CN109425483A - Running of wind generating set status assessment and prediction technique based on SCADA and CMS - Google Patents
Running of wind generating set status assessment and prediction technique based on SCADA and CMS Download PDFInfo
- Publication number
- CN109425483A CN109425483A CN201710787298.9A CN201710787298A CN109425483A CN 109425483 A CN109425483 A CN 109425483A CN 201710787298 A CN201710787298 A CN 201710787298A CN 109425483 A CN109425483 A CN 109425483A
- Authority
- CN
- China
- Prior art keywords
- wind turbines
- subsystem
- index
- wind
- running
- 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
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Wind Motors (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
The present invention discloses a kind of running of wind generating set status assessment and prediction technique based on SCADA and CMS, the following steps are included: extracting the operating status feature of Wind turbines subsystems, the vibration performance of temperature, revolving speed, position, power, angle and CMS system including SCADA system based on SCADA system and CMS system；According to the operating status feature of Wind turbines subsystems, the operating status for assessing each subsystem is calculated with variable synthesis assessment models；The operating status of the entire Wind turbines of current time is obtained according to the operating status of each subsystem of Wind turbines and predicts the operating status of the following setting time Wind turbines.Compared with prior art, the present invention assesses running of wind generating set current state and prediction operating status in future is more accurate.
Description
Technical field
The invention belongs to wind power generation fields, in particular to a kind of running of wind generating set based on SCADA and CMS
Status assessment and prediction technique.
Background technique
As China's wind power plant competes more and more fierce requirement continuous improvement to being safely operated and reducing maintenance cost,
A set of effective fan operation state evaluation system is constructed, accurately operating status assessment is carried out in real time to Wind turbines,
Grasp the variation tendency of unit health condition, arranged rational maintenance time and maintenance items, thus effectively trouble saving
Occur particularly significant.
Traditional running of wind generating set status assessment is often directed to certain critical components, such as gear-box, generator, or
State monitoring method of the person based on studying Wind turbines SCADA data.
Summary of the invention
The present invention provides a kind of running of wind generating set status assessment and prediction technique based on SCADA and CMS, to gram
Take at least one problem existing in the prior art.
In order to achieve the above objectives, the present invention provides a kind of running of wind generating set status assessments based on SCADA and CMS
With prediction technique, comprising the following steps:
The operating status feature of Wind turbines subsystems, including SCADA are extracted based on SCADA system and CMS system
The temperature of system, revolving speed, position, power, angle and CMS system vibration performance；
According to the operating status feature of Wind turbines subsystems, it is each that assessment is calculated with variable synthesis assessment models
The operating status of subsystem；
According to the operating status of each subsystem of Wind turbines obtain the entire Wind turbines of current time operating status and
Predict the operating status of the following setting time Wind turbines.
Preferably, the operating status for extracting Wind turbines subsystems based on SCADA system and CMS system is special
Sign, the vibration performance step of temperature, revolving speed, position, power, angle and CMS system including SCADA system include:
S1: it is adopted according in the measurement parameter of each important component sensor of the unit acquired in SCADA system and CMS system
The vibration data of collection establishes running of wind generating set status assessment model, in running of wind generating set status assessment model, project
Layer includes 7 subsystems, X={ X1,X2,X3,X4,X5,X6,X7, i.e., { base bearing, gear-box, generator, cabin and control are
System, converter system, pitch-controlled system, network system }；7 subsystems separately include a series of index Xij, X1={ X11,X12,
X13..., X7={ X71,X72,X73,X74, wherein the data of CMS system acquisition are { X12,X13}={ base bearing axial vibration,
Base bearing radial vibration }, { X25,X26,X27,X28}={ primary planet grade radial vibration, secondary planet grade radial vibration, high speed
Grade radial vibration, the axial vibration of high speed grade }
{X35,X36The end radial vibration of }={ generator drive, the radial vibration of generator anti-drive end }；
S2: using analytic hierarchy process (AHP), calculates 7 normal Quan Quanchong of subsystem in running of wind generating set status assessment modelThe normal Quan Quanchong of each each index feature parameter of subsystem Its
InIndicate the normal Quan Quanchong of i-th of Wind turbines, j-th of subsystem index feature parameter,Indicate Wind turbines i-th
J-th of a subsystem, k-th of index characteristic parameter normal Quan Quanchong, i, j, k are natural number.
Preferably, the operating status feature according to Wind turbines subsystems, with variable synthesis assessment models
It calculates and assesses the operating status step of each subsystem and include:
S3: by CMS system record base bearing axially and radially, the vibrating sensor at generator drive end and anti-drive end
Signal calculates separately following time domain index: absolute meanVirtual value xrms, peak index cf, kurtosis index Kv, low pass it is effective
Value DRMS, in which:
Y (t) is the vibration signal of vibrating sensor acquisition, and length n, n are natural number.
