CN110907170A - Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method - Google Patents

Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method Download PDF

Info

Publication number
CN110907170A
CN110907170A CN201911207401.3A CN201911207401A CN110907170A CN 110907170 A CN110907170 A CN 110907170A CN 201911207401 A CN201911207401 A CN 201911207401A CN 110907170 A CN110907170 A CN 110907170A
Authority
CN
China
Prior art keywords
gearbox
wind turbine
turbine generator
temperature
bearing
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.)
Granted
Application number
CN201911207401.3A
Other languages
Chinese (zh)
Other versions
CN110907170B (en
Inventor
王忠杰
韩斌
赵勇
陈晓路
周国栋
陈正华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huaneng Rudong Eight Immortals Sea Wind Power Co Ltd
Xian Thermal Power Research Institute Co Ltd
Original Assignee
Huaneng Rudong Eight Immortals Sea Wind Power Co Ltd
Thermal Power Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huaneng Rudong Eight Immortals Sea Wind Power Co Ltd, Thermal Power Research Institute filed Critical Huaneng Rudong Eight Immortals Sea Wind Power Co Ltd
Priority to CN201911207401.3A priority Critical patent/CN110907170B/en
Publication of CN110907170A publication Critical patent/CN110907170A/en
Application granted granted Critical
Publication of CN110907170B publication Critical patent/CN110907170B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00Testing of machine parts
    • G01M13/02Gearings; Transmission mechanisms
    • G01M13/021Gearings
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01KMEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K1/00Details of thermometers not specially adapted for particular types of thermometer
    • G01K1/02Means for indicating or recording specially adapted for thermometers
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00Testing of machine parts
    • G01M13/04Bearings

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Wind Motors (AREA)

Abstract

A wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method has important practical value for reducing maintenance cost of a wind power plant and improving operation level. Because the unit operation parameters with similar geographical positions of the wind power plant have special distribution rules and extremely strong correlation, the invention carries out transverse comparison analysis on the bearing temperatures of four 1.5MW unit gear boxes with strong correlation of a certain wind power plant. The method comprises the steps of counting the temperature-power dispersion point distribution characteristics of four strongly-related wind turbine generator gearbox bearings, finding out abnormal changes of the relationship between the monitored wind turbine generator gearbox bearing temperature and the temperatures of other related wind turbine generator gearbox bearings, judging the state of the monitored wind turbine generator gearbox, and sending out fault early warning.

