condition monitoring system and wind turbine generation apparatus | |
| Yang | A condition-based failure-prediction and processing-scheme for preventive maintenance | |
| US10496466B2 (en) | Preprocessor of abnormality sign diagnosing device and processing method of the same | |
| CN116433009A (en) | Abnormality monitoring method and device for power transformation equipment and storage medium | |
| EP2166422B1 (en) | Method of alarm mask generation and condition monitoring of wind turbines | |
| CN110689141B (en) | Fault diagnosis method and equipment for wind generating set | |
| CN116593811B (en) | Integrated frequency converter running state monitoring system and monitoring method | |
| CN109469896A (en) | A kind of diagnostic method and system based on time series analysis Industrial Boiler failure | |
| US20130173215A1 (en) | Adaptive trend-change detection and function fitting system and method | |
| CN114994543A (en) | Energy storage power station battery fault diagnosis method and device and storage medium | |
| US10895873B2 (en) | Machine health monitoring of rotating machinery | |
| CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
| CN113586239A (en) | Engine fault diagnosis method, engine fault diagnosis device, controller and storage medium | |
| US11726469B2 (en) | Error-based method for calculating a remaining useful life of an apparatus | |
| CN111504450A (en) | Equipment fault alarm method and device | |
| CN113312758B (en) | Health state evaluation method and device for wind generating set | |
| CN115587673A (en) | Voltage transformer error state prediction method and system | |
| US20220156586A1 (en) | System for monitoring a circuit breaker | |
| CN113219337B (en) | Battery degradation determination system, method, and non-transitory storage medium storing program | |
| CN111120221B (en) | Method and equipment for evaluating power generation performance of wind generating set | |
| CN117591839A (en) | Gas turbine fault early warning method, system, electronic equipment and storage medium | |
| CN113487141B (en) | Bearing state evaluation method based on multisource information clustering fusion | |
| CN113468818B (en) | Winding running state monitoring method and device for wind generating set | |
| CN111350638A (en) | Method and device for calculating power generation loss of wind generating set | |
| JP7415654B2 (en) | battery monitoring 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 |