Wherein β is kurtosis,
DRMS is then to calculate its virtual value to vibration signal y (t) low-pass filtering using low-pass filter；
S4: CMS system is recorded into the radial direction of gear-box primary planet grade, the radial direction of gear-box secondary planet grade, gear-box
The vibration sensor signal axially and radially of high speed grade, calculates separately following time domain index: absolute meanVirtual value
xrms, peak index cf, kurtosis index Kv, furthermore calculate frequency-domain index: sideband energy rate SER, wherein；
Wherein the amplitude of meshing frequency a side band is y (t)
After Fast Fourier Transform FFT, meshing frequency side rotates frequency with engaging tooth as the amplitude of sideband；
S5: pressing running of wind generating set status assessment model, defines the reality of the index feature parameter of each subsystem of Wind turbines
Measured value xij, (i=1,2 ... 7), and xijk, (i=1,2,3), wherein xijIndicate i-th of Wind turbines, j-th of subsystem index
The measured value of characteristic parameter, xijkIndicate the measured value of i-th of Wind turbines, j-th of subsystem index kth characteristic parameter；
S6: the measured value x of parameter characteristic parameterij, (i=1,2 ... 7), and xijk, the impairment grade of (i=1,2,3)；
S7: Wind turbines subsystem variable synthesis assessment models V is derivedi'(xi1,...,xin), wherein
Wherein, wij(xi1,...,xin)、Respectively i-th of Wind turbines, j-th of subsystem index feature parameter
Variable weight weight, normal Quan Quanchong；
Introduce balance functionObtain final variable weight weight w 'ij(xi1,...,
xin) and Wind turbines subsystem variable synthesis assessment models Vi'(xi1,...,xin),
Wherein, n is the index feature number of parameters of i-th of subsystem of Wind turbines, and α is variable weight coefficient；
S8: the impairment grade D of each subsystem of Wind turbines is calculatedi:
By the wellness g of i-th of Wind turbines, j-th of subsystem index feature parameterijBring the change of Wind turbines subsystem into
Weigh Integrated Evaluation Model Vi'(xi1,...,xin), it obtains,
gij=1-dij,
Di=1-Vi(xi1,...,xin)
Wherein, gijFor the wellness of i-th of Wind turbines, j-th of subsystem index feature parameter, Vi(xi1,...,
xin)、DiThe respectively wellness, impairment grade of i-th of subsystem of Wind turbines；
For the data { X of CMS system acquisition12,X13, { X25,X26,X27,X28, { X35,X36, wellness is calculated first
{g12,g13, { g25,g26,g27,g28, { g35,g36,
gijk=1-dijk,
Wherein, k is the characteristic parameter serial number of i-th of Wind turbines, j-th of subsystem index, n1It is i-th of Wind turbines
The characteristic parameter number of j-th of index of subsystem；
S9: calculating the impairment grade D of Wind turbines whole system, wherein
gi=1-Di,
Wherein, gi、The respectively wellness of i-th of subsystem of Wind turbines, normal Quan Quanchong, P are Wind turbines
The number of system.
Preferably, the operating status according to each subsystem of Wind turbines obtains the entire Wind turbines of current time
Operating status and the operating status step for predicting the following setting time Wind turbines include:
S10: in the SCADA system and CMS system of Wind turbines, every 10min records each important component of a unit and passes
The measurement parameter of sensor records altogether 144 time hop counts evidences in one day；With 7 days 1 week totally 1008 time hop counts evidences, according to step
Rapid S3-S8, calculates separately the wellness of 7 subsystems；Utilize 7 days 1008 groups of 7 subsystem wellness data training small echos
Neural network, wherein wavelet basis function is Morlet morther wavelet basic function, finally predicts the with trained wavelet neural network
8 days 7 subsystem wellness calculate the impairment grade of the 8th day Wind turbines whole system according to step S9；
S11: impairment grade is divided, and [0,0.2), [0.2,0.4), [0.4,0.6), [0.6,1] corresponds respectively to wind
The kilter of motor group, preferable state, general state and quasi- malfunction, it is final to obtain current time and second day wind-powered electricity generation
The operating states of the units and its subsystems of unit whole system and the operating status of index.
Preferably, above-mentioned running of wind generating set status assessment and prediction technique are further comprising the steps of:
The impairment grade of the 8th week Wind turbines whole system is calculated using 7 weeks SCADA and CMS data.
Preferably, the low-pass filtering cutoff frequency of vibration signal y (t) is set, and base bearing setting range is that impeller turns frequency
100 are multiplied to 150 frequencys multiplication, and generator setting range turns the 100 of frequency for generator and is multiplied to 150 frequencys multiplication.
Preferably, in step s 6, for the index feature value of smaller more excellent type, impairment grade calculation formula is as follows:
Or
Wherein, dij、xij、αij、βijRespectively the impairment grade of i-th of Wind turbines, j-th of subsystem index feature parameter,
Measured value, permissible value, limit value；dijk、xijk、αijk、βijkRespectively k-th of i-th of Wind turbines, j-th of subsystem index special
Levy impairment grade, the measured value, permissible value, limit value of parameter；kij、kijkReflect that j-th of index of i-th of subsystem of Wind turbines is special
Levy the relationship of parameter or j-th index k-th of characteristic parameter and equipment health status, value range for (0,2].
Preferably, in step s 6, for the index feature value of intermediate excellent type, impairment grade calculation formula is as follows:
Wherein, βij2、αij1For the upper limit value and lower limit value of i-th of Wind turbines, j-th of subsystem index feature parameter；αij2、
βij1For the upper and lower limit permissible value of i-th of Wind turbines, j-th of subsystem index feature parameter.
Preferably, in the step s 7, when the measured value of the certain subsystems of Wind turbines is less than 2 times of permissible values, α > 1/ is taken
2；When the measured value of the certain subsystems of Wind turbines is greater than 2 times of permissible values, α < 1/2 is taken；As α=1, it is equal to Chang Quanmo
Formula.