Description

Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method
Technical Field
The invention belongs to the technical field of wind turbine generator gearbox bearing fault diagnosis, and particularly relates to a wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method.
Background
Along with the economic development and the improvement of the living standard of people, the consumption of human beings to energy sources is increased day by day, and the pollution to the environment is more and more serious. In the face of the energy crisis and the environmental crisis, clean and sustainable alternative energy sources must be found. Wind energy is the most promising alternative energy source. In recent years, wind power generation technology is becoming mature, and the power generation cost is gradually reduced and is close to the thermal power cost.
The wind turbine generator has severe operating conditions, such as large external temperature difference change, random wind speed change and the like. The fault rate of the wind turbine generator is high due to uncertain external factors, so that the later operation and maintenance cost of the wind power plant is high.
The gearbox is one of important parts of the wind turbine generator, and the manufacturing technology of the gearbox is mature and has high reliability. Although the failure rate of the gearbox is low, compared with an electric control system and a hydraulic system with the highest failure occurrence frequency, the maintenance process is complex, particularly for offshore wind turbines, special equipment such as ships and cranes and proper weather are needed in the maintenance process, and therefore the downtime and the maintenance cost caused by the failure of the gearbox are the highest among various failures. The wind turbine generator gearbox has the characteristics of speed change and load change during operation. With the change of the wind speed, the rotating speed and the load of each stage of the gearbox change at any time, which brings great challenges for the application of the traditional state monitoring method to the gearbox of the wind turbine generator. The choice of a gearbox condition monitoring method also requires consideration of the cost/performance ratio of the monitoring method. Compared with a thermal power generating unit and a hydroelectric generating unit, the cost of a single fan is lower, and the cost of a gear box monitoring system is a factor which must be considered.
The traditional gearbox bearing fault diagnosis technology, such as vibration analysis, oil analysis and the like, achieves certain results. The wind speed changes randomly, so that the rotating speed and the load of each stage of bearing of the gearbox of the wind turbine generator set change time instead of the stable working condition that the rotating speed is not changed. The current vibration analysis technology is low in fault diagnosis accuracy and high in false alarm and false alarm rate under the time-varying complex working condition of variable rotating speed and variable load of a gearbox bearing. The gear box oil analysis technology is used for collecting a gear box oil sample during the shutdown of the wind turbine generator, analyzing the water content, the number of metal particles and the diameter of lubricating oil in a laboratory to diagnose the state of a gear box bearing, but the oil analysis can only be used for off-line diagnosis, and the on-line real-time monitoring and diagnosis of the gear box bearing cannot be realized. And a multilayer forward neural network is adopted to model and monitor the temperature of the bearing of the gearbox of the wind turbine generator, but the forward neural network has a simple structure and low modeling precision, so that the abnormal change of the temperature of the bearing of the gearbox is difficult to be timely and accurately pre-warned.
The wind turbine generator gearbox fault can cause the long-time halt of the generator, the maintenance cost is high, the halt loss is large, and the wind turbine generator gearbox fault monitoring and diagnosing device has important significance for monitoring and diagnosing the running state of the gearbox.
Disclosure of Invention
In order to solve the problems in the prior art, the invention aims to provide a method for monitoring the temperature state and diagnosing the fault of the bearing of the gearbox of the wind turbine generator. The variation relation and trend between the temperature of the bearing of the gear box of the monitored unit and the temperature of the bearing of the related unit are researched by a control graph method and a gamma curve parameter fitting method, so that the running state of the gear box of the monitored wind turbine generator is monitored and diagnosed on line. The invention does not need to install additional sensors, has simple algorithm, and can realize the state monitoring of the gear box only by the existing operating data of the wind turbine generator.
In order to achieve the purpose, the invention adopts the following technical scheme:
a wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method comprises the following steps:
step 1, selecting three wind turbine generators with highest temperature correlation with a bearing of a gearbox of a monitored wind turbine generator, and simultaneously removing shutdown period data, wherein the total number of the three wind turbine generators is four; collecting all monitored wind turbine generator operation data, calculating the correlation between the temperature of a plurality of wind turbine generator gearbox bearings and the temperature of the monitored wind turbine generator gearbox bearings by using a Pearson correlation coefficient formula, and selecting three machines with the highest correlation with the temperature of the monitored wind turbine generator gearbox bearings from the correlation, wherein the Pearson correlation coefficient formula is as follows:
Figure BDA0002297212510000031
wherein:
r-Pearson correlation coefficient;
n is the number of samples;
wi-monitored unit gearbox bearing temperature sample values;
Figure BDA0002297212510000032
-monitored unit gearbox bearing temperature sample mean;
δw-the monitored unit gearbox bearing temperature standard deviation;
zi-other unit gearbox bearing temperature sample values for correlation analysis;
Figure BDA0002297212510000033
-mean values of temperature samples of other unit gearbox bearings for correlation analysis;
δz-other unit gearbox bearing temperature standard deviations for correlation analysis;
step 2, picking out points with power greater than 0 from original data of four related wind turbines, and setting an active power interval as [ P ]min,Pmax](ii) a Drawing a bearing temperature-power scatter diagram of the gearbox of the wind turbine generator system by taking the bearing temperature of the gearbox as a vertical coordinate and taking power as a horizontal coordinate; equally dividing the power of the abscissa into P at intervals of 40KWnumEach interval is divided into P if the lower limit of power is zero and the upper limit is 1600KW num40 intervals;
for each of four related wind turbines, the number of bearing temperature dispersion points of the gear box falling in each power interval is counted in sequence and stored in X4×40In an array;
Figure BDA0002297212510000041
wherein:
Xi,jthe bearing temperature dispersion point number of the gearbox in the jth power interval of the ith unit;
step 3, observing the difference between the bearing temperature scatter numbers of the gear boxes of the four related wind turbines in different power intervals by using a control chart; the control chart comprises a range (j) of the polar difference of the bearing temperature dispersion points of four wind turbine generator sets in the jth power interval; the average range of the number average pole difference MRange of bearing temperature scatter points of the gearbox in 40 power intervals; the average value M of the number of scattered points of the bearing temperature of the gearbox; the upper control limit UCL of the bearing temperature scatter number of the gearbox; the lower limit LCL is controlled by the number of scattered points of the bearing temperature of the gear box, and the variables are calculated by adopting the following formula:
Range(j)=Max(Xi,j)-Min(Xi,j)
Figure BDA0002297212510000042
UCL=M+0.729MRange
LCL=M-0.729MRange
wherein:
Max(Xi,j) In the jth power interval, the maximum value of the bearing temperature dispersion point number of the gearbox in the four related wind turbines;
Min(Xi,j) In the jth power interval, four phasesTurning off the minimum value of the bearing temperature dispersion points of a gearbox in the wind turbine generator;
range (j) -the range of the bearing temperature dispersion number of the four wind turbine generator gearbox in the jth power interval;
MRange-40 power interval scatter number average pole difference;
UCL-upper limit of scattered point number control;
LCL-lower control limit of scattered point number;
the bearing temperature of the gearbox of the monitored wind turbine generator set has strong correlation with the bearing temperatures of the gearboxes of the other three wind turbine generators; when the gearbox of the monitored wind turbine generator set operates normally, the bearing temperature of the gearbox is very similar to the change trend of the bearing temperature of the gearbox of the other three wind turbine generator sets along with the power; therefore, in each power interval, the temperature range of the bearings of the gear boxes of the four wind turbine generator sets is very small;
when the gearbox of the monitored wind turbine generator system breaks down and the bearing temperature rises abnormally, the bearing temperature variation trend of the monitored wind turbine generator system is greatly different from the bearing temperature variation trend of the gearbox of the other three wind turbine generators which normally operate; the temperature dispersion point number range of the bearings of the gear boxes among the four sets is abnormally increased in certain power intervals;
therefore, when the pole difference of the number of scattered points of the bearing temperature of the gearbox in certain power intervals is found to be abnormally increased, the abnormal operation alarm of the gearbox of the monitored unit is sent out;
step 4, a Kolmogorov-Smirnov method is used for detecting the temperature scatter distribution of the gearbox bearing, and gamma distribution is adopted to fit the scatter distribution; finding abnormal operation of the wind turbine generator gearbox to be monitored according to the deviation of the bearing temperature scatter gamma distribution simulation parameter of the wind turbine generator gearbox to be monitored and the average value of the fitting parameters of the other three wind turbine generators;
an assumption is provided for the distribution situation of the bearing temperature scatter of the four wind turbine generator gearbox, fitting goodness inspection is carried out, and the following formula is adopted for calculation:
Figure BDA0002297212510000061
Dn=max|F(x)-Fn(x)|
wherein:
fn (x) -a cumulative distribution function representing the sample observations;
Xi-is the sample observed value;
x is a theoretical value;
I[-∞,x](Xi) An index function, if XiX is equal to 1, otherwise equal to 0;
dn-the maximum deviation between assay amount, F (x) and Fn (x);
f (x) -a cumulative probability distribution function representing the theoretical distribution;
the partial values of the check mass critical value D (n, a) are shown in the following table 1, wherein n is the number of samples;
TABLE 1 partial values of the check quantity threshold D (n, a)
Figure BDA0002297212510000062
Figure BDA0002297212510000071
If the sample is from the distribution function F (x), Dn converges to 0; determining a critical value D (n, a) of the Kolmogorov-Smirnov method test according to the confidence level a of 0.05 and the number n of the samples of 40, wherein if Dn < D (n, a), the samples are accepted to be in accordance with the corresponding gamma distribution or Weibull distribution or normal distribution at the significance level of a; after statistical analysis and Kolmogorov-Smirnov method inspection are carried out on the temperature data of the bearing of the gearbox, the temperature data of the bearing of the gearbox conforms to gamma distribution; determining a shape parameter K and a scale parameter theta of the gamma distribution of the bearing temperature scatter points of the gear boxes of the four wind turbine generators by adopting a maximum likelihood estimation method to obtain a gamma distribution curve with the optimal fitting degree of the four wind turbine generators;
when the difference between the fitting parameters of the monitored wind turbine generator and the mean value of the fitting parameters of the three related wind turbine generators exceeds a threshold value, sending an abnormal alarm of the bearing temperature of the gearbox of the monitored wind turbine generator, as follows:
Figure BDA0002297212510000072
wherein:
Kmfitting shape parameters of the gamma distribution of the bearing temperature scatter points of the monitored wind turbine generator;