Preferably, when the measured value of the certain subsystems of Wind turbines is greater than 3 times of permissible values, α=0.1 is taken.
Present invention introduces CMS system vibration data and sensitive features are extracted, establish more complete wind with analytic hierarchy process (AHP)
Motor group status assessment model predicts wind-powered electricity generation in conjunction with wavelet neural network while assessing current running of wind generating set state
Unit operating status in future.Compared with prior art, the present invention assesses running of wind generating set current state and prediction is run in the future
State is more accurate.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
Some embodiments of the present invention, for those of ordinary skill in the art, without creative efforts, also
Other drawings may be obtained according to these drawings without any creative labor.
Fig. 1 is the running of wind generating set status assessment model schematic of one embodiment of the invention；
Fig. 2 is the impairment grade of the running of wind generating set status assessment model of one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art under that premise of not paying creative labor it is obtained it is all its
His embodiment, shall fall within the protection scope of the present invention.
In the SCADA system of Wind turbines, the measurement ginseng of every 10min record each important component sensor of unit
The content of number, each 10min record includes time tag, active power, reactive power, wind speed, environment and cabin temperature, tooth
Roller box and bearing temperature, impeller and generator speed, tower oscillation acceleration etc. amount to 46 parameters, for storing wind turbine
The important measurement parameter of each component of transmission system acquired in group operation, these operation datas have been truly reflected the reality of blower
Border operating status.
In the CMS system of Wind turbines, 8 vibrating sensors are mounted in base bearing, gear-box and generator, are remembered
Recorded the vibration data of 8 measuring points, vibrating sensor installation site be base bearing axially and radially, gear-box primary planet
Grade radial direction, the radial direction of gear-box secondary planet grade, gearbox high-speed grade axially and radially, generator drive end and non-drive
The radial direction of moved end is used for diagnostic analysis base bearing, gear-box and generator health status and probable trouble area.
Running of wind generating set status assessment according to an embodiment of the invention based on SCADA and CMS and prediction side
Method, comprising the following steps:
The operating status feature of Wind turbines subsystems, including SCADA are extracted based on SCADA system and CMS system
The temperature of system, revolving speed, position, power, angle and CMS system vibration performance；
According to the operating status feature of Wind turbines subsystems, it is each that assessment is calculated with variable synthesis assessment models
The operating status of subsystem；
According to the operating status of each subsystem of Wind turbines obtain the entire Wind turbines of current time operating status and
Predict the operating status of the following setting time Wind turbines.
Running of wind generating set status assessment based on SCADA and CMS and prediction in accordance with a preferred embodiment of the present invention
Method, to carry out operating status assessment to multiple Wind turbines in wind power plant comprising following steps:
S1: after researching and analysing running of wind generating set state influence factor, establishing running of wind generating set status assessment model,
As shown in Figure 1.
S2: in running of wind generating set status assessment model, item layer includes 7 subsystems, X={ X1,X2,X3,X4,
X5,X6,X7, i.e. { base bearing, gear-box, generator, cabin and control system, current transformer system
System, pitch-controlled system, network system }.7 subsystems separately include a series of index Xij, X1={ X11,X12,
X13..., X7={ X71,X72,X73,X74, wherein the data of CMS system acquisition are
{X12,X13}={ base bearing axial vibration, base bearing radial vibration },
{X25,X26,X27,X28}={ primary planet grade radial vibration, secondary planet grade radial vibration, high speed grade are radially shaken
It is dynamic, the axial vibration of high speed grade }
{X35,X36The end radial vibration of }={ generator drive, the radial vibration of generator anti-drive end }.
With analytic hierarchy process (AHP), 7 normal Quan Quanchong of subsystem in running of wind generating set status assessment model are calculatedThe normal Quan Quanchong of each each index feature parameter of subsystem
WhereinIndicate the normal Quan Quanchong of i-th of Wind turbines, j-th of subsystem index feature parameter,Indicate Wind turbines the
The i normal Quan Quanchong of j-th of subsystem, k-th of index characteristic parameter.
Wherein, the vector and number that a series of indexs that each subsystem is included are included, it is main according to artificial judgement
46 parameters acquired in index referenced by each system running state (experience) and SCADA system.
S3: by CMS system record base bearing axially and radially, the vibrating sensor at generator drive end and anti-drive end
Signal calculates separately following time domain index: absolute meanVirtual value xrms, peak index cf, kurtosis index Kv, low pass it is effective
Value DRMS, in which:
Y (t) is the vibration signal of vibrating sensor acquisition, and length n, n are natural number, when by sample frequency and acquisition
Between determine.
Wherein β is kurtosis,
DRMS is then to calculate its virtual value, wherein basis to vibration signal y (t) low-pass filtering using low-pass filter
The low-pass filtering cutoff frequency of vibration signal is arranged in experience, and the principle of setting can be according to 1. VDI3834；2. analyzing frequency extremely
It is less 2 times, then at least 3.3 times of gear-box of unit failure characteristic frequency to be analyzed；And 3. base bearing, generator failure are special
Sign frequency and the relationship for turning frequency.For example, the low-pass filtering cutoff frequency of setting vibration signal, it is impeller that range, which is arranged, in base bearing
Turn the 100 of frequency and be multiplied to 150 frequencys multiplication, generator setting range turns the 100 of frequency for generator and is multiplied to 150 frequencys multiplication.