θmfitting scale parameters of the gamma distribution of the bearing temperature scatter points of the monitored wind turbine generator;
Figure BDA0002297212510000073
-fitting the mean value of the shape parameters to the gamma distribution of the temperature of the gearbox bearings of the other three related wind turbines;
Figure BDA0002297212510000074
-fitting the mean value of the scale parameters to the temperature gamma distribution of the gearbox bearings of the other three related wind turbines;
Δm-the variance between the fitting parameters of the monitored wind turbines and the mean of the fitting parameters of the three related turbines;
ξ -to set a threshold;
step 5, synthesizing the abnormal temperature alarm of the monitored wind turbine generator gearbox bearing sent by the step 3 and the step 4 respectively:
when the abnormal temperature alarm of the bearing of the gearbox of the monitored wind turbine generator is sent out simultaneously in the steps 3 and 4, the two abnormal alarms can be mutually verified, the alarm authenticity is strong, and the abnormal operation alarm of the gearbox is sent out to field operators;
when one of the step 3 or the step 4 sends out the abnormal temperature alarm of the bearing of the gearbox of the monitored wind turbine generator, in order to reduce the false alarm rate, the abnormal temperature alarm of the bearing of the gearbox of the monitored wind turbine generator is not sent out, and only the prompt of needing to pay attention to the running state of the gearbox is sent out to field operators.
The method adopts the operation data of the wind turbine generator to analyze, does not need to additionally add a sensor, has low cost and simple principle, and can find the temperature abnormity of the bearing of the gearbox of the wind turbine generator in time and give an alarm.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a distribution control diagram of temperature dispersion of four wind turbine generator gearbox bearings when a monitored unit is normal.
Fig. 3 is a gear box bearing temperature-power dispersion point gamma distribution parameter when the monitored unit is normal.
FIG. 4 is a cross-contrast gamma distribution plot for the associated unit.
Fig. 5 is a timing chart for monitoring a gearbox bearing temperature anomaly of the unit.
FIG. 6 is a gamma distribution curve comparison diagram of a monitored unit with abnormal temperature of a bearing of a gearbox and a related normal unit.
Detailed Description
The invention is described in detail below with reference to the figures and examples. The method comprises the steps of taking gear boxes of 4 1.5MW units in a certain wind power plant as research objects, and selecting 1-minute-level operation data of the units.
As shown in fig. 1, the method for monitoring the temperature state and diagnosing the fault of the bearing of the gearbox of the wind turbine generator set comprises the following steps:
step 1, selecting other three wind turbine generators with high correlation with the monitored wind turbine generator on the temperature parameter of the bearing of the gear box as reference comparison units by adopting the Pearson coefficient.
And 2, drawing a gear box bearing temperature-power scatter diagram which takes power as an abscissa and takes gear box bearing temperature as an integrated coordinate for the four wind turbines with strong correlation. Counting the number of temperature scatter points of bearings of the gear box in each power interval divided by 40KW of each unit, and dividing the power interval into P if the lower limit of the power is zero and the upper limit of the power is 1600KWnum40 intervals, and X is stored4×40
And 3, observing the difference between the bearing temperature scatter points of the gear boxes of the four related wind turbines in different power intervals by using a control chart. And drawing a control chart, and displaying the temperature dispersion point mean distribution condition of the four selected wind turbine generator gearbox bearings as shown in FIG. 2. The temperature dispersion point range of the bearings of the gear boxes of the four units is small in each power interval, the temperature variation trend of the bearings of the gear boxes of the monitored unit is consistent with that of the bearings of the other three relevant units, abnormal variation does not exist, and the running state of the gear boxes of the monitored unit is normal.
And 4, selecting Kolmogorov-Smirnov for carrying out distribution inspection on the bearing temperature-power dispersion points of the gear boxes of the four wind turbine generators.
As shown in fig. 3, the temperature data of the gearbox bearings conforms to gamma distribution, and the distribution parameters are monitored unit parameters K-2.9943 and θ -1.0428. The gamma distribution parameters of the other three related units have K value fluctuating within 3.0000 +/-0.2000 and theta value fluctuating within 1.0000 +/-0.1000. FIG. 4 is a gamma distribution curve diagram comparing with other related units in the transverse direction, and the trend and the parameters are approximately the same, so that the gear box bearing temperature dispersion point distribution among the units with stronger correlation has strong similarity.
Fig. 5 is a control diagram of the monitored wind turbine generator set when the bearing temperature of the gearbox is abnormal, and shows that the high power interval range is far higher than the average range value and fluctuates violently compared with other related units, which indicates that the bearing temperature of the gearbox of the monitored wind turbine generator set is obviously abnormally increased under the high load working condition compared with the other three related units.
Fig. 6 is a fitting curve comparison of the mean gamma distribution parameters of the temperature scatter gamma distribution fitting curve of the monitored wind turbine generator set when the temperature of the gearbox bearing is abnormal and other three related units. In fig. 6, the gamma distribution parameters of the monitored unit are K-5.9824 and θ -0.7256, which are much larger than the mean value of the gamma distribution parameters of the other three related normal units in the same time segment
Figure BDA0002297212510000101
Therefore, the abnormal temperature of the gearbox bearing of the monitored unit can be seen from the control chart of fig. 5 and the gamma distribution parameter of fig. 6, and therefore an alarm for the abnormal temperature of the gearbox bearing of the monitored unit is sent out.

Claims (1)

1. A wind turbine generator system gear box bearing temperature state monitoring and fault diagnosis method is characterized in that: the method comprises the following steps:
step 1, selecting three wind turbine generators with highest temperature correlation with a bearing of a gearbox of a monitored wind turbine generator, and simultaneously removing shutdown period data, wherein the total number of the three wind turbine generators is four; collecting all monitored wind turbine generator operation data, calculating the correlation between the temperature of a plurality of wind turbine generator gearbox bearings and the temperature of the monitored wind turbine generator gearbox bearings by using a Pearson correlation coefficient formula, and selecting three machines with the highest correlation with the temperature of the monitored wind turbine generator gearbox bearings from the correlation, wherein the Pearson correlation coefficient formula is as follows:
Figure FDA0002297212500000011
wherein:
r-Pearson correlation coefficient;
n is the number of samples;
wi-monitored unit gearbox bearing temperature sample values;
Figure FDA0002297212500000012
-monitored unit gearbox bearing temperature sample mean;
δw-the monitored unit gearbox bearing temperature standard deviation;
zi-other unit gearbox bearing temperature sample values for correlation analysis;
Figure FDA0002297212500000013
-mean values of temperature samples of other unit gearbox bearings for correlation analysis;
δz-other unit gearbox bearing temperature standard deviations for correlation analysis;
step 2, picking out points with power greater than 0 from original data of four related wind turbines, and setting an active power interval as [ P ]min,Pmax](ii) a Drawing a bearing temperature-power scatter diagram of the gearbox of the wind turbine generator system by taking the bearing temperature of the gearbox as a vertical coordinate and taking power as a horizontal coordinate; equally dividing the power of the abscissa into P at intervals of 40KWnumEach interval is divided into P if the lower limit of power is zero and the upper limit is 1600KWnum40 intervals;
for each of four related wind turbines, the number of bearing temperature dispersion points of the gear box falling in each power interval is counted in sequence and stored in X4×40In an array;
Figure FDA0002297212500000021
wherein:
Xi,jthe bearing temperature dispersion point number of the gearbox in the jth power interval of the ith unit;
step 3, observing the difference between the bearing temperature scatter numbers of the gear boxes of the four related wind turbines in different power intervals by using a control chart; the control chart comprises a range (j) of the polar difference of the bearing temperature dispersion points of four wind turbine generator sets in the jth power interval; the average range of the number average pole difference MRange of bearing temperature scatter points of the gearbox in 40 power intervals; the average value M of the number of scattered points of the bearing temperature of the gearbox; the upper control limit UCL of the bearing temperature scatter number of the gearbox; the lower limit LCL is controlled by the number of scattered points of the bearing temperature of the gear box, and the variables are calculated by adopting the following formula:
Range(j)=Max(Xi,j)-Min(Xi,j)
Figure FDA0002297212500000022
UCL=M+0.729MRange
LCL=M-0.729MRange
wherein:
Max(Xi,j) In the jth power interval, the maximum value of the bearing temperature dispersion point number of the gearbox in the four related wind turbines;
Min(Xi,j) -in the jth power interval,the minimum value of the bearing temperature dispersion points of the gear box in the four related wind turbines;
range (j) -the range of the bearing temperature dispersion number of the four wind turbine generator gearbox in the jth power interval;
MRange-40 power interval scatter number average pole difference;
UCL-upper limit of scattered point number control;
LCL-lower control limit of scattered point number;
the bearing temperature of the gearbox of the monitored wind turbine generator set has strong correlation with the bearing temperatures of the gearboxes of the other three wind turbine generators; when the gearbox of the monitored wind turbine generator set operates normally, the bearing temperature of the gearbox is very similar to the change trend of the bearing temperature of the gearbox of the other three wind turbine generator sets along with the power; therefore, in each power interval, the temperature range of the bearings of the gear boxes of the four wind turbine generator sets is very small;
when the gearbox of the monitored wind turbine generator system breaks down and the bearing temperature rises abnormally, the bearing temperature variation trend of the monitored wind turbine generator system is greatly different from the bearing temperature variation trend of the gearbox of the other three wind turbine generators which normally operate; the temperature dispersion point number range of the bearings of the gear boxes among the four sets is abnormally increased in certain power intervals;
therefore, when the pole difference of the number of scattered points of the bearing temperature of the gearbox in certain power intervals is found to be abnormally increased, the abnormal operation alarm of the gearbox of the monitored unit is sent out;
step 4, a Kolmogorov-Smirnov method is used for detecting the temperature scatter distribution of the gearbox bearing, and gamma distribution is adopted to fit the scatter distribution; finding abnormal operation of the wind turbine generator gearbox to be monitored according to the deviation of the bearing temperature scatter gamma distribution simulation parameter of the wind turbine generator gearbox to be monitored and the average value of the fitting parameters of the other three wind turbine generators;
an assumption is provided for the distribution situation of the bearing temperature scatter of the four wind turbine generator gearbox, fitting goodness inspection is carried out, and the following formula is adopted for calculation:
Figure FDA0002297212500000031
Dn=max|F(x)-Fn(x)|
wherein:
fn (x) -a cumulative distribution function representing the sample observations;
Xi-is the sample observed value;
x is a theoretical value;
I[-∞,x](Xi) An index function, if XiX is equal to 1, otherwise equal to 0;
dn-the maximum deviation between assay amount, F (x) and Fn (x);
f (x) -a cumulative probability distribution function representing the theoretical distribution;
the partial values of the check mass critical value D (n, a) are shown in the following table 1, wherein n is the number of samples;
TABLE 1 partial values of the check quantity threshold D (n, a)
Figure FDA0002297212500000041
If the sample is from the distribution function F (x), Dn converges to 0; determining a critical value D (n, a) of the Kolmogorov-Smirnov method test according to the confidence level a of 0.05 and the number n of the samples of 40, wherein if Dn < D (n, a), the samples are accepted to be in accordance with the corresponding gamma distribution or Weibull distribution or normal distribution at the significance level of a; after statistical analysis and Kolmogorov-Smirnov method inspection are carried out on the temperature data of the bearing of the gearbox, the temperature data of the bearing of the gearbox conforms to gamma distribution; determining a shape parameter K and a scale parameter theta of the gamma distribution of the bearing temperature scatter points of the gear boxes of the four wind turbine generators by adopting a maximum likelihood estimation method to obtain a gamma distribution curve with the optimal fitting degree of the four wind turbine generators;
when the difference between the fitting parameters of the monitored wind turbine generator and the mean value of the fitting parameters of the three related wind turbine generators exceeds a threshold value, sending an abnormal alarm of the bearing temperature of the gearbox of the monitored wind turbine generator, as follows:
Figure FDA0002297212500000051
wherein:
Kmfitting shape parameters of the gamma distribution of the bearing temperature scatter points of the monitored wind turbine generator;
θmfitting scale parameters of the gamma distribution of the bearing temperature scatter points of the monitored wind turbine generator;
Figure FDA0002297212500000052
-fitting the mean value of the shape parameters to the gamma distribution of the temperature of the gearbox bearings of the other three related wind turbines;
Figure FDA0002297212500000053
-fitting the mean value of the scale parameters to the temperature gamma distribution of the gearbox bearings of the other three related wind turbines;
Δm-the variance between the fitting parameters of the monitored wind turbines and the mean of the fitting parameters of the three related turbines;
ξ -to set a threshold;
step 5, synthesizing the abnormal temperature alarm of the monitored wind turbine generator gearbox bearing sent by the step 3 and the step 4 respectively:
when the abnormal temperature alarm of the bearing of the gearbox of the monitored wind turbine generator is sent out simultaneously in the steps 3 and 4, the two abnormal alarms can be mutually verified, the alarm authenticity is strong, and the abnormal operation alarm of the gearbox is sent out to field operators;
when one of the step 3 or the step 4 sends out the abnormal temperature alarm of the bearing of the gearbox of the monitored wind turbine generator, in order to reduce the false alarm rate, the abnormal temperature alarm of the bearing of the gearbox of the monitored wind turbine generator is not sent out, and only the prompt of needing to pay attention to the running state of the gearbox is sent out to field operators.
CN201911207401.3A 2019-11-30 2019-11-30 Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method Active CN110907170B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911207401.3A CN110907170B (en) 2019-11-30 2019-11-30 Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911207401.3A CN110907170B (en) 2019-11-30 2019-11-30 Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method