S4: CMS system is recorded into the radial direction of gear-box primary planet grade, the radial direction of gear-box secondary planet grade, gear-box
The vibration sensor signal axially and radially of high speed grade, calculates separately following time domain index: absolute meanVirtual value
xrms, peak index cf, kurtosis index Kv, furthermore calculate frequency-domain index: sideband energy rate SER, wherein；
Wherein the amplitude of meshing frequency a side band is y (t)
After Fast Fourier Transform FFT, meshing frequency side rotates frequency with engaging tooth as the amplitude of sideband.
S5: pressing running of wind generating set status assessment model, as shown in Figure 1, the index for defining each subsystem of Wind turbines is special
Levy the measured value x of parameterij, (i=1,2 ... 7), and xijk, (i=1,2,3), wherein xijIndicate i-th of subsystem of Wind turbines
The measured value of j-th of index feature parameter, xijkIndicate i-th of subsystem jth k-th of characteristic parameter of index of Wind turbines
Measured value.
S6: the measured value x of parameter characteristic parameterij, (i=1,2 ... 7), and xijk, the impairment grade of (i=1,2,3).
For the index feature value of smaller more excellent type, such as the relevant temperature of base bearing, gear-box, generator, current transformer
And Faults by Vibrating, impairment grade calculation formula are as follows:
Or
Wherein, dij、xij、αij、βijRespectively the impairment grade of i-th of Wind turbines, j-th of subsystem index feature parameter,
Measured value, permissible value (good value), limit value；dijk、xijk、αijk、βijkRespectively i-th of Wind turbines, j-th of subsystem index
The impairment grade of k-th of characteristic parameter, measured value, permissible value (good value), limit value；kij、kijkReflect i-th of subsystem of Wind turbines
J-th of index feature parameter of system or the relationship of j-th index k-th of characteristic parameter and equipment health status, rule of thumb set
It sets, value range (0,2].
It is bad for the index feature value of intermediate excellent type, such as yaw angle, revolving speed, oil temperature, nacelle position, network system
Change degree calculation formula is as follows:
Wherein, βij2、αij1For the upper limit value and lower limit value of i-th of Wind turbines, j-th of subsystem index feature parameter；αij2、
βij1For the upper and lower limit permissible value (good value) of i-th of Wind turbines, j-th of subsystem index feature parameter.
S7: Wind turbines subsystem variable synthesis assessment models V is derivedi'(xi1,...,xin), wherein
Wherein, wij(xi1,...,xin)、Respectively i-th of Wind turbines, j-th of subsystem index feature parameter
Variable weight weight, normal Quan Quanchong.
Introduce balance functionObtain final variable weight weight w 'ij(xi1,...,
xin) and Wind turbines subsystem variable synthesis assessment models Vi'(xi1,...,xin),
Wherein, n is the index feature number of parameters of i-th of subsystem of Wind turbines, and α is variable weight coefficient, when each factor
When equalization problem considers few, α > 1/2 is taken；When can't stand the substantial deviation of certain factors, α < 1/2 is taken；As α=1,
It is equal to normal power mode.In view of if the certain subsystem substantial deviation normal conditions of Wind turbines will affect entire unit
Safety can use α=0.1.
For example, in the step s 7, when the measured value of the certain subsystems of Wind turbines is less than 2 times of permissible values, taking α > 1/2；
When the measured value of the certain subsystems of Wind turbines is greater than 2 times of permissible values, α < 1/2 is taken；As α=1, it is equal to normal power mode.
When the measured value of the certain subsystems of Wind turbines is greater than 3 times of permissible values, α=0.1 is taken.
S8: the impairment grade D of each subsystem of Wind turbines is calculatedi
By the wellness g of i-th of Wind turbines, j-th of subsystem index feature parameterijBring the change of Wind turbines subsystem into
Weigh Integrated Evaluation Model Vi'(xi1,...,xin), it obtains,
gij=1-dij,
Di=1-Vi(xi1,...,xin)
Wherein, gijFor the wellness of i-th of Wind turbines, j-th of subsystem index feature parameter, Vi(xi1,...,
xin)、DiThe respectively wellness, impairment grade of i-th of subsystem of Wind turbines.
For the data { X of CMS system acquisition12,X13, { X25,X26,X27,X28, { X35,X36, wellness is calculated first
{g12,g13, { g25,g26,g27,g28, { g35,g36,
gijk=1-dijk,
Wherein, k is the characteristic parameter serial number of i-th of Wind turbines, j-th of subsystem index, n1It is i-th of Wind turbines
The characteristic parameter number of j-th of index of subsystem.
S9: calculating the impairment grade D of Wind turbines whole system, wherein
gi=1-Di,
Wherein, gi、The respectively wellness of i-th of subsystem of Wind turbines, normal Quan Quanchong, P are Wind turbines
The number of system.
S10: in the SCADA system and CMS system of Wind turbines, every 10min records each important component of a unit and passes
The measurement parameter of sensor records altogether 144 time hop counts evidences in one day.With 7 days 1 week totally 1008 time hop counts evidences, according to step
Rapid S3-S8, calculates separately the wellness of 7 subsystems.Utilize 7 days 1008 groups of 7 subsystem wellness data training small echos
Neural network, wherein wavelet basis function is Morlet morther wavelet basic function, finally predicts the with trained wavelet neural network
8 days 7 subsystem wellness calculate the impairment grade of the 8th day Wind turbines whole system according to step S9.(wavelet neural
Network is the concept and algorithm that ZhangQinghua and Benvenistes in 1992 is clearly proposed for the first time.)