Publications (2)

Publication Number Publication Date
CN110907170A true CN110907170A (en) 2020-03-24
CN110907170B CN110907170B (en) 2021-03-16

Family

ID=69821085

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911207401.3A Active CN110907170B (en) 2019-11-30 2019-11-30 Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method

Country Status (1)

Country Link
CN (1) CN110907170B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112324627A (en) * 2020-09-22 2021-02-05 大唐可再生能源试验研究院有限公司 Wind generating set generator bearing temperature alarm system
CN112699598A (en) * 2020-12-14 2021-04-23 龙源(北京)风电工程技术有限公司 Intelligent diagnosis method and device for abnormal oil temperature of gear box
EP3893070A1 (en) * 2020-04-08 2021-10-13 Siemens Gamesa Renewable Energy A/S Method and system for monitoring operation of wind turbines
CN115450853A (en) * 2022-08-26 2022-12-09 西安热工研究院有限公司 Variable pitch motor temperature abnormity early warning method and system based on discrete rate
CN116223037A (en) * 2023-05-09 2023-06-06 山东金帝精密机械科技股份有限公司 Operation monitoring method and equipment for wind power bearing retainer
CN116561593A (en) * 2023-07-11 2023-08-08 北京寄云鼎城科技有限公司 Model training method, temperature prediction method, device and medium of gearbox