S11: impairment grade is divided, and [0,0.2), [0.2,0.4), [0.4,0.6), [0.6,1] corresponds respectively to wind
The kilter of motor group, preferable state, general state and quasi- malfunction.It is final to obtain current time and second day wind-powered electricity generation
The operating states of the units and its subsystems of unit whole system and the operating status of index, as shown in Figure 2.From Fig. 2,
It can intuitively show current time and the whole operating status situation with part of second day Wind turbines.
It is provided by the invention effectively to be mentioned based on the running of wind generating set status assessment of SCADA and CMS and prediction technique
The operating status feature for taking Wind turbines subsystems, temperature, revolving speed, position, power, angle including SCADA system etc.
It with the vibration performance of CMS system, is calculated with variable synthesis assessment models and assesses its overall operation state, and can shown
The operating status of current time and second day Wind turbines subsystems and index feature.
For step S10, similarly, can use 7 weeks SCADA and CMS data calculate the 8th week Wind turbines be entirely
The impairment grade of system.
Present invention introduces CMS system vibration data and sensitive features are extracted, establish more complete wind with analytic hierarchy process (AHP)
Motor group status assessment model predicts wind-powered electricity generation in conjunction with wavelet neural network while assessing current running of wind generating set state
Unit operating status in future.Compared with prior art, the present invention assesses running of wind generating set current state and prediction is run in the future
State is more accurate.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, those skilled in the art should understand that: it is still
It can modify to technical solution documented by previous embodiment or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of the embodiment of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of running of wind generating set status assessment and prediction technique based on SCADA and CMS, which is characterized in that including following
Step:
The operating status feature of Wind turbines subsystems, including SCADA system are extracted based on SCADA system and CMS system
Temperature, revolving speed, position, power, angle and CMS system vibration performance；
According to the operating status feature of Wind turbines subsystems, is calculated with variable synthesis assessment models and assess each subsystem
Operating status；
The operating status and prediction of the entire Wind turbines of current time are obtained according to the operating status of each subsystem of Wind turbines
The operating status of the following setting time Wind turbines.
2. running of wind generating set status assessment according to claim 1 and prediction technique, which is characterized in that described to be based on
SCADA system and CMS system extract the operating status feature of Wind turbines subsystems, and temperature including SCADA system turns
Speed, position, power, angle and CMS system vibration performance step include:
S1: according to the vibration acquired in the measurement parameter of each important component sensor of the unit acquired in SCADA system and CMS system
Dynamic data, establish running of wind generating set status assessment model, and in running of wind generating set status assessment model, item layer includes 7
A subsystem, X={ X1,X2,X3,X4,X5,X6,X7, i.e. { base bearing, gear-box, generator, cabin and control system, unsteady flow
Device system, pitch-controlled system, network system }；7 subsystems separately include a series of index Xij, X1={ X11,X12,X13..., X7
={ X71,X72,X73,X74, wherein the data of CMS system acquisition are { X12,X13}={ base bearing axial vibration, base bearing are radial
Vibration }, { X25,X26,X27,X28}={ primary planet grade radial vibration, secondary planet grade radial vibration, high speed grade radial vibration,
High speed grade axial vibration }
{X35,X36The end radial vibration of }={ generator drive, the radial vibration of generator anti-drive end }；
S2: using analytic hierarchy process (AHP), calculates 7 normal Quan Quanchong of subsystem in running of wind generating set status assessment model(i=
1,2 ..., 7), the normal Quan Quanchong of each each index feature parameter of subsystem(i=1,2 ..., 7),(i=1,2,3),
WhereinIndicate the normal Quan Quanchong of i-th of Wind turbines, j-th of subsystem index feature parameter,Indicate Wind turbines i-th
J-th of a subsystem, k-th of index characteristic parameter normal Quan Quanchong, i, j, k are natural number.
3. running of wind generating set status assessment according to claim 2 and prediction technique, which is characterized in that described according to wind
The operating status feature of motor group subsystems calculates the operating status for assessing each subsystem with variable synthesis assessment models
Step includes:
S3: by CMS system record base bearing axially and radially, the vibration sensor signal of generator drive end and anti-drive end point
Following time domain index: absolute mean is not calculatedVirtual value xrms, peak index cf, kurtosis index Kv, low pass virtual value DRMS,
Wherein:
Y (t) is the vibration signal of vibrating sensor acquisition, and length n, n are natural number；
Wherein β is kurtosis,
DRMS is then to calculate its virtual value to vibration signal y (t) low-pass filtering using low-pass filter；
S4: CMS system is recorded into the radial direction of gear-box primary planet grade, the radial direction of gear-box secondary planet grade, gearbox high-speed
The vibration sensor signal axially and radially of grade, calculates separately following time domain index: absolute meanVirtual value xrms, peak value
Index cf, kurtosis index Kv, furthermore calculate frequency-domain index: sideband energy rate SER, wherein；
Wherein the amplitude of meshing frequency a side band is quick Fu of y (t)
After vertical leaf transformation FFT, meshing frequency side rotates frequency with engaging tooth as the amplitude of sideband；
S5: pressing running of wind generating set status assessment model, defines the measured value of the index feature parameter of each subsystem of Wind turbines
xij, (i=1,2 ... 7), and xijk, (i=1,2,3), wherein xijIndicate i-th of Wind turbines, j-th of subsystem index feature ginseng
Several measured values, xijkIndicate the measured value of i-th of Wind turbines, j-th of subsystem, k-th of characteristic parameter of index；
S6: the measured value x of parameter characteristic parameterij, (i=1,2 ... 7), and xijk, the impairment grade of (i=1,2,3)；
S7: Wind turbines subsystem variable synthesis assessment models V is derivedi'(xi1,...,xin), wherein
Wherein, wij(xi1,...,xin)、The respectively variable weight power of i-th of Wind turbines, j-th of subsystem index feature parameter
Weight, normal Quan Quanchong；
Introduce balance functionObtain final variable weight weight wi'j(xi1,...,xin) and wind
Motor group subsystem variable synthesis assessment models Vi'(xi1,...,xin),
Wherein, n is the index feature number of parameters of i-th of subsystem of Wind turbines, and α is variable weight coefficient；
S8: the impairment grade D of each subsystem of Wind turbines is calculatedi:
By the wellness g of i-th of Wind turbines, j-th of subsystem index feature parameterijIt is comprehensive to bring Wind turbines subsystem variable weight into
Close assessment models Vi'(xi1,...,xin), it obtains,
gij=1-dij,
Di=1-Vi(xi1,...,xin)
Wherein, gijFor the wellness of i-th of Wind turbines, j-th of subsystem index feature parameter, Vi(xi1,...,xin)、DiPoint
Not Wei i-th of subsystem of Wind turbines wellness, impairment grade；
For the data { X of CMS system acquisition12,X13, { X25,X26,X27,X28, { X35,X36, calculating wellness { g first12,
g13, { g25,g26,g27,g28, { g35,g36,
gijk=1-dijk,
Wherein, k is the characteristic parameter serial number of i-th of Wind turbines, j-th of subsystem index, n1For i-th of subsystem of Wind turbines
The characteristic parameter number of j-th of index；
S9: calculating the impairment grade D of Wind turbines whole system, wherein
gi=1-Di,
Wherein, gi、The respectively wellness of i-th of subsystem of Wind turbines, normal Quan Quanchong, P are Wind turbines subsystem
Number.
4. running of wind generating set status assessment according to claim 3 and prediction technique, which is characterized in that described according to wind
When the operating status of each subsystem of motor group obtains the operating status and prediction future setting of the entire Wind turbines of current time
Between the operating status steps of Wind turbines include:
S10: in the SCADA system and CMS system of Wind turbines, every 10min records each important component sensor of a unit
Measurement parameter, one day altogether record 144 time hop counts evidences；With 7 days 1 week totally 1008 time hop counts evidences, according to step
S3-S8 calculates separately the wellness of 7 subsystems；Utilize 7 days 1008 groups of 7 subsystem wellness data training wavelet neurals
Network, wherein wavelet basis function is Morlet morther wavelet basic function, finally predicts the 8th day with trained wavelet neural network
7 subsystem wellness calculate the impairment grade of the 8th day Wind turbines whole system according to step S9；
S11: impairment grade is divided, and [0,0.2), [0.2,0.4), [0.4,0.6), [0.6,1] corresponds respectively to wind turbine
Kilter, preferable state, general state and the quasi- malfunction of group, final acquisition current time and second day Wind turbines are whole
The operating states of the units and its subsystems of a system and the operating status of index.
5. running of wind generating set status assessment according to claim 4 and prediction technique, which is characterized in that further include following
Step:
The impairment grade of the 8th week Wind turbines whole system is calculated using 7 weeks SCADA and CMS data.
6. running of wind generating set status assessment according to claim 3 and prediction technique, which is characterized in that setting vibration letter
The low-pass filtering cutoff frequency of number y (t), base bearing setting range are that impeller turns the 100 of frequency and is multiplied to 150 frequencys multiplication, and generator is set
Setting range is that generator turns the 100 of frequency and is multiplied to 150 frequencys multiplication.
7. running of wind generating set status assessment according to claim 3 and prediction technique, which is characterized in that in step S6
In, for the index feature value of smaller more excellent type, impairment grade calculation formula is as follows:
Or
Wherein, dij、xij、αij、βijThe respectively impairment grade of i-th of Wind turbines, j-th of subsystem index feature parameter, actual measurement
Value, permissible value, limit value；dijk、xijk、αijk、βijkRespectively i-th of Wind turbines, j-th of subsystem index, k-th of characteristic parameter
Impairment grade, measured value, permissible value, limit value；kij、kijkReflect j-th of index feature parameter of i-th of subsystem of Wind turbines
Or the relationship of j-th index k-th of characteristic parameter and equipment health status, value range be (0,2].
8. running of wind generating set status assessment according to claim 3 and prediction technique, which is characterized in that in step S6
In, for the index feature value of intermediate excellent type, impairment grade calculation formula is as follows:
Wherein, βij2、αij1For the upper limit value and lower limit value of i-th of Wind turbines, j-th of subsystem index feature parameter；αij2、βij1For wind
The upper and lower limit permissible value of i-th of motor group, j-th of subsystem index feature parameter.
9. running of wind generating set status assessment according to claim 3 and prediction technique, which is characterized in that in step S7
In, when the measured value of the certain subsystems of Wind turbines is less than 2 times of permissible values, take α > 1/2；When the certain subsystems of Wind turbines
When measured value is greater than 2 times of permissible values, α < 1/2 is taken；As α=1, it is equal to normal power mode.