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10214891A1 (en) * 2002-04-04 2003-10-16 Zahnradfabrik Friedrichshafen Measuring and evaluating method for gearbox data on a testing stand uses test stand input values to determine systems reactions compared for quality control with reactions calculated isochronically
US20050284225A1 (en) * 2004-06-28 2005-12-29 Huageng Luo System and method for monitoring the condition of a drive train
CN102262648A (en) * 2010-05-31 2011-11-30 索尼公司 Evaluation predicting device, evaluation predicting method, and program
EP2565658A1 (en) * 2011-08-29 2013-03-06 General Electric Company Fault detection based on current signature analysis for a generator
CN103645052A (en) * 2013-12-11 2014-03-19 北京航空航天大学 Wind turbine set gearbox remote online state monitoring and life assessment method
CN103681395A (en) * 2012-09-04 2014-03-26 台湾积体电路制造股份有限公司 Qualitative fault detection and classification system for tool condition monitoring and associated methods
CN106089328A (en) * 2016-08-10 2016-11-09 西安热工研究院有限公司 Steam turbine pitch rating curve discrimination method based on DCS data mining
CN106644483A (en) * 2017-02-24 2017-05-10 成都柏森松传感技术有限公司 Bearing fault detection method and system for gear box
CN107153929A (en) * 2017-07-10 2017-09-12 龙源(北京)风电工程技术有限公司 Gearbox of wind turbine fault monitoring method and system based on deep neural network
CN107742053A (en) * 2017-11-28 2018-02-27 国华(河北)新能源有限公司 Wind turbines abnormality recognition method and device
CN108072524A (en) * 2016-11-10 2018-05-25 中国电力科学研究院 A kind of gearbox of wind turbine bearing fault method for early warning
CN108629095A (en) * 2018-04-23 2018-10-09 明阳智慧能源集团股份公司 A kind of modeling method of gearbox of wind turbine bearing temperature
CN108871821A (en) * 2017-10-25 2018-11-23 中国石油化工股份有限公司 Based on mean value-moving range method air cooler energy efficiency state method of real-time
CN109297716A (en) * 2018-10-23 2019-02-01 西安热工研究院有限公司 Vibration fault diagnosis method for double-fed wind driven generator
CN109425483A (en) * 2017-09-04 2019-03-05 锐电科技有限公司 Running of wind generating set status assessment and prediction technique based on SCADA and CMS
CN110196160A (en) * 2019-05-29 2019-09-03 国电联合动力技术有限公司 A kind of wind turbine gearbox monitoring method based on residual error network

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10214891A1 (en) * 2002-04-04 2003-10-16 Zahnradfabrik Friedrichshafen Measuring and evaluating method for gearbox data on a testing stand uses test stand input values to determine systems reactions compared for quality control with reactions calculated isochronically
US20050284225A1 (en) * 2004-06-28 2005-12-29 Huageng Luo System and method for monitoring the condition of a drive train
CN102262648A (en) * 2010-05-31 2011-11-30 索尼公司 Evaluation predicting device, evaluation predicting method, and program
EP2565658A1 (en) * 2011-08-29 2013-03-06 General Electric Company Fault detection based on current signature analysis for a generator
CN103681395A (en) * 2012-09-04 2014-03-26 台湾积体电路制造股份有限公司 Qualitative fault detection and classification system for tool condition monitoring and associated methods
CN103645052A (en) * 2013-12-11 2014-03-19 北京航空航天大学 Wind turbine set gearbox remote online state monitoring and life assessment method
CN106089328A (en) * 2016-08-10 2016-11-09 西安热工研究院有限公司 Steam turbine pitch rating curve discrimination method based on DCS data mining
CN108072524A (en) * 2016-11-10 2018-05-25 中国电力科学研究院 A kind of gearbox of wind turbine bearing fault method for early warning
CN106644483A (en) * 2017-02-24 2017-05-10 成都柏森松传感技术有限公司 Bearing fault detection method and system for gear box
CN107153929A (en) * 2017-07-10 2017-09-12 龙源(北京)风电工程技术有限公司 Gearbox of wind turbine fault monitoring method and system based on deep neural network
CN109425483A (en) * 2017-09-04 2019-03-05 锐电科技有限公司 Running of wind generating set status assessment and prediction technique based on SCADA and CMS
CN108871821A (en) * 2017-10-25 2018-11-23 中国石油化工股份有限公司 Based on mean value-moving range method air cooler energy efficiency state method of real-time
CN107742053A (en) * 2017-11-28 2018-02-27 国华(河北)新能源有限公司 Wind turbines abnormality recognition method and device
CN108629095A (en) * 2018-04-23 2018-10-09 明阳智慧能源集团股份公司 A kind of modeling method of gearbox of wind turbine bearing temperature
CN109297716A (en) * 2018-10-23 2019-02-01 西安热工研究院有限公司 Vibration fault diagnosis method for double-fed wind driven generator
CN110196160A (en) * 2019-05-29 2019-09-03 国电联合动力技术有限公司 A kind of wind turbine gearbox monitoring method based on residual error network