10. running of wind generating set status assessment according to claim 9 and prediction technique, which is characterized in that work as wind turbine
When the measured value of the certain subsystems of group is greater than 3 times of permissible values, α=0.1 is taken.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710787298.9A CN109425483B (en) | 2017-09-04 | 2017-09-04 | Wind turbine generator running state evaluation and prediction method based on SCADA and CMS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710787298.9A CN109425483B (en) | 2017-09-04 | 2017-09-04 | Wind turbine generator running state evaluation and prediction method based on SCADA and CMS |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109425483A true CN109425483A (en) | 2019-03-05 |
| CN109425483B CN109425483B (en) | 2021-05-25 |
Family
ID=65513773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710787298.9A Active CN109425483B (en) | 2017-09-04 | 2017-09-04 | Wind turbine generator running state evaluation and prediction method based on SCADA and CMS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109425483B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110044610A (en) * | 2019-05-17 | 2019-07-23 | 苏州德姆斯信息技术有限公司 | Gear failure diagnosing method |
| CN110132597A (en) * | 2019-04-29 | 2019-08-16 | 清华大学 | A kind of bearing inner race peels off the measuring method of width |
| CN110544003A (en) * | 2019-07-18 | 2019-12-06 | 湖南科技大学 | temperature prediction-based wind power plant wind turbine generator set frequency converter state evaluation method |
| CN110794683A (en) * | 2019-11-27 | 2020-02-14 | 中国大唐集团科学技术研究院有限公司华中电力试验研究院 | Wind power gear box state evaluation method based on deep neural network and kurtosis characteristics |
| CN110907170A (en) * | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method |
| CN111639842A (en) * | 2020-05-20 | 2020-09-08 | 湖北博华自动化系统工程有限公司 | Equipment health evaluation method, evaluation system and equipment health prediction method |
| CN112001632A (en) * | 2020-08-25 | 2020-11-27 | 中国船舶重工集团海装风电股份有限公司 | Wind turbine generator gearbox bearing performance degradation state evaluation method |
| CN112067297A (en) * | 2020-09-23 | 2020-12-11 | 昆明理工大学 | Bearing fault feature extraction method |
| CN112381352A (en) * | 2020-10-19 | 2021-02-19 | 大唐（赤峰）新能源有限公司 | Wind turbine generator running state evaluation method based on multi-source heterogeneous monitoring |
| CN113095693A (en) * | 2021-04-19 | 2021-07-09 | 重庆理工大学 | Wind power bearing health state assessment method based on temperature characteristic quantity |
| CN113449985A (en) * | 2021-06-25 | 2021-09-28 | 上海电气风电集团股份有限公司 | Gearbox monitoring method and system and computer readable storage medium |
| CN113821420A (en) * | 2021-08-24 | 2021-12-21 | 浙江运达风电股份有限公司 | Performance comparison and data conversion method for CMS (CMS) system of wind turbine generator |
| CN114638060A (en) * | 2022-03-10 | 2022-06-17 | 重庆英科铸数网络科技有限公司 | Fault prediction method, system, electronic device and computer program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101858312A (en) * | 2010-05-31 | 2010-10-13 | 重庆大学 | System and method thereof for evaluating real-time running state of wind generating set |
| US20120066544A1 (en) * | 2011-06-22 | 2012-03-15 | Mitsubishi Heavy Industries, Ltd. | Remote monitoring apparatus, wind turbine generator system, and method of controlling remote monitoring apparatus |
| CN203216722U (en) * | 2013-01-28 | 2013-09-25 | 杭州胄天新能源技术有限公司 | Wind generating set integration state monitoring system |
| CN106199305A (en) * | 2016-07-01 | 2016-12-07 | 太原理工大学 | Underground coal mine electric power system dry-type transformer insulation health state evaluation method |
| CN106324502A (en) * | 2016-08-22 | 2017-01-11 | 哈尔滨理工大学 | Asynchronous motor fault analysis method based on wavelet |
-
2017
- 2017-09-04 CN CN201710787298.9A patent/CN109425483B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101858312A (en) * | 2010-05-31 | 2010-10-13 | 重庆大学 | System and method thereof for evaluating real-time running state of wind generating set |
| US20120066544A1 (en) * | 2011-06-22 | 2012-03-15 | Mitsubishi Heavy Industries, Ltd. | Remote monitoring apparatus, wind turbine generator system, and method of controlling remote monitoring apparatus |
| CN203216722U (en) * | 2013-01-28 | 2013-09-25 | 杭州胄天新能源技术有限公司 | Wind generating set integration state monitoring system |
| CN106199305A (en) * | 2016-07-01 | 2016-12-07 | 太原理工大学 | Underground coal mine electric power system dry-type transformer insulation health state evaluation method |
| CN106324502A (en) * | 2016-08-22 | 2017-01-11 | 哈尔滨理工大学 | Asynchronous motor fault analysis method based on wavelet |
Non-Patent Citations (2)
| Title |
|---|
| 庞春凤 等: "基于SCADA及振动监测数据的风电机组变权综合状态评价", 《可再生能源》 * |
| 詹棠森 等: "基于关联变权的小波神经网络算法及变异系数法在艺术陶瓷定价应用", 《江西科学》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110132597A (en) * | 2019-04-29 | 2019-08-16 | 清华大学 | A kind of bearing inner race peels off the measuring method of width |
| CN110044610A (en) * | 2019-05-17 | 2019-07-23 | 苏州德姆斯信息技术有限公司 | Gear failure diagnosing method |
| CN110044610B (en) * | 2019-05-17 | 2021-09-07 | 苏州德姆斯信息技术有限公司 | Gear fault diagnosis method |
| CN110544003A (en) * | 2019-07-18 | 2019-12-06 | 湖南科技大学 | temperature prediction-based wind power plant wind turbine generator set frequency converter state evaluation method |
| CN110544003B (en) * | 2019-07-18 | 2023-09-15 | 湖南科技大学 | Wind turbine generator system frequency converter state evaluation method based on temperature prediction |
| CN110794683A (en) * | 2019-11-27 | 2020-02-14 | 中国大唐集团科学技术研究院有限公司华中电力试验研究院 | Wind power gear box state evaluation method based on deep neural network and kurtosis characteristics |
| CN110907170A (en) * | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method |
| CN110907170B (en) * | 2019-11-30 | 2021-03-16 | 华能如东八仙角海上风力发电有限责任公司 | Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method |
| CN111639842A (en) * | 2020-05-20 | 2020-09-08 | 湖北博华自动化系统工程有限公司 | Equipment health evaluation method, evaluation system and equipment health prediction method |
| CN112001632B (en) * | 2020-08-25 | 2022-07-19 | 中国船舶重工集团海装风电股份有限公司 | Wind turbine generator gearbox bearing performance degradation state evaluation method |
| CN112001632A (en) * | 2020-08-25 | 2020-11-27 | 中国船舶重工集团海装风电股份有限公司 | Wind turbine generator gearbox bearing performance degradation state evaluation method |
| CN112067297A (en) * | 2020-09-23 | 2020-12-11 | 昆明理工大学 | Bearing fault feature extraction method |
| CN112381352A (en) * | 2020-10-19 | 2021-02-19 | 大唐（赤峰）新能源有限公司 | Wind turbine generator running state evaluation method based on multi-source heterogeneous monitoring |
| CN113095693A (en) * | 2021-04-19 | 2021-07-09 | 重庆理工大学 | Wind power bearing health state assessment method based on temperature characteristic quantity |
| CN113095693B (en) * | 2021-04-19 | 2024-02-06 | 重庆理工大学 | Wind power bearing health state assessment method based on temperature characteristic quantity |
| CN113449985A (en) * | 2021-06-25 | 2021-09-28 | 上海电气风电集团股份有限公司 | Gearbox monitoring method and system and computer readable storage medium |
| CN113821420A (en) * | 2021-08-24 | 2021-12-21 | 浙江运达风电股份有限公司 | Performance comparison and data conversion method for CMS (CMS) system of wind turbine generator |
| CN114638060A (en) * | 2022-03-10 | 2022-06-17 | 重庆英科铸数网络科技有限公司 | Fault prediction method, system, electronic device and computer program product |
| CN114638060B (en) * | 2022-03-10 | 2023-02-17 | 重庆英科铸数网络科技有限公司 | Fault prediction method, system and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109425483B (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109425483A (en) | Running of wind generating set status assessment and prediction technique based on SCADA and CMS | |
| CN104066978B (en) | Wind field with real-time measuring wind speed | |
| Kusiak et al. | Prediction, operations, and condition monitoring in wind energy | |
| KR101706508B1 (en) | Data Analysis System of Mechanical Load Measurement Data for Wind Turbine | |
| CN201311360Y (en) | Vibrating online monitoring failure diagnostic device | |
| CN105003453A (en) | Online monitoring and fault diagnosis system of mine fan | |
| WO2012125842A2 (en) | Load shape control of wind turbines | |
| CN110469462A (en) | A kind of Wind turbines intelligent condition monitoring system based on multi-template | |
| CN107728059B (en) | Pitch system state evaluation method | |
| CN106815771A (en) | A kind of long-term evaluation method of wind power plant load | |
| CN104747367A (en) | Power curve characteristic detecting system for wind power generation units | |
| CN103940611A (en) | Self-adaptive anomaly detection method for rolling bearing of wind generator set under variable working conditions | |
| Li et al. | Imbalance fault detection based on the integrated analysis strategy for variable-speed wind turbines | |
| CN106762452A (en) | Fan master control system fault diagnosis and on-line monitoring method based on data-driven | |
| CN103925155A (en) | Self-adaptive detection method for abnormal wind turbine output power | |
| CN110146813A (en) | A kind of distributing Wind turbines electric energy quality test method | |
| Kim et al. | Design of wind turbine fault detection system based on performance curve | |
| Barber et al. | Development of a wireless, non-intrusive, MEMS-based pressure and acoustic measurement system for large-scale operating wind turbine blades | |
| CN107103167A (en) | For the DEH speed-regulating functions diagnostic method and system of removal of load operating mode | |
| CN109583075A (en) | Permanent magnet direct-drive wind-force machine military service quality evaluating method based on temperature parameter prediction | |
| CN114414037A (en) | Health monitoring device and monitoring method for blades of wind generating set | |
| CN106647706A (en) | Wind turbine generator set tower drum load shedding verification method and system | |
| CN110838725B (en) | Parameter setting method and device for wind power plant closed-loop PI controller | |
| CN102954834B (en) | Error processing method and device for wind-driven generator vibration monitoring system | |
| Bechhoefer et al. | Condition monitoring architecture: To reduce total cost of ownership |
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 |