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
HSU-HAOYANG 等: "An approach combining data mining and control charts-based model for fault detection in wind turbines", 《RENEWABLE ENERGY》 *
MENGYAN NIE 等: "Review of Condition Monitoring and Fault Diagnosis Technologies for Wind Turbine Gearbox", 《PROCEDIA CIRP》 *
向健平 等: "基于SCADA系统的风电机组主轴承故障预警方法", 《电力科学与技术学报》 *
范少群 等: "微组装金丝键合工序统计过程控制技术", 《电子与封装》 *
邢月 等: "基于温度参数的风电机组异常识别", 《可再生能源》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3893070A1 (en) * 2020-04-08 2021-10-13 Siemens Gamesa Renewable Energy A/S Method and system for monitoring operation of wind turbines
CN112324627A (en) * 2020-09-22 2021-02-05 大唐可再生能源试验研究院有限公司 Wind generating set generator bearing temperature alarm system
CN112699598A (en) * 2020-12-14 2021-04-23 龙源(北京)风电工程技术有限公司 Intelligent diagnosis method and device for abnormal oil temperature of gear box
CN115450853A (en) * 2022-08-26 2022-12-09 西安热工研究院有限公司 Variable pitch motor temperature abnormity early warning method and system based on discrete rate
CN116223037A (en) * 2023-05-09 2023-06-06 山东金帝精密机械科技股份有限公司 Operation monitoring method and equipment for wind power bearing retainer
CN116223037B (en) * 2023-05-09 2023-09-19 山东金帝精密机械科技股份有限公司 Operation monitoring method and equipment for wind power bearing retainer
CN116561593A (en) * 2023-07-11 2023-08-08 北京寄云鼎城科技有限公司 Model training method, temperature prediction method, device and medium of gearbox

Also Published As

Publication number Publication date
CN110907170B (en) 2021-03-16

Similar Documents

Publication Publication Date Title
CN110907170B (en) Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method
Cui et al. An anomaly detection approach based on machine learning and scada data for condition monitoring of wind turbines
Kim et al. Use of SCADA data for failure detection in wind turbines
CN105205569B (en) State of fan gear box online evaluation method for establishing model and online evaluation method
CN108072524B (en) Wind turbine generator gearbox bearing fault early warning method
CN101995290A (en) Method and system for monitoring vibration of wind driven generator
CN110469462A (en) A kind of Wind turbines intelligent condition monitoring system based on multi-template
CN202326011U (en) State-monitoring and fault-diagnosis system of wind-power set
Cui et al. An anomaly detection approach using wavelet transform and artificial neural networks for condition monitoring of wind turbines' gearboxes
CN112065668A (en) Wind turbine generator state abnormity assessment method and system
Zhu et al. Operational state assessment of wind turbine gearbox based on long short-term memory networks and fuzzy synthesis
CN110794683A (en) Wind power gear box state evaluation method based on deep neural network and kurtosis characteristics
Wiggelinkhuizen et al. CONMOW: Condition monitoring for offshore wind farms
CN113777351B (en) Fault diagnosis method and device for wind speed sensor of wind power plant
CN108491622A (en) A kind of fault diagnosis method and system of Wind turbines
Liu et al. A review of bearing fault diagnosis for wind turbines
Lydia et al. Condition monitoring in wind turbines: a review
Kruger et al. A data-driven approach for sensor fault diagnosis in gearbox of wind energy conversion system
CN115842408A (en) Wind power plant operation state detection system and method based on SCADA
CN107218180B (en) A kind of wind power generating set driving unit fault alarm method based on vibration acceleration measurement
Song et al. Framework of designing an adaptive and multi-regime prognostics and health management for wind turbine reliability and efficiency improvement
Zhu et al. Condition monitoring of wind turbine gearbox using multidimensional hybrid outlier detection
Bilendo et al. Wind turbine anomaly detection based on SCADA data
Tingting et al. Early warning method for power station auxiliary failure considering large-scale operating conditions
Kuseyri Condition monitoring of wind turbines: Challenges and opportunities